SlideShare une entreprise Scribd logo
1  sur  30
Télécharger pour lire hors ligne
VOXCELL®	
  -­‐	
  SUPERCOMPUTING
	
  
	
  CLOUD	
  MEDICAL	
  IMAGING	
  PLATFORM	
  USING	
  GPU/APU
	
  
KOVEY	
  KOVALAN	
  &	
  SANKET	
  GAJJAR	
  
KJAYA	
  MEDICAL	
  
	
  
BUSINESS	
  CASE:	
  
Opportunity	
  to	
  
Improve	
  PaDent	
  Care	
  
OPPORTUNITY	
  TO	
  IMPROVE	
  PATIENT	
  CARE	
  
MEDICAL	
  IMAGING	
  MARKET	
  

!  US	
  spends	
  $100B	
  on	
  520,500,000	
  medical	
  scans	
  !	
  $3.5B	
  on	
  soTware	
  
‒ RIS	
  CVIS	
  PACS	
  !	
  $1.8B	
  in	
  2010	
  !	
  3.5%	
  CAGR	
  
‒ Image	
  Analysis	
  !	
  $1.7B	
  in	
  2012	
  	
  !	
  7.1%	
  CAGR	
  

!  Why	
  Scan?	
  !	
  early	
  detecDon	
  !	
  survive	
  	
  
‒ e.g.	
  13M	
  cancer	
  paDents	
  alive	
  in	
  2012	
  

!  30,000	
  radiologists	
  !	
  10	
  minutes/scan	
  !	
  limits	
  diagnosDc	
  outcome	
  	
  
!  Survival	
  rate	
  could	
  be	
  increased	
  through	
  Dmely	
  physicians	
  and	
  paDent	
  interacDon	
  
!  Physicians	
  and	
  paDents	
  need	
  enhanced	
  visualizaDons,	
  computer	
  aided	
  diagnosis,	
  and	
  
social	
  media	
  
!  KJAYA	
  Medical	
  has	
  a	
  soluDon	
  
3	
   |	
  	
  	
  PRESENTATION	
  TITLE	
  	
  	
  |	
  	
  	
  November	
  22,	
  2013	
  	
  	
  |	
  	
  	
  CONFIDENTIAL	
  
MEDICAL	
  IMAGE	
  MANAGEMENT	
  IS	
  CURRENTLY	
  ON	
  PREMISES	
  
PICTURE	
  ARCHIVING	
  AND	
  COMMUNICATION	
  SYSTEMS	
  (PACS)	
  

Film	
  Warehouse	
  

Digital	
  	
  Warehouse	
  
Onsite	
  
PACS	
  

Specialized	
  
WorkstaDon	
  
4	
   |	
  	
  	
  PRESENTATION	
  TITLE	
  	
  	
  |	
  	
  	
  November	
  22,	
  2013	
  	
  	
  |	
  	
  	
  CONFIDENTIAL	
  
CROWDED	
  MARKET	
  –	
  OLDER	
  TECHNOLOGY	
  	
  
CURRENT	
  PACS	
  MARKET	
  IS	
  FRAGMENTED	
  

Onsite	
  PACS	
  

Blue	
  Ocean	
  Markets	
  
Cloud	
  

Social	
  Media	
  

Third	
  GeneraDon	
  PACS	
  Technology	
  

Current	
  Technology	
  

5	
   |	
  	
  	
  PRESENTATION	
  TITLE	
  	
  	
  |	
  	
  	
  November	
  22,	
  2013	
  	
  	
  |	
  	
  	
  CONFIDENTIAL	
  
CURRENT	
  CLOUD	
  PACS	
  MARKET	
  -­‐	
  LESS	
  THAN	
  1%	
  	
  

FOCUSED	
  ON	
  NON-­‐DIAGNOSTIC	
  USE	
  OF	
  IMAGE	
  SHARING	
  AND	
  	
  OFFSITE	
  BACKUP	
  

13%	
  

3%	
   2%	
  

1%	
  Cloud	
  

Current	
  Cloud	
  accounts	
  about	
  1%	
  of	
  the	
  market	
  
•  $56m	
  in	
  2010	
  expected	
  to	
  grow	
  27%	
  CAGR	
  to	
  2018	
  
•  Mostly	
  in	
  archival	
  and	
  image	
  sharing	
  
•  Third	
  generaDon	
  PACS	
  on	
  cloud	
  in	
  its	
  infancy	
  

81%	
  Onsite	
  	
  

Challenges	
  for	
  cloud	
  PACS	
  
•  Access	
  speeds	
  
•  DiagnosDc	
  quality	
  
•  Tools	
  to	
  manipulate	
  data	
  in	
  real	
  Dme	
  

6	
   |	
  	
  	
  PRESENTATION	
  TITLE	
  	
  	
  |	
  	
  	
  November	
  22,	
  2013	
  	
  	
  |	
  	
  	
  CONFIDENTIAL	
  
PACS	
  FUTURE	
  	
  

ENTERPRISE	
  IMAGING	
  CLOUD	
  

Onsite	
  PACS	
  

Cloud	
  based	
  Enterprise	
  PACS	
  

Third	
  generaMon	
  PACS	
  requirements	
  

Current	
  RIS/PACS	
  
• 91%	
  penetraDon	
  
• 52%	
  older	
  than	
  5	
  years	
  
• 21%	
  plan	
  to	
  replace	
  in	
  12	
  months	
  

Cardiology	
  :	
  60%	
  have	
  no	
  PACS	
  
Pathology:	
  90%	
  have	
  no	
  PACS	
  
7	
   |	
  	
  	
  PRESENTATION	
  TITLE	
  	
  	
  |	
  	
  	
  November	
  22,	
  2013	
  	
  	
  |	
  	
  	
  CONFIDENTIAL	
  

• Enterprise	
  PACS	
  –	
  PaDent	
  centered,	
  mulD-­‐departmental,	
  integrated	
  
image	
  management	
  plalorm	
  
• Cloud	
  based	
  –	
  Strong	
  ROI,	
  distributed	
  mulD-­‐site	
  access	
  at	
  speeds	
  
equal	
  to	
  on	
  site	
  PACS	
  
• Image/report	
  sharing	
  with	
  referring	
  physicians	
  and	
  paDents	
  on	
  
demand	
  	
  
• Higher	
  levels	
  of	
  funcDonality	
  -­‐	
  advanced	
  visualizaDon,	
  computer	
  
aided	
  diagnosis	
  
• IntegraDon	
  with	
  EHRs,	
  HIEs	
  
VoXcell®	
  Cloud	
  

On-­‐Demand	
  	
  
Cloud	
  CompuMng	
  for	
  	
  
Medical	
  Imaging	
  
VOXCELL	
  DEMO	
  
.	
  

!  Bullet	
  
‒  Sub-­‐bullet	
  
‒  TerDary	
  Bullet	
  

9	
   |	
  	
  	
  PRESENTATION	
  TITLE	
  	
  	
  |	
  	
  	
  November	
  22,	
  2013	
  	
  	
  |	
  	
  	
  CONFIDENTIAL	
  
VoXcell®	
  Cloud	
  
Technical	
  Detail	
  
DIFFERENTIATED	
  APPROACH	
  :	
  GPU	
  CLOUD	
  
GPU	
  CLOUD	
  BENEFITS	
  

GPU	
  :	
  1100	
  GFLOPS	
  

Real-­‐Dme	
  diagnosDc	
  quality	
  visualizaDons	
  
• 	
  On-­‐demand	
  and	
  real-­‐Dme	
  radiology	
  
• 	
  IntuiDve	
  results	
  for	
  ordering	
  physicians	
  	
  
• 	
  Connect	
  with	
  paDents	
  	
  

CPU	
  :	
  90	
  GFLOPS	
  

11	
   |	
  	
  	
  PRESENTATION	
  TITLE	
  	
  	
  |	
  	
  	
  November	
  22,	
  2013	
  	
  	
  |	
  	
  	
  CONFIDENTIAL	
  

Faster	
  and	
  Affordable	
  CAD	
  and	
  ‘Big	
  Data’	
  AnalyDcs	
  

• 	
  Improve	
  accuracy	
  
• 	
  Less	
  radiaDon	
  to	
  paDents	
  by	
  reducing	
  unnecessary	
  use	
  of	
  imaging	
  
• 	
  Streamline	
  healthcare	
  and	
  reduce	
  costs	
  
DIFFERENTIATED	
  APPROACH	
  :	
  GPU	
  CLOUD	
  
HIGH	
  DEFINITION	
  VISUALIZATION	
  

" CPU	
  Ray	
  CasDng	
  	
  
(Compromise	
  Quality	
  for	
  Speed)	
  

12	
   |	
  	
  	
  PRESENTATION	
  TITLE	
  	
  	
  |	
  	
  	
  November	
  22,	
  2013	
  	
  	
  |	
  	
  	
  CONFIDENTIAL	
  

" VoXcell	
  GPU	
  Pre-­‐integrated	
  Texturing	
  
DIFFERENTIATED	
  APPROACH	
  :	
  GPU	
  CLOUD	
  
HIGH	
  DEFINITION	
  VISUALIZATION	
  

" CPU	
  Ray	
  CasDng	
  	
  
(Compromise	
  Quality	
  for	
  Speed)	
  

" VoXcell	
  GPU	
  Pre-­‐integrated	
  Texturing	
  

" Real-­‐Dme	
  performance	
  requires	
  early	
  ray	
  
terminaDon	
  once	
  opacity	
  is	
  reached	
  (25%)	
  
!	
  results	
  in	
  hard	
  plasDc	
  looking	
  surfaces.	
  
Transparent	
  surfaces	
  degrades	
  performance.	
  

