Abstract

Breast cancer is a major concern in the world today, and early and accurate diagnosis is most crucial
in the case of breast cancer, as it is among the disorders where the total cost of loss of life is high.
Traditional screening processes are subjective and vulnerable to inter-observer reliability issues and
diagnostic errors, being primarily based on manual interpretation of medical images. To address these limitations, Deep Learning (DL) is now a leading approach for medical image analysis. However, training deep Convolutional Neural Networks (CNNs) from scratch remains a significant drawback due to the small sizes of labeled medical datasets. This paper gives an in-depth comparison of five state-of- the-art Transfer Learning (TL) models, which comprise VGG16, VGG19, ResNet50, DenseNet121, and MobileNet models, and apply them to undertake automated classification of breast cancer. Optimization of models was performed on the publicly available dataset, and more demanding data augmentation procedures were employed to lower overfitting levels and enhance generalization characteristics. Several measures of accuracy, precision, recall, F1-score, and computational complexity were used to measure performance. According to experimental results, DenseNet121 achieved a higher overall testing accuracy of 98.85% and an F1-score of 98.40, owing to effective feature propagation. MobileNet, on its part, showed outstanding computational powers and an accuracy of 94.50%, which means that it is feasible in resource-constrained mobile health activities. This paper proves that transfer learning is the most effective method to maximize the diagnosis accuracy and reduce the computation costs incurred to generate a highly formidable Computer-Aided Diagnosis (CAD) structure to directly
help radiologists make important clinical decisions.

Keyword: Breast cancer detection, computer-aided diagnosis (CAD), deep learning, denseNet121, medical image analysis, ResNet50, transfer learning

Full Text PDF

Refrences:

1. Sung H, Ferlay J, Siegel RL, Laversanne M, Soerjomataram I, Jemal A, et al. Global cancer
statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185
countries. CA Cancer J Clin. 2021;71(3):209–249.
2. DeSantis C, Siegel R, Jemal A. Breast cancer facts and figures 2013–2014. Atlanta (GA): American
Cancer Society; 2013. p.1–38.
3. Spanhol FA, Oliveira LS, Petitjean C, Heutte L. A dataset for breast cancer histopathological image
classification. IEEE Trans Biomed Eng. 2016;63(7):1455–1462.
4. Litjens G, Kooi T, Bejnordi BE, Setio AAA, Ciompi F, Ghafoorian M, et al. A survey on deep
learning in medical image analysis. Med Image Anal. 2017;42:60–88.
5. LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015;521(7553):436–444; doi:
10.1038/nature14539. PMID: 26017442.
6. Tajbakhsh N, Shin JY, Gurudu SR, Hurst RT, Kendall CB, Gotway MB, et al. Convolutional neural
networks for medical image analysis: Full training or fine tuning? IEEE Trans Med Imaging.
2016;35(5):1299–1312.
7. Pan SJ, Yang Q. A survey on transfer learning. IEEE Trans Knowl Data Eng. 2010;22(10):1345–1359.
8. Shin HC, Roth HR, Gao M, Lu L, Xu Z, Nogues I, et al. Deep convolutional neural networks for
computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE
Trans Med Imaging. 2016;35(5):1285–1298.
9. Alheejawi S, Mandal M, Xu H, Lu C, Berendt R, Jha N. Deep learning-based histopathological
image analysis for automated detection and staging of melanoma. In: Deep Learning Techniques
for Biomedical and Health Informatics. Cambridge (MA): Academic Press; 2020. p.237–265.
10. Al-Haija QA, Manasra GF. Development of breast cancer detection model using transfer learning
of residual neural network (ResNet-50). Am J Sci Eng. 2020;1(3):30–39.
11. Wakili MA, Shehu HA, Sharif MH, Sharif MHU, Umar A, Kusetogullari H, et al. Classification of
breast cancer histopathological images using DenseNet and transfer learning. Comput Intell
Neurosci. 2022;2022:8904768.
12. Ahmadi M, Karimi N, Samavi S. A lightweight deep learning pipeline with DRDA-Net and
MobileNet for breast cancer classification. arXiv [Preprint]. 2024; arXiv:2403.11135.
13. Alzubaidi L, Zhang J, Humaidi AJ, Al-Dujaili A, Duan Y, Al-Shamma O, et al. Review of deep
learning: Concepts, CNN architectures, challenges, applications, future directions. J Big Data.
2021;8(1):53.