A new method of content based medical image retrieval and its applications to CT imaging sign retrieval

Abstract

This paper proposes a new method of content based medical image retrieval through considering fused, context-sensitive similarity. Firstly, we fuse the semantic and visual similarities between the query image and each image in the database as their pairwise similarities. Then, we construct a weighted graph whose nodes represent the images and edges measure their pairwise similarities. By using the shortest path algorithm over the weighted graph, we obtain a new similarity measure, context-sensitive similarity measure, between the query image and each database image to complete the retrieval process. Actually, we use the fused pairwise similarity to narrow down the semantic gap for obtaining a more accurate pairwise similarity measure, and spread it on the intrinsic data manifold to achieve the context-sensitive similarity for a better retrieval performance. The proposed method has been evaluated on the retrieval of the Common CT Imaging Signs of Lung Diseases (CISLs) and achieved not only better retrieval results but also the satisfactory computation efficiency.

Content-based medical image retrieval system based on gradient orientation and edge information

“…Recently, pulse coupled neural network and non-subsampled contourlet transform based CBMIR method is introduced by Kundu et al [26] . Ma et al [27] propose a new CBMIR method know as fused context-sensitive similarity (FCSS) based on support vector machine (SVM) and several distance measures. vector quantization with fuzzy signatures is used in [28] to develop a new system called fuzzy medical image retrieval (FMIR).…”

An Insight Framework for Content based Medical Image Retrieval using Deep Convolutional Neural Network

“…Ma, L., Liu, X. [9] proposed the Fused Context-Sensitive Similarity based on Content based Medical Image retrieval focusing specifically on CT images especially for Lung related diseases [9]. This was done based on similarity between visual feature and classification information from the LISS dataset images.…”

Heterogeneous Medical Image Retrieval using Multi-Trend Structure Descriptor and Fuzzy SVM Classifier

“…A multi-tiered imaa ge retrieval system foo r microscopic imaa ges is presented by Akakin et al, in [15]. Lan et al, [16] [17] for lung CT image rett rieval which uses the shortest pat th algorithm over thee weighted graph to o measure the both semantic and visual similarities. Image retrieval systee m for heterogeneoo us medical images is proposed ii n [18] by combining the color autocorrelogram, micro-textures and enhanced edge orientation autocorrelogram features, computed using a framewor rk based on Fulll range Autoregressive modd el and it is reported that it is superior in efficiency because of comprising color, texture, shape and its spatial information at both local ann d global level.…”