SlideShare une entreprise Scribd logo
1  sur  37
Télécharger pour lire hors ligne
MedGIFT projects in medical imaging 
Henning Müller
Where we are 
2
Who I am 
• Medical informatics studies in  
Heidelberg, Germany (1992-1997) 
• Exchange with Daimler Benz research, USA 
• PhD in image processing, image retrieval, 
Geneva, Switzerland (1998-2002) 
• Exchange with Monash University, Melbourne, AUS 
• Titular professor in radiology and medical 
informatics at the University of Geneva (2014-) 
• Postdoc, assistant professor between 2002-2013 
• Professor in Computer Science at the  
HES-SO, Sierre, Switzerland (2007-) 
3
Why working on image retrieval? 
• Much imaging data is produced 
• Imaging data is very complex 
• And getting more complex 
• Imaging is essential in diagnosis  
and treatment planning 
• Images out of their context 
loose most of their sense 
• Clinical data is necessary 
• Diagnoses are often not precise 
• Evidence-based medicine  case-based reasoning 
4
Khresmoi – retrieval 
5
The informed patient 
6
Steps for our retrieval system 
7 
Image pre-treatment 
Visual feature 
extraction 
Feature 
modeling 
Multimodal 
fusion 
Classification, 
detection, 
retrieval 
Resource 
creation 
Visualization, 
results 
presentation
Diagnosis aid 
8
Identifying user requirements 
• Surveys among radiologists 
• Also GPs and patients 
• Observing diagnosis processes 
• Analyzing search log files (Goldminer, PubMed, HON) 
• Eye tracking on a radiology viewing station 
• What are information needs and what are 
tasks that are hard and where help is needed? 
• Test the developed systems in user studies 
• Analyze feedback 
• Record the system use for understanding problems 
9
Eye tracking 
10
Data used for ParaDISE 
• Scientific data of the biomedical literature 
• 600’000 articles and 1.6 mio figures of the open access 
literature (4 mio images if separating compound figures) 
• Public data source but only 2D data 
• Clinical data from the Vienna Medical University 
image archive 
• 5TB of data of two consecutive months 
• Radiology reports for each case (in German) 
• Private data source, so access only with password 
• Link medical cases with similar cases from the 
literature based on image data and text 
11
Creation of the VISCERAL database 
12
Annotations (20 organs, 55 landmarks) 
13
Connecting different data levels 
14 
EHR, PACS
Classification of journal figures 
• Most figures in articles 
are not diagnostic  
imaging 
• Captions do not always  
allow to identify the  
image type 
• Visual information can help 
• All these image types are  
mapped to RadLex and  
UMLS/MeSH 
• Allows reusing information and search in related terms 
H Müller, J Kalpathy-Cramer, D Demner-Fushman, S 
Antani, Creating a classification of image types in the 
medical literature for visual categorization, SPIE medical 
15 
imaging, San Diego, USA, 2012.
Context is important (25 yo vs. 88 yo)! 
16
Visual feature extraction 
• Colors  grey levels 
• Shapes after segmentations 
• Texture information 
• In 2D, 3D, 4D 
• In several scales and directions 
• Local vs. global information extraction 
• Finding interest points 
• Finding regions or volumes of interest 
• Combination of features is usually best 
17
Visual feature modeling 
• Visual words instead of raw visual features 
• Reducing the curse of dimensionality 
• Find models similar to text (synonyms, polysemy) 
18 
A Foncubierta, AG Seco de Herrera, H Müller, Medical Image Retrieval using a Bag of Meaningful Visual Words, 
ACM MM workshop on medical multimedia retrieval, Barcelona, Spain, 2013.
Feature extraction and detection 
• Learn combinations of Riesz wavelets as digital 
signatures using SVMs 
• Create signatures to detect small local lesions and 
visualize them 
19 
A Depeursinge, A Foncubierta–Rodriguez, D Van de Ville, H Müller, Rotation–covariant feature learning  
using steerable Riesz wavelets, IEEE Transactions on Image Processing, 2014.
Information fusion 
• Combine information from 
text or structured data  
with visual information 
• Text data can be mapped 
to semantics to understand 
links 
• Also language-independent 
• Early fusion 
• Late fusion 
• Rank-based vs. score-based 
20 
⎛ 1 
⎞ 
⎜ ⎜ M 
⎟ 
⎟ 
⎜ ⎟ 
⎜ M 
⎟ 
⎜ 1 
⎟ 
⎜ ⎟ 
⎜⎜ ⎟⎟ 
⎝ ⎠ 
M SVM 
N 
t 
t 
c 
c 
⎛ 1 
⎞ 
⎜ ⎟ 
⎜ M 
⎟ 
⎜ ⎟ 
⎝ M 
⎠ 
t 
t 
t q 
SVM 
⎛ 1 
⎞ 
⎜ ⎟ 
⎜ M 
⎟ 
⎜ ⎟ 
⎝ N 
⎠ 
c 
c 
c q 
SVM 
mod N Π 
( ) t i p w 
( ) c i p w
Detection and retrieval of similar cases 
A Depeursinge, D Van de Ville, A Platon, A Geissbuhler, PA Poletti, H Müller, Near-Affine-Invariant Texture Learning for Lung 
Tissue Analysis Using Isotropic Wavelet Frames, IEEE Transactions on Information Technology in Biomedicine, 16(4), 2012. 
21
Khresmoi4radiology interface 
22
Khresmoi4professionals interface 
23
Semantic search, also for images 
24
Khresmoi4everyone interface 
25
Shambala – a simple web interface 
26
Much involvement in benchmarking 
• ImageCLEF 
• Has had a medical task since 2004 
• 2013: modality classification, compound figure separation, 
image-based and case-based retrieval 
• 2014: liver annotation 
• VISCERAL 
• Organ segmentation and landmark detection (ISBI) 
• Lesion detection and retrieval task 
• Khresmoi LinkedIn group, … 
27
Cloud-based evaluation in VISCERAL 
28 
Test
VISCERAL data 
29
4D data analysis 
30 
Material Attenuation Coefficient vs keV 
10 
0 
1 
0 
0. 
1 
• Dual Energy CT for perfusion analysis in 
pulmonary embolism 
• Collaboration with emergency radiology 
• Epileptogenic lesion detection in several MRI 
image series (T1, T2, DTI) 
OA Jimenez del Toro, A Foncubierta-Rodriguez, MI Vargas Gomez, H Müller, A Depeursinge, Epileptogenic lesion 
quantification in MRI using contralateral 3D texture comparisons, MICCAI 2013, Springer LNCS, Nagoya, Japan, 2013. 
A Depeursinge, A Foncubierta-Rodriguez, A Vargas, D Van de Ville, A Platon, PA Poletti, H Müller, Rotation-covariant texture 
analysis of 4D dual-energy CT as an indicator of local pulmonary perfusion, ISBI 2013, San Francisco, USA, 2013. 
1 
40 
50 
60 
70 
80 
90 
100 
110 
120 
130 
140 
Photon Energy (keV) 
m(E) (cm2/ 
mg) 
Iodine 
Water 
80 keV 140 keV
4D visualization 
31 
• Visualization of two (min and max) energy 
levels to visualize pulmonary embolisms
Another view on 4D 
32
An infrastructure supporting the load 
• Small, fixed experiments are easy, large routine 
updates and use are difficult!! Big data is hard! 
• Workflow for data re-indexation, maximum automation 
• Khresmoi: Private cloud 
• All components in virtual machines connected with a 
SOA infrastructure, reattribution of resources possible 
• Local computation 
• Hadoop/MapReduce to distribute the computation 
• Needs some optimization 
• Cloud use when local resources are not sufficient 
33
System overview 
34
Infostructure in MD-Paedigree 
35
Conclusions 
• Visual information retrieval has many 
interesting challenges in the medical field 
• Many supporting techniques are required 
• Treating big data is a challenge and digital 
medicine is really big data 
• Many techniques can and need to be used with image 
analysis and machine learning as the basis 
• Digital medicine is a reality and more is yet to 
come … genetics, molecular imaging, … 
• We also need corresponding infrastructures 
36
Contact and more information 
• More information can be found at 
• http://khresmoi.eu/ 
• http://visceral.eu/ 
• http://medgift.hevs.ch/ 
• http://publications.hevs.ch/ 
• Contact: 
• Henning.mueller@hevs.ch 
37

