Breast mass classification based on supervised contrastive learning and multi‐view consistency penalty on mammography
Abstract Breast cancer accounts for the largest number of patients among all cancers in the world. Intervention treatment for early breast cancer can dramatically extend a woman's 5‐year survival rate. However, the lack of public available breast mammography databases in the field of Computer‐a...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-11-01
|
| Series: | IET Biometrics |
| Online Access: | https://doi.org/10.1049/bme2.12076 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832546656730480640 |
|---|---|
| author | Lilei Sun Jie Wen Junqian Wang Zheng Zhang Yong Zhao Guiying Zhang Yong Xu |
| author_facet | Lilei Sun Jie Wen Junqian Wang Zheng Zhang Yong Zhao Guiying Zhang Yong Xu |
| author_sort | Lilei Sun |
| collection | DOAJ |
| description | Abstract Breast cancer accounts for the largest number of patients among all cancers in the world. Intervention treatment for early breast cancer can dramatically extend a woman's 5‐year survival rate. However, the lack of public available breast mammography databases in the field of Computer‐aided Diagnosis and the insufficient feature extraction ability from breast mammography limit the diagnostic performance of breast cancer. In this paper, A novel classification algorithm based on Convolutional Neural Network (CNN) is proposed to improve the diagnostic performance for breast cancer on mammography. A multi‐view network is designed to extract the complementary information between the Craniocaudal (CC) and Mediolateral Oblique (MLO) mammographic views of a breast mass. For the different predictions of the features extracted from the CC view and MLO view of the same breast mass, the proposed algorithm forces the network to extract the consistent features from the two views by the cross‐entropy function with an added consistent penalty term. To exploit the discriminative features from the insufficient mammographic images, the authors learnt an encoder in the classification model to learn the invariable representations from the mammographic breast mass by Supervised Contrastive Learning (SCL) to weaken the side effect of colour jitter and illumination of mammographic breast mass on image quality degradation. The experimental results of all the classification algorithms mentioned in this paper on Digital Database for Screening Mammography (DDSM) illustrate that the proposed algorithm greatly improves the classification performance and diagnostic speed of mammographic breast mass, which is of great significance for breast cancer diagnosis. |
| format | Article |
| id | doaj-art-3cfcb2d6d8e445508786ff77e402f30b |
| institution | Kabale University |
| issn | 2047-4938 2047-4946 |
| language | English |
| publishDate | 2022-11-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Biometrics |
| spelling | doaj-art-3cfcb2d6d8e445508786ff77e402f30b2025-02-03T06:47:37ZengWileyIET Biometrics2047-49382047-49462022-11-0111658860010.1049/bme2.12076Breast mass classification based on supervised contrastive learning and multi‐view consistency penalty on mammographyLilei Sun0Jie Wen1Junqian Wang2Zheng Zhang3Yong Zhao4Guiying Zhang5Yong Xu6College of Computer Science and Technology Guizhou University Guiyang ChinaShenzhen Key Laboratory of Visual Object Detection and Recognition Harbin Institute of Technology Shenzhen ChinaShenzhen Key Laboratory of Visual Object Detection and Recognition Harbin Institute of Technology Shenzhen ChinaHarbin Institute of Technology Shenzhen ChinaCollege of Computer Science and Technology Guizhou University Guiyang ChinaQingyuan People's Hospital Guangzhou Medical University Qingyuan ChinaShenzhen Key Laboratory of Visual Object Detection and Recognition Harbin Institute of Technology Shenzhen ChinaAbstract Breast cancer accounts for the largest number of patients among all cancers in the world. Intervention treatment for early breast cancer can dramatically extend a woman's 5‐year survival rate. However, the lack of public available breast mammography databases in the field of Computer‐aided Diagnosis and the insufficient feature extraction ability from breast mammography limit the diagnostic performance of breast cancer. In this paper, A novel classification algorithm based on Convolutional Neural Network (CNN) is proposed to improve the diagnostic performance for breast cancer on mammography. A multi‐view network is designed to extract the complementary information between the Craniocaudal (CC) and Mediolateral Oblique (MLO) mammographic views of a breast mass. For the different predictions of the features extracted from the CC view and MLO view of the same breast mass, the proposed algorithm forces the network to extract the consistent features from the two views by the cross‐entropy function with an added consistent penalty term. To exploit the discriminative features from the insufficient mammographic images, the authors learnt an encoder in the classification model to learn the invariable representations from the mammographic breast mass by Supervised Contrastive Learning (SCL) to weaken the side effect of colour jitter and illumination of mammographic breast mass on image quality degradation. The experimental results of all the classification algorithms mentioned in this paper on Digital Database for Screening Mammography (DDSM) illustrate that the proposed algorithm greatly improves the classification performance and diagnostic speed of mammographic breast mass, which is of great significance for breast cancer diagnosis.https://doi.org/10.1049/bme2.12076 |
| spellingShingle | Lilei Sun Jie Wen Junqian Wang Zheng Zhang Yong Zhao Guiying Zhang Yong Xu Breast mass classification based on supervised contrastive learning and multi‐view consistency penalty on mammography IET Biometrics |
| title | Breast mass classification based on supervised contrastive learning and multi‐view consistency penalty on mammography |
| title_full | Breast mass classification based on supervised contrastive learning and multi‐view consistency penalty on mammography |
| title_fullStr | Breast mass classification based on supervised contrastive learning and multi‐view consistency penalty on mammography |
| title_full_unstemmed | Breast mass classification based on supervised contrastive learning and multi‐view consistency penalty on mammography |
| title_short | Breast mass classification based on supervised contrastive learning and multi‐view consistency penalty on mammography |
| title_sort | breast mass classification based on supervised contrastive learning and multi view consistency penalty on mammography |
| url | https://doi.org/10.1049/bme2.12076 |
| work_keys_str_mv | AT lileisun breastmassclassificationbasedonsupervisedcontrastivelearningandmultiviewconsistencypenaltyonmammography AT jiewen breastmassclassificationbasedonsupervisedcontrastivelearningandmultiviewconsistencypenaltyonmammography AT junqianwang breastmassclassificationbasedonsupervisedcontrastivelearningandmultiviewconsistencypenaltyonmammography AT zhengzhang breastmassclassificationbasedonsupervisedcontrastivelearningandmultiviewconsistencypenaltyonmammography AT yongzhao breastmassclassificationbasedonsupervisedcontrastivelearningandmultiviewconsistencypenaltyonmammography AT guiyingzhang breastmassclassificationbasedonsupervisedcontrastivelearningandmultiviewconsistencypenaltyonmammography AT yongxu breastmassclassificationbasedonsupervisedcontrastivelearningandmultiviewconsistencypenaltyonmammography |