SKIN LESION DIAGNOSIS THROUGH DEEP LEARNING AND HYBRID TEXTURE FEATURE AUGMENTATION

Skin cancer is a leading cause of cancer-related deaths globally, with melanoma being the most lethal subtype. Early detectionremains critical for improving patient outcomes. However, dermoscopic image analysis faces challenges due to inter-classsimilarity between malignant melanoma and benign nevi. This study proposes a robust framework for optimizing Gray-LevelCo-occurrence Matrix (GLCM) and Local Binary Pattern (LBP) parameters using the ISIC 2023 dataset. The frameworkintegrates handcrafted features with Convolutional Neural Networks (CNNs) to enhance classification accuracy. Keycontributions include: Automated parameter tuning for GLCM and LBP using grid search and cross-validation; A hybrid modelcombining EfficientNet-B3 with full handcrafted features; Comprehensive evaluation on the ISIC 2023 dataset (10,015 images).Results demonstrate that the hybrid model (Scenario 2) achieves 93.7% accuracy and 92.8% F1-score, outperforming thestandalone CNN model (Scenario 1) by 3.5%. The proposed framework reduces false positives by 15% compared todermatologist assessments, highlighting its potential for clinical decision support. Future work will explore advancedarchitectures like EfficientNet-B4 and integration of external factors such as lesion location.