Contenu connexe

Tendances

A novel-approach-for-retinal-lesion-detection-indiabetic-retinopathy-images
A novel-approach-for-retinal-lesion-detection-indiabetic-retinopathy-imagesA novel-approach-for-retinal-lesion-detection-indiabetic-retinopathy-images
A novel-approach-for-retinal-lesion-detection-indiabetic-retinopathy-images
SrinivasaRaoNaga
 
First seminar presentation
First seminar presentationFirst seminar presentation
First seminar presentation
FatmaSamy
 
thesis_Jerzy_Zielinski_2012-08-27
thesis_Jerzy_Zielinski_2012-08-27thesis_Jerzy_Zielinski_2012-08-27
thesis_Jerzy_Zielinski_2012-08-27
Jerzy Zielinski
 
MICCAI CLIP 2013 - Endoscopy Navigation System
MICCAI CLIP 2013 - Endoscopy Navigation SystemMICCAI CLIP 2013 - Endoscopy Navigation System
MICCAI CLIP 2013 - Endoscopy Navigation System
Frederic Perez
 
An investigation on combination methods
An investigation on combination methodsAn investigation on combination methods
An investigation on combination methods
Ali HOSSEINZADEH VAHID
 
MR Image Segmentation of Patients’ Brain Using Disease Specific a priori Know...
MR Image Segmentation of Patients’ Brain Using Disease Specific a priori Know...MR Image Segmentation of Patients’ Brain Using Disease Specific a priori Know...
MR Image Segmentation of Patients’ Brain Using Disease Specific a priori Know...
CSCJournals
 

Tendances (20)

Identification of Brain Regions Related to Alzheimers' Diseases using MRI Ima...
Identification of Brain Regions Related to Alzheimers' Diseases using MRI Ima...Identification of Brain Regions Related to Alzheimers' Diseases using MRI Ima...
Identification of Brain Regions Related to Alzheimers' Diseases using MRI Ima...
 
Determination with Deep Learning and One Layer Neural Network for Image Proce...
Determination with Deep Learning and One Layer Neural Network for Image Proce...Determination with Deep Learning and One Layer Neural Network for Image Proce...
Determination with Deep Learning and One Layer Neural Network for Image Proce...
 
Machine Learning for Medical Image Analysis: What, where and how?
Machine Learning for Medical Image Analysis:What, where and how?Machine Learning for Medical Image Analysis:What, where and how?
Machine Learning for Medical Image Analysis: What, where and how?
 
