A novel web service for mammography images indexing

Abstract

Medical community needs to extract precise information from a large amount of data. These data are a collection of different types such as text documents, images and video. Currently medical technology do not provide an intelligent methodology for documents recovery and classification of such documents based on their content. In this work the radiological structured reports are analysed with the corresponding mammographic images. The presented system is composed of an Indexing Engine and a Searching Engine, based on innovative methods for IR (Information Retrieval). The proposed work is useful for physicians as support diagnosis system, for students as learning support system, and finally, for epidemiological studies. The system allows for submitting a query through a web interface, consulting a structured report and showing associated mammographic images. The dataset is composed of both healthy and pathological patients. The proposed architecture achieved satisfactory results in terms of Sensitivity and Specificity. Three scenarios are presented and described. © 2013 IEEE.