Breast cancer is the second leading cause of death among women worldwide. Breast cancer diagnosis helps to provide better breast cancer treatment and raise the survival rate of breast cancer patients. Due to technological development, breast cancers are diagnosed using computer-aided systems and data learning technologies, as manual diagnosis is inaccurate, error-prone, and time-consuming.
  Machine learning methods have recently been applied to distinguish breast cancer from normal and abnormal for accurate breast cancer detection. Deep learning technology is an emerging technique for breast cancer diagnosis. Medical image analysis facilitates a significant role in the diagnosis and prognosis of breast cancer.
  In the healthcare domain, various imaging techniques have been established for cancer diagnosis. More specifically, some of the imaging modalities utilized for breast cancer diagnosis are histopathology images, breast X-ray images, Digital Mammographic Images (DMG), Ultrasound Sonograms (ULS), infrared thermal imaging, Magnetic Resonance Imaging (MRI), and Computerized Thermography (CT), digital breast tomosynthesis, and mass-spectrometry imaging.
  Recent studies show that various machine learning algorithms, namely, Logistic Regression, K-Nearest Neighbor (KNN), Support Vector Machine, Naïve Bayes, Decision Tree, and Random Forest, are utilized for breast cancer detection and classification.
  In addition, extreme learning machines, ensemble approaches, artificial neural networks, fuzzy classifiers, boosting algorithms, and various deep learning classifiers are also exploited for breast cancer detection, prediction, and prognosis. Some major challenges in machine learning and deep learning models for breast cancer detection, prediction, and classification are inadequate comprehensive training data, utilization of data expansion techniques, insufficiency of flexibility, and robustness issues.
  A few interesting future research scopes of breast cancer diagnosis using machine learning and deep learning techniques are unsupervised models, reinforcement methods, generalizability, imbalanced dataset, combining non-imaging and imaging data, and utilization of diverse modalities.
  Several literature reviews and surveys have been published on breast cancer analysis using machine learning, describing various machine learning and deep learning approaches, remarkable challenges, future research works, open problems, and research gaps. Such literature reviews and surveys are listed below;