State-Of-The-Art Techniques for Classification of Breast Cancer Using Machine Learning and Deep Learning Methods: A Review
Keywords:
Artificial Intelligence (AI), Breast Cancer, Classification, Deep Learning (DL), Machine Learning (ML), MammogramABSTRACT
Breast cancer is among the most challenging illnesses for medical workers to diagnose. Breast cancer is none other than the formation of cancer cells in the area of breasts, and it can occur mostly in women rather than in men. So, diagnosing this disease at the earliest stage possible is the main aim of healthcare workers. Machine Learning (ML) and Deep Learning (DL) methodologies made significant advancements in Computer Vision and adapted to the healthcare domain. When DL methodologies adapted for diagnosing breast cancer, two main challenges affect the performance. One is with the non-availability of the large dataset for training the models; other is with the datasets having an imbalanced distribution of the classes. As a result, this study provides a review of several DL and ML-based classifiers presented by various academics over the last decade to tackle these problems, while also emphasizing the significance of the classification process of breast mammographic images. The key accomplishments expressed in the diagnostic measures and their success indicators of qualitative and quantitative measurements are reviewed.
REFERENCES
American Cancer Society. How Common Is Breast Cancer? https://www.cancer.org/cancer/breast-cancer/about/howcommon-is-breast-cancer.html (2018).
Oeffinger, K. C. et al. Breast Cancer Screening for Women at Average Risk: 2015 Guideline Update From the American Cancer Society. JAMA 314, 1599–1614 (2015).
Lehman, C. D. et al. National Performance Benchmarks for Modern Screening Digital Mammography: Update from the Breast Cancer Surveillance Consortium. Radiol. 283, 49–58 (2016).