Enhancing Breast Cancer Diagnosis with Deep Learning in Histopathology Images
Latikesh Dhomane, Swati V. Shinde · 2023
The form of cancer that is most common in women is Breast Cancer (BC), with more than 1 in 10 new cases diagnosed each year. BC is one of the primary and most prevalent factors in cancer-related deaths in women. By enabling the patient to get appropriate medication, early detection of BC can save the lives of cancer patients. Deep learning algorithms are presently the topic of promising research for their early detection. Today, to use a proposed algorithm in medical image analysis the model must be highly accurate. To categorize BC histopathological images, this study compares the performance of various deep learning algorithms from previous studies. The study identifies the most accurate binary classification models for the histopathology image databases of breast cancer. The authors also implement and assess the performance of EfficientNetV2 models, a cutting-edge deep learning architecture, in the categorization of breast cancer histopathological images for binary classifications in addition to contrasting various deep learning algorithms. Future possibilities in this area of research are also discussed.