• 2019-10
  • 2019-11
  • 2020-03
  • 2020-07
  • 2020-08
  • br ipsilateral mammographic surveillance following


    ipsilateral mammographic surveillance following breast 1031
    historical review, current status and future potential. 1034
    Multi-image CAD employing features derived from 1037
    Computerized localization of breast lesions from two views: 1041
    an experimental comparison of two methods. Invest Radiol 1042
    Improvement of mammographic lesion detection by fusion 1045
    Hadjiiski LM. Recognition of lesion correspondence on two 1049
    mammographic views – a new method of false-positive 1050
    reduction for computerized mass detection. Proc. 2001 SPIE 1051
    regions of interest in mediolateral oblique and craniocaudal 1054
    GS, et al. Multiview-based computer-aided detection 1057
    correlation of regions in ipsilateral views – a pilot study. 1062
    breast masses depicted on different views: a comparison of 1065
    detection performance in a multiview CAD system for 1068
    Improved location features for linkage of regions across 1071
    International Workshop on Digital Mammography; 1998. 1075
    image fusion for contrast enhancement of mammogram. J 1078
    Please cite this article in press as: Sapate S, et al. Breast cancer diagnosis using abnormalities on ipsilateral views of digital mammograms. Biocybern Biomed Eng (2019),
    Local gray level S-curve transformation – a generalized 1082
    contrast enhancement technique for medical images. 1083
    means, GMM and fuzzy clustering for 1393477-72-9 tumour 1086
    using an automatic density segmentation algorithm. J Digit 1092
    extraction algorithms applied to digital mammograms. In: 1095
    Dey N, et al., editors. Medical imaging in clinical 1096
    based on non-negative matrix factorization and fuzzy 1099
    ultrasound echography images of breast using texture 1102
    M. Radiomics based detection and characterization of 1105
    suspicious lesions on full field digital mammograms. 1106
    Swierniak A. Simplification of breast deformation 1109
    modelling to support breast cancer treatment planning. 1110
    feature extraction and classification of mammograms with
    SVM. Proc. 2011 IEEE Biomedical Circuits and Systems 1113
    transform and Gabor filter banks processing for 1116
    International New Circuits and Systems Conference; 2011. 1118 [43] Vert JP, Tsuda K, Bernhard S. A primer on kernel methods. 1119
    transform and Gabor filter banks processing for features 1122
    Computer-assisted detection of mammographic masses: a 1126
    template matching scheme based on mutual information. 1127
    Comparison of similarity measures for the task of template 1130
    matching of masses on serial mammograms. Med Phys 1131
    regions in mediolateral oblique and cranio caudal views: a 1134
    probabilistic approach. In: Giger ML, Karssemeijer N, 1135
    transform-based processing for digital mammogram 1138
    feature extraction and classification with SVM. Proc. 2011 1139
    Annual International Conference of the IEEE Engineering in 1140
    Please cite this article in press as: Sapate S, et al. Breast cancer diagnosis using abnormalities on ipsilateral views of digital mammograms. Biocybern Biomed Eng (2019), Methods xxx (xxxx) xxx–xxx
    Contents lists available at ScienceDirect
    journal homepage:
    Breast cancer histopathological image classification using a hybrid deep neural network
    Rui Yana,b, Fei Renb, Zihao Wangb,c, Lihua Wangd, Tong Zhangd, Yudong Liub, Xiaosong Raod, Chunhou Zhenga, , Fa Zhangb, a College of Computer Science and Technology, Anhui University, Hefei, China b High Performance Computer Research Center, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China c University of Chinese Academy of Sciences, Beijing, China d Department of Pathology, Peking University International Hospital, Beijing, China
    Breast cancer
    Histopathological images
    Image classification
    Deep neural network
    Even with the rapid advances in medical sciences, histopathological diagnosis is still considered the gold standard in diagnosing cancer. However, the complexity of histopathological images and the dramatic increase in workload make this task time consuming, and the results may be subject to pathologist subjectivity. Therefore, the development of automatic and precise histopathological image analysis methods is essential for the field. In this paper, we propose a new hybrid convolutional and recurrent deep neural network for breast cancer his-topathological image classification. Based on the richer multilevel feature representation of the histopathological image patches, our method integrates the advantages of convolutional and recurrent neural networks, and the short-term and long-term spatial correlations between patches are preserved. The experimental results show that our method outperforms the state-of-the-art method with an obtained average accuracy of 91.3% for the 4-class classification task. We also release a dataset with 3771 breast cancer histopathological images to the scientific community that is now publicly available at Our dataset is not only the largest publicly released dataset for breast cancer histopathological image classification, but it covers as many different subclasses spanning different age groups as possible, thus providing enough data diversity to alleviate the problem of relatively low classification accuracy of benign images.