" Real-­‐Dme	
  performance	
  achieved	
  through	
  
texture	
  mapping	
  polygons	
  !	
  results	
  in	
  
soTer,	
  more	
  realisDc	
  surfaces	
  that	
  includes	
  
interior	
  points.	
  Enables	
  transparent	
  surfaces	
  

13	
   |	
  	
  	
  PRESENTATION	
  TITLE	
  	
  	
  |	
  	
  	
  November	
  22,	
  2013	
  	
  	
  |	
  	
  	
  CONFIDENTIAL	
  
DIFFERENTIATED	
  APPROACH	
  :	
  GPU	
  CLOUD	
  

PREDICTIVE	
  INTELLIGENT	
  STREAMING	
  OVERCOMES	
  LARGE	
  DATA	
  ACCESS	
  SPEED	
  AND	
  LATENCY	
  OVER	
  INTERNET	
  	
  

" Use	
  GPU	
  to	
  manipulate	
  GB	
  of	
  paDent	
  data	
  remotely	
  without	
  transmiqng	
  data	
  to	
  end	
  user	
  
" Access	
  visualizaDons	
  on	
  any	
  device	
  on-­‐demand	
  and	
  real-­‐Dme	
  
" Streaming	
  visualizaDons	
  done	
  by	
  predicDng	
  next	
  frames	
  
" Fast	
  FPS	
  from	
  GPU	
  enable	
  discarding	
  incorrectly	
  predicted	
  frames	
  and	
  generaDng	
  new	
  ones	
  
" Predicted	
  frames	
  are	
  buffered	
  to	
  client	
  overcoming	
  latency	
  
14	
   |	
  	
  	
  PRESENTATION	
  TITLE	
  	
  	
  |	
  	
  	
  November	
  22,	
  2013	
  	
  	
  |	
  	
  	
  CONFIDENTIAL	
  
DIFFERENTIATED	
  APPROACH	
  :	
  GPU	
  CLOUD	
  

ARTIFICIAL	
  INTELLIGENCE	
  LEADS	
  TO	
  INTELLIGENT	
  VISUALIZATIONS®	
  
" Pasern	
  RecogniDon	
  Using	
  ArDficial	
  Neural	
  Network	
  

" HeurisDc	
  Search	
  Using	
  GeneDc	
  Algorithm	
  

CPU	
  :	
  500s	
  

GPU	
  :	
  10s	
  
15K	
  Paserns	
  
" Uses:	
  	
  
" Computer	
  Aided	
  Diagnosis	
  	
  through	
  IntuiDve	
  VisualizaDons	
  
" Cancer	
  or	
  Tumor	
  DetecDon	
  
" SegmenDng	
  Body	
  Parts	
  
" Intelligent	
  VisualizaDon®	
  R&D	
  ParDally	
  Funded	
  by	
  NaDonal	
  Science	
  FoundaDon	
  
15	
   |	
  	
  	
  PRESENTATION	
  TITLE	
  	
  	
  |	
  	
  	
  November	
  22,	
  2013	
  	
  	
  |	
  	
  	
  CONFIDENTIAL	
  

GPU	
  is	
  3000x	
  
over	
  CPU	
  
IP	
  SUMMARY	
  :	
  SUPERCOMPUTING	
  CLOUD	
  
COMPARISON	
  
Legacy	
  PACS	
  

ConvenMonal	
  Cloud	
  

KJAYA’s	
  SupercompuMng	
  Cloud	
  PlaVorm	
  

Transmits	
  raw	
  scans	
  to	
  end	
  users	
  

Streams	
  visualizaDon	
  on	
  demand	
  

Compromises	
  raw	
  scan	
  for	
  faster	
  transmission	
  
• 	
  Not	
  fit	
  for	
  diagnosis	
  
• 	
  Computer	
  Aided	
  Diagnosis	
  (CAD)	
  inaccuracy	
  

HD	
  quality	
  without	
  transmiqng	
  raw	
  scan	
  
• 	
  FDA	
  510K	
  cleared	
  primary	
  diagnosDc	
  use	
  
• 	
  ArDficial	
  Intelligence	
  CAD	
  on	
  gaming	
  technology	
  

Storage	
  servers	
  cannot	
  manipulate	
  or	
  analyze	
  large	
  data	
  –	
  not	
  scalable	
  

Graphics	
  processors	
  for	
  large	
  scan	
  manipulaDon	
  and	
  analyDcs	
  

Powerful	
  PC	
  workstaDon	
  to	
  run	
  clinical	
  app	
  

Clinical	
  apps	
  run	
  on	
  any	
  device	
  

CAD	
  lack	
  breadth	
  of	
  data	
  and	
  processing	
  power	
  

CAD	
  on	
  vast	
  historical	
  and	
  powerful	
  processors	
  using	
  arDficial	
  
intelligence	
  algorithms	
  on	
  GPU	
  

Tools	
  limited	
  by	
  vendor	
  capability	
  

Flexible	
  toolkit	
  >	
  App	
  store	
  for	
  medical	
  imaging	
  

No	
  barriers	
  to	
  entry	
  

Filed	
  patents	
  since	
  2009	
  

16	
   |	
  	
  	
  PRESENTATION	
  TITLE	
  	
  	
  |	
  	
  	
  November	
  22,	
  2013	
  	
  	
  |	
  	
  	
  CONFIDENTIAL	
  
IP	
  :	
  PATENT	
  PENDING	
  PLATFORM	
  
PATENT	
  APPLICATIONS	
  

I.  Secure	
  Cloud	
  SupercompuMng	
  based	
  Medical	
  Imaging	
  System	
  	
  

PCT/US2010/036355	
  for	
  “Method	
  and	
  System	
  for	
  Fast	
  Access	
  to	
  Advanced	
  
VisualizaDon	
  of	
  Medical	
  Scans	
  Using	
  a	
  Dedicated	
  Web	
  Portal”	
  

II.  Hybrid	
  Cloud	
  for	
  Medical	
  Imaging	
  

61/514,295	
  for	
  “Method	
  and	
  System	
  for	
  Fast	
  Access	
  to	
  Advanced	
  
VisualizaDon	
  of	
  Medical	
  Scans	
  Using	
  Hybrid	
  Local	
  and	
  Dedicated	
  Web	
  Portal”	
  

III.  A	
  Scalable	
  Architecture	
  to	
  handle	
  large	
  amounts	
  of	
  data	
  and	
  users	
  

11/672,581	
  for	
  "Method	
  and	
  	
  System	
  for	
  Processing	
  a	
  Volume	
  VisualizaDon	
  
Dataset	
  

IV.  ArMficial	
  Intelligence	
  on	
  GPU	
  for	
  3D	
  and	
  Computer	
  Aided	
  DetecMon	
  
PCT/US11/45047	
  for	
  “AdapDve	
  	
  VisualizaDon	
  for	
  Direct	
  Physician	
  Use”	
  
	
  

V.  Patent	
  Firm:	
  DeLio	
  &	
  Peterson,	
  New	
  Haven,	
  CT	
  
(near	
  Yale	
  University)	
  
17	
   |	
  	
  	
  PRESENTATION	
  TITLE	
  	
  	
  |	
  	
  	
  November	
  22,	
  2013	
  	
  	
  |	
  	
  	
  CONFIDENTIAL	
  
COMPETITIVE	
  LANDSCAPE	
  

PACS	
  	
  

RIS	
  

Intelligent	
  
VisualizaDons®	
  (AI)	
  

3D	
  	
  on	
  any	
  PC	
  

4D	
  	
  on	
  any	
  PC	
  

Image	
  Sharing	
  

Archive	
  &	
  Disaster	
  
Recovery	
  

DiagnosDc	
  Quality	
  
over	
  Internet	
  

FDA	
  Cleared	
  

PredicDve	
  
Streaming	
  (not	
  
downloading)	
  

MulD	
  data	
  center	
  

SupercompuDng	
  
plalorm	
  

.	
  

KJAYA	
  	
  

Y	
  

Y	
  

Y	
  

Y	
  

Y	
  

Y	
  

Y	
  

Y	
  

Y	
  

Y	
  

Y	
  

Y	
  

CareStream	
  	
  

Y	
  

Y	
  

N	
  

N	
  

N	
  

?	
  

Y	
  

N	
  

Y	
  

N	
  

Y	
  

N	
  

TeraRecon*1	
  

N	
  

N	
  

N	
  

Y	
  

N	
  

N	
  

N	
  

?	
  

Y	
  

N	
  

N	
  

N	
  

Shina*1	
  on	
  Amazon	
  Cloud	
  

N	
  

N	
  

N	
  

Y	
  

N	
  

N	
  

N	
  

N	
  

Y	
  

N	
  

Y	
  

N	
  

vRAD	
  

Y	
  

N	
  

N	
  

N	
  

N	
  

N	
  

Y	
  

N	
  

Y	
  

N	
  

Y	
  

N	
  

DICOM	
  Grid	
  	
  

Y	
  

N	
  

N	
  

N	
  

N	
  

Y	
  

Y	
  

N	
  

N	
  

N	
  

N	
  

N	
  

LifeImage*1	
  	
  

N	
  

N	
  

N	
  

N	
  

N	
  

Y	
  

N	
  

N	
  

N	
  

N	
  

N	
  

N	
  

AccelaRad	
  	
  

Y	
  

N	
  

N	
  

N	
  

N	
  

Y	
  

N	
  

N	
  

N	
  

N	
  

N	
  

N	
  

InsiteOne*1	
  	
  

N	
  

N	
  

N	
  

N	
  

N	
  

N	
  

Y	
  

N	
  

N	
  

N	
  

Y	
  

N	
  

BRIT	
  

Y	
  

Y	
  

N	
  

N	
  

N	
  

N	
  

N	
  

N	
  

Y	
  

N	
  

N	
  

N	
  

MedWeb	
  

Y	
  

Y	
  

N	
  

N	
  

N	
  

N	
  

N	
  

N	
  

Y	
  

N	
  

N	
  

N	
  

secureRAD	
  	
  

Y	
  

N	
  

N	
  

N	
  

N	
  

N	
  

?	
  

N	
  

?	
  

N	
  

N	
  

N	
  

ScImage	
  	
  

Y	
  

N	
  

N	
  

N	
  

N	
  

N	
  

?	
  

N	
  

?	
  

N	
  

N	
  

N	
  

NCS	
  

Y	
  

Y	
  

N	
  

N	
  

N	
  

N	
  

?	
  

N	
  

Y	
  

N	
  

N	
  

N	
  

18	
   |	
  	
  	
  PRESENTATION	
  TITLE	
  	
  	
  |	
  	
  	
  November	
  22,	
  2013	
  	
  	
  |	
  	
  	
  CONFIDENTIAL	
  
INDUSTRY	
  INSIDER	
  
RECOGNITIONS	
  

"Most	
  cloud-­‐compuDng	
  services	
  don’t	
  offer	
  diagnosDc-­‐quality	
  images,	
  and	
  the	
  ones	
  
that	
  do	
  typically	
  feature	
  lag	
  Dme,	
  slowing	
  the	
  process.	
  The	
  ability	
  to	
  quickly	
  process	
  
and	
  transmit	
  diagnosDc-­‐level	
  images	
  sets	
  KJAYA	
  apart	
  in	
  this	
  regard."	
  	
  

Christopher	
  Gaerig,	
  	
  
Imaging	
  Economics	
  

“Today’s	
  medical	
  environment	
  demands	
  efficient,	
  cost-­‐effecDve	
  workflow	
  and	
  
VoXcell	
  delivers	
  the	
  tools	
  that	
  can	
  empower	
  faster	
  and	
  more	
  accurate	
  diagnosis	
  
within	
  an	
  extremely	
  affordable	
  fee	
  structure."	
  	
  

Frost	
  &	
  Sullivan	
  

	
  
	
  
“These	
  are	
  ambiDous	
  companies,	
  with	
  highly	
  innovaDve	
  products	
  and	
  business	
  
development	
  strategies	
  that	
  will	
  enable	
  them	
  to	
  carve	
  out	
  a	
  place	
  in	
  global	
  markets....”	
  	
