This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
MVMDNet: A Weakly-Supervised Multi-View Enhancing Network for Mass Detection in Mammograms
Technical Paper
2022-01-7030
ISSN: 0148-7191, e-ISSN: 2688-3627
Annotation ability available
Sector:
Language:
English
Abstract
Mass is one important suspicious object for breast cancer diagnosis in mammograms. Computer-aided detection (CAD) based on fully supervised deep learning achieves high performance for mass detection in mammograms. The lack of fine-grained expert labels becomes the bottleneck for the large-scale application of CAD to achieve detection in mammograms. Weakly supervised methods provide a solution to tackle the annotation problems, including in the application for mass detection. However, previous works face the problem of insufficient localization information, which affect the ability of mass detection. In this paper, we propose a multi-view enhancing mass detection network (MVMDNet) with dual view inputs that contains craniocaudal (CC) and mediolateral oblique (MLO) view of mammograms, where different view features are interacted and fused to enhance localization information. After backbone extracts dual view features, the multi-view enhancement is contributed by following modules: First, by Special Correlation Attention (SCA) module, the correlation between dual views features, which contains extra localization information, is extracted to generate the auxiliary features. Second, by Sigmoid Weighted Fusion module, examined features are generated from the fusion of auxiliary feature and the main diagnostic CC view feature, where the weights of fusion are automatically learned in training. Examined features are conducted a binary classification training by image-level labels that indicate whether masses are contained in mammograms. Aiming to realize the detection, Class Activating Mapping-based detection module catch the network’s attention regions on examined features to generate the detection boxes for breast mass. We conduct experiments on both in-house dataset and public INbreast dataset. The recall rate of 0.96±0.02 on public INbreast dataset and the recall rate of 0.92 on in-house dataset demonstrate the performance of MVMDNet is similar to the fully-supervised methods and achieves the state-of-the-art among weakly-supervised methods. This performance on the public INbreast dataset also indicates a robust generalization ability.
Authors
- Huairui Zhao - School of Information Science and Technology, Fudan Universi
- Jia Hua - School of Medicine, Shanghai Jiao Tong University, China
- Xiaochuan Geng - School of Medicine, Shanghai Jiao Tong University, China
- Jianrong Xu - School of Medicine, Shanghai Jiao Tong University, China
- Yi Guo - Fudan University, School of Information Science and Technolo
- Shiteng Suo - School of Medicine, Shanghai Jiao Tong University, China
- Yan Zhou - School of Medicine, Shanghai Jiao Tong University, China
- Yuanyuan Wang - School of Information Science and Technology, Fudan Universi
Topic
Citation
Zhao, H., Hua, J., Geng, X., Xu, J. et al., "MVMDNet: A Weakly-Supervised Multi-View Enhancing Network for Mass Detection in Mammograms," SAE Technical Paper 2022-01-7030, 2022, https://doi.org/10.4271/2022-01-7030.Also In
References
- Siegel , R.L. , Miller , K.D. , Fuchs , H.E. , and Jemal , A. Cancer Statistics, 2021 CA: A Cancer Journal for Clinicians 71 1 2021 7 33 https://doi.org/10.3322/caac.21654
- Tabár , L. , Vitak , B. , Chen , T.H.-H. , Yen , A.M.-F. et al. Swedish Two-County Trial: Impact of Mammographic Screening on Breast Cancer Mortality During 3 Decades Radiology 260 3 2011 658 663 https://doi.org/10.1148/radiol.11110469
- Marmot , M.G. , Altman , D.G. , Cameron , D.A. , Dewar , J.A. et al. The Benefits and Harms of Breast Cancer Screening: An Independent Review: A Report Jointly Commissioned by Cancer Research UK and the Department of Health (England) October 2012 Br J Cancer 108 11 2013 2205 2240 https://doi.org/10.1038/bjc.2013.177
- Anwar , S.M. , Majid , M. , Qayyum , A. , Awais , M. et al. Medical Image Analysis using Convolutional Neural Networks: A Review J Med Syst 42 11 2018 226 https://doi.org/10.1007/s10916-018-1088-1
- Cheplygina , V. , Bruijne , M. de , and Pluim , J.P.W. Not-So-Supervised: A Survey of Semi-Supervised, Multi-Instance, and Transfer Learning in Medical Image Analysis Medical Image Analysis 54 280 296 2019 https://doi.org/10.1016/j.media.2019.03.009
- Agarwal , R. , Díaz , O. , Yap , M.H. , Lladó , X. et al. Deep Learning for Mass Detection in Full Field Digital Mammograms Computers in Biology and Medicine 121 2020 103774 https://doi.org/10.1016/j.compbiomed.2020.103774
- Shen , L. , Margolies , L.R. , Rothstein , J.H. , Fluder , E. et al. Deep Learning to Improve Breast Cancer Detection on Screening Mammography Sci Rep 9 1 2019 12495 https://doi.org/10.1038/s41598-019-48995-4
