Supervised Content Based Image Retrieval Using Radiology Reports

J. Ramos, T. Kockelkorn, B. van Ginneken, M. Viergever, R. Ramos and A. Campilho

Image Analysis and Recognition 2012;7325:249-258.

DOI Cited by ~3

Content based image retrieval (CBIR) is employed in medicine to improve radiologistsA-A?A 1/2 diagnostic performance. Today effective medical CBIR systems are limited to specific applications, as to reduce the amount of medical knowledge to model. Although supervised approaches could ease the incorporation of medical expertise, its application is not common due to the scarce number of available user annotations. This paper introduces the application of radiology reports to supervise CBIR systems. The concept is to make use of the textual distances between reports to build a transformation in image space through a manifold learning algorithm. A comparison was made between the presented approach and non-supervised CBIR systems, using a Leave-One- Patient-Out evaluation in a database of computer tomography scans of interstitial lung diseases. Supervised CBIR augmented the mean average precision consistently with an increase between 3 to 8 points, which suggests supervision by radiology reports increases CBIR performance.