Evaluating deep learning for enhanced breast cancer diagnosis: a comparative analysis of CNN architectures
| dc.contributor.advisor | Sinkala, Musalula | |
| dc.contributor.author | Frankle, Solyle | |
| dc.date.accessioned | 2025-11-21T06:49:43Z | |
| dc.date.available | 2025-11-21T06:49:43Z | |
| dc.date.issued | 2025 | |
| dc.date.updated | 2025-11-21T06:46:50Z | |
| dc.description.abstract | Artificial Intelligence (AI), particularly its machine learning (ML) subfield, has revolutionised various sectors, including healthcare. In breast cancer care, AI's ability to analyse vast datasets and extract complex patterns from medical images has the potential to transform diagnostics and treatment strategies. Breast cancer remains one of the most prevalent cancers affecting women globally, with early and accurate diagnosis being crucial for effective treatment. AI, through its advanced image analysis capabilities, significantly improves the accuracy and efficiency of breast cancer diagnosis, specifically in distinguishing between cancer subtypes. Here, we aim to explore the application of deep learning, particularly convolutional neural networks (CNNs), in breast cancer subtype classification using histology images. A custom CNN model, alongside well-established models like ResNet50 and EfficientNetB0, was developed and evaluated for its accuracy in predicting benign and malignant breast cancer subtypes. The results demonstrated that while the custom CNN achieved an accuracy of 65% for malignant and 67% for benign subtypes with ROC-AUC scores of 0.86 and 0.90, respectively, ResNet50 significantly outperformed both the custom model and EfficientNetB0. ResNet50 attained an accuracy of 77% in classifying malignant subtypes and 77% for benign subtypes, accompanied by ROC-AUC scores of 0.92 and 0.96, respectively. Additionally, ResNet50 exhibited higher precision (0.68 for malignant, 0.67 for benign), recall (0.65 for malignant, 0.67 for benign), and F1 scores (0.65 for malignant, 0.67 for benign) across most subtypes, underscoring its robust performance and reliability in clinical settings. In conclusion, AI, specifically through advanced CNN architectures, can greatly enhance breast cancer diagnosis by providing more accurate subtype classifications. Future work should focus on integrating these models into clinical workflows, enabling faster and more personalised treatment planning. Moreover, continued refinement of these models, including addressing the complexities of tumour heterogeneity and incorporating multimodal data, will be crucial for their widespread adoption in oncology. | |
| dc.identifier.apacitation | Frankle, S. (2025). <i>Evaluating deep learning for enhanced breast cancer diagnosis: a comparative analysis of CNN architectures</i>. (). University of Cape Town ,Faculty of Health Sciences ,Division of Chemical and Systems Biology. Retrieved from http://hdl.handle.net/11427/42289 | en_ZA |
| dc.identifier.chicagocitation | Frankle, Solyle. <i>"Evaluating deep learning for enhanced breast cancer diagnosis: a comparative analysis of CNN architectures."</i> ., University of Cape Town ,Faculty of Health Sciences ,Division of Chemical and Systems Biology, 2025. http://hdl.handle.net/11427/42289 | en_ZA |
| dc.identifier.citation | Frankle, S. 2025. Evaluating deep learning for enhanced breast cancer diagnosis: a comparative analysis of CNN architectures. . University of Cape Town ,Faculty of Health Sciences ,Division of Chemical and Systems Biology. http://hdl.handle.net/11427/42289 | en_ZA |
| dc.identifier.ris | TY - Thesis / Dissertation AU - Frankle, Solyle AB - Artificial Intelligence (AI), particularly its machine learning (ML) subfield, has revolutionised various sectors, including healthcare. In breast cancer care, AI's ability to analyse vast datasets and extract complex patterns from medical images has the potential to transform diagnostics and treatment strategies. Breast cancer remains one of the most prevalent cancers affecting women globally, with early and accurate diagnosis being crucial for effective treatment. AI, through its advanced image analysis capabilities, significantly improves the accuracy and efficiency of breast cancer diagnosis, specifically in distinguishing between cancer subtypes. Here, we aim to explore the application of deep learning, particularly convolutional neural networks (CNNs), in breast cancer subtype classification using histology images. A custom CNN model, alongside well-established models like ResNet50 and EfficientNetB0, was developed and evaluated for its accuracy in predicting benign and malignant breast cancer subtypes. The results demonstrated that while the custom CNN achieved an accuracy of 65% for malignant and 67% for benign subtypes with ROC-AUC scores of 0.86 and 0.90, respectively, ResNet50 significantly outperformed both the custom model and EfficientNetB0. ResNet50 attained an accuracy of 77% in classifying malignant subtypes and 77% for benign subtypes, accompanied by ROC-AUC scores of 0.92 and 0.96, respectively. Additionally, ResNet50 exhibited higher precision (0.68 for malignant, 0.67 for benign), recall (0.65 for malignant, 0.67 for benign), and F1 scores (0.65 for malignant, 0.67 for benign) across most subtypes, underscoring its robust performance and reliability in clinical settings. In conclusion, AI, specifically through advanced CNN architectures, can greatly enhance breast cancer diagnosis by providing more accurate subtype classifications. Future work should focus on integrating these models into clinical workflows, enabling faster and more personalised treatment planning. Moreover, continued refinement of these models, including addressing the complexities of tumour heterogeneity and incorporating multimodal data, will be crucial for their widespread adoption in oncology. DA - 2025 DB - OpenUCT DP - University of Cape Town KW - Breast Cancer KW - CNN KW - AI LK - https://open.uct.ac.za PB - University of Cape Town PY - 2025 T1 - Evaluating deep learning for enhanced breast cancer diagnosis: a comparative analysis of CNN architectures TI - Evaluating deep learning for enhanced breast cancer diagnosis: a comparative analysis of CNN architectures UR - http://hdl.handle.net/11427/42289 ER - | en_ZA |
| dc.identifier.uri | http://hdl.handle.net/11427/42289 | |
| dc.identifier.vancouvercitation | Frankle S. Evaluating deep learning for enhanced breast cancer diagnosis: a comparative analysis of CNN architectures. []. University of Cape Town ,Faculty of Health Sciences ,Division of Chemical and Systems Biology, 2025 [cited yyyy month dd]. Available from: http://hdl.handle.net/11427/42289 | en_ZA |
| dc.language.iso | en | |
| dc.language.rfc3066 | eng | |
| dc.publisher.department | Division of Chemical and Systems Biology | |
| dc.publisher.faculty | Faculty of Health Sciences | |
| dc.publisher.institution | University of Cape Town | |
| dc.subject | Breast Cancer | |
| dc.subject | CNN | |
| dc.subject | AI | |
| dc.title | Evaluating deep learning for enhanced breast cancer diagnosis: a comparative analysis of CNN architectures | |
| dc.type | Thesis / Dissertation | |
| dc.type.qualificationlevel | Masters | |
| dc.type.qualificationlevel | MSc |