  

KJAYA’s	
  INVESTOR:	
  Enterprise	
  Ireland	
  

19	
   |	
  	
  	
  PRESENTATION	
  TITLE	
  	
  	
  |	
  	
  	
  November	
  22,	
  2013	
  	
  	
  |	
  	
  	
  CONFIDENTIAL	
  
VOXCELL	
  CLOUD	
  
IMPLEMENTATION	
  
CLUSTER	
  COMPONENTS	
  
BIG	
  DATA	
  CLUSTER	
  

A	
  Node	
  
24	
  TB	
  Storage	
  
5	
  TFLOPS	
  	
  AMD	
  GPU	
  
2	
  CPU	
  
Up	
  to	
  192GB	
  Memory	
  
90,000	
  IOPS	
  

Two	
  Nodes	
  
48	
  TB	
  Storage	
  
2	
  AMD	
  GPU	
  (10,000	
  GFLOPS)	
  
4	
  CPU	
  (360	
  GFLOPS)	
  
Up	
  to	
  384GB	
  Memory	
  
180,000	
  IOPS	
  

21	
   |	
  	
  	
  PRESENTATION	
  TITLE	
  	
  	
  |	
  	
  	
  November	
  22,	
  2013	
  	
  	
  |	
  	
  	
  CONFIDENTIAL	
  
CONTENT	
  HEADER	
  
CONTENT	
  SUBHEADER	
  

!  Bullet	
  
‒  Sub-­‐bullet	
  
‒  TerDary	
  Bullet	
  

22	
   |	
  	
  	
  PRESENTATION	
  TITLE	
  	
  	
  |	
  	
  	
  November	
  22,	
  2013	
  	
  	
  |	
  	
  	
  CONFIDENTIAL	
  
APU:	
  	
  
Natural	
  
Progression	
  
ARCHITECTURAL	
  COMPARISON	
  

" CPU+GPU=APU	
  

CPU	
  VERSUS	
  HYBRID	
  CLOUD	
  

ConvenDonal	
  
DiagnosMc	
  

KJAYA’s	
  VoXcell®	
  Cloud	
  

Non-­‐	
  DiagnosMc	
  

	
  " Not	
  	
  on	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  " On	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  Access	
  
	
  	
  	
  	
  	
  	
  	
  	
  	
  	
   	
  	
  	
  	
  	
  
	
  	
  	
  	
  	
  	
  	
  	
  	
  
demand	
  
demand	
  

DiagnosMc	
  

" On	
  
demand	
  
Cloud	
  

Cloud	
  
CPU	
  

	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  Process	
  

CPU	
  

GPU	
  

	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  Data	
  
RelaDonal	
  Database	
  

Storage	
  
	
  

24	
   |	
  	
  	
  PRESENTATION	
  TITLE	
  	
  	
  |	
  	
  	
  November	
  22,	
  2013	
  	
  	
  |	
  	
  	
  CONFIDENTIAL	
  

Big	
  Data	
  Clusters	
  
WHY	
  APU?	
  

REDUCED	
  POWER	
  CONSUMPTION	
  

CPU	
  

GPU	
  

" 5A	
  	
  
" Mostly	
  dissipated	
  as	
  heat	
  	
  

!  VS	
  

25	
   |	
  	
  	
  PRESENTATION	
  TITLE	
  	
  	
  |	
  	
  	
  November	
  22,	
  2013	
  	
  	
  |	
  	
  	
  CONFIDENTIAL	
  
WHY	
  APU?	
  

MANAGE	
  EVER-­‐EXPANDING	
  VOLUMES	
  OF	
  MEDICAL	
  IMAGING	
  DATA	
  

26	
   |	
  	
  	
  PRESENTATION	
  TITLE	
  	
  	
  |	
  	
  	
  November	
  22,	
  2013	
  	
  	
  |	
  	
  	
  CONFIDENTIAL	
  
WHY	
  APU	
  WITH	
  HSA?	
  

HETEROGENEOUS	
  UNIFORM	
  MEMORY	
  ACCESS	
  (HUMA)	
  

27	
   |	
  	
  	
  PRESENTATION	
  TITLE	
  	
  	
  |	
  	
  	
  November	
  22,	
  2013	
  	
  	
  |	
  	
  	
  CONFIDENTIAL	
  
HUMA	
  USAGE	
  IN	
  GPU	
  BASED	
  VOLUME	
  RENDERING	
  
PRE-­‐COMPUTED	
  CLASSIFICATION	
  VOLUME	
  

" Intensity	
  

28	
   |	
  	
  	
  PRESENTATION	
  TITLE	
  	
  	
  |	
  	
  	
  November	
  22,	
  2013	
  	
  	
  |	
  	
  	
  CONFIDENTIAL	
  

" {Bone,	
  Tissue,	
  	
  Air}	
  
GPU	
  BASED	
  MULTIDIMENSIONAL	
  TRANFER	
  FUNCTION	
  VOLUME	
  RENDERING	
  
USING	
  PRE-­‐COMPUTED	
  CLASSIFICATION	
  VOLUME	
  

29	
   |	
  	
  	
  PRESENTATION	
  TITLE	
  	
  	
  |	
  	
  	
  November	
  22,	
  2013	
  	
  	
  |	
  	
  	
  CONFIDENTIAL	
  
DISCLAIMER	
  &	
  ATTRIBUTION	
  

The	
  informaDon	
  presented	
  in	
  this	
  document	
  is	
  for	
  informaDonal	
  purposes	
  only	
  and	
  may	
  contain	
  technical	
  inaccuracies,	
  omissions	
  and	
  typographical	
  errors.	
  
	
  
The	
  informaDon	
  contained	
  herein	
  is	
  subject	
  to	
  change	
  and	
  may	
  be	
  rendered	
  inaccurate	
  for	
  many	
  reasons,	
  including	
  but	
  not	
  limited	
  to	
  product	
  and	
  roadmap	
  
changes,	
  component	
  and	
  motherboard	
  version	
  changes,	
  new	
  model	
  and/or	
  product	
  releases,	
  product	
  differences	
  between	
  differing	
  manufacturers,	
  soTware	
  
changes,	
  BIOS	
  flashes,	
  firmware	
  upgrades,	
  or	
  the	
  like.	
  AMD	
  assumes	
  no	
  obligaDon	
  to	
  update	
  or	
  otherwise	
  correct	
  or	
  revise	
  this	
  informaDon.	
  However,	
  AMD	
  
reserves	
  the	
  right	
  to	
  revise	
  this	
  informaDon	
  and	
  to	
  make	
  changes	
  from	
  Dme	
  to	
  Dme	
  to	
  the	
  content	
  hereof	
  without	
  obligaDon	
  of	
  AMD	
  to	
  noDfy	
  any	
  person	
  of	
  
such	
  revisions	
  or	
  changes.	
  
	
  
AMD	
  MAKES	
  NO	
  REPRESENTATIONS	
  OR	
  WARRANTIES	
  WITH	
  RESPECT	
  TO	
  THE	
  CONTENTS	
  HEREOF	
  AND	
  ASSUMES	
  NO	
  RESPONSIBILITY	
  FOR	
  ANY	
  
INACCURACIES,	
  ERRORS	
  OR	
  OMISSIONS	
  THAT	
  MAY	
  APPEAR	
  IN	
  THIS	
  INFORMATION.	
  
	
  
AMD	
  SPECIFICALLY	
  DISCLAIMS	
  ANY	
  IMPLIED	
  WARRANTIES	
  OF	
  MERCHANTABILITY	
  OR	
  FITNESS	
  FOR	
  ANY	
  PARTICULAR	
  PURPOSE.	
  IN	
  NO	
  EVENT	
  WILL	
  AMD	
  BE	
  
LIABLE	
  TO	
  ANY	
  PERSON	
  FOR	
  ANY	
  DIRECT,	
  INDIRECT,	
  SPECIAL	
  OR	
  OTHER	
  CONSEQUENTIAL	
  DAMAGES	
  ARISING	
  FROM	
  THE	
  USE	
  OF	
  ANY	
  INFORMATION	
  
CONTAINED	
  HEREIN,	
  EVEN	
  IF	
  AMD	
  IS	
  EXPRESSLY	
  ADVISED	
  OF	
  THE	
  POSSIBILITY	
  OF	
  SUCH	
  DAMAGES.	
  
	
  
ATTRIBUTION	
  
©	
  2013	
  Advanced	
  Micro	
  Devices,	
  Inc.	
  All	
  rights	
  reserved.	
  AMD,	
  the	
  AMD	
  Arrow	
  logo	
  and	
  combinaDons	
  thereof	
  are	
  trademarks	
  of	
  Advanced	
  Micro	
  Devices,	
  
Inc.	
  in	
  the	
  United	
  States	
  and/or	
  other	
  jurisdicDons.	
  	
  SPEC	
  	
  is	
  a	
  registered	
  trademark	
  of	
  the	
  Standard	
  Performance	
  EvaluaDon	
  CorporaDon	
  (SPEC).	
  Other	
  
names	
  are	
  for	
  informaDonal	
  purposes	
  only	
  and	
  may	
  be	
  trademarks	
  of	
  their	
  respecDve	
  owners.	
  
