Breast Cancer Segmentation by K-Means and Classification by Machine Learning
Konapala Srilakshmi Anjana Priya, V. Senthilkumar, J. Samson Isaac, Sreekanth Kottu, V S Ramakrishna, M. Jogendra Kumar · 2022 International Conference on Automation, Computing and Renewable Systems (ICACRS) · 2022
Breast Cancer (BC) progression is currently a common health problem among modern women. It is the cause of death for a significant number of women. BC is the growth of malignant cells in the breast tissue. Adipose or connective tissue can also develop BC. Because of developments in medical technology, ultrasonography is one of many procedures utilised for the early identification of cancer. Ultrasound is a technique that uses high-frequency sound wave technology to create images of inside body structures such as organs and soft tissues. Because of the poor quality of the information, there is a lot of possibility for interpretational mistakes when diagnosing cancer based on ultrasound images. As a result of these concerns, this paper uses the idea of Machine Learning (ML) is employed for the classification and segmentation of BC. The K-means clustering approach is used as part of the segmentation procedure to detect where the cancer is present. A recent study has demonstrated that machine learning produces reliable findings, allowing specialists to make better decisions. Using standard BC datasets, the performance of three different Machine Learning algorithms—Logistic Regression (LR), Random Forest (RF), and K-Nearest Neighbors (KNN)—is tested in this work. In terms of accuracy, RF outperformed the other algorithms, according to the finding. Future BC researchers will be able to utilise the findings of this study to guide their investigations and influence their efforts to improve the efficiency of specific algorithms.