A novel-approach-for-retinal-lesion-detection-indiabetic-retinopathy-images
A novel-approach-for-retinal-lesion-detection-indiabetic-retinopathy-imagesA novel-approach-for-retinal-lesion-detection-indiabetic-retinopathy-images
A novel-approach-for-retinal-lesion-detection-indiabetic-retinopathy-images
 
Retinal image analysis using morphological process and clustering technique
Retinal image analysis using morphological process and clustering techniqueRetinal image analysis using morphological process and clustering technique
Retinal image analysis using morphological process and clustering technique
 
Deep Learning for Computer Vision: Medical Imaging (UPC 2016)
Deep Learning for Computer Vision: Medical Imaging (UPC 2016)Deep Learning for Computer Vision: Medical Imaging (UPC 2016)
Deep Learning for Computer Vision: Medical Imaging (UPC 2016)
 
Master's Thesis
Master's ThesisMaster's Thesis
Master's Thesis
 
First seminar presentation
First seminar presentationFirst seminar presentation
First seminar presentation
 
thesis_Jerzy_Zielinski_2012-08-27
thesis_Jerzy_Zielinski_2012-08-27thesis_Jerzy_Zielinski_2012-08-27
thesis_Jerzy_Zielinski_2012-08-27
 
MICCAI CLIP 2013 - Endoscopy Navigation System
MICCAI CLIP 2013 - Endoscopy Navigation SystemMICCAI CLIP 2013 - Endoscopy Navigation System
MICCAI CLIP 2013 - Endoscopy Navigation System
 
Xiaohong Gao (Middlesex University) – MIRAGE 2011 (developing an embedding vi...
Xiaohong Gao (Middlesex University) – MIRAGE 2011 (developing an embedding vi...Xiaohong Gao (Middlesex University) – MIRAGE 2011 (developing an embedding vi...
Xiaohong Gao (Middlesex University) – MIRAGE 2011 (developing an embedding vi...
 
IRJET -An Automatated Learning Approach for Detection of Diabetic Retinopathy...
IRJET -An Automatated Learning Approach for Detection of Diabetic Retinopathy...IRJET -An Automatated Learning Approach for Detection of Diabetic Retinopathy...
IRJET -An Automatated Learning Approach for Detection of Diabetic Retinopathy...
 
An investigation on combination methods
An investigation on combination methodsAn investigation on combination methods
An investigation on combination methods
 
Medical Imaging (D3L3 2017 UPC Deep Learning for Computer Vision)
Medical Imaging (D3L3 2017 UPC Deep Learning for Computer Vision)Medical Imaging (D3L3 2017 UPC Deep Learning for Computer Vision)
Medical Imaging (D3L3 2017 UPC Deep Learning for Computer Vision)
 
MR Image Segmentation of Patients’ Brain Using Disease Specific a priori Know...
MR Image Segmentation of Patients’ Brain Using Disease Specific a priori Know...MR Image Segmentation of Patients’ Brain Using Disease Specific a priori Know...
MR Image Segmentation of Patients’ Brain Using Disease Specific a priori Know...
 
Deep learning application to medical imaging: Perspectives as a physician
Deep learning application to medical imaging: Perspectives as a physicianDeep learning application to medical imaging: Perspectives as a physician
Deep learning application to medical imaging: Perspectives as a physician
 
Haemorrhage Detection and Classification: A Review
Haemorrhage Detection and Classification: A ReviewHaemorrhage Detection and Classification: A Review
Haemorrhage Detection and Classification: A Review
 
Brain Tumor Area Calculation in CT-scan image using Morphological Operations
Brain Tumor Area Calculation in CT-scan image using Morphological OperationsBrain Tumor Area Calculation in CT-scan image using Morphological Operations
Brain Tumor Area Calculation in CT-scan image using Morphological Operations
 
Automated fundus image quality assessment and segmentation of optic disc usin...
Automated fundus image quality assessment and segmentation of optic disc usin...Automated fundus image quality assessment and segmentation of optic disc usin...
Automated fundus image quality assessment and segmentation of optic disc usin...
 
Beyond Broken Stick Modeling: R Tutorial for interpretable multivariate analysis
Beyond Broken Stick Modeling: R Tutorial for interpretable multivariate analysisBeyond Broken Stick Modeling: R Tutorial for interpretable multivariate analysis
Beyond Broken Stick Modeling: R Tutorial for interpretable multivariate analysis
 

Similaire à MedGIFT projects in medical imaging

PhD dissertation Luis Marco Ruiz
PhD dissertation Luis Marco RuizPhD dissertation Luis Marco Ruiz
PhD dissertation Luis Marco Ruiz
Luis Marco Ruiz
 
2004 10-19 rudi vdv
2004 10-19 rudi vdv2004 10-19 rudi vdv
2004 10-19 rudi vdv
guest3cf4991
 
Reproducibility in human cognitive neuroimaging: a community-­driven data sha...
Reproducibility in human cognitive neuroimaging: a community-­driven data sha...Reproducibility in human cognitive neuroimaging: a community-­driven data sha...
Reproducibility in human cognitive neuroimaging: a community-­driven data sha...
Nolan Nichols
 

Similaire à MedGIFT projects in medical imaging (20)

Medical image analysis and big data evaluation infrastructures
Medical image analysis and big data evaluation infrastructuresMedical image analysis and big data evaluation infrastructures
Medical image analysis and big data evaluation infrastructures
 
Medical image analysis, retrieval and evaluation infrastructures
Medical image analysis, retrieval and evaluation infrastructuresMedical image analysis, retrieval and evaluation infrastructures
Medical image analysis, retrieval and evaluation infrastructures
 
Information Access to Medical Image Data: from Big Data to Semantics - Academ...
Information Access to Medical Image Data: from Big Data to Semantics - Academ...Information Access to Medical Image Data: from Big Data to Semantics - Academ...
Information Access to Medical Image Data: from Big Data to Semantics - Academ...
 
