Enhanced skin cancer diagnosis using optimized CNN architecture and checkpoints for automated dermatological lesion classification

• Published in: BMC medical imaging Vol. 24; no. 1; pp. 201 - 20
• Main Authors: Musthafa, M Mohamed, T R, Mahesh, V, Vinoth Kumar, Guluwadi, Suresh
• Format: Journal Article
• Language: English
• Published: England BioMed Central Ltd 02.08.2024; BioMed Central; BMC
• Subjects: Artificial intelligence; Artificial neural networks; Automation; Cancer; Classification; Convolutional neural networks (CNN); Data Augmentation; Datasets; Decision making; Deep Learning; Dermatology; Dermatoscopic images; Dermoscopy - methods; Diagnosis; Humans; Image enhancement; Image Interpretation, Computer-Assisted - methods; Image Preprocessing; Lesions; Machine learning; Mechanization; Medical imaging; Medical imaging equipment; Neural networks; Neural Networks, Computer; Skin; Skin cancer; Skin diseases; Skin lesion classification; Skin lesions; Skin Neoplasms - diagnostic imaging; