Principal component analysis and fine-tuned vision transformation integrating model explainability for breast cancer prediction
Abstract Breast cancer, which is the most commonly diagnosed cancers among women, is a notable health issues globally. Breast cancer is a result of abnormal cells in the breast tissue growing out of control. Histopathology, which refers to the detection and learning of tissue diseases, has appeared...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2025-03-01
|
| Series: | Visual Computing for Industry, Biomedicine, and Art |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s42492-025-00186-x |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849774811841036288 |
|---|---|
| author | Huong Hoang Luong Phuc Phan Hong Dat Vo Minh Thinh Nguyen Le Quang Anh Dinh The Nguyen Thai-Nghe Hai Thanh Nguyen |
| author_facet | Huong Hoang Luong Phuc Phan Hong Dat Vo Minh Thinh Nguyen Le Quang Anh Dinh The Nguyen Thai-Nghe Hai Thanh Nguyen |
| author_sort | Huong Hoang Luong |
| collection | DOAJ |
| description | Abstract Breast cancer, which is the most commonly diagnosed cancers among women, is a notable health issues globally. Breast cancer is a result of abnormal cells in the breast tissue growing out of control. Histopathology, which refers to the detection and learning of tissue diseases, has appeared as a solution for breast cancer treatment as it plays a vital role in its diagnosis and classification. Thus, considerable research on histopathology in medical and computer science has been conducted to develop an effective method for breast cancer treatment. In this study, a vision Transformer (ViT) was employed to classify tumors into two classes, benign and malignant, in the Breast Cancer Histopathological Database (BreakHis). To enhance the model performance, we introduced the novel multi-head locality large kernel self-attention during fine-tuning, achieving an accuracy of 95.94% at 100× magnification, thereby improving the accuracy by 3.34% compared to a standard ViT (which uses multi-head self-attention). In addition, the application of principal component analysis for dimensionality reduction led to an accuracy improvement of 3.34%, highlighting its role in mitigating overfitting and reducing the computational complexity. In the final phase, SHapley Additive exPlanations, Local Interpretable Model-agnostic Explanations, and Gradient-weighted Class Activation Mapping were used for the interpretability and explainability of machine-learning models, aiding in understanding the feature importance and local explanations, and visualizing the model attention. In another experiment, ensemble learning with VGGIN further boosted the performance to 97.13% accuracy. Our approach exhibited a 0.98% to 17.13% improvement in accuracy compared with state-of-the-art methods, establishing a new benchmark for breast cancer histopathological image classification. |
| format | Article |
| id | doaj-art-eea26d4d13214fcb9ccab46b2f5b91c9 |
| institution | DOAJ |
| issn | 2524-4442 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Visual Computing for Industry, Biomedicine, and Art |
| spelling | doaj-art-eea26d4d13214fcb9ccab46b2f5b91c92025-08-20T03:01:36ZengSpringerOpenVisual Computing for Industry, Biomedicine, and Art2524-44422025-03-018111910.1186/s42492-025-00186-xPrincipal component analysis and fine-tuned vision transformation integrating model explainability for breast cancer predictionHuong Hoang Luong0Phuc Phan Hong1Dat Vo Minh2Thinh Nguyen Le Quang3Anh Dinh The4Nguyen Thai-Nghe5Hai Thanh Nguyen6College of Information and Communication Technology, Can Tho UniversityInformation Technology Department, FPT UniversityInformation Technology Department, FPT UniversityInformation Technology Department, FPT UniversityInformation Technology Department, FPT UniversityCollege of Information and Communication Technology, Can Tho UniversityCollege of Information and Communication Technology, Can Tho UniversityAbstract Breast cancer, which is the most commonly diagnosed cancers among women, is a notable health issues globally. Breast cancer is a result of abnormal cells in the breast tissue growing out of control. Histopathology, which refers to the detection and learning of tissue diseases, has appeared as a solution for breast cancer treatment as it plays a vital role in its diagnosis and classification. Thus, considerable research on histopathology in medical and computer science has been conducted to develop an effective method for breast cancer treatment. In this study, a vision Transformer (ViT) was employed to classify tumors into two classes, benign and malignant, in the Breast Cancer Histopathological Database (BreakHis). To enhance the model performance, we introduced the novel multi-head locality large kernel self-attention during fine-tuning, achieving an accuracy of 95.94% at 100× magnification, thereby improving the accuracy by 3.34% compared to a standard ViT (which uses multi-head self-attention). In addition, the application of principal component analysis for dimensionality reduction led to an accuracy improvement of 3.34%, highlighting its role in mitigating overfitting and reducing the computational complexity. In the final phase, SHapley Additive exPlanations, Local Interpretable Model-agnostic Explanations, and Gradient-weighted Class Activation Mapping were used for the interpretability and explainability of machine-learning models, aiding in understanding the feature importance and local explanations, and visualizing the model attention. In another experiment, ensemble learning with VGGIN further boosted the performance to 97.13% accuracy. Our approach exhibited a 0.98% to 17.13% improvement in accuracy compared with state-of-the-art methods, establishing a new benchmark for breast cancer histopathological image classification.https://doi.org/10.1186/s42492-025-00186-xVision TransformerMulti-head locality large kernel self-attentionPrincipal component analysis |
| spellingShingle | Huong Hoang Luong Phuc Phan Hong Dat Vo Minh Thinh Nguyen Le Quang Anh Dinh The Nguyen Thai-Nghe Hai Thanh Nguyen Principal component analysis and fine-tuned vision transformation integrating model explainability for breast cancer prediction Visual Computing for Industry, Biomedicine, and Art Vision Transformer Multi-head locality large kernel self-attention Principal component analysis |
| title | Principal component analysis and fine-tuned vision transformation integrating model explainability for breast cancer prediction |
| title_full | Principal component analysis and fine-tuned vision transformation integrating model explainability for breast cancer prediction |
| title_fullStr | Principal component analysis and fine-tuned vision transformation integrating model explainability for breast cancer prediction |
| title_full_unstemmed | Principal component analysis and fine-tuned vision transformation integrating model explainability for breast cancer prediction |
| title_short | Principal component analysis and fine-tuned vision transformation integrating model explainability for breast cancer prediction |
| title_sort | principal component analysis and fine tuned vision transformation integrating model explainability for breast cancer prediction |
| topic | Vision Transformer Multi-head locality large kernel self-attention Principal component analysis |
| url | https://doi.org/10.1186/s42492-025-00186-x |
| work_keys_str_mv | AT huonghoangluong principalcomponentanalysisandfinetunedvisiontransformationintegratingmodelexplainabilityforbreastcancerprediction AT phucphanhong principalcomponentanalysisandfinetunedvisiontransformationintegratingmodelexplainabilityforbreastcancerprediction AT datvominh principalcomponentanalysisandfinetunedvisiontransformationintegratingmodelexplainabilityforbreastcancerprediction AT thinhnguyenlequang principalcomponentanalysisandfinetunedvisiontransformationintegratingmodelexplainabilityforbreastcancerprediction AT anhdinhthe principalcomponentanalysisandfinetunedvisiontransformationintegratingmodelexplainabilityforbreastcancerprediction AT nguyenthainghe principalcomponentanalysisandfinetunedvisiontransformationintegratingmodelexplainabilityforbreastcancerprediction AT haithanhnguyen principalcomponentanalysisandfinetunedvisiontransformationintegratingmodelexplainabilityforbreastcancerprediction |