MVilla IUI 2012 Lisbon
MVilla IUI 2012 LisbonMVilla IUI 2012 Lisbon
MVilla IUI 2012 Lisbon
 
PhD dissertation Luis Marco Ruiz
PhD dissertation Luis Marco RuizPhD dissertation Luis Marco Ruiz
PhD dissertation Luis Marco Ruiz
 
An introduction to machine learning in biomedical research: Key concepts, pr...
An introduction to machine learning in biomedical research:  Key concepts, pr...An introduction to machine learning in biomedical research:  Key concepts, pr...
An introduction to machine learning in biomedical research: Key concepts, pr...
 
The MedRed Ontology for Representing Clinical Data Acquisition Metadata
The MedRed Ontology for Representing Clinical Data Acquisition MetadataThe MedRed Ontology for Representing Clinical Data Acquisition Metadata
The MedRed Ontology for Representing Clinical Data Acquisition Metadata
 
MIE2014: A Framework for Evaluating and Utilizing Medical Terminology Mappings
MIE2014: A Framework for Evaluating and Utilizing Medical Terminology Mappings MIE2014: A Framework for Evaluating and Utilizing Medical Terminology Mappings
MIE2014: A Framework for Evaluating and Utilizing Medical Terminology Mappings
 
Information Technology and Radiology: challenges and future perspectives
Information Technology and Radiology: challenges and future perspectivesInformation Technology and Radiology: challenges and future perspectives
Information Technology and Radiology: challenges and future perspectives
 
Medical Multimedia Information Systems (ACMMM17 Tutorial)
Medical Multimedia Information Systems (ACMMM17 Tutorial) Medical Multimedia Information Systems (ACMMM17 Tutorial)
Medical Multimedia Information Systems (ACMMM17 Tutorial)
 
Data supporting precision oncology fda wakibbe
Data supporting precision oncology fda wakibbeData supporting precision oncology fda wakibbe
Data supporting precision oncology fda wakibbe
 
2004 10-19 rudi vdv
2004 10-19 rudi vdv2004 10-19 rudi vdv
2004 10-19 rudi vdv
 
Data Harmonization for a Molecularly Driven Health System
Data Harmonization for a Molecularly Driven Health SystemData Harmonization for a Molecularly Driven Health System
Data Harmonization for a Molecularly Driven Health System
 
Standards in health informatics - Problem, clinical models and terminologies
Standards in health informatics - Problem, clinical models and terminologiesStandards in health informatics - Problem, clinical models and terminologies
Standards in health informatics - Problem, clinical models and terminologies
 
Text Mining Radiology Reports for Deep Learning Radiology Images
Text Mining Radiology Reports for Deep Learning Radiology Images Text Mining Radiology Reports for Deep Learning Radiology Images
Text Mining Radiology Reports for Deep Learning Radiology Images
 
Deep learning in healthcare: Oppotunities and challenges with Electronic Medi...
Deep learning in healthcare: Oppotunities and challenges with Electronic Medi...Deep learning in healthcare: Oppotunities and challenges with Electronic Medi...
Deep learning in healthcare: Oppotunities and challenges with Electronic Medi...
 
International Journal of Computational Engineering Research(IJCER)
International Journal of Computational Engineering Research(IJCER)International Journal of Computational Engineering Research(IJCER)
International Journal of Computational Engineering Research(IJCER)
 
(2017/06)Practical points of deep learning for medical imaging
(2017/06)Practical points of deep learning for medical imaging(2017/06)Practical points of deep learning for medical imaging
(2017/06)Practical points of deep learning for medical imaging
 
My top 5 papers of 2017 about clinical informatics and digital health implica...
My top 5 papers of 2017 about clinical informatics and digital health implica...My top 5 papers of 2017 about clinical informatics and digital health implica...
My top 5 papers of 2017 about clinical informatics and digital health implica...
 
Reproducibility in human cognitive neuroimaging: a community-­driven data sha...
Reproducibility in human cognitive neuroimaging: a community-­driven data sha...Reproducibility in human cognitive neuroimaging: a community-­driven data sha...
Reproducibility in human cognitive neuroimaging: a community-­driven data sha...
 

Plus de Institute of Information Systems (HES-SO)

Solar production prediction based on non linear meteo source adaptation
Solar production prediction based on non linear meteo source adaptationSolar production prediction based on non linear meteo source adaptation
Solar production prediction based on non linear meteo source adaptation
Institute of Information Systems (HES-SO)
 

Plus de Institute of Information Systems (HES-SO) (20)

MIE20232.pptx
MIE20232.pptxMIE20232.pptx
MIE20232.pptx
 
Classification of noisy free-text prostate cancer pathology reports using nat...
Classification of noisy free-text prostate cancer pathology reports using nat...Classification of noisy free-text prostate cancer pathology reports using nat...
Classification of noisy free-text prostate cancer pathology reports using nat...
 
Machine learning assisted citation screening for Systematic Reviews - Anjani ...
Machine learning assisted citation screening for Systematic Reviews - Anjani ...Machine learning assisted citation screening for Systematic Reviews - Anjani ...
Machine learning assisted citation screening for Systematic Reviews - Anjani ...
 
Exploiting biomedical literature to mine out a large multimodal dataset of ra...
Exploiting biomedical literature to mine out a large multimodal dataset of ra...Exploiting biomedical literature to mine out a large multimodal dataset of ra...
Exploiting biomedical literature to mine out a large multimodal dataset of ra...
 
