A Comparative Study of Various Machine Learning Methods on Ovarian Tumor

• Published in: 2021 Sixth International Conference on Image Information Processing (ICIIP) Vol. 6; pp. 314 - 319
• Main Authors: Sundari, M. Jeya, Brintha, N. C.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 26.11.2021
• Subjects: Convolution Neural Networks (CNN); Feature extraction; Internet of Medical Things; Liver diseases; Machine Learning Methods (MLTs); ovarian tumour; Prognostics and health management; Reliability; Support Vector Machine (SVM); Support vector machines; Ultrasonic imaging
• ISSN: 2640-074X
• DOI: 10.1109/ICIIP53038.2021.9702697

Ovarian tumor is a kind of cancer which is commonly encountered in females. It is critical to accurately anticipate the development of Benign Ovarian Tumors (BOT) cancers. This research focuses on Machine Learning Methods (MLTs), which are utilized to battle important common diseases such as malignancies, hepatitis, and heart disease among others. Artificial Neural Networks, K-Nearest Neighbors, Decision Trees, image processing methods and Associative Classification are some of the topics discussed in this study. As part of a comparative research, this work looks at the current management of illness, which includes the use of MLT on ovarian tumors. Deep learning, networking, clustering, feature extraction and transformation, as well as feature facilitation approaches, are used to analyze all of the survey data collected. On the basis of this study, we provide an overview and a comparative analysis of the key categories of tumor detection while emphasizing the relationships between them.