30	
   |	
  	
  	
  PRESENTATION	
  TITLE	
  	
  	
  |	
  	
  	
  November	
  22,	
  2013	
  	
  	
  |	
  	
  	
  CONFIDENTIAL	
  

Contenu connexe

Tendances

Accelerate AI w/ Synthetic Data using GANs
Accelerate AI w/ Synthetic Data using GANsAccelerate AI w/ Synthetic Data using GANs
Accelerate AI w/ Synthetic Data using GANsRenee Yao
 
Enabling Artificial Intelligence - Alison B. Lowndes
Enabling Artificial Intelligence - Alison B. LowndesEnabling Artificial Intelligence - Alison B. Lowndes
Enabling Artificial Intelligence - Alison B. LowndesWithTheBest
 
AI, A New Computing Model
AI, A New Computing ModelAI, A New Computing Model
AI, A New Computing ModelNVIDIA Taiwan
 
GTC Taiwan 2017 自主駕駛車輛發展平台與技術研發
GTC Taiwan 2017 自主駕駛車輛發展平台與技術研發 GTC Taiwan 2017 自主駕駛車輛發展平台與技術研發
GTC Taiwan 2017 自主駕駛車輛發展平台與技術研發 NVIDIA Taiwan
 
GTC Taiwan 2017 在 Google Cloud 當中使用 GPU 進行效能最佳化
GTC Taiwan 2017 在 Google Cloud 當中使用 GPU 進行效能最佳化GTC Taiwan 2017 在 Google Cloud 當中使用 GPU 進行效能最佳化
GTC Taiwan 2017 在 Google Cloud 當中使用 GPU 進行效能最佳化NVIDIA Taiwan
 
GTC China 2016
GTC China 2016GTC China 2016
GTC China 2016NVIDIA
 
State of the Art Robot Predictive Maintenance with Real-time Sensor Data
State of the Art Robot Predictive Maintenance with Real-time Sensor DataState of the Art Robot Predictive Maintenance with Real-time Sensor Data
State of the Art Robot Predictive Maintenance with Real-time Sensor DataMathieu Dumoulin
 
Nvidia Deep Learning Solutions - Alex Sabatier
Nvidia Deep Learning Solutions - Alex SabatierNvidia Deep Learning Solutions - Alex Sabatier
Nvidia Deep Learning Solutions - Alex SabatierSri Ambati
 
Simplifying AI Infrastructure: Lessons in Scaling on DGX Systems
Simplifying AI Infrastructure: Lessons in Scaling on DGX SystemsSimplifying AI Infrastructure: Lessons in Scaling on DGX Systems
Simplifying AI Infrastructure: Lessons in Scaling on DGX SystemsRenee Yao
 
GPU Accelerated Deep Learning for CUDNN V2
GPU Accelerated Deep Learning for CUDNN V2GPU Accelerated Deep Learning for CUDNN V2
GPU Accelerated Deep Learning for CUDNN V2NVIDIA
 
How to Choose Mobile Workstation? VR Ready
How to Choose Mobile Workstation? VR ReadyHow to Choose Mobile Workstation? VR Ready
How to Choose Mobile Workstation? VR ReadyNVIDIA Taiwan
 
MapR and Machine Learning Primer
MapR and Machine Learning PrimerMapR and Machine Learning Primer
MapR and Machine Learning PrimerMathieu Dumoulin
 
The Visual Computing Company
The Visual Computing CompanyThe Visual Computing Company
The Visual Computing CompanyGrupo Texium
 
Streaming Architecture to Connect Everything (Including Hybrid Cloud) - Strat...
Streaming Architecture to Connect Everything (Including Hybrid Cloud) - Strat...Streaming Architecture to Connect Everything (Including Hybrid Cloud) - Strat...
Streaming Architecture to Connect Everything (Including Hybrid Cloud) - Strat...Mathieu Dumoulin
 
Building the World's Largest GPU
Building the World's Largest GPUBuilding the World's Largest GPU
Building the World's Largest GPURenee Yao
 
Transparent Hardware Acceleration for Deep Learning
Transparent Hardware Acceleration for Deep LearningTransparent Hardware Acceleration for Deep Learning
Transparent Hardware Acceleration for Deep LearningIndrajit Poddar
 

Tendances (20)

Accelerate AI w/ Synthetic Data using GANs
Accelerate AI w/ Synthetic Data using GANsAccelerate AI w/ Synthetic Data using GANs
Accelerate AI w/ Synthetic Data using GANs
 
NVIDIA Keynote #GTC21
NVIDIA Keynote #GTC21 NVIDIA Keynote #GTC21
NVIDIA Keynote #GTC21
 
Enabling Artificial Intelligence - Alison B. Lowndes
Enabling Artificial Intelligence - Alison B. LowndesEnabling Artificial Intelligence - Alison B. Lowndes
Enabling Artificial Intelligence - Alison B. Lowndes
 
AI, A New Computing Model
AI, A New Computing ModelAI, A New Computing Model
AI, A New Computing Model
 
GTC Taiwan 2017 自主駕駛車輛發展平台與技術研發
GTC Taiwan 2017 自主駕駛車輛發展平台與技術研發 GTC Taiwan 2017 自主駕駛車輛發展平台與技術研發
GTC Taiwan 2017 自主駕駛車輛發展平台與技術研發
 
GTC Taiwan 2017 在 Google Cloud 當中使用 GPU 進行效能最佳化
GTC Taiwan 2017 在 Google Cloud 當中使用 GPU 進行效能最佳化GTC Taiwan 2017 在 Google Cloud 當中使用 GPU 進行效能最佳化
GTC Taiwan 2017 在 Google Cloud 當中使用 GPU 進行效能最佳化
 
GTC China 2016
GTC China 2016GTC China 2016
GTC China 2016
 
State of the Art Robot Predictive Maintenance with Real-time Sensor Data
State of the Art Robot Predictive Maintenance with Real-time Sensor DataState of the Art Robot Predictive Maintenance with Real-time Sensor Data
State of the Art Robot Predictive Maintenance with Real-time Sensor Data
 
Nvidia Deep Learning Solutions - Alex Sabatier
Nvidia Deep Learning Solutions - Alex SabatierNvidia Deep Learning Solutions - Alex Sabatier
Nvidia Deep Learning Solutions - Alex Sabatier
 
NVIDIA DataArt IT
NVIDIA DataArt ITNVIDIA DataArt IT
NVIDIA DataArt IT
 
Simplifying AI Infrastructure: Lessons in Scaling on DGX Systems
Simplifying AI Infrastructure: Lessons in Scaling on DGX SystemsSimplifying AI Infrastructure: Lessons in Scaling on DGX Systems
Simplifying AI Infrastructure: Lessons in Scaling on DGX Systems
 
AI + E-commerce
AI + E-commerceAI + E-commerce
AI + E-commerce
 
GPU Accelerated Deep Learning for CUDNN V2
GPU Accelerated Deep Learning for CUDNN V2GPU Accelerated Deep Learning for CUDNN V2
GPU Accelerated Deep Learning for CUDNN V2
 
How to Choose Mobile Workstation? VR Ready
How to Choose Mobile Workstation? VR ReadyHow to Choose Mobile Workstation? VR Ready
How to Choose Mobile Workstation? VR Ready
 
MapR and Machine Learning Primer
MapR and Machine Learning PrimerMapR and Machine Learning Primer
MapR and Machine Learning Primer
 
The Visual Computing Company
The Visual Computing CompanyThe Visual Computing Company
The Visual Computing Company
 
Streaming Architecture to Connect Everything (Including Hybrid Cloud) - Strat...
Streaming Architecture to Connect Everything (Including Hybrid Cloud) - Strat...Streaming Architecture to Connect Everything (Including Hybrid Cloud) - Strat...
Streaming Architecture to Connect Everything (Including Hybrid Cloud) - Strat...
 
Hardware in Space
Hardware in SpaceHardware in Space
Hardware in Space
 
Building the World's Largest GPU
Building the World's Largest GPUBuilding the World's Largest GPU
Building the World's Largest GPU
 
Transparent Hardware Acceleration for Deep Learning
Transparent Hardware Acceleration for Deep LearningTransparent Hardware Acceleration for Deep Learning
Transparent Hardware Acceleration for Deep Learning
 

En vedette

Cloud Computing - Fergal O'Connor
Cloud Computing - Fergal O'ConnorCloud Computing - Fergal O'Connor
Cloud Computing - Fergal O'Connorhealthcareisi
 
Gerard Hurl - Industry Presentation 26-04-12
Gerard Hurl - Industry Presentation 26-04-12Gerard Hurl - Industry Presentation 26-04-12
Gerard Hurl - Industry Presentation 26-04-12healthcareisi
 
Medical Records in the Cloud
Medical Records in the CloudMedical Records in the Cloud
Medical Records in the Cloudcadcamservices
 
CRTC Cloud- Scott Sadler
CRTC Cloud- Scott SadlerCRTC Cloud- Scott Sadler
CRTC Cloud- Scott SadlerKrisValerio
 
Securing_Medical_Imaging_in_the_Cloud_Whitepaper
Securing_Medical_Imaging_in_the_Cloud_WhitepaperSecuring_Medical_Imaging_in_the_Cloud_Whitepaper
Securing_Medical_Imaging_in_the_Cloud_Whitepaperlaurenstill
 
Medical imaging in_the_cloud
Medical imaging in_the_cloudMedical imaging in_the_cloud
Medical imaging in_the_cloudAccenture
 
Imaging in the Cloud: A New Era for Radiology
Imaging in the Cloud: A New Era for RadiologyImaging in the Cloud: A New Era for Radiology
Imaging in the Cloud: A New Era for RadiologyCarestream
 
Mobile cloud for Healthcare
Mobile cloud for HealthcareMobile cloud for Healthcare
Mobile cloud for HealthcareSaurav Gupta
 
Health IT Summit DC 2015 - Cloud Storage and Medical Image Management: Resp...
Health IT Summit DC 2015 -  Cloud Storage and Medical Image Management:  Resp...Health IT Summit DC 2015 -  Cloud Storage and Medical Image Management:  Resp...
Health IT Summit DC 2015 - Cloud Storage and Medical Image Management: Resp...Health IT Conference – iHT2
 
Cloud eHealth in Medical Imaging & Radiology
Cloud eHealth in Medical Imaging & RadiologyCloud eHealth in Medical Imaging & Radiology
Cloud eHealth in Medical Imaging & RadiologyCarestream
 
DriCloud. Cloud based Electronic Medical Record
DriCloud. Cloud based Electronic Medical RecordDriCloud. Cloud based Electronic Medical Record
DriCloud. Cloud based Electronic Medical Recorddricloud
 
2016 AWS Healthcare Days | Nashville, TN – May 3,2016
2016 AWS Healthcare Days | Nashville, TN – May 3,20162016 AWS Healthcare Days | Nashville, TN – May 3,2016
2016 AWS Healthcare Days | Nashville, TN – May 3,2016Amazon Web Services
 
DICOM Medical Imaging by Cloud Medical Imaging
DICOM Medical Imaging by Cloud Medical ImagingDICOM Medical Imaging by Cloud Medical Imaging
DICOM Medical Imaging by Cloud Medical ImagingCloudMedicalImaging
 
Strategic Uses for Cost Efficient Long-Term Cloud Storage
Strategic Uses for Cost Efficient Long-Term Cloud StorageStrategic Uses for Cost Efficient Long-Term Cloud Storage
Strategic Uses for Cost Efficient Long-Term Cloud StorageAmazon Web Services
 
Introduction of Cloud computing
Introduction of Cloud computingIntroduction of Cloud computing
Introduction of Cloud computingRkrishna Mishra
 

En vedette (17)

Cloud Computing - Fergal O'Connor
Cloud Computing - Fergal O'ConnorCloud Computing - Fergal O'Connor
Cloud Computing - Fergal O'Connor
 
Gerard Hurl - Industry Presentation 26-04-12
Gerard Hurl - Industry Presentation 26-04-12Gerard Hurl - Industry Presentation 26-04-12
Gerard Hurl - Industry Presentation 26-04-12
 
Medical Records in the Cloud
Medical Records in the CloudMedical Records in the Cloud
Medical Records in the Cloud
 
CRTC Cloud- Scott Sadler
CRTC Cloud- Scott SadlerCRTC Cloud- Scott Sadler
CRTC Cloud- Scott Sadler
 
Securing_Medical_Imaging_in_the_Cloud_Whitepaper
Securing_Medical_Imaging_in_the_Cloud_WhitepaperSecuring_Medical_Imaging_in_the_Cloud_Whitepaper
Securing_Medical_Imaging_in_the_Cloud_Whitepaper
 
Medical imaging in_the_cloud
Medical imaging in_the_cloudMedical imaging in_the_cloud
Medical imaging in_the_cloud
 
Imaging in the Cloud: A New Era for Radiology
Imaging in the Cloud: A New Era for RadiologyImaging in the Cloud: A New Era for Radiology
Imaging in the Cloud: A New Era for Radiology
 
Mobile cloud for Healthcare
Mobile cloud for HealthcareMobile cloud for Healthcare
Mobile cloud for Healthcare
 
Health IT Summit DC 2015 - Cloud Storage and Medical Image Management: Resp...
Health IT Summit DC 2015 -  Cloud Storage and Medical Image Management:  Resp...Health IT Summit DC 2015 -  Cloud Storage and Medical Image Management:  Resp...
Health IT Summit DC 2015 - Cloud Storage and Medical Image Management: Resp...
 