L'IoT dans les usines. Quels avantages ?
L'IoT dans les usines. Quels avantages ?L'IoT dans les usines. Quels avantages ?
L'IoT dans les usines. Quels avantages ?
 
Studying Public Medical Images from Open Access Literature and Social Network...
Studying Public Medical Images from Open Access Literature and Social Network...Studying Public Medical Images from Open Access Literature and Social Network...
Studying Public Medical Images from Open Access Literature and Social Network...
 
Risques opérationnels et le système de contrôle interne : les limites d’un te...
Risques opérationnels et le système de contrôle interne : les limites d’un te...Risques opérationnels et le système de contrôle interne : les limites d’un te...
Risques opérationnels et le système de contrôle interne : les limites d’un te...
 
Le contrôle interne dans les administrations publiques tient-il toutes ses pr...
Le contrôle interne dans les administrations publiques tient-il toutes ses pr...Le contrôle interne dans les administrations publiques tient-il toutes ses pr...
Le contrôle interne dans les administrations publiques tient-il toutes ses pr...
 
Le système de contrôle interne : Présentation générale, enjeux et méthodes
Le système de contrôle interne : Présentation générale, enjeux et méthodesLe système de contrôle interne : Présentation générale, enjeux et méthodes
Le système de contrôle interne : Présentation générale, enjeux et méthodes
 
Crowdsourcing-based Mobile Application for Wheelchair Accessibility
Crowdsourcing-based Mobile Application for Wheelchair AccessibilityCrowdsourcing-based Mobile Application for Wheelchair Accessibility
Crowdsourcing-based Mobile Application for Wheelchair Accessibility
 
Quelle(s) valeur(s) pour le leadership stratégique ?
Quelle(s) valeur(s) pour le leadership stratégique ?Quelle(s) valeur(s) pour le leadership stratégique ?
Quelle(s) valeur(s) pour le leadership stratégique ?
 
A 3-D Riesz-Covariance Texture Model for the Prediction of Nodule Recurrence ...
A 3-D Riesz-Covariance Texture Model for the Prediction of Nodule Recurrence ...A 3-D Riesz-Covariance Texture Model for the Prediction of Nodule Recurrence ...
A 3-D Riesz-Covariance Texture Model for the Prediction of Nodule Recurrence ...
 
Challenges in medical imaging and the VISCERAL model
Challenges in medical imaging and the VISCERAL modelChallenges in medical imaging and the VISCERAL model
Challenges in medical imaging and the VISCERAL model
 
NOSE: une approche Smart-City pour les zones périphériques et extra-urbaines
NOSE: une approche Smart-City pour les zones périphériques et extra-urbainesNOSE: une approche Smart-City pour les zones périphériques et extra-urbaines
NOSE: une approche Smart-City pour les zones périphériques et extra-urbaines
 
How to detect soft falls on devices
How to detect soft falls on devicesHow to detect soft falls on devices
How to detect soft falls on devices
 
FUNDAMENTALS OF TEXTURE PROCESSING FOR BIOMEDICAL IMAGE ANALYSIS
FUNDAMENTALS OF TEXTURE PROCESSING FOR BIOMEDICAL IMAGE ANALYSISFUNDAMENTALS OF TEXTURE PROCESSING FOR BIOMEDICAL IMAGE ANALYSIS
FUNDAMENTALS OF TEXTURE PROCESSING FOR BIOMEDICAL IMAGE ANALYSIS
 
MOBILE COLLECTION AND DISSEMINATION OF SENIORS’ SKILLS
MOBILE COLLECTION AND DISSEMINATION OF SENIORS’ SKILLSMOBILE COLLECTION AND DISSEMINATION OF SENIORS’ SKILLS
MOBILE COLLECTION AND DISSEMINATION OF SENIORS’ SKILLS
 
Enhanced Students Laboratory The GET project
Enhanced Students Laboratory The GET projectEnhanced Students Laboratory The GET project
Enhanced Students Laboratory The GET project
 
Solar production prediction based on non linear meteo source adaptation
Solar production prediction based on non linear meteo source adaptationSolar production prediction based on non linear meteo source adaptation
Solar production prediction based on non linear meteo source adaptation
 
Exploring the New Trends of Chinese Tourists in Switzerland
Exploring the New Trends of Chinese Tourists in SwitzerlandExploring the New Trends of Chinese Tourists in Switzerland
Exploring the New Trends of Chinese Tourists in Switzerland
 

Dernier

Call Girl In Pune 👉 Just CALL ME: 9352988975 💋 Call Out Call Both With High p...
Call Girl In Pune 👉 Just CALL ME: 9352988975 💋 Call Out Call Both With High p...Call Girl In Pune 👉 Just CALL ME: 9352988975 💋 Call Out Call Both With High p...
Call Girl In Pune 👉 Just CALL ME: 9352988975 💋 Call Out Call Both With High p...
chetankumar9855
 
💚Call Girls In Amritsar 💯Anvi 📲🔝8725944379🔝Amritsar Call Girl No💰Advance Cash...
💚Call Girls In Amritsar 💯Anvi 📲🔝8725944379🔝Amritsar Call Girl No💰Advance Cash...💚Call Girls In Amritsar 💯Anvi 📲🔝8725944379🔝Amritsar Call Girl No💰Advance Cash...
💚Call Girls In Amritsar 💯Anvi 📲🔝8725944379🔝Amritsar Call Girl No💰Advance Cash...
Sheetaleventcompany
 
