Related Experiment Videos
IDEM: a Web application of case-based reasoning in histopathology
C Le Bozec1, M C Jaulent, E Zapletal
1Service d'Informatique Médicale, Hôpital Broussais, Paris, France.
Computers in Biology and Medicine
|December 23, 1998
Summary
This study introduces the Image and Diagnosis from Examples in Medicine (IDEM) system, using case-based reasoning (CBR) for intelligent retrieval of breast pathology images online. The system offers flexible querying and relevant data retrieval for clinical practice.
Area of Science:
- Medical Informatics
- Artificial Intelligence
- Software Engineering
Background:
- Accessing prototypical medical images for diagnosis and education is challenging.
- Internet-based retrieval systems require intelligent design for efficient data access.
Purpose of the Study:
- To present a Web interface for the case-based reasoning (CBR) system IDEM (Image and Diagnosis from Examples in Medicine).
- To enable intelligent access to a collection of illustrated medical cases in breast pathology via the Internet.
Main Methods:
- Utilized case-based reasoning (CBR) approach for medical image retrieval.
- Developed a Web interface for the IDEM system.
- Defined a similarity measure for flexible querying and quantitative browsing of medical cases.
Main Results:
- The IDEM system provides flexible querying of a breast pathology case-base.
- Similarity links enable quantitative browsing, with resemblance rates indicating data quality and relevance.
- The system demonstrates robustness to missing information, adaptable for daily clinical practice.
Conclusions:
- The case-based reasoning (CBR) approach is a promising method for clinical and efficient retrieval of reference images.
- IDEM facilitates access to diagnosis clues through Internet-based medical image retrieval.
- The developed system supports clinical decision-making by providing relevant medical case data.