Cloud eHealth in Medical Imaging & Radiology
Cloud eHealth in Medical Imaging & RadiologyCloud eHealth in Medical Imaging & Radiology
Cloud eHealth in Medical Imaging & Radiology
 
DriCloud. Cloud based Electronic Medical Record
DriCloud. Cloud based Electronic Medical RecordDriCloud. Cloud based Electronic Medical Record
DriCloud. Cloud based Electronic Medical Record
 
2016 iHT2 Miami Health IT Summit
2016 iHT2 Miami Health IT Summit2016 iHT2 Miami Health IT Summit
2016 iHT2 Miami Health IT Summit
 
2016 AWS Healthcare Days | Nashville, TN – May 3,2016
2016 AWS Healthcare Days | Nashville, TN – May 3,20162016 AWS Healthcare Days | Nashville, TN – May 3,2016
2016 AWS Healthcare Days | Nashville, TN – May 3,2016
 
IoT in Healthcare
IoT in HealthcareIoT in Healthcare
IoT in Healthcare
 
DICOM Medical Imaging by Cloud Medical Imaging
DICOM Medical Imaging by Cloud Medical ImagingDICOM Medical Imaging by Cloud Medical Imaging
DICOM Medical Imaging by Cloud Medical Imaging
 
Strategic Uses for Cost Efficient Long-Term Cloud Storage
Strategic Uses for Cost Efficient Long-Term Cloud StorageStrategic Uses for Cost Efficient Long-Term Cloud Storage
Strategic Uses for Cost Efficient Long-Term Cloud Storage
 
Introduction of Cloud computing
Introduction of Cloud computingIntroduction of Cloud computing
Introduction of Cloud computing
 

Similaire à IS-4003, A Cloud Based Medical Imaging Platform Using APU, by Kovey Kovalan

Pellucid radproducts
Pellucid radproductsPellucid radproducts
Pellucid radproductsdieple88
 
Pellucid radproducts
Pellucid radproductsPellucid radproducts
Pellucid radproductsdieple88
 
Deep Learning & AI for Healthcare and Retail
Deep Learning & AI for Healthcare and RetailDeep Learning & AI for Healthcare and Retail
Deep Learning & AI for Healthcare and RetailE2E Networks Limited
 
Virtual Human Brain Simulations with Abaqus in the Cloud
Virtual Human Brain Simulations with Abaqus in the CloudVirtual Human Brain Simulations with Abaqus in the Cloud
Virtual Human Brain Simulations with Abaqus in the CloudThe UberCloud
 
Deep learning customer stories
Deep learning customer storiesDeep learning customer stories
Deep learning customer storiesAlison B. Lowndes
 
How sdp delivers_zero_trust
How sdp delivers_zero_trustHow sdp delivers_zero_trust
How sdp delivers_zero_trustZscaler
 
Cloud-Based Solutions for Clinical Data Management
Cloud-Based Solutions for Clinical Data ManagementCloud-Based Solutions for Clinical Data Management
Cloud-Based Solutions for Clinical Data ManagementClinosolIndia
 
I V I F2 F July 2005 Talk
I V I  F2 F  July 2005  TalkI V I  F2 F  July 2005  Talk
I V I F2 F July 2005 Talkbattagline
 
20670-39030-2-PB.pdf
20670-39030-2-PB.pdf20670-39030-2-PB.pdf
20670-39030-2-PB.pdfIjictTeam
 
Internet of Things (IoT) is a King, Big data is a Queen and Cloud is a Palace
Internet of Things (IoT) is a King, Big data is a Queen and Cloud is a PalaceInternet of Things (IoT) is a King, Big data is a Queen and Cloud is a Palace
Internet of Things (IoT) is a King, Big data is a Queen and Cloud is a PalaceDr.-Ing Abdur Rahim Biswas
 
Dell NVIDIA AI Powered Transformation in Healthcare and Life Sciences Webinar
Dell NVIDIA AI Powered Transformation in Healthcare and Life Sciences WebinarDell NVIDIA AI Powered Transformation in Healthcare and Life Sciences Webinar
Dell NVIDIA AI Powered Transformation in Healthcare and Life Sciences WebinarBill Wong
 
Welcome to Your Compact, Data-Driven, Generator-Free Data Center Future
Welcome to Your Compact, Data-Driven, Generator-Free Data Center FutureWelcome to Your Compact, Data-Driven, Generator-Free Data Center Future
Welcome to Your Compact, Data-Driven, Generator-Free Data Center FutureAbaram Network Solutions
 
Digital supply chain quality management
Digital supply chain quality managementDigital supply chain quality management
Digital supply chain quality managementMartin Geddes
 
Steve Jenkins - Business Opportunities for Big Data in the Enterprise
Steve Jenkins - Business Opportunities for Big Data in the Enterprise Steve Jenkins - Business Opportunities for Big Data in the Enterprise
Steve Jenkins - Business Opportunities for Big Data in the Enterprise WeAreEsynergy
 
Unlocking the Power of Data: Data Driven Product Engineering, Evren Eryurek, ...
Unlocking the Power of Data: Data Driven Product Engineering, Evren Eryurek, ...Unlocking the Power of Data: Data Driven Product Engineering, Evren Eryurek, ...
Unlocking the Power of Data: Data Driven Product Engineering, Evren Eryurek, ...Zinnov
 
AIDC NY: Applications of Intel AI by QuEST Global - 09.19.2019
AIDC NY: Applications of Intel AI by QuEST Global - 09.19.2019AIDC NY: Applications of Intel AI by QuEST Global - 09.19.2019
AIDC NY: Applications of Intel AI by QuEST Global - 09.19.2019Intel® Software
 
Seminar (patient monitoring using wireless system)(new)
Seminar (patient monitoring using wireless system)(new)Seminar (patient monitoring using wireless system)(new)
Seminar (patient monitoring using wireless system)(new)SagarKumar153
 
Miacell Project leaflet
Miacell Project leafletMiacell Project leaflet
Miacell Project leafletAndrea Corona
 

Similaire à IS-4003, A Cloud Based Medical Imaging Platform Using APU, by Kovey Kovalan (20)

Pellucid radproducts
Pellucid radproductsPellucid radproducts
Pellucid radproducts
 
Pellucid radproducts
Pellucid radproductsPellucid radproducts
Pellucid radproducts
 
Deep Learning & AI for Healthcare and Retail
Deep Learning & AI for Healthcare and RetailDeep Learning & AI for Healthcare and Retail
Deep Learning & AI for Healthcare and Retail
 
Digital pathology
Digital pathologyDigital pathology
Digital pathology
 
Virtual Human Brain Simulations with Abaqus in the Cloud
Virtual Human Brain Simulations with Abaqus in the CloudVirtual Human Brain Simulations with Abaqus in the Cloud
Virtual Human Brain Simulations with Abaqus in the Cloud
 
Deep learning customer stories
Deep learning customer storiesDeep learning customer stories
Deep learning customer stories
 
How sdp delivers_zero_trust
How sdp delivers_zero_trustHow sdp delivers_zero_trust
How sdp delivers_zero_trust
 
Cloud-Based Solutions for Clinical Data Management
Cloud-Based Solutions for Clinical Data ManagementCloud-Based Solutions for Clinical Data Management
Cloud-Based Solutions for Clinical Data Management
 
I V I F2 F July 2005 Talk
I V I  F2 F  July 2005  TalkI V I  F2 F  July 2005  Talk
I V I F2 F July 2005 Talk
 
20670-39030-2-PB.pdf
20670-39030-2-PB.pdf20670-39030-2-PB.pdf
20670-39030-2-PB.pdf
 
Internet of Things (IoT) is a King, Big data is a Queen and Cloud is a Palace
Internet of Things (IoT) is a King, Big data is a Queen and Cloud is a PalaceInternet of Things (IoT) is a King, Big data is a Queen and Cloud is a Palace
Internet of Things (IoT) is a King, Big data is a Queen and Cloud is a Palace
 
Dell NVIDIA AI Powered Transformation in Healthcare and Life Sciences Webinar
Dell NVIDIA AI Powered Transformation in Healthcare and Life Sciences WebinarDell NVIDIA AI Powered Transformation in Healthcare and Life Sciences Webinar
Dell NVIDIA AI Powered Transformation in Healthcare and Life Sciences Webinar
 
Welcome to Your Compact, Data-Driven, Generator-Free Data Center Future
Welcome to Your Compact, Data-Driven, Generator-Free Data Center FutureWelcome to Your Compact, Data-Driven, Generator-Free Data Center Future
Welcome to Your Compact, Data-Driven, Generator-Free Data Center Future
 
Digital supply chain quality management
Digital supply chain quality managementDigital supply chain quality management
Digital supply chain quality management
 
Digtal radiography and imaging
Digtal radiography and imagingDigtal radiography and imaging
Digtal radiography and imaging
 
Steve Jenkins - Business Opportunities for Big Data in the Enterprise
Steve Jenkins - Business Opportunities for Big Data in the Enterprise Steve Jenkins - Business Opportunities for Big Data in the Enterprise
Steve Jenkins - Business Opportunities for Big Data in the Enterprise
 
Unlocking the Power of Data: Data Driven Product Engineering, Evren Eryurek, ...
Unlocking the Power of Data: Data Driven Product Engineering, Evren Eryurek, ...Unlocking the Power of Data: Data Driven Product Engineering, Evren Eryurek, ...
Unlocking the Power of Data: Data Driven Product Engineering, Evren Eryurek, ...
 