Dehradun Call Girls Service {8854095900} ❤️VVIP ROCKY Call Girl in Dehradun U...
Dehradun Call Girls Service {8854095900} ❤️VVIP ROCKY Call Girl in Dehradun U...Dehradun Call Girls Service {8854095900} ❤️VVIP ROCKY Call Girl in Dehradun U...
Dehradun Call Girls Service {8854095900} ❤️VVIP ROCKY Call Girl in Dehradun U...
Sheetaleventcompany
 
Call Girls in Gagan Vihar (delhi) call me [🔝 9953056974 🔝] escort service 24X7
Call Girls in Gagan Vihar (delhi) call me [🔝  9953056974 🔝] escort service 24X7Call Girls in Gagan Vihar (delhi) call me [🔝  9953056974 🔝] escort service 24X7
Call Girls in Gagan Vihar (delhi) call me [🔝 9953056974 🔝] escort service 24X7
9953056974 Low Rate Call Girls In Saket, Delhi NCR
 

Dernier (20)

VIP Hyderabad Call Girls Bahadurpally 7877925207 ₹5000 To 25K With AC Room 💚😋
VIP Hyderabad Call Girls Bahadurpally 7877925207 ₹5000 To 25K With AC Room 💚😋VIP Hyderabad Call Girls Bahadurpally 7877925207 ₹5000 To 25K With AC Room 💚😋
VIP Hyderabad Call Girls Bahadurpally 7877925207 ₹5000 To 25K With AC Room 💚😋
 
Call Girl In Pune 👉 Just CALL ME: 9352988975 💋 Call Out Call Both With High p...
Call Girl In Pune 👉 Just CALL ME: 9352988975 💋 Call Out Call Both With High p...Call Girl In Pune 👉 Just CALL ME: 9352988975 💋 Call Out Call Both With High p...
Call Girl In Pune 👉 Just CALL ME: 9352988975 💋 Call Out Call Both With High p...
 
Most Beautiful Call Girl in Bangalore Contact on Whatsapp
Most Beautiful Call Girl in Bangalore Contact on WhatsappMost Beautiful Call Girl in Bangalore Contact on Whatsapp
Most Beautiful Call Girl in Bangalore Contact on Whatsapp
 
Top Rated Hyderabad Call Girls Chintal ⟟ 9332606886 ⟟ Call Me For Genuine Se...
Top Rated  Hyderabad Call Girls Chintal ⟟ 9332606886 ⟟ Call Me For Genuine Se...Top Rated  Hyderabad Call Girls Chintal ⟟ 9332606886 ⟟ Call Me For Genuine Se...
Top Rated Hyderabad Call Girls Chintal ⟟ 9332606886 ⟟ Call Me For Genuine Se...
 
Call Girls Coimbatore Just Call 8250077686 Top Class Call Girl Service Available
Call Girls Coimbatore Just Call 8250077686 Top Class Call Girl Service AvailableCall Girls Coimbatore Just Call 8250077686 Top Class Call Girl Service Available
Call Girls Coimbatore Just Call 8250077686 Top Class Call Girl Service Available
 
Call Girls Hyderabad Just Call 8250077686 Top Class Call Girl Service Available
Call Girls Hyderabad Just Call 8250077686 Top Class Call Girl Service AvailableCall Girls Hyderabad Just Call 8250077686 Top Class Call Girl Service Available
Call Girls Hyderabad Just Call 8250077686 Top Class Call Girl Service Available
 
💚Call Girls In Amritsar 💯Anvi 📲🔝8725944379🔝Amritsar Call Girl No💰Advance Cash...
💚Call Girls In Amritsar 💯Anvi 📲🔝8725944379🔝Amritsar Call Girl No💰Advance Cash...💚Call Girls In Amritsar 💯Anvi 📲🔝8725944379🔝Amritsar Call Girl No💰Advance Cash...
💚Call Girls In Amritsar 💯Anvi 📲🔝8725944379🔝Amritsar Call Girl No💰Advance Cash...
 
Independent Call Girls Service Mohali Sector 116 | 6367187148 | Call Girl Ser...
Independent Call Girls Service Mohali Sector 116 | 6367187148 | Call Girl Ser...Independent Call Girls Service Mohali Sector 116 | 6367187148 | Call Girl Ser...
Independent Call Girls Service Mohali Sector 116 | 6367187148 | Call Girl Ser...
 
💕SONAM KUMAR💕Premium Call Girls Jaipur ↘️9257276172 ↙️One Night Stand With Lo...
💕SONAM KUMAR💕Premium Call Girls Jaipur ↘️9257276172 ↙️One Night Stand With Lo...💕SONAM KUMAR💕Premium Call Girls Jaipur ↘️9257276172 ↙️One Night Stand With Lo...
💕SONAM KUMAR💕Premium Call Girls Jaipur ↘️9257276172 ↙️One Night Stand With Lo...
 
Call Girls Rishikesh Just Call 8250077686 Top Class Call Girl Service Available
Call Girls Rishikesh Just Call 8250077686 Top Class Call Girl Service AvailableCall Girls Rishikesh Just Call 8250077686 Top Class Call Girl Service Available
Call Girls Rishikesh Just Call 8250077686 Top Class Call Girl Service Available
 
Low Rate Call Girls Bangalore {7304373326} ❤️VVIP NISHA Call Girls in Bangalo...
Low Rate Call Girls Bangalore {7304373326} ❤️VVIP NISHA Call Girls in Bangalo...Low Rate Call Girls Bangalore {7304373326} ❤️VVIP NISHA Call Girls in Bangalo...
Low Rate Call Girls Bangalore {7304373326} ❤️VVIP NISHA Call Girls in Bangalo...
 
