Vision-Transformer-Based Transfer Learning for Mammogram Classification
Breast mass identification is a crucial procedure during mammogram-based early breast cancer diagnosis. However, it is difficult to determine whether a breast lump is benign or cancerous at early stages. Convolutional neural networks (CNNs) have been used to solve this problem and have provided usef...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/13/2/178 |
| _version_ | 1797443913604136960 |
|---|---|
| author | Gelan Ayana Kokeb Dese Yisak Dereje Yonas Kebede Hika Barki Dechassa Amdissa Nahimiya Husen Fikadu Mulugeta Bontu Habtamu Se-Woon Choe |
| author_facet | Gelan Ayana Kokeb Dese Yisak Dereje Yonas Kebede Hika Barki Dechassa Amdissa Nahimiya Husen Fikadu Mulugeta Bontu Habtamu Se-Woon Choe |
| author_sort | Gelan Ayana |
| collection | DOAJ |
| description | Breast mass identification is a crucial procedure during mammogram-based early breast cancer diagnosis. However, it is difficult to determine whether a breast lump is benign or cancerous at early stages. Convolutional neural networks (CNNs) have been used to solve this problem and have provided useful advancements. However, CNNs focus only on a certain portion of the mammogram while ignoring the remaining and present computational complexity because of multiple convolutions. Recently, vision transformers have been developed as a technique to overcome such limitations of CNNs, ensuring better or comparable performance in natural image classification. However, the utility of this technique has not been thoroughly investigated in the medical image domain. In this study, we developed a transfer learning technique based on vision transformers to classify breast mass mammograms. The area under the receiver operating curve of the new model was estimated as 1 ± 0, thus outperforming the CNN-based transfer-learning models and vision transformer models trained from scratch. The technique can, hence, be applied in a clinical setting, to improve the early diagnosis of breast cancer. |
| first_indexed | 2024-03-09T13:03:59Z |
| format | Article |
| id | doaj.art-95294fb0fdf945ff99a8d07d6a2e84bc |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-09T13:03:59Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-95294fb0fdf945ff99a8d07d6a2e84bc2023-11-30T21:50:41ZengMDPI AGDiagnostics2075-44182023-01-0113217810.3390/diagnostics13020178Vision-Transformer-Based Transfer Learning for Mammogram ClassificationGelan Ayana0Kokeb Dese1Yisak Dereje2Yonas Kebede3Hika Barki4Dechassa Amdissa5Nahimiya Husen6Fikadu Mulugeta7Bontu Habtamu8Se-Woon Choe9Department of Medical IT Convergence Engineering, Kumoh National Institute of Technology, Gumi 39253, Republic of KoreaSchool of Biomedical Engineering, Jimma University, Jimma 378, EthiopiaDepartment of Information Engineering, Marche Polytechnic University, 60121 Ancona, ItalyBiomedical Engineering Unit, Black Lion Hospital, Addis Ababa University, Addis Ababa 1000, EthiopiaDepartment of Artificial Intelligence Convergence, Pukyong National University, Busan 48513, Republic of KoreaDepartment of Basic and Applied Science for Engineering, Sapienza University of Rome, 00161 Roma, ItalyDepartment of Bioengineering and Robotics, Campus Bio-Medico University of Rome, 00128 Roma, ItalyCenter of Biomedical Engineering, Addis Ababa Institute of Technology, Addis Ababa University, Addis Ababa 1000, EthiopiaSchool of Biomedical Engineering, Jimma University, Jimma 378, EthiopiaDepartment of Medical IT Convergence Engineering, Kumoh National Institute of Technology, Gumi 39253, Republic of KoreaBreast mass identification is a crucial procedure during mammogram-based early breast cancer diagnosis. However, it is difficult to determine whether a breast lump is benign or cancerous at early stages. Convolutional neural networks (CNNs) have been used to solve this problem and have provided useful advancements. However, CNNs focus only on a certain portion of the mammogram while ignoring the remaining and present computational complexity because of multiple convolutions. Recently, vision transformers have been developed as a technique to overcome such limitations of CNNs, ensuring better or comparable performance in natural image classification. However, the utility of this technique has not been thoroughly investigated in the medical image domain. In this study, we developed a transfer learning technique based on vision transformers to classify breast mass mammograms. The area under the receiver operating curve of the new model was estimated as 1 ± 0, thus outperforming the CNN-based transfer-learning models and vision transformer models trained from scratch. The technique can, hence, be applied in a clinical setting, to improve the early diagnosis of breast cancer.https://www.mdpi.com/2075-4418/13/2/178transfer learningtransformersbreast cancermammography |
| spellingShingle | Gelan Ayana Kokeb Dese Yisak Dereje Yonas Kebede Hika Barki Dechassa Amdissa Nahimiya Husen Fikadu Mulugeta Bontu Habtamu Se-Woon Choe Vision-Transformer-Based Transfer Learning for Mammogram Classification Diagnostics transfer learning transformers breast cancer mammography |
| title | Vision-Transformer-Based Transfer Learning for Mammogram Classification |
| title_full | Vision-Transformer-Based Transfer Learning for Mammogram Classification |
| title_fullStr | Vision-Transformer-Based Transfer Learning for Mammogram Classification |
| title_full_unstemmed | Vision-Transformer-Based Transfer Learning for Mammogram Classification |
| title_short | Vision-Transformer-Based Transfer Learning for Mammogram Classification |
| title_sort | vision transformer based transfer learning for mammogram classification |
| topic | transfer learning transformers breast cancer mammography |
| url | https://www.mdpi.com/2075-4418/13/2/178 |
| work_keys_str_mv | AT gelanayana visiontransformerbasedtransferlearningformammogramclassification AT kokebdese visiontransformerbasedtransferlearningformammogramclassification AT yisakdereje visiontransformerbasedtransferlearningformammogramclassification AT yonaskebede visiontransformerbasedtransferlearningformammogramclassification AT hikabarki visiontransformerbasedtransferlearningformammogramclassification AT dechassaamdissa visiontransformerbasedtransferlearningformammogramclassification AT nahimiyahusen visiontransformerbasedtransferlearningformammogramclassification AT fikadumulugeta visiontransformerbasedtransferlearningformammogramclassification AT bontuhabtamu visiontransformerbasedtransferlearningformammogramclassification AT sewoonchoe visiontransformerbasedtransferlearningformammogramclassification |