Mutual information-based radiomic feature selection with SHAP explainability for breast cancer diagnosis
Breast cancer is a prevalent concern for women globally, with misdiagnosis potentially leading to detrimental outcomes. Early detection is crucial, often reliant on medical imaging analysis. Digital Breast Tomosynthesis (DBT) is a promising modality, addressing limitations of traditional mammograms....
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-12-01
|
| Series: | Results in Engineering |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590123024013264 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850112374981263360 |
|---|---|
| author | Oladosu Oyebisi Oladimeji Hamail Ayaz Ian McLoughlin Saritha Unnikrishnan |
| author_facet | Oladosu Oyebisi Oladimeji Hamail Ayaz Ian McLoughlin Saritha Unnikrishnan |
| author_sort | Oladosu Oyebisi Oladimeji |
| collection | DOAJ |
| description | Breast cancer is a prevalent concern for women globally, with misdiagnosis potentially leading to detrimental outcomes. Early detection is crucial, often reliant on medical imaging analysis. Digital Breast Tomosynthesis (DBT) is a promising modality, addressing limitations of traditional mammograms. However, diagnosing breast cancer involves subjective visual examination, leading to inaccuracies. Radiomics, applied in various imaging modalities such as MRI, and digital mammography, remains underutilized in DBT. This study introduces a Mutual Information-based Radiomic Feature Selection (MIRFS) framework for DBT breast cancer evaluation followed by SHAP explanations. Selected features were assessed using machine learning algorithms, with Random Forest achieving 92% accuracy in lesion classification. MIRFS demonstrates significant performance improvements, addressing subjectivity and enhancing diagnostic accuracy through explainability. SHAP methodology elucidates feature importance, aiding model interpretation. Compared to deep learning methods, MIRFS outperforms both deep learning and existing machine learning approaches, promising advancements in breast cancer diagnosis and treatment. |
| format | Article |
| id | doaj-art-afc0eb9e63fd40e987fcd8455d2d7752 |
| institution | OA Journals |
| issn | 2590-1230 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Results in Engineering |
| spelling | doaj-art-afc0eb9e63fd40e987fcd8455d2d77522025-08-20T02:37:24ZengElsevierResults in Engineering2590-12302024-12-012410307110.1016/j.rineng.2024.103071Mutual information-based radiomic feature selection with SHAP explainability for breast cancer diagnosisOladosu Oyebisi Oladimeji0Hamail Ayaz1Ian McLoughlin2Saritha Unnikrishnan3Mathematical Modelling and Intelligent Systems for Health and Environment (MISHE), Atlantic Technological University, Sligo, F91 YW50, Ireland; Faculty of Engineering and Design, Atlantic Technological University, Sligo, F91 YW50, Ireland; Corresponding authors.Mathematical Modelling and Intelligent Systems for Health and Environment (MISHE), Atlantic Technological University, Sligo, F91 YW50, Ireland; Faculty of Engineering and Design, Atlantic Technological University, Sligo, F91 YW50, IrelandDepartment of Computer Science and Applied Physics, Atlantic Technological University, Galway, IrelandMathematical Modelling and Intelligent Systems for Health and Environment (MISHE), Atlantic Technological University, Sligo, F91 YW50, Ireland; Faculty of Engineering and Design, Atlantic Technological University, Sligo, F91 YW50, Ireland; Corresponding authors.Breast cancer is a prevalent concern for women globally, with misdiagnosis potentially leading to detrimental outcomes. Early detection is crucial, often reliant on medical imaging analysis. Digital Breast Tomosynthesis (DBT) is a promising modality, addressing limitations of traditional mammograms. However, diagnosing breast cancer involves subjective visual examination, leading to inaccuracies. Radiomics, applied in various imaging modalities such as MRI, and digital mammography, remains underutilized in DBT. This study introduces a Mutual Information-based Radiomic Feature Selection (MIRFS) framework for DBT breast cancer evaluation followed by SHAP explanations. Selected features were assessed using machine learning algorithms, with Random Forest achieving 92% accuracy in lesion classification. MIRFS demonstrates significant performance improvements, addressing subjectivity and enhancing diagnostic accuracy through explainability. SHAP methodology elucidates feature importance, aiding model interpretation. Compared to deep learning methods, MIRFS outperforms both deep learning and existing machine learning approaches, promising advancements in breast cancer diagnosis and treatment.http://www.sciencedirect.com/science/article/pii/S2590123024013264RadiomicsExplainable AIBreast cancerDigital breast tomosynthesisMachine learningClassification |
| spellingShingle | Oladosu Oyebisi Oladimeji Hamail Ayaz Ian McLoughlin Saritha Unnikrishnan Mutual information-based radiomic feature selection with SHAP explainability for breast cancer diagnosis Results in Engineering Radiomics Explainable AI Breast cancer Digital breast tomosynthesis Machine learning Classification |
| title | Mutual information-based radiomic feature selection with SHAP explainability for breast cancer diagnosis |
| title_full | Mutual information-based radiomic feature selection with SHAP explainability for breast cancer diagnosis |
| title_fullStr | Mutual information-based radiomic feature selection with SHAP explainability for breast cancer diagnosis |
| title_full_unstemmed | Mutual information-based radiomic feature selection with SHAP explainability for breast cancer diagnosis |
| title_short | Mutual information-based radiomic feature selection with SHAP explainability for breast cancer diagnosis |
| title_sort | mutual information based radiomic feature selection with shap explainability for breast cancer diagnosis |
| topic | Radiomics Explainable AI Breast cancer Digital breast tomosynthesis Machine learning Classification |
| url | http://www.sciencedirect.com/science/article/pii/S2590123024013264 |
| work_keys_str_mv | AT oladosuoyebisioladimeji mutualinformationbasedradiomicfeatureselectionwithshapexplainabilityforbreastcancerdiagnosis AT hamailayaz mutualinformationbasedradiomicfeatureselectionwithshapexplainabilityforbreastcancerdiagnosis AT ianmcloughlin mutualinformationbasedradiomicfeatureselectionwithshapexplainabilityforbreastcancerdiagnosis AT sarithaunnikrishnan mutualinformationbasedradiomicfeatureselectionwithshapexplainabilityforbreastcancerdiagnosis |