Fusion of genomic and pathological data for breast cancer detection using BCDNN.
[BACKGROUND OF STUDY] Breast cancer is one of the leading causes of mortality among women worldwide.
APA
Bilal A, Obidallah WJ, et al. (2026). Fusion of genomic and pathological data for breast cancer detection using BCDNN.. Frontiers in medicine, 13, 1726223. https://doi.org/10.3389/fmed.2026.1726223
MLA
Bilal A, et al.. "Fusion of genomic and pathological data for breast cancer detection using BCDNN.." Frontiers in medicine, vol. 13, 2026, pp. 1726223.
PMID
41788706
Abstract
[BACKGROUND OF STUDY] Breast cancer is one of the leading causes of mortality among women worldwide. Early and accurate detection is crucial for improving treatment outcomes and survival rates. Recent advancements in Deep Learning (DL), Artificial and Intelligence (AI), have shown promising results in medical image analysis and cancer prediction.
[PURPOSE] This study aims to develop and evaluate a BCDNN model that classifies tumors as benign or malignant using genomic and histopathological data. The research focuses on improving diagnostic accuracy through AI-driven methods.
[METHOD] The proposed BCDNN model was implemented in MATLAB R2016. A publicly available breast cancer dataset from Kaggle was used, encompassing both genomic and pathological features. The dataset was pre-processed and feature selected before training the BCDNN with optimized hyperparameters.
[RESULT] The proposed model achieved a mean classification accuracy of 93.84% during cross-validation, demonstrating stable, reliable performance in distinctive between benign and malignant cases.
[CONCLUSION] The BCDNN model shows significant promise in supporting clinical decision-making for breast cancer diagnosis. Future work may enhance model generalizability and explore integration with real-time diagnostic systems, contributing to better health outcomes for women globally. The code for this study is available on GitHub.
[PURPOSE] This study aims to develop and evaluate a BCDNN model that classifies tumors as benign or malignant using genomic and histopathological data. The research focuses on improving diagnostic accuracy through AI-driven methods.
[METHOD] The proposed BCDNN model was implemented in MATLAB R2016. A publicly available breast cancer dataset from Kaggle was used, encompassing both genomic and pathological features. The dataset was pre-processed and feature selected before training the BCDNN with optimized hyperparameters.
[RESULT] The proposed model achieved a mean classification accuracy of 93.84% during cross-validation, demonstrating stable, reliable performance in distinctive between benign and malignant cases.
[CONCLUSION] The BCDNN model shows significant promise in supporting clinical decision-making for breast cancer diagnosis. Future work may enhance model generalizability and explore integration with real-time diagnostic systems, contributing to better health outcomes for women globally. The code for this study is available on GitHub.