Breast Cancer Histopathological Images Recognition Based on Low Dimensional Three-Channel Features
Breast cancer (BC) is the primary threat to women’s health, and early diagnosis of breast cancer is imperative. Although there are many ways to diagnose breast cancer, the gold standard is still pathological examination. In this paper, a low dimensional three-channel features based breast cancer his...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2021-06-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2021.657560/full |
| _version_ | 1819088987098185728 |
|---|---|
| author | Yan Hao Shichang Qiao Li Zhang Ting Xu Yanping Bai Hongping Hu Wendong Zhang Guojun Zhang |
| author_facet | Yan Hao Shichang Qiao Li Zhang Ting Xu Yanping Bai Hongping Hu Wendong Zhang Guojun Zhang |
| author_sort | Yan Hao |
| collection | DOAJ |
| description | Breast cancer (BC) is the primary threat to women’s health, and early diagnosis of breast cancer is imperative. Although there are many ways to diagnose breast cancer, the gold standard is still pathological examination. In this paper, a low dimensional three-channel features based breast cancer histopathological images recognition method is proposed to achieve fast and accurate breast cancer benign and malignant recognition. Three-channel features of 10 descriptors were extracted, which are gray level co-occurrence matrix on one direction (GLCM1), gray level co-occurrence matrix on four directions (GLCM4), average pixel value of each channel (APVEC), Hu invariant moment (HIM), wavelet features, Tamura, completed local binary pattern (CLBP), local binary pattern (LBP), Gabor, histogram of oriented gradient (Hog), respectively. Then support vector machine (SVM) was used to assess their performance. Experiments on BreaKHis dataset show that GLCM1, GLCM4 and APVEC achieved the recognition accuracy of 90.2%-94.97% at the image level and 89.18%-94.24% at the patient level, which is better than many state-of-the-art methods, including many deep learning frameworks. The experimental results show that the breast cancer recognition based on high dimensional features will increase the recognition time, but the recognition accuracy is not greatly improved. Three-channel features will enhance the recognizability of the image, so as to achieve higher recognition accuracy than gray-level features. |
| first_indexed | 2024-12-21T22:00:46Z |
| format | Article |
| id | doaj.art-ace8146912a6495391ceb29c9af38ba4 |
| institution | Directory Open Access Journal |
| issn | 2234-943X |
| language | English |
| last_indexed | 2024-12-21T22:00:46Z |
| publishDate | 2021-06-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj.art-ace8146912a6495391ceb29c9af38ba42022-12-21T18:48:50ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2021-06-011110.3389/fonc.2021.657560657560Breast Cancer Histopathological Images Recognition Based on Low Dimensional Three-Channel FeaturesYan Hao0Shichang Qiao1Li Zhang2Ting Xu3Yanping Bai4Hongping Hu5Wendong Zhang6Guojun Zhang7School of Information and Communication Engineering, North University of China, Taiyuan, ChinaDepartment of Mathematics, School of Science, North University of China, Taiyuan, ChinaDepartment of Mathematics, School of Science, North University of China, Taiyuan, ChinaDepartment of Mathematics, School of Science, North University of China, Taiyuan, ChinaDepartment of Mathematics, School of Science, North University of China, Taiyuan, ChinaDepartment of Mathematics, School of Science, North University of China, Taiyuan, ChinaSchool of Instrument and Electronics, Key Laboratory of Dynamic Testing Technology, North University of China, Taiyuan, ChinaSchool of Instrument and Electronics, Key Laboratory of Dynamic Testing Technology, North University of China, Taiyuan, ChinaBreast cancer (BC) is the primary threat to women’s health, and early diagnosis of breast cancer is imperative. Although there are many ways to diagnose breast cancer, the gold standard is still pathological examination. In this paper, a low dimensional three-channel features based breast cancer histopathological images recognition method is proposed to achieve fast and accurate breast cancer benign and malignant recognition. Three-channel features of 10 descriptors were extracted, which are gray level co-occurrence matrix on one direction (GLCM1), gray level co-occurrence matrix on four directions (GLCM4), average pixel value of each channel (APVEC), Hu invariant moment (HIM), wavelet features, Tamura, completed local binary pattern (CLBP), local binary pattern (LBP), Gabor, histogram of oriented gradient (Hog), respectively. Then support vector machine (SVM) was used to assess their performance. Experiments on BreaKHis dataset show that GLCM1, GLCM4 and APVEC achieved the recognition accuracy of 90.2%-94.97% at the image level and 89.18%-94.24% at the patient level, which is better than many state-of-the-art methods, including many deep learning frameworks. The experimental results show that the breast cancer recognition based on high dimensional features will increase the recognition time, but the recognition accuracy is not greatly improved. Three-channel features will enhance the recognizability of the image, so as to achieve higher recognition accuracy than gray-level features.https://www.frontiersin.org/articles/10.3389/fonc.2021.657560/fullbreast cancerhistopathological images recognitionfeature extractionlow dimensional featuresthree-channel features |
| spellingShingle | Yan Hao Shichang Qiao Li Zhang Ting Xu Yanping Bai Hongping Hu Wendong Zhang Guojun Zhang Breast Cancer Histopathological Images Recognition Based on Low Dimensional Three-Channel Features Frontiers in Oncology breast cancer histopathological images recognition feature extraction low dimensional features three-channel features |
| title | Breast Cancer Histopathological Images Recognition Based on Low Dimensional Three-Channel Features |
| title_full | Breast Cancer Histopathological Images Recognition Based on Low Dimensional Three-Channel Features |
| title_fullStr | Breast Cancer Histopathological Images Recognition Based on Low Dimensional Three-Channel Features |
| title_full_unstemmed | Breast Cancer Histopathological Images Recognition Based on Low Dimensional Three-Channel Features |
| title_short | Breast Cancer Histopathological Images Recognition Based on Low Dimensional Three-Channel Features |
| title_sort | breast cancer histopathological images recognition based on low dimensional three channel features |
| topic | breast cancer histopathological images recognition feature extraction low dimensional features three-channel features |
| url | https://www.frontiersin.org/articles/10.3389/fonc.2021.657560/full |
| work_keys_str_mv | AT yanhao breastcancerhistopathologicalimagesrecognitionbasedonlowdimensionalthreechannelfeatures AT shichangqiao breastcancerhistopathologicalimagesrecognitionbasedonlowdimensionalthreechannelfeatures AT lizhang breastcancerhistopathologicalimagesrecognitionbasedonlowdimensionalthreechannelfeatures AT tingxu breastcancerhistopathologicalimagesrecognitionbasedonlowdimensionalthreechannelfeatures AT yanpingbai breastcancerhistopathologicalimagesrecognitionbasedonlowdimensionalthreechannelfeatures AT hongpinghu breastcancerhistopathologicalimagesrecognitionbasedonlowdimensionalthreechannelfeatures AT wendongzhang breastcancerhistopathologicalimagesrecognitionbasedonlowdimensionalthreechannelfeatures AT guojunzhang breastcancerhistopathologicalimagesrecognitionbasedonlowdimensionalthreechannelfeatures |