AIDC NY: Applications of Intel AI by QuEST Global - 09.19.2019
AIDC NY: Applications of Intel AI by QuEST Global - 09.19.2019AIDC NY: Applications of Intel AI by QuEST Global - 09.19.2019
AIDC NY: Applications of Intel AI by QuEST Global - 09.19.2019
 
Seminar (patient monitoring using wireless system)(new)
Seminar (patient monitoring using wireless system)(new)Seminar (patient monitoring using wireless system)(new)
Seminar (patient monitoring using wireless system)(new)
 
Miacell Project leaflet
Miacell Project leafletMiacell Project leaflet
Miacell Project leaflet
 

Plus de AMD Developer Central

DX12 & Vulkan: Dawn of a New Generation of Graphics APIs
DX12 & Vulkan: Dawn of a New Generation of Graphics APIsDX12 & Vulkan: Dawn of a New Generation of Graphics APIs
DX12 & Vulkan: Dawn of a New Generation of Graphics APIsAMD Developer Central
 
Leverage the Speed of OpenCL™ with AMD Math Libraries
Leverage the Speed of OpenCL™ with AMD Math LibrariesLeverage the Speed of OpenCL™ with AMD Math Libraries
Leverage the Speed of OpenCL™ with AMD Math LibrariesAMD Developer Central
 
An Introduction to OpenCL™ Programming with AMD GPUs - AMD & Acceleware Webinar
An Introduction to OpenCL™ Programming with AMD GPUs - AMD & Acceleware WebinarAn Introduction to OpenCL™ Programming with AMD GPUs - AMD & Acceleware Webinar
An Introduction to OpenCL™ Programming with AMD GPUs - AMD & Acceleware WebinarAMD Developer Central
 
Webinar: Whats New in Java 8 with Develop Intelligence
Webinar: Whats New in Java 8 with Develop IntelligenceWebinar: Whats New in Java 8 with Develop Intelligence
Webinar: Whats New in Java 8 with Develop IntelligenceAMD Developer Central
 
The Small Batch (and other) solutions in Mantle API, by Guennadi Riguer, Mant...
The Small Batch (and other) solutions in Mantle API, by Guennadi Riguer, Mant...The Small Batch (and other) solutions in Mantle API, by Guennadi Riguer, Mant...
The Small Batch (and other) solutions in Mantle API, by Guennadi Riguer, Mant...AMD Developer Central
 
TressFX The Fast and The Furry by Nicolas Thibieroz
TressFX The Fast and The Furry by Nicolas ThibierozTressFX The Fast and The Furry by Nicolas Thibieroz
TressFX The Fast and The Furry by Nicolas ThibierozAMD Developer Central
 
Rendering Battlefield 4 with Mantle by Yuriy ODonnell
Rendering Battlefield 4 with Mantle by Yuriy ODonnellRendering Battlefield 4 with Mantle by Yuriy ODonnell
Rendering Battlefield 4 with Mantle by Yuriy ODonnellAMD Developer Central
 
Low-level Shader Optimization for Next-Gen and DX11 by Emil Persson
Low-level Shader Optimization for Next-Gen and DX11 by Emil PerssonLow-level Shader Optimization for Next-Gen and DX11 by Emil Persson
Low-level Shader Optimization for Next-Gen and DX11 by Emil PerssonAMD Developer Central
 
Direct3D12 and the Future of Graphics APIs by Dave Oldcorn
Direct3D12 and the Future of Graphics APIs by Dave OldcornDirect3D12 and the Future of Graphics APIs by Dave Oldcorn
Direct3D12 and the Future of Graphics APIs by Dave OldcornAMD Developer Central
 
Introduction to Direct 3D 12 by Ivan Nevraev
Introduction to Direct 3D 12 by Ivan NevraevIntroduction to Direct 3D 12 by Ivan Nevraev
Introduction to Direct 3D 12 by Ivan NevraevAMD Developer Central
 
Holy smoke! Faster Particle Rendering using Direct Compute by Gareth Thomas
Holy smoke! Faster Particle Rendering using Direct Compute by Gareth ThomasHoly smoke! Faster Particle Rendering using Direct Compute by Gareth Thomas
Holy smoke! Faster Particle Rendering using Direct Compute by Gareth ThomasAMD Developer Central
 
Computer Vision Powered by Heterogeneous System Architecture (HSA) by Dr. Ha...
Computer Vision Powered by Heterogeneous System Architecture (HSA) by  Dr. Ha...Computer Vision Powered by Heterogeneous System Architecture (HSA) by  Dr. Ha...
Computer Vision Powered by Heterogeneous System Architecture (HSA) by Dr. Ha...AMD Developer Central
 
Productive OpenCL Programming An Introduction to OpenCL Libraries with Array...
Productive OpenCL Programming An Introduction to OpenCL Libraries  with Array...Productive OpenCL Programming An Introduction to OpenCL Libraries  with Array...
Productive OpenCL Programming An Introduction to OpenCL Libraries with Array...AMD Developer Central
 
Rendering Battlefield 4 with Mantle by Johan Andersson - AMD at GDC14
Rendering Battlefield 4 with Mantle by Johan Andersson - AMD at GDC14Rendering Battlefield 4 with Mantle by Johan Andersson - AMD at GDC14
Rendering Battlefield 4 with Mantle by Johan Andersson - AMD at GDC14AMD Developer Central
 

Plus de AMD Developer Central (20)

DX12 & Vulkan: Dawn of a New Generation of Graphics APIs
DX12 & Vulkan: Dawn of a New Generation of Graphics APIsDX12 & Vulkan: Dawn of a New Generation of Graphics APIs
DX12 & Vulkan: Dawn of a New Generation of Graphics APIs
 
Leverage the Speed of OpenCL™ with AMD Math Libraries
Leverage the Speed of OpenCL™ with AMD Math LibrariesLeverage the Speed of OpenCL™ with AMD Math Libraries
Leverage the Speed of OpenCL™ with AMD Math Libraries
 
Introduction to Node.js
Introduction to Node.jsIntroduction to Node.js
Introduction to Node.js
 
Media SDK Webinar 2014
Media SDK Webinar 2014Media SDK Webinar 2014
Media SDK Webinar 2014
 
An Introduction to OpenCL™ Programming with AMD GPUs - AMD & Acceleware Webinar
An Introduction to OpenCL™ Programming with AMD GPUs - AMD & Acceleware WebinarAn Introduction to OpenCL™ Programming with AMD GPUs - AMD & Acceleware Webinar
An Introduction to OpenCL™ Programming with AMD GPUs - AMD & Acceleware Webinar
 
DirectGMA on AMD’S FirePro™ GPUS
DirectGMA on AMD’S  FirePro™ GPUSDirectGMA on AMD’S  FirePro™ GPUS
DirectGMA on AMD’S FirePro™ GPUS
 
Webinar: Whats New in Java 8 with Develop Intelligence
Webinar: Whats New in Java 8 with Develop IntelligenceWebinar: Whats New in Java 8 with Develop Intelligence
Webinar: Whats New in Java 8 with Develop Intelligence
 
The Small Batch (and other) solutions in Mantle API, by Guennadi Riguer, Mant...
The Small Batch (and other) solutions in Mantle API, by Guennadi Riguer, Mant...The Small Batch (and other) solutions in Mantle API, by Guennadi Riguer, Mant...
The Small Batch (and other) solutions in Mantle API, by Guennadi Riguer, Mant...
 
Inside XBox- One, by Martin Fuller
Inside XBox- One, by Martin FullerInside XBox- One, by Martin Fuller
Inside XBox- One, by Martin Fuller
 
TressFX The Fast and The Furry by Nicolas Thibieroz
TressFX The Fast and The Furry by Nicolas ThibierozTressFX The Fast and The Furry by Nicolas Thibieroz
TressFX The Fast and The Furry by Nicolas Thibieroz
 
Rendering Battlefield 4 with Mantle by Yuriy ODonnell
Rendering Battlefield 4 with Mantle by Yuriy ODonnellRendering Battlefield 4 with Mantle by Yuriy ODonnell
Rendering Battlefield 4 with Mantle by Yuriy ODonnell
 
Low-level Shader Optimization for Next-Gen and DX11 by Emil Persson
Low-level Shader Optimization for Next-Gen and DX11 by Emil PerssonLow-level Shader Optimization for Next-Gen and DX11 by Emil Persson
Low-level Shader Optimization for Next-Gen and DX11 by Emil Persson
 
Gcn performance ftw by stephan hodes
Gcn performance ftw by stephan hodesGcn performance ftw by stephan hodes
Gcn performance ftw by stephan hodes
 
Inside XBOX ONE by Martin Fuller
Inside XBOX ONE by Martin FullerInside XBOX ONE by Martin Fuller
Inside XBOX ONE by Martin Fuller
 
Direct3D12 and the Future of Graphics APIs by Dave Oldcorn
Direct3D12 and the Future of Graphics APIs by Dave OldcornDirect3D12 and the Future of Graphics APIs by Dave Oldcorn
Direct3D12 and the Future of Graphics APIs by Dave Oldcorn
 
Introduction to Direct 3D 12 by Ivan Nevraev
Introduction to Direct 3D 12 by Ivan NevraevIntroduction to Direct 3D 12 by Ivan Nevraev
Introduction to Direct 3D 12 by Ivan Nevraev
 
Holy smoke! Faster Particle Rendering using Direct Compute by Gareth Thomas
Holy smoke! Faster Particle Rendering using Direct Compute by Gareth ThomasHoly smoke! Faster Particle Rendering using Direct Compute by Gareth Thomas
Holy smoke! Faster Particle Rendering using Direct Compute by Gareth Thomas
 
Computer Vision Powered by Heterogeneous System Architecture (HSA) by Dr. Ha...
Computer Vision Powered by Heterogeneous System Architecture (HSA) by  Dr. Ha...Computer Vision Powered by Heterogeneous System Architecture (HSA) by  Dr. Ha...
Computer Vision Powered by Heterogeneous System Architecture (HSA) by Dr. Ha...
 
Productive OpenCL Programming An Introduction to OpenCL Libraries with Array...
Productive OpenCL Programming An Introduction to OpenCL Libraries  with Array...Productive OpenCL Programming An Introduction to OpenCL Libraries  with Array...
Productive OpenCL Programming An Introduction to OpenCL Libraries with Array...
 
