Ovarian Cancer Segmentation and Classification Using Machine Learning

Cervical cancer affects a sizable portion of the female population worldwide across all age categories. As a result, many researchers, pathologists, and academics have offered numerous strategies for detecting this malignancy using Pap smear screening test photos. Large-scale cell proliferation is what is known as cancer. There are various types of cancer. One of the most prevalent diseases among women, cervical cancer, is the subject of this study. Cervical cancer is most frequently diagnosed in women, where it is the second-most prevalent malignancy after breast cancer. The study’s goal is to decrease errors by automatically identifying size, shape, and the texture of the tumour. Segmentation, clustering, feature extraction, and classification techniques serve as the foundation for the proposed study. The test findings display the differentiation between malignant and healthy cells as well as the stages of cancer. The algorithms used in this research are random forest and support vector machines. As a result, the results increase diagnostic accuracy while minimising the workload and human error.