Deep Learning Framework for Melanoma Subtype Classification from mRNA Expression Profiles

Résumé fourni par la source

Melanoma is the most aggressive form of skin cancer, and its early and accurate diagnosis is crucial for patient treatment. Gene expression profiling has become a powerful tool to capture the molecular portraits of tumors, but it suffers from the difficulties of small sample size and high dimensionality. In this study, we propose a lightweight one-dimensional convolutional neural network (1D-CNN) for melanoma sample classification from mRNA expression data. The proposed framework involves mutual information for feature selection to reduce dimensionality, supported by preprocessing steps such as log transformation, low-variance gene removal, and filtering of weakly expressed genes to improve data quality before modeling. The proposed CNN is benchmarked against classical machine learning (ML) methods- K-nearest neighbors (KNN), Random Forest (RF), and AdaBoost-across multiple gene subsets (150, 300, and 450). Experimental results indicate that when 300 genes are selected, the proposed CNN demonstrates a consistent improvement with an F 1 -score of 97% and a peak accuracy of 96%, while providing robustness across different feature sizes. Compared with classical models, the proposed CNN delivers a more stable trade-off between precision and recall. The results show that streamlined deep learning (DL) models enable accurate and efficient melanoma subtype classification, which highlights potential for clinical application.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.