Rendering Battlefield 4 with Mantle by Johan Andersson - AMD at GDC14
Rendering Battlefield 4 with Mantle by Johan Andersson - AMD at GDC14Rendering Battlefield 4 with Mantle by Johan Andersson - AMD at GDC14
Rendering Battlefield 4 with Mantle by Johan Andersson - AMD at GDC14
 

Dernier

WordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your BrandWordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your Brandgvaughan
 
DevoxxFR 2024 Reproducible Builds with Apache Maven
DevoxxFR 2024 Reproducible Builds with Apache MavenDevoxxFR 2024 Reproducible Builds with Apache Maven
DevoxxFR 2024 Reproducible Builds with Apache MavenHervé Boutemy
 
Vector Databases 101 - An introduction to the world of Vector Databases
Vector Databases 101 - An introduction to the world of Vector DatabasesVector Databases 101 - An introduction to the world of Vector Databases
Vector Databases 101 - An introduction to the world of Vector DatabasesZilliz
 
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr LapshynFwdays
 
Artificial intelligence in cctv survelliance.pptx
Artificial intelligence in cctv survelliance.pptxArtificial intelligence in cctv survelliance.pptx
Artificial intelligence in cctv survelliance.pptxhariprasad279825
 
Vertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsVertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsMiki Katsuragi
 
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024BookNet Canada
 
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticscarlostorres15106
 
AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsMemoori
 
Streamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupStreamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupFlorian Wilhelm
 
Dev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebDev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebUiPathCommunity
 
Unraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfUnraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfAlex Barbosa Coqueiro
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Scott Keck-Warren
 
Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Mattias Andersson
 
"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr BaganFwdays
 
What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024Stephanie Beckett
 
Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Enterprise Knowledge
 
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024BookNet Canada
 
Search Engine Optimization SEO PDF for 2024.pdf
Search Engine Optimization SEO PDF for 2024.pdfSearch Engine Optimization SEO PDF for 2024.pdf
Search Engine Optimization SEO PDF for 2024.pdfRankYa
 
DevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsDevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsSergiu Bodiu
 

Dernier (20)

WordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your BrandWordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your Brand
 
DevoxxFR 2024 Reproducible Builds with Apache Maven
DevoxxFR 2024 Reproducible Builds with Apache MavenDevoxxFR 2024 Reproducible Builds with Apache Maven
DevoxxFR 2024 Reproducible Builds with Apache Maven
 
Vector Databases 101 - An introduction to the world of Vector Databases
Vector Databases 101 - An introduction to the world of Vector DatabasesVector Databases 101 - An introduction to the world of Vector Databases
Vector Databases 101 - An introduction to the world of Vector Databases
 
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
 
Artificial intelligence in cctv survelliance.pptx
Artificial intelligence in cctv survelliance.pptxArtificial intelligence in cctv survelliance.pptx
Artificial intelligence in cctv survelliance.pptx
 
Vertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsVertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering Tips
 
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
 
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
 
AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial Buildings
 
Streamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupStreamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project Setup
 
Dev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebDev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio Web
 
Unraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfUnraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdf
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024
 
Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?
 
"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan
 
What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024
 
Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024
 
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
 
Search Engine Optimization SEO PDF for 2024.pdf
Search Engine Optimization SEO PDF for 2024.pdfSearch Engine Optimization SEO PDF for 2024.pdf
Search Engine Optimization SEO PDF for 2024.pdf
 
DevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsDevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platforms
 

