Date of Award
Computer and Information Science
Machine learning and image processing techniques have been widely implemented in the field of medicine to help accurately diagnose a multitude of medical conditions. The automated diagnosis of skin melanoma is one such instance. However, a majority of the successful machine learning models that have been implemented in the past have used deep learning approaches where only raw image data has been utilized to train machine learning models, such as neural networks. While they have been quite effective at predicting the condition of these lesions, they lack key information about the images, such as clinical data, and features that medical professionals consistently rely on for diagnosis. This research project will explore methods to enhance machine learning models with three drastically different skin melanoma datasets, each with their own set of unique challenges. Various preprocessing techniques, machine learning models, and feature extraction methods will be compared to determine the most optimal approach for each dataset. In addition, time and space complexities of the approaches will also be analyzed in order to minimize resource consumption without causing major performance degradation to the models
Alasandagutti, Akhil Reddy, "Using Deep Learning to Automate the Diagnosis of Skin Melanoma" (2021). Honors Theses. 1928.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Artificial Intelligence and Robotics Commons, Data Science Commons, Skin and Connective Tissue Diseases Commons