PriMera Scientific Engineering (ISSN: 2834-2550)

Research Article

Volume 7 Issue 6

From traditional ML to Advanced Neural Networks: A Multidimensional Analysis and Systematic Evaluation of Classification Models for Breast Cancer Detection

Manoa Fandresena*, Alexander Igorevich Gavrilov and Arofenitra Rarivonjy

November 26, 2025

DOI : 10.56831/PSEN-07-237

View PDF

Abstract

Breast cancer is among the most common cancers in women worldwide and has notable international implications. Although the number of survival have upgraded due to medical advances, it is still considered as one of the leading causes of death. Artificial intelligence (AI), especially deep learning, is playing a key role in medicine, particularly in oncology, where early detection helps lessening mortality rate by allowing quicker action and more effective treatment. A comprehensive comparative analysis of machine learning and deep learning approaches for breast cancer prediction using the Wisconsin Diagnostic Breast Cancer (WDBC) dataset is presented by this study. 29 traditional machine learning algorithms and neural network architectures, evaluating their performance through multiple metrics including accuracy, precision, recall, F1-score, and ROC curves, has been evaluated. Our study shows that traditional machine learning methods, especially Logistic Regression reaches a higher ranking performance with 98.2% accuracy, outperforming deep learning perspective. The study provides insights into feature correlations, dimensionality reduction techniques, and model interpretability for clinical decision support systems.

Keyword: Machine Learning; Deep Learning; Neural Networks; Artificial Intelligence; Breast Cancer; Wisconsin Dataset; Medical Diagnosis

References

  1. W. H. Organization. “Breast cancer diagnoses and deaths expected to surge worldwide”. (2025).
  2. W. H. Organization. “Africa: Nearly 135,000 women could die from breast cancer by 2040 (WHO)”. (2025).
  3. W. H. Organization. “Madagascar: Breast cancer”. (2025).
  4. W. H. Organization. “Russia: Breast cancer”. (2025).
  5. W. H. Organization. “Usa: Breast cancer”. (2025).
  6. LeMonde. “Faced with the steady increase in breast cancer, we call for more resources to be allocated to research in order to better target risk factors.”. (2024).
  7. TheAustralian. “Australia worst for breast                cancer”. (2025).
  8. Iranmakani S., et al. “A review of various modalities in breast imaging: technical aspects and clinical outcomes”. Egyptian Journal of Radiology and Nuclear Medicine 51.57 (2020).
  9. W Du., et al. “Conformable ultrasound breast patch for deep tissue scanning and imaging”. Science Advances 9 (2023).
  10. A Pawl-owska., et al. “Curated benchmark dataset for ultrasound based breast lesion analysis”. Scientific Data 11.148 (2024).
  11. V Papalouka., et al. “Mri-guided breast biopsy: a review of technique, indications, and radiological-pathological correlations”. Clinical Radiology 73.10 (2018): 908.e17-908.e25.
  12. I Sechopoulos. “A review of breast tomosynthesis. part i. the image acquisition process”. Medical Physics 40.1 (2013): 014301-12.
  13. AI Huppe, AK Mehta and RF Brem. “Molecular breast imaging: A comprehensive review”. Seminars in Ultrasound, CT and MRI 39.1 (2018): 60-69.
  14. RG Barr. “Future of breast elastography”. Ultrasonography 39.2 (2019): 93-105.
  15. J-L Gonzalez-Hernandez., et al. “Technology, application and potential of dynamic breast thermography for the detection of breast cancer”. International Journal of Heat and Mass Transfer 131 (2019): 558- 573.
  16. S Alimirzaie, M Bagherzadeh and MR Akbari. “Liquid biopsy in breast cancer: A comprehensive review”. Clinical Genetics 95.6 (2019): 643-660.
  17. A H., et al. “Using machine learning algorithms for breast cancer risk prediction and diagnosis”. Procedia Computer Science 83 (2016): 1064-1069.
  18. C V and P S. “Early prediction of heart diseases using data mining techniques.”. Caribbean Journal of Science and Technology 2 (2014): 208-217.
  19. A L G., et al. “Using three machine learning techniques for predicting breast cancer recurrence”. Journal of Health and Medical Informatics 2 (2013): 124.
  20. A N, H B Q and G M L. “A deep feature fusion methodology for breast cancer diagnosis demonstrated on three imaging modality datasets”. Medical Physics 44.10 (2017): 5162- 5171.
  21. D N, C G and B A P. “A deep learning approach for the analysis of masses in mammograms with minimal user intervention”. Medical Image Analysis 37 (2017): 114-128.
  22. O A H and B A A. “A comparative study of machine learning algorithms for abnormal web usage detection”. International Conference on Soft Computing and Data Mining  (2017): 566-576.