8. Introduction Content-based image retrieval (CBIR) is the digital image searching problem in large databases that makes use of the contents of the images . 5
9. Rather than relying on manual indexing and text description for every image, low-level visual features automatically extracted are used for representation of the image content. 6 Introduction
10. The medical domain is often cited as one of the principal application domains for content based access technologies. this technology is still in the early development stage. Much research work is needed before the CBIR-based CAD schemes can be accepted in the clinical practice. 7 Introduction
11. Problem definition In the clinical practice physicians decide on a diagnosis by visually comparing the case at hand with previously published cases in the medical literature. 8
12. Searching for and identifying the similar reference cases (or images) from the large and diverse clinical databases is a quite difficult task. 9 Problem definition
13. Currently, the most of available search systems developed and implemented in medical informatics and picture archiving use TBIR(Text Based Image Retrieval) schemes that are based on the annotated textual information to select similar or clinically relevant cases . 10 Problem definition
14. This approach is typically limited to retrieve or select the same type of medical images (i.e., mammograms or CT brain images). However, the relevant clinical information depicted on medical images is locally presented (i.e., breast masses depicted on mammograms and emphysema lesions depicted on lung CT images). 11 Problem definition
15. Since the nature of the queried suspicious regions is often un-determined, the CBIR is the only available and reliable approach to retrieve the clinically relevant (reference) cases along with the proven pathology and other related clinical information. As a result, developing CBIR schemes has been attracting extensive research interest in the areas of medical informatics for the last decade. 12 Problem definition
16. Objective Providing a software system that helps physicians in the diagnosis of lung tumors using the CBIR technique. By comparing the patient's CT (Computed Tomography) image by the previously saved CTs in the database . 13
17. Then displaying the images and description of the cases that match with the patient's CT. To help the physicians in reaching the right diagnosis. 14 Objective
18. System overview 15 Queried image Depicting the detected or identified suspicious lesions A set of the most similar cases with diagnosis. User Interface Queried seed Region growth and segmentation Similar images Segmented ROI Matching algorithm Feature extraction and computation Images Database indexed with feature vector Feature vector Similarity comparison 15
21. References Bin Zheng - Computer-Aided Diagnosis in Mammography Using Content-Based Image Retrieval Approaches: Current Status and Future Perspectives-2009- http://www.mdpi.com/journal/algorithms Alex M. Aisen, MD-Lynn S. Broderick, MD-Helen Winer-Muram, MD-Carla E. Brodley, PhD-Avinash C. Kak, PhD-Christina Pavlopoulou, MS-Jennifer Dy, PhD-Chi-RenShyu, PhD-Alan Marchiori, BS- Automated Storage and Retrieval of Thin-Section CT Images to Assist Diagnosis: System Description and Preliminary Assessment-2003 . http://rvl.www.ecn.purdue.edu/RVL/CBIR/CBIROverview.html 18