Mammogram Image Retrieval System Using Texture and Semantic Features

Abstract

Image retrieval systems might help radiologists in aiding their diagnostic decision-making by giving a way to discover and identify similar images from databases. Keyword-based search became the dominant paradigm for searching multimedia datasets in the early years of image retrieval. However, using keywords alone has numerous drawbacks: human annotation is time-consuming and intrinsically incomplete, and the relationship between words and concepts is sometimes complicated. These significant challenges have motivated research in the field of Content-Based Image Retrieval (CBIR). However, using visual content has its own set of restrictions, owing to the Semantic Gap, which describes the disparity between low-level information that can be extracted quickly from images and high-level descriptions that are meaningful to users. As a result, a system with integrated approaches is important. In this paper a mammogram image retrieval system based on low level visual features and high-level semantic features has been proposed. Based upon the proposed framework, a prototype of mammogram image retrieval system has been developed. The proposed framework for retrieval of mammograms consists of two phases. The system first exploits the textual features and then further refines the search using visual features. Further, if the user is unsatisfied with the search results, he or she can send Relevance Feedback (RF) to the retrieval system, which has methods to learn about the user’s information needs. A system like this might be utilised for Computer Aided Diagnosis, medical education, and research. The framework established is generalizable and adaptable to a variety of anatomic and diagnostic circumstances. The proposed system’s performance is demonstrated by the experimental findings.