A similarity measure method combining location feature for mammogram retrieval.

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.

[1]  Xuelong Li,et al.  Image categorization: Graph edit distance+edge direction histogram , 2008, Pattern Recognit..

[2]  Bo Zhang,et al.  An efficient and effective region-based image retrieval framework , 2004, IEEE Transactions on Image Processing.

[3]  Ingo Wegener,et al.  Modified repeated median filters , 2006, Stat. Comput..

[4]  Débora C. Muchaluat-Saade,et al.  Hybrid analysis for indicating patients with breast cancer using temperature time series , 2016, Comput. Methods Programs Biomed..

[5]  Haibin Ling,et al.  An Efficient Earth Mover's Distance Algorithm for Robust Histogram Comparison , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  H. Greenspan,et al.  Automated retrieval of CT images of liver lesions on the basis of image similarity: method and preliminary results. , 2010, Radiology.

[7]  David J. Hawkes,et al.  Deformable Vessel-Based Registration Using Landmark-Guided Coherent Point Drift , 2010, MIAR.

[8]  Matti Pietikäinen,et al.  Texture classification by center-symmetric auto-correlation, using Kullback discrimination of distributions , 1995, Pattern Recognit. Lett..

[9]  Andriy Myronenko,et al.  Point Set Registration: Coherent Point Drift , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  D. Abraham Chandy,et al.  Texture feature extraction using gray level statistical matrix for content-based mammogram retrieval , 2013, Multimedia Tools and Applications.

[11]  A. Jemal,et al.  Cancer Statistics, 2010 , 2010, CA: a cancer journal for clinicians.

[12]  Wanli Ma,et al.  Tensor decomposition and application in image classification with histogram of oriented gradients , 2015, Neurocomputing.

[13]  Yunlong Liu,et al.  From genes to networks: in systematic points of view , 2011, BMC Systems Biology.

[14]  Vipin Tyagi,et al.  An integrated approach for image retrieval using local binary pattern , 2015, Multimedia Tools and Applications.

[15]  André Carlos Ponce de Leon Ferreira de Carvalho,et al.  Endowing a Content-Based Medical Image Retrieval System with Perceptual Similarity Using Ensemble Strategy , 2016, Journal of Digital Imaging.

[16]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Leonidas J. Guibas,et al.  A metric for distributions with applications to image databases , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[18]  Pau-Choo Chung,et al.  A Fast Algorithm for Multilevel Thresholding , 2001, J. Inf. Sci. Eng..

[19]  Qian Chen,et al.  Image enhancement based on equal area dualistic sub-image histogram equalization method , 1999, IEEE Trans. Consumer Electron..

[20]  Arnaldo de Albuquerque Araújo,et al.  MammoSys: A content-based image retrieval system using breast density patterns , 2010, Comput. Methods Programs Biomed..

[21]  Xiaohui Liu,et al.  Mammogram retrieval on similar mass lesions , 2012, Comput. Methods Programs Biomed..

[22]  Peter Xiaoping Liu,et al.  Semiparametric Decolorization With Laplacian-Based Perceptual Quality Metric , 2017, IEEE Transactions on Circuits and Systems for Video Technology.

[23]  Lubomir M. Hadjiiski,et al.  Automated registration of breast lesions in temporal pairs of mammograms for interval change analysis--local affine transformation for improved localization. , 2001, Medical physics.

[24]  Liang-Tien Chia,et al.  Efficient image retrieval using MPEG-7 descriptors , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[25]  Li Shun.  Medical Image Retrieve Based on Gray Histogram and Correlation , 2001 .

[26]  Haejun Lee,et al.  Medical Image Retrieval: Past and Present , 2012, Healthcare informatics research.