IS-4003, A Cloud Based Medical Imaging Platform Using APU, by Kovey Kovalan

  • 1. VOXCELL®  -­‐  SUPERCOMPUTING    CLOUD  MEDICAL  IMAGING  PLATFORM  USING  GPU/APU   KOVEY  KOVALAN  &  SANKET  GAJJAR   KJAYA  MEDICAL    
  • 2. BUSINESS  CASE:   Opportunity  to   Improve  PaDent  Care  
  • 3. OPPORTUNITY  TO  IMPROVE  PATIENT  CARE   MEDICAL  IMAGING  MARKET   !  US  spends  $100B  on  520,500,000  medical  scans  !  $3.5B  on  soTware   ‒ RIS  CVIS  PACS  !  $1.8B  in  2010  !  3.5%  CAGR   ‒ Image  Analysis  !  $1.7B  in  2012    !  7.1%  CAGR   !  Why  Scan?  !  early  detecDon  !  survive     ‒ e.g.  13M  cancer  paDents  alive  in  2012   !  30,000  radiologists  !  10  minutes/scan  !  limits  diagnosDc  outcome     !  Survival  rate  could  be  increased  through  Dmely  physicians  and  paDent  interacDon   !  Physicians  and  paDents  need  enhanced  visualizaDons,  computer  aided  diagnosis,  and   social  media   !  KJAYA  Medical  has  a  soluDon   3   |      PRESENTATION  TITLE      |      November  22,  2013      |      CONFIDENTIAL  
  • 4. MEDICAL  IMAGE  MANAGEMENT  IS  CURRENTLY  ON  PREMISES   PICTURE  ARCHIVING  AND  COMMUNICATION  SYSTEMS  (PACS)   Film  Warehouse   Digital    Warehouse   Onsite   PACS   Specialized   WorkstaDon   4   |      PRESENTATION  TITLE      |      November  22,  2013      |      CONFIDENTIAL  
  • 5. CROWDED  MARKET  –  OLDER  TECHNOLOGY     CURRENT  PACS  MARKET  IS  FRAGMENTED   Onsite  PACS   Blue  Ocean  Markets   Cloud   Social  Media   Third  GeneraDon  PACS  Technology   Current  Technology   5   |      PRESENTATION  TITLE      |      November  22,  2013      |      CONFIDENTIAL  
  • 6. CURRENT  CLOUD  PACS  MARKET  -­‐  LESS  THAN  1%     FOCUSED  ON  NON-­‐DIAGNOSTIC  USE  OF  IMAGE  SHARING  AND    OFFSITE  BACKUP   13%   3%   2%   1%  Cloud   Current  Cloud  accounts  about  1%  of  the  market   •  $56m  in  2010  expected  to  grow  27%  CAGR  to  2018   •  Mostly  in  archival  and  image  sharing   •  Third  generaDon  PACS  on  cloud  in  its  infancy   81%  Onsite     Challenges  for  cloud  PACS   •  Access  speeds   •  DiagnosDc  quality   •  Tools  to  manipulate  data  in  real  Dme   6   |      PRESENTATION  TITLE      |      November  22,  2013      |      CONFIDENTIAL  
  • 7. PACS  FUTURE     ENTERPRISE  IMAGING  CLOUD   Onsite  PACS   Cloud  based  Enterprise  PACS   Third  generaMon  PACS  requirements   Current  RIS/PACS   • 91%  penetraDon   • 52%  older  than  5  years   • 21%  plan  to  replace  in  12  months   Cardiology  :  60%  have  no  PACS   Pathology:  90%  have  no  PACS   7   |      PRESENTATION  TITLE      |      November  22,  2013      |      CONFIDENTIAL   • Enterprise  PACS  –  PaDent  centered,  mulD-­‐departmental,  integrated   image  management  plalorm   • Cloud  based  –  Strong  ROI,  distributed  mulD-­‐site  access  at  speeds   equal  to  on  site  PACS   • Image/report  sharing  with  referring  physicians  and  paDents  on   demand     • Higher  levels  of  funcDonality  -­‐  advanced  visualizaDon,  computer   aided  diagnosis   • IntegraDon  with  EHRs,  HIEs  
  • 8. VoXcell®  Cloud   On-­‐Demand     Cloud  CompuMng  for     Medical  Imaging  
  • 9. VOXCELL  DEMO   .   !  Bullet   ‒  Sub-­‐bullet   ‒  TerDary  Bullet   9   |      PRESENTATION  TITLE      |      November  22,  2013      |      CONFIDENTIAL  
  • 11. DIFFERENTIATED  APPROACH  :  GPU  CLOUD   GPU  CLOUD  BENEFITS   GPU  :  1100  GFLOPS   Real-­‐Dme  diagnosDc  quality  visualizaDons   •   On-­‐demand  and  real-­‐Dme  radiology   •   IntuiDve  results  for  ordering  physicians     •   Connect  with  paDents     CPU  :  90  GFLOPS   11   |      PRESENTATION  TITLE      |      November  22,  2013      |      CONFIDENTIAL   Faster  and  Affordable  CAD  and  ‘Big  Data’  AnalyDcs   •   Improve  accuracy   •   Less  radiaDon  to  paDents  by  reducing  unnecessary  use  of  imaging   •   Streamline  healthcare  and  reduce  costs  
  • 12. DIFFERENTIATED  APPROACH  :  GPU  CLOUD   HIGH  DEFINITION  VISUALIZATION   " CPU  Ray  CasDng     (Compromise  Quality  for  Speed)   12   |      PRESENTATION  TITLE      |      November  22,  2013      |      CONFIDENTIAL   " VoXcell  GPU  Pre-­‐integrated  Texturing  
  • 13. DIFFERENTIATED  APPROACH  :  GPU  CLOUD   HIGH  DEFINITION  VISUALIZATION   " CPU  Ray  CasDng     (Compromise  Quality  for  Speed)   " VoXcell  GPU  Pre-­‐integrated  Texturing   " Real-­‐Dme  performance  requires  early  ray   terminaDon  once  opacity  is  reached  (25%)   !  results  in  hard  plasDc  looking  surfaces.   Transparent  surfaces  degrades  performance.   " Real-­‐Dme  performance  achieved  through   texture  mapping  polygons  !  results  in   soTer,  more  realisDc  surfaces  that  includes   interior  points.  Enables  transparent  surfaces   13   |      PRESENTATION  TITLE      |      November  22,  2013      |      CONFIDENTIAL  
  • 14. DIFFERENTIATED  APPROACH  :  GPU  CLOUD   PREDICTIVE  INTELLIGENT  STREAMING  OVERCOMES  LARGE  DATA  ACCESS  SPEED  AND  LATENCY  OVER  INTERNET     " Use  GPU  to  manipulate  GB  of  paDent  data  remotely  without  transmiqng  data  to  end  user   " Access  visualizaDons  on  any  device  on-­‐demand  and  real-­‐Dme   " Streaming  visualizaDons  done  by  predicDng  next  frames   " Fast  FPS  from  GPU  enable  discarding  incorrectly  predicted  frames  and  generaDng  new  ones   " Predicted  frames  are  buffered  to  client  overcoming  latency   14   |      PRESENTATION  TITLE      |      November  22,  2013      |      CONFIDENTIAL  
  • 15. DIFFERENTIATED  APPROACH  :  GPU  CLOUD   ARTIFICIAL  INTELLIGENCE  LEADS  TO  INTELLIGENT  VISUALIZATIONS®   " Pasern  RecogniDon  Using  ArDficial  Neural  Network   " HeurisDc  Search  Using  GeneDc  Algorithm   CPU  :  500s   GPU  :  10s   15K  Paserns   " Uses:     " Computer  Aided  Diagnosis    through  IntuiDve  VisualizaDons   " Cancer  or  Tumor  DetecDon   " SegmenDng  Body  Parts   " Intelligent  VisualizaDon®  R&D  ParDally  Funded  by  NaDonal  Science  FoundaDon   15   |      PRESENTATION  TITLE      |      November  22,  2013      |      CONFIDENTIAL   GPU  is  3000x   over  CPU  
  • 16. IP  SUMMARY  :  SUPERCOMPUTING  CLOUD   COMPARISON   Legacy  PACS   ConvenMonal  Cloud   KJAYA’s  SupercompuMng  Cloud  PlaVorm   Transmits  raw  scans  to  end  users   Streams  visualizaDon  on  demand   Compromises  raw  scan  for  faster  transmission   •   Not  fit  for  diagnosis   •   Computer  Aided  Diagnosis  (CAD)  inaccuracy   HD  quality  without  transmiqng  raw  scan   •   FDA  510K  cleared  primary  diagnosDc  use   •   ArDficial  Intelligence  CAD  on  gaming  technology   Storage  servers  cannot  manipulate  or  analyze  large  data  –  not  scalable   Graphics  processors  for  large  scan  manipulaDon  and  analyDcs   Powerful  PC  workstaDon  to  run  clinical  app   Clinical  apps  run  on  any  device   CAD  lack  breadth  of  data  and  processing  power   CAD  on  vast  historical  and  powerful  processors  using  arDficial   intelligence  algorithms  on  GPU   Tools  limited  by  vendor  capability   Flexible  toolkit  >  App  store  for  medical  imaging   No  barriers  to  entry   Filed  patents  since  2009   16   |      PRESENTATION  TITLE      |      November  22,  2013      |      CONFIDENTIAL  
  • 17. IP  :  PATENT  PENDING  PLATFORM   PATENT  APPLICATIONS   I.  Secure  Cloud  SupercompuMng  based  Medical  Imaging  System     PCT/US2010/036355  for  “Method  and  System  for  Fast  Access  to  Advanced   VisualizaDon  of  Medical  Scans  Using  a  Dedicated  Web  Portal”   II.  Hybrid  Cloud  for  Medical  Imaging   61/514,295  for  “Method  and  System  for  Fast  Access  to  Advanced   VisualizaDon  of  Medical  Scans  Using  Hybrid  Local  and  Dedicated  Web  Portal”   III.  A  Scalable  Architecture  to  handle  large  amounts  of  data  and  users   11/672,581  for  "Method  and    System  for  Processing  a  Volume  VisualizaDon   Dataset   IV.  ArMficial  Intelligence  on  GPU  for  3D  and  Computer  Aided  DetecMon   PCT/US11/45047  for  “AdapDve    VisualizaDon  for  Direct  Physician  Use”     V.  Patent  Firm:  DeLio  &  Peterson,  New  Haven,  CT   (near  Yale  University)   17   |      PRESENTATION  TITLE      |      November  22,  2013      |      CONFIDENTIAL  
  • 18. COMPETITIVE  LANDSCAPE   PACS     RIS   Intelligent   VisualizaDons®  (AI)   3D    on  any  PC   4D    on  any  PC   Image  Sharing   Archive  &  Disaster   Recovery   DiagnosDc  Quality   over  Internet   FDA  Cleared   PredicDve   Streaming  (not   downloading)   MulD  data  center   SupercompuDng   plalorm   .   KJAYA     Y   Y   Y   Y   Y   Y   Y   Y   Y   Y   Y   Y   CareStream     Y   Y   N   N   N   ?   Y   N   Y   N   Y   N   TeraRecon*1   N   N   N   Y   N   N   N   ?   Y   N   N   N   Shina*1  on  Amazon  Cloud   N   N   N   Y   N   N   N   N   Y   N   Y   N   vRAD   Y   N   N   N   N   N   Y   N   Y   N   Y   N   DICOM  Grid     Y   N   N   N   N   Y   Y   N   N   N   N   N   LifeImage*1     N   N   N   N   N   Y   N   N   N   N   N   N   AccelaRad     Y   N   N   N   N   Y   N   N   N   N   N   N   InsiteOne*1     N   N   N   N   N   N   Y   N   N   N   Y   N   BRIT   Y   Y   N   N   N   N   N   N   Y   N   N   N   MedWeb   Y   Y   N   N   N   N   N   N   Y   N   N   N   secureRAD     Y   N   N   N   N   N   ?   N   ?   N   N   N   ScImage     Y   N   N   N   N   N   ?   N   ?   N   N   N   NCS   Y   Y   N   N   N   N   ?   N   Y   N   N   N   18   |      PRESENTATION  TITLE      |      November  22,  2013      |      CONFIDENTIAL  
  • 19. INDUSTRY  INSIDER   RECOGNITIONS   "Most  cloud-­‐compuDng  services  don’t  offer  diagnosDc-­‐quality  images,  and  the  ones   that  do  typically  feature  lag  Dme,  slowing  the  process.  The  ability  to  quickly  process   and  transmit  diagnosDc-­‐level  images  sets  KJAYA  apart  in  this  regard."     Christopher  Gaerig,     Imaging  Economics   “Today’s  medical  environment  demands  efficient,  cost-­‐effecDve  workflow  and   VoXcell  delivers  the  tools  that  can  empower  faster  and  more  accurate  diagnosis   within  an  extremely  affordable  fee  structure."     Frost  &  Sullivan       “These  are  ambiDous  companies,  with  highly  innovaDve  products  and  business   development  strategies  that  will  enable  them  to  carve  out  a  place  in  global  markets....”     KJAYA’s  INVESTOR:  Enterprise  Ireland   19   |      PRESENTATION  TITLE      |      November  22,  2013      |      CONFIDENTIAL  
  • 21. CLUSTER  COMPONENTS   BIG  DATA  CLUSTER   A  Node   24  TB  Storage   5  TFLOPS    AMD  GPU   2  CPU   Up  to  192GB  Memory   90,000  IOPS   Two  Nodes   48  TB  Storage   2  AMD  GPU  (10,000  GFLOPS)   4  CPU  (360  GFLOPS)   Up  to  384GB  Memory   180,000  IOPS   21   |      PRESENTATION  TITLE      |      November  22,  2013      |      CONFIDENTIAL  
  • 22. CONTENT  HEADER   CONTENT  SUBHEADER   !  Bullet   ‒  Sub-­‐bullet   ‒  TerDary  Bullet   22   |      PRESENTATION  TITLE      |      November  22,  2013      |      CONFIDENTIAL  
  • 23. APU:     Natural   Progression  
  • 24. ARCHITECTURAL  COMPARISON   " CPU+GPU=APU   CPU  VERSUS  HYBRID  CLOUD   ConvenDonal   DiagnosMc   KJAYA’s  VoXcell®  Cloud   Non-­‐  DiagnosMc    " Not    on                                                            " On                              Access                                                   demand   demand   DiagnosMc   " On   demand   Cloud   Cloud   CPU                                                                                                                                            Process   CPU   GPU                                                                                                                                                Data   RelaDonal  Database   Storage     24   |      PRESENTATION  TITLE      |      November  22,  2013      |      CONFIDENTIAL   Big  Data  Clusters  
  • 25. WHY  APU?   REDUCED  POWER  CONSUMPTION   CPU   GPU   " 5A     " Mostly  dissipated  as  heat     !  VS   25   |      PRESENTATION  TITLE      |      November  22,  2013      |      CONFIDENTIAL  
  • 26. WHY  APU?   MANAGE  EVER-­‐EXPANDING  VOLUMES  OF  MEDICAL  IMAGING  DATA   26   |      PRESENTATION  TITLE      |      November  22,  2013      |      CONFIDENTIAL  
  • 27. WHY  APU  WITH  HSA?   HETEROGENEOUS  UNIFORM  MEMORY  ACCESS  (HUMA)   27   |      PRESENTATION  TITLE      |      November  22,  2013      |      CONFIDENTIAL  
  • 28. HUMA  USAGE  IN  GPU  BASED  VOLUME  RENDERING   PRE-­‐COMPUTED  CLASSIFICATION  VOLUME   " Intensity   28   |      PRESENTATION  TITLE      |      November  22,  2013      |      CONFIDENTIAL   " {Bone,  Tissue,    Air}  
  • 29. GPU  BASED  MULTIDIMENSIONAL  TRANFER  FUNCTION  VOLUME  RENDERING   USING  PRE-­‐COMPUTED  CLASSIFICATION  VOLUME   29   |      PRESENTATION  TITLE      |      November  22,  2013      |      CONFIDENTIAL  
  • 30. DISCLAIMER  &  ATTRIBUTION   The  informaDon  presented  in  this  document  is  for  informaDonal  purposes  only  and  may  contain  technical  inaccuracies,  omissions  and  typographical  errors.     The  informaDon  contained  herein  is  subject  to  change  and  may  be  rendered  inaccurate  for  many  reasons,  including  but  not  limited  to  product  and  roadmap   changes,  component  and  motherboard  version  changes,  new  model  and/or  product  releases,  product  differences  between  differing  manufacturers,  soTware   changes,  BIOS  flashes,  firmware  upgrades,  or  the  like.  AMD  assumes  no  obligaDon  to  update  or  otherwise  correct  or  revise  this  informaDon.  However,  AMD   reserves  the  right  to  revise  this  informaDon  and  to  make  changes  from  Dme  to  Dme  to  the  content  hereof  without  obligaDon  of  AMD  to  noDfy  any  person  of   such  revisions  or  changes.     AMD  MAKES  NO  REPRESENTATIONS  OR  WARRANTIES  WITH  RESPECT  TO  THE  CONTENTS  HEREOF  AND  ASSUMES  NO  RESPONSIBILITY  FOR  ANY   INACCURACIES,  ERRORS  OR  OMISSIONS  THAT  MAY  APPEAR  IN  THIS  INFORMATION.     AMD  SPECIFICALLY  DISCLAIMS  ANY  IMPLIED  WARRANTIES  OF  MERCHANTABILITY  OR  FITNESS  FOR  ANY  PARTICULAR  PURPOSE.  IN  NO  EVENT  WILL  AMD  BE   LIABLE  TO  ANY  PERSON  FOR  ANY  DIRECT,  INDIRECT,  SPECIAL  OR  OTHER  CONSEQUENTIAL  DAMAGES  ARISING  FROM  THE  USE  OF  ANY  INFORMATION   CONTAINED  HEREIN,  EVEN  IF  AMD  IS  EXPRESSLY  ADVISED  OF  THE  POSSIBILITY  OF  SUCH  DAMAGES.     ATTRIBUTION   ©  2013  Advanced  Micro  Devices,  Inc.  All  rights  reserved.  AMD,  the  AMD  Arrow  logo  and  combinaDons  thereof  are  trademarks  of  Advanced  Micro  Devices,   Inc.  in  the  United  States  and/or  other  jurisdicDons.    SPEC    is  a  registered  trademark  of  the  Standard  Performance  EvaluaDon  CorporaDon  (SPEC).  Other   names  are  for  informaDonal  purposes  only  and  may  be  trademarks  of  their  respecDve  owners.   30   |      PRESENTATION  TITLE      |      November  22,  2013      |      CONFIDENTIAL