Deep Learning With Optical Coherence Tomography for Melanoma Identification and Risk Prediction

• Published in: Journal of biophotonics 2025-01, Vol.18 (1), p.e202400277-n/a
• Main Authors: Lai, Pei‐Yu, Shih, Tai‐Yu, Chang, Yu‐Huan, Chang, Chung‐Hsing, Kuo, Wen‐Chuan
• Format: Article
• Language: English
• Subjects: Animal models; Artificial neural networks; convolutional neural network; Deep learning; Diagnosis; Machine learning; Medical imaging; Melanoma; mice model; Neural networks; Nevus; Optical Coherence Tomography; risk prediction; Skin cancer; Skin tests; Tomography
• ISSN: 1864-063X; 1864-0648; 1864-0648
• DOI: 10.1002/jbio.202400277

ABSTRACT Malignant melanoma is the most severe skin cancer with a rising incidence rate. Several noninvasive image techniques and computer‐aided diagnosis systems have been developed to help find melanoma in its early stages. However, most previous research utilized dermoscopic images to build a diagnosis model, and only a few used prospective datasets. This study develops and evaluates a convolutional neural network (CNN) for melanoma identification and risk prediction using optical coherence tomography (OCT) imaging of mice skin. Longitudinal tests are performed on four animal models: melanoma mice, dysplastic nevus mice, and their respective controls. The CNN classifies melanoma and healthy tissues with high sensitivity (0.99) and specificity (0.98) and also assigns a risk score to each image based on the probability of melanoma presence, which may facilitate early diagnosis and management of melanoma in clinical settings. This study uses the noninvasive optical coherence tomography (OCT) technique to add a novel and practical approach to melanoma diagnosis. In addition, the convolutional neural network (CNN) model can provide a risk score for each OCT image, indicating the probability of melanoma presence.