An Efficient Machine Learning Model for Breast cancer categorization using Logistic Regression on Histopathological images
G. Sajiv, G. Ramkumar
Abstract
Most cases of breast cancer are found in women, and as early detection is key to effective treatment, it is important to identify the condition as soon as possible. Machine Learning models have recently been used in the field of biomedical and informatics to aid in the battle against breast cancer. The elimination of the internal subjective human elements in the detection process is a major benefit of automating the process; this may also lead to increased detection accuracy. Breast cancer tumors often worsen and progress over time, eventually leading to death. Although women are disproportionately affected, guys are not immune. Age and family history are two other risk factors for developing breast cancer. Tumors seen in the breast can either be benign or cancerous. In order to better categorize breast cancer, this study advocated using a machine learning model. Logistic regression (LR) was used, and the results of our model were compared to those of other existing ML models. This research will demonstrate the reliability of different models for this breast cancer classification, allowing for the most appropriate strategy to be used moving forward. This research aims to make predictions about how well existing algorithms for classifying breast cancer will perform in the future.