Year: 2024
Type: conference-paper
Abstract: Melanoma is one of the deadliest skin cancer. It can, however, be cured with a high success rate if found in the early stage. With the recent development in Artificial Intelligence (AI), there has been an increase in the research of Machine Learning (ML) and Deep Learning (DL) models for melanoma detection. However, such deployments are primarily trial-based and still waiting to gain wider acceptance from the practitioners. One of the primary reasons for such lower acceptance lies in the inherent approach and ethical concerns. To this end, our study designs a Deep Learning based recommendation application for the patients to advise whether they need to see a dermatologist based on provided skin lesion image. The traditional AI-based melanoma classifiers tend to be developed based on bulk image training and hence would classify images on an individual level. However, they neglect that a single skin lesion is merely a part of the patient. Thereby this research considers the contextual information between different lesions on the same patient. It produces a personalized patient classification rather than focusing on lesion level prediction. Several models are developed using ML and DL techniques, such as transfer learning and deep neural networks. These models are then tested on a real melanoma dataset with the true label provided. External benchmark is also established from recent similar studies using the same dataset. The best classifier achieves an 81.6% Area Under the Receiver Operating Characteristic Curve (AUROC) score using the patient's unique biological features.
Authors: Hanlin Dong, Farnaz Farid
Institution: Western Sydney University
Language: English
Subfield: Oncology
Field: Medicine
Domain: Health Sciences
Open Access status: green
OpenAlex ID: W4408861608