- Shen , Y. , Wu , N. , Phang , J. , Park , J. et al. Globally-Aware Multiple Instance Classifier for Breast Cancer Screening Suk , H.-I. , Liu , M. , Yan , P. and Lian , C. Machine Learning in Medical Imaging Cham Springer International Publishing 2019 18 26 https://doi.org/10.1007/978-3-030-32692-0_3 978-3-030-32692-0
- Shao , F. , Chen , L. , Shao , J. , Ji , W. et al. ArXiv:2105.12694 [Cs] 2021
- Liang , G. , Wang , X. , Zhang , Y. , and Jacobs , N. Weakly-Supervised Self-Training for Breast Cancer Localization* 42nd Annual International Conference of the IEEE Engineering in Medicine Biology Society (EMBC) 1124 1127 2020 https://doi.org/10.1109/EMBC44109.2020.9176617
- Samulski , M. and Karssemeijer , N. Optimizing Case-Based Detection Performance in a Multiview CAD System for Mammography IEEE Transactions on Medical Imaging 30 4 2011 1001 1009 https://doi.org/10.1109/TMI.2011.2105886
- Bekker , A.J. , Shalhon , M. , Greenspan , H. , and Goldberger , J. Multi-View Probabilistic Classification of Breast Microcalcifications IEEE Transactions on Medical Imaging 35 2 2016 645 653 https://doi.org/10.1109/TMI.2015.2488019
- Ma , J. , Li , X. , Li , H. , Wang , R. et al. Cross-View Relation Networks for Mammogram Mass Detection 25th International Conference on Pattern Recognition (ICPR) 8632 8638 2021 https://doi.org/10.1109/ICPR48806.2021.9413132
- Liu , Y. , Zhang , F. , Zhang , Q. , Wang , S. et al. Cross-View Correspondence Reasoning Based on Bipartite Graph Convolutional Network for Mammogram Mass Detection IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 3811 3821 2020 https://doi.org/10.1109/CVPR42600.2020.00387
- Illingworth , J. and Kittler , J. A Survey of the Hough Transform Computer Vision, Graphics, and Image Processing 44 1 1988 87 116 https://doi.org/10.1016/S0734-189X(88)80033-1
- Tan , M. and Le , Q.V. ArXiv:2104.00298 [Cs] 2021
- Muhammad , M.B. and Yeasin , M. Eigen-CAM: Class Activation Map using Principal Components International Joint Conference on Neural Networks (IJCNN) 1 7 2020 https://doi.org/10.1109/IJCNN48605.2020.9206626
- Moreira , I.C. , Amaral , I. , Domingues , I. , Cardoso , A. et al. INbreast: Toward a Full-Field Digital Mammographic Database Academic Radiology 19 2 2012 236 248 https://doi.org/10.1016/j.acra.2011.09.014
- Lotter , W. , Diab , A.R. , Haslam , B. , Kim , J.G. et al. ArXiv:1912.11027 [Cs, Eess] 2019
- Dhungel , N. , Carneiro , G. , and Bradley , A.P. A Deep Learning Approach for the Analysis of Masses in Mammograms with Minimal User Intervention Medical Image Analysis 37 2017 114 128 https://doi.org/10.1016/j.media.2017.01.009
- Agarwal , R. , Diaz , O. , Lladó , X. , Yap , M.H. et al. Automatic Mass Detection in Mammograms using Deep Convolutional Neural Networks JMI 6 3 2019 031409 https://doi.org/10.1117/1.JMI.6.3.031409
- Yang , Z. , Cao , Z. , Zhang , Y. , Tang , Y. et al. MommiNet-v2: Mammographic Multi-View Mass Identification Networks Medical Image Analysis 73 2021 102204 https://doi.org/10.1016/j.media.2021.102204
- Tang , Y. , Cao , Z. , Zhang , Y. , Yang , Z. et al. Leveraging Large-Scale Weakly Labeled Data for Semi-Supervised Mass Detection in Mammograms IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE Nashville, TN, USA 978-1-66544-509-2 3854 3863 2021 https://doi.org/10.1109/CVPR46437.2021.00385
- Tardy , M. and Mateus , D. Looking for Abnormalities in Mammograms With Self- and Weakly Supervised Reconstruction IEEE Transactions on Medical Imaging 40 10 2021 2711 2722 https://doi.org/10.1109/TMI.2021.3050040
- https://github.com/ultralytics/YOLOv5
- Shen , Y. , Wu , N. , Phang , J. , Park , J. et al. An Interpretable Classifier for High-Resolution Breast Cancer Screening Images Utilizing Weakly Supervised Localization Medical Image Analysis 68 2021 101908 https://doi.org/10.1016/j.media.2020.101908
- Dhungel , N. , Carneiro , G. , and Bradley , A.P. A Deep Learning Approach for the Analysis of Masses in Mammograms with Minimal User Intervention Medical Image Analysis 37 2017 114 128 https://doi.org/10.1016/j.media.2017.01.009
- Tardy , M. and Mateus , D. Looking for Abnormalities in Mammograms with Self- and Weakly Supervised Reconstruction IEEE Transactions on Medical Imaging 40 10 2021 2711 2722 https://doi.org/10.1109/TMI.2021.3050040
- Selvaraju , R.R. , Cogswell , M. , Das , A. , Vedantam , R. et al. Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization IEEE International Conference on Computer Vision (ICCV) 618 626 2017 https://doi.org/10.1109/ICCV.2017.74
- Wang , H. , Wang , Z. , Du , M. , Yang , F. et al. Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) IEEE, Seattle, WA, USA 978-1-72819-360-1 111 119 2020 https://doi.org/10.1109/CVPRW50498.2020.00020