Skip to Main content Skip to Navigation
Conference papers

An image retrieval approach to setup difficulty levels in training systems for endomicroscopy diagnosis

Abstract : Learning medical image interpretation is an evolutive process that requires modular training systems, from non-expert to expert users. Our study aims at developing such a system for endomicroscopy diagnosis. It uses a difficulty predictor to try and shorten the physician learning curve. As the understanding of video diagnosis is driven by visual similarities, we propose a content-based video retrieval approach to estimate the level of interpretation difficulty. The performance of our retrieval method is compared with several state of the art methods, and its genericity is demonstrated with two different clinical databases, on the Barrett's Esophagus and on colonic polyps. From our retrieval results, we learn a difficulty predictor against a ground truth given by the percentage of false diagnoses among several physicians. Our experiments show that, although our datasets are not large enough to test for statistical significance, there is a noticeable relationship between our retrieval-based difficulty estimation and the difficulty experienced by the physicians.
Complete list of metadatas

Cited literature [13 references]  Display  Hide  Download

https://hal.inria.fr/inria-00616153
Contributor : Project-Team Asclepios <>
Submitted on : Thursday, July 4, 2013 - 7:19:00 PM
Last modification on : Thursday, August 22, 2019 - 11:02:36 AM
Document(s) archivé(s) le : Saturday, October 5, 2013 - 2:25:10 AM

File

ANDRE-MICCAI10.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Barbara André, Tom Vercauteren, Anna M. Buchner, Muhammad Waseem Shahid, Michael B. Wallace, et al.. An image retrieval approach to setup difficulty levels in training systems for endomicroscopy diagnosis. Medical Image Computing and Computer-Assisted Intervention (MICCAI'10), 2010, Beijing, China, United States. pp.480--487, ⟨10.1007/978-3-642-15745-5_59⟩. ⟨inria-00616153⟩

Share

Metrics

Record views

210

Files downloads

252