Case based diagnosis in histopathology of breast tumours

• Published in: Studies in health technology and informatics Vol. 52 Pt 1; p. 544
• Main Authors: Jaulent, M C, Le Bozec, C, Zapletal, E, Degoulet, P
• Format: Journal Article
• Language: English
• Published: Netherlands 1998
• Subjects: Algorithms; Artificial Intelligence; Breast Neoplasms - pathology; Decision Support Techniques; Diagnosis, Computer-Assisted; Humans
• ISSN: 0926-9630
• DOI: 10.3233/978-1-60750-896-0-544

Relevant knowledge and decision making process in histopathology is mostly included in typical pathological cases encountered by the expert. In this article we address the issue of exploiting this knowledge in the diagnosis process. We present the first steps of a Case-Based-Reasoning (CBR) system that uses the previously resolved pathological cases in order to facilitate decision making and diagnosis formulation of a new case. The work has been performed in two phases. Firstly, an object-oriented model of the domain was developed and 35 pathological cases of breast tumours were represented within this model. Secondly, the functional architecture of the CBR system was designed and the main procedure, the selection of similar cases, was achieved. The selection procedure is based on an original similarity measure that takes into account both semantic and structural resemblances and differences between the cases. A first evaluation of the system was performed on several cases of the data base. The interest of the CBR approach in situations where heuristic rules cannot be clearly defined is discussed.