Top Rated Call Girls Kerala ☎ 8250092165👄 Delivery in 20 Mins Near Me
Top Rated Call Girls Kerala ☎ 8250092165👄 Delivery in 20 Mins Near MeTop Rated Call Girls Kerala ☎ 8250092165👄 Delivery in 20 Mins Near Me
Top Rated Call Girls Kerala ☎ 8250092165👄 Delivery in 20 Mins Near Me
 
Premium Call Girls In Jaipur {8445551418} ❤️VVIP SEEMA Call Girl in Jaipur Ra...
Premium Call Girls In Jaipur {8445551418} ❤️VVIP SEEMA Call Girl in Jaipur Ra...Premium Call Girls In Jaipur {8445551418} ❤️VVIP SEEMA Call Girl in Jaipur Ra...
Premium Call Girls In Jaipur {8445551418} ❤️VVIP SEEMA Call Girl in Jaipur Ra...
 
Call Girls Madurai Just Call 9630942363 Top Class Call Girl Service Available
Call Girls Madurai Just Call 9630942363 Top Class Call Girl Service AvailableCall Girls Madurai Just Call 9630942363 Top Class Call Girl Service Available
Call Girls Madurai Just Call 9630942363 Top Class Call Girl Service Available
 
Kollam call girls Mallu aunty service 7877702510
Kollam call girls Mallu aunty service 7877702510Kollam call girls Mallu aunty service 7877702510
Kollam call girls Mallu aunty service 7877702510
 
Dehradun Call Girls Service {8854095900} ❤️VVIP ROCKY Call Girl in Dehradun U...
Dehradun Call Girls Service {8854095900} ❤️VVIP ROCKY Call Girl in Dehradun U...Dehradun Call Girls Service {8854095900} ❤️VVIP ROCKY Call Girl in Dehradun U...
Dehradun Call Girls Service {8854095900} ❤️VVIP ROCKY Call Girl in Dehradun U...
 
Top Rated Pune Call Girls (DIPAL) ⟟ 8250077686 ⟟ Call Me For Genuine Sex Serv...
Top Rated Pune Call Girls (DIPAL) ⟟ 8250077686 ⟟ Call Me For Genuine Sex Serv...Top Rated Pune Call Girls (DIPAL) ⟟ 8250077686 ⟟ Call Me For Genuine Sex Serv...
Top Rated Pune Call Girls (DIPAL) ⟟ 8250077686 ⟟ Call Me For Genuine Sex Serv...
 
(Low Rate RASHMI ) Rate Of Call Girls Jaipur ❣ 8445551418 ❣ Elite Models & Ce...
(Low Rate RASHMI ) Rate Of Call Girls Jaipur ❣ 8445551418 ❣ Elite Models & Ce...(Low Rate RASHMI ) Rate Of Call Girls Jaipur ❣ 8445551418 ❣ Elite Models & Ce...
(Low Rate RASHMI ) Rate Of Call Girls Jaipur ❣ 8445551418 ❣ Elite Models & Ce...
 
Call Girls in Gagan Vihar (delhi) call me [🔝 9953056974 🔝] escort service 24X7
Call Girls in Gagan Vihar (delhi) call me [🔝  9953056974 🔝] escort service 24X7Call Girls in Gagan Vihar (delhi) call me [🔝  9953056974 🔝] escort service 24X7
Call Girls in Gagan Vihar (delhi) call me [🔝 9953056974 🔝] escort service 24X7
 
Mumbai ] (Call Girls) in Mumbai 10k @ I'm VIP Independent Escorts Girls 98333...
Mumbai ] (Call Girls) in Mumbai 10k @ I'm VIP Independent Escorts Girls 98333...Mumbai ] (Call Girls) in Mumbai 10k @ I'm VIP Independent Escorts Girls 98333...
Mumbai ] (Call Girls) in Mumbai 10k @ I'm VIP Independent Escorts Girls 98333...
 

