The similarity measure is an essential part of medical image retrieval systems for assisting in radiological diagnosis. Attempts have been made to use distance metric learning approaches to improve the retrieval performance while decreasing the semantic gap. However, existing approaches did not resolve the problem of dependency between images (e.g. normal and abnormal images are compared with the same distance). This affects the semantic and the visual similarity. Thus, this work aims at learning a distance metric which preserves both visual resemblance and semantic similarity and modeling this distance in order to treat each query independently. The proposed method is described in three stages: (1) low-level image feature extraction, (2) offline distance metric modeling, and (3) online retrieval. The first stage exploits transform-domain texture descriptors based on local binary pattern histogram Fourier, shearlet, and curvelet transforms. The second stage is carried out using low-level features and machine learning. Given a query image, the online retrieval is based on the evaluation of the similarity between this image and each image within the dataset, while using a distance that is dynamically defined according to the query image. Realized experiments on the challenging Mammographic Image Analysis Society (MIAS) and Digital Database for Screening Mammography (DDSM) datasets prove the effectiveness of the proposed method in determining dynamically the adequate distance and retrieving the most semantically similar images, while investigating single low-level features as well as fused ones.
Keywords: Dynamic distance learning; Feature fusion; Medical image retrieval; Semantic similarity; Visual similarity.
Copyright © 2020 Elsevier Ltd. All rights reserved.