A similarity measure method combining location feature for mammogram retrieval

Article type: Research Article

Authors: Wang, Zhiqiong^a | Xin, Junchang^{b; *} | Huang, Yukun^a | Li, Chen^a | Xu, Ling^a | Li, Yang^a | Zhang, Hao^c | Gu, Huizi^d | Qian, Wei^e

Affiliations: [a] Sino-Dutch Biomedical and Information Engineering School, Northeastern University, China | [b] School of Computer Science and Engineering, Key Laboratory of Big Data Management and Analytics (Liaoning Province), Northeastern University, China | [c] Breast Disease and Reconstruction Center, Breast Cancer Key Lab of Dalian, the Second Hospital of Dalian Medical University, China | [d] Department of Internal Neurology, the Second Hospital of Dalian Medical University, China | [e] College of Engineering, University of Texas at El Paso, USA

Correspondence: [*] Corresponding author: Junchang Xin, Northeastern University, Chuangxin Road 195, Shenyang, Liaoning, 110169, China. Email: [email protected].

Abstract: BACKGROUND:Breast cancer, the most common malignancy among women, has a high mortality rate in clinical practice. Early detection, diagnosis and treatment can reduce the mortalities of breast cancer greatly. The method of mammogram retrieval can help doctors to find the early breast lesions effectively and determine a reasonable feature set for image similarity measure. This will improve the accuracy effectively for mammogram retrieval. METHODS:This paper proposes a similarity measure method combining location feature for mammogram retrieval. Firstly, the images are pre-processed, the regions of interest are detected and the lesions are segmented in order to get the center point and radius of the lesions. Then, the method, namely Coherent Point Drift, is used for image registration with the pre-defined standard image. The center point and radius of the lesions after registration are obtained and the standard location feature of the image is constructed. This standard location feature can help figure out the location similarity between the image pair from the query image to each dataset image in the database. Next, the content feature of the image is extracted, including the Histogram of Oriented Gradients, the Edge Direction Histogram, the Local Binary Pattern and the Gray Level Histogram, and the image pair content similarity can be calculated using the Earth Mover’s Distance. Finally, the location similarity and content similarity are fused to form the image fusion similarity, and the specified number of the most similar images can be returned according to it. RESULTS:In the experiment, 440 mammograms, which are from Chinese women in Northeast China, are used as the database. When fusing 40% lesion location feature similarity and 60% content feature similarity, the results have obvious advantages. At this time, precision is 0.83, recall is 0.76, comprehensive indicator is 0.79, satisfaction is 96.0%, mean is 4.2 and variance is 17.7. CONCLUSIONS:The results show that the precision and recall of this method have obvious advantage, compared with the content-based image retrieval.

Keywords: Image retrieval, mammograms, location feature, content feature, similarity measure

DOI: 10.3233/XST-18374

Journal: Journal of X-Ray Science and Technology, vol. 26, no. 4, pp. 553-571, 2018