MedGIFT projects in medical imaging

  • 1. MedGIFT projects in medical imaging Henning Müller
  • 3. Who I am • Medical informatics studies in Heidelberg, Germany (1992-1997) • Exchange with Daimler Benz research, USA • PhD in image processing, image retrieval, Geneva, Switzerland (1998-2002) • Exchange with Monash University, Melbourne, AUS • Titular professor in radiology and medical informatics at the University of Geneva (2014-) • Postdoc, assistant professor between 2002-2013 • Professor in Computer Science at the HES-SO, Sierre, Switzerland (2007-) 3
  • 4. Why working on image retrieval? • Much imaging data is produced • Imaging data is very complex • And getting more complex • Imaging is essential in diagnosis and treatment planning • Images out of their context loose most of their sense • Clinical data is necessary • Diagnoses are often not precise • Evidence-based medicine case-based reasoning 4
  • 7. Steps for our retrieval system 7 Image pre-treatment Visual feature extraction Feature modeling Multimodal fusion Classification, detection, retrieval Resource creation Visualization, results presentation
  • 9. Identifying user requirements • Surveys among radiologists • Also GPs and patients • Observing diagnosis processes • Analyzing search log files (Goldminer, PubMed, HON) • Eye tracking on a radiology viewing station • What are information needs and what are tasks that are hard and where help is needed? • Test the developed systems in user studies • Analyze feedback • Record the system use for understanding problems 9
  • 11. Data used for ParaDISE • Scientific data of the biomedical literature • 600’000 articles and 1.6 mio figures of the open access literature (4 mio images if separating compound figures) • Public data source but only 2D data • Clinical data from the Vienna Medical University image archive • 5TB of data of two consecutive months • Radiology reports for each case (in German) • Private data source, so access only with password • Link medical cases with similar cases from the literature based on image data and text 11
  • 12. Creation of the VISCERAL database 12
  • 13. Annotations (20 organs, 55 landmarks) 13
  • 14. Connecting different data levels 14 EHR, PACS
  • 15. Classification of journal figures • Most figures in articles are not diagnostic imaging • Captions do not always allow to identify the image type • Visual information can help • All these image types are mapped to RadLex and UMLS/MeSH • Allows reusing information and search in related terms H Müller, J Kalpathy-Cramer, D Demner-Fushman, S Antani, Creating a classification of image types in the medical literature for visual categorization, SPIE medical 15 imaging, San Diego, USA, 2012.
  • 16. Context is important (25 yo vs. 88 yo)! 16
  • 17. Visual feature extraction • Colors grey levels • Shapes after segmentations • Texture information • In 2D, 3D, 4D • In several scales and directions • Local vs. global information extraction • Finding interest points • Finding regions or volumes of interest • Combination of features is usually best 17
  • 18. Visual feature modeling • Visual words instead of raw visual features • Reducing the curse of dimensionality • Find models similar to text (synonyms, polysemy) 18 A Foncubierta, AG Seco de Herrera, H Müller, Medical Image Retrieval using a Bag of Meaningful Visual Words, ACM MM workshop on medical multimedia retrieval, Barcelona, Spain, 2013.
  • 19. Feature extraction and detection • Learn combinations of Riesz wavelets as digital signatures using SVMs • Create signatures to detect small local lesions and visualize them 19 A Depeursinge, A Foncubierta–Rodriguez, D Van de Ville, H Müller, Rotation–covariant feature learning using steerable Riesz wavelets, IEEE Transactions on Image Processing, 2014.
  • 20. Information fusion • Combine information from text or structured data with visual information • Text data can be mapped to semantics to understand links • Also language-independent • Early fusion • Late fusion • Rank-based vs. score-based 20 ⎛ 1 ⎞ ⎜ ⎜ M ⎟ ⎟ ⎜ ⎟ ⎜ M ⎟ ⎜ 1 ⎟ ⎜ ⎟ ⎜⎜ ⎟⎟ ⎝ ⎠ M SVM N t t c c ⎛ 1 ⎞ ⎜ ⎟ ⎜ M ⎟ ⎜ ⎟ ⎝ M ⎠ t t t q SVM ⎛ 1 ⎞ ⎜ ⎟ ⎜ M ⎟ ⎜ ⎟ ⎝ N ⎠ c c c q SVM mod N Π ( ) t i p w ( ) c i p w
  • 21. Detection and retrieval of similar cases A Depeursinge, D Van de Ville, A Platon, A Geissbuhler, PA Poletti, H Müller, Near-Affine-Invariant Texture Learning for Lung Tissue Analysis Using Isotropic Wavelet Frames, IEEE Transactions on Information Technology in Biomedicine, 16(4), 2012. 21
  • 24. Semantic search, also for images 24
  • 26. Shambala – a simple web interface 26
  • 27. Much involvement in benchmarking • ImageCLEF • Has had a medical task since 2004 • 2013: modality classification, compound figure separation, image-based and case-based retrieval • 2014: liver annotation • VISCERAL • Organ segmentation and landmark detection (ISBI) • Lesion detection and retrieval task • Khresmoi LinkedIn group, … 27
  • 28. Cloud-based evaluation in VISCERAL 28 Test
  • 30. 4D data analysis 30 Material Attenuation Coefficient vs keV 10 0 1 0 0. 1 • Dual Energy CT for perfusion analysis in pulmonary embolism • Collaboration with emergency radiology • Epileptogenic lesion detection in several MRI image series (T1, T2, DTI) OA Jimenez del Toro, A Foncubierta-Rodriguez, MI Vargas Gomez, H Müller, A Depeursinge, Epileptogenic lesion quantification in MRI using contralateral 3D texture comparisons, MICCAI 2013, Springer LNCS, Nagoya, Japan, 2013. A Depeursinge, A Foncubierta-Rodriguez, A Vargas, D Van de Ville, A Platon, PA Poletti, H Müller, Rotation-covariant texture analysis of 4D dual-energy CT as an indicator of local pulmonary perfusion, ISBI 2013, San Francisco, USA, 2013. 1 40 50 60 70 80 90 100 110 120 130 140 Photon Energy (keV) m(E) (cm2/ mg) Iodine Water 80 keV 140 keV
  • 31. 4D visualization 31 • Visualization of two (min and max) energy levels to visualize pulmonary embolisms
  • 33. An infrastructure supporting the load • Small, fixed experiments are easy, large routine updates and use are difficult!! Big data is hard! • Workflow for data re-indexation, maximum automation • Khresmoi: Private cloud • All components in virtual machines connected with a SOA infrastructure, reattribution of resources possible • Local computation • Hadoop/MapReduce to distribute the computation • Needs some optimization • Cloud use when local resources are not sufficient 33
  • 36. Conclusions • Visual information retrieval has many interesting challenges in the medical field • Many supporting techniques are required • Treating big data is a challenge and digital medicine is really big data • Many techniques can and need to be used with image analysis and machine learning as the basis • Digital medicine is a reality and more is yet to come … genetics, molecular imaging, … • We also need corresponding infrastructures 36
  • 37. Contact and more information • More information can be found at • http://khresmoi.eu/ • http://visceral.eu/ • http://medgift.hevs.ch/ • http://publications.hevs.ch/ • Contact: • Henning.mueller@hevs.ch 37