@article{10.11648/j.ajai.20261001.11,
  author = {Kasim Chambulilo and Paul Wako and Davis Bassa and Asha Kisonga and Emmanuel Shija},
  title = {Hybrid CNN-Transformer Model for Early Detection and Diagnosis of Breast Cancer: A Multi-Regional Dataset Study with Implications for African Healthcare Settings},
  journal = {American Journal of Artificial Intelligence},
  volume = {10},
  number = {1},
  pages = {1-13},
  doi = {10.11648/j.ajai.20261001.11},
  url = {https://doi.org/10.11648/j.ajai.20261001.11},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajai.20261001.11},
  abstract = {Breast cancer remains the most common cancer among African women, contributing to high mortality largely due to late-stage diagnosis. More than 70% of cases in many African countries are detected at advanced stages, when treatment options are limited and survival rates are significantly reduced. Barriers such as limited access to screening, a shortage of radiologists, and socio-economic constraints further delay early detection. Artificial intelligence (AI)-based diagnostic tools offer an opportunity to strengthen screening systems and improve timely diagnosis; however, the lack of publicly available African mammography datasets remains a major challenge. This study introduces MAMMOAI, an AI-driven framework designed to enhance early breast cancer detection with potential applicability to African contexts. Due to the scarcity of large-scale annotated African mammography datasets a critical barrier identified in current literature we adopted a pragmatic approach combining a multi-task deep learning model integrating convolutional neural networks (CNN) with Transformer layers to perform simultaneous risk assessment, cancer detection, staging, risk factor analysis, and differential diagnosis using mammograms. The model was trained using the King AbdulAziz University Breast Cancer Mammogram Dataset (KAU-BCMD) from Saudi Arabia, supplemented with preliminary data collected from Kenyan healthcare facilities. This multi-regional approach was necessitated by insufficient African data volume for robust deep learning model training. The framework employs a multi-task learning approach that integrates a ResNet50–Transformer backbone for spatial feature extraction, feeding five specialized branches for risk assessment, cancer detection, staging, risk factor analysis, and differential diagnosis. All images underwent standardized preprocessing, including resizing to 224×224 pixels, normalization, contrast enhancement, and extensive data augmentation. Weighted categorical cross-entropy losses supported joint optimization across tasks. Model interpretability was ensured using Grad-CAM–based heatmaps and uncertainty estimation, and predictions were compiled into automated, clinician-friendly HTML reports. The model achieved overall accuracy of 98% on the majority class (BI-RADS 1), with macro-averaged F1-scores of 0.61-0.62 across all branches, reflecting challenges in detecting minority classes. Critically, the model failed to identify any BI-RADS 5 (highly malignant) cases, misclassifying all as BI-RADS 4. Grad-CAM visualizations provided interpretable insights, supporting clinical decision-making. While these results demonstrate technical feasibility and the potential of hybrid architectures, they also underscore critical limitations: severe class imbalance, inadequate minority class performance, and unproven generalizability to diverse African populations. Future work must prioritize collection of larger, balanced, multi-center African datasets and external validation across diverse Sub-Saharan African healthcare settings before clinical deployment can be considered.},
 year = {2025}
}

Copy | Download

TY  - JOUR
T1  - Hybrid CNN-Transformer Model for Early Detection and Diagnosis of Breast Cancer: A Multi-Regional Dataset Study with Implications for African Healthcare Settings
AU  - Kasim Chambulilo
AU  - Paul Wako
AU  - Davis Bassa
AU  - Asha Kisonga
AU  - Emmanuel Shija
Y1  - 2025/12/29
PY  - 2025
N1  - https://doi.org/10.11648/j.ajai.20261001.11
DO  - 10.11648/j.ajai.20261001.11
T2  - American Journal of Artificial Intelligence
JF  - American Journal of Artificial Intelligence
JO  - American Journal of Artificial Intelligence
SP  - 1
EP  - 13
PB  - Science Publishing Group
SN  - 2639-9733
UR  - https://doi.org/10.11648/j.ajai.20261001.11
AB  - Breast cancer remains the most common cancer among African women, contributing to high mortality largely due to late-stage diagnosis. More than 70% of cases in many African countries are detected at advanced stages, when treatment options are limited and survival rates are significantly reduced. Barriers such as limited access to screening, a shortage of radiologists, and socio-economic constraints further delay early detection. Artificial intelligence (AI)-based diagnostic tools offer an opportunity to strengthen screening systems and improve timely diagnosis; however, the lack of publicly available African mammography datasets remains a major challenge. This study introduces MAMMOAI, an AI-driven framework designed to enhance early breast cancer detection with potential applicability to African contexts. Due to the scarcity of large-scale annotated African mammography datasets a critical barrier identified in current literature we adopted a pragmatic approach combining a multi-task deep learning model integrating convolutional neural networks (CNN) with Transformer layers to perform simultaneous risk assessment, cancer detection, staging, risk factor analysis, and differential diagnosis using mammograms. The model was trained using the King AbdulAziz University Breast Cancer Mammogram Dataset (KAU-BCMD) from Saudi Arabia, supplemented with preliminary data collected from Kenyan healthcare facilities. This multi-regional approach was necessitated by insufficient African data volume for robust deep learning model training. The framework employs a multi-task learning approach that integrates a ResNet50–Transformer backbone for spatial feature extraction, feeding five specialized branches for risk assessment, cancer detection, staging, risk factor analysis, and differential diagnosis. All images underwent standardized preprocessing, including resizing to 224×224 pixels, normalization, contrast enhancement, and extensive data augmentation. Weighted categorical cross-entropy losses supported joint optimization across tasks. Model interpretability was ensured using Grad-CAM–based heatmaps and uncertainty estimation, and predictions were compiled into automated, clinician-friendly HTML reports. The model achieved overall accuracy of 98% on the majority class (BI-RADS 1), with macro-averaged F1-scores of 0.61-0.62 across all branches, reflecting challenges in detecting minority classes. Critically, the model failed to identify any BI-RADS 5 (highly malignant) cases, misclassifying all as BI-RADS 4. Grad-CAM visualizations provided interpretable insights, supporting clinical decision-making. While these results demonstrate technical feasibility and the potential of hybrid architectures, they also underscore critical limitations: severe class imbalance, inadequate minority class performance, and unproven generalizability to diverse African populations. Future work must prioritize collection of larger, balanced, multi-center African datasets and external validation across diverse Sub-Saharan African healthcare settings before clinical deployment can be considered.
VL  - 10
IS  - 1
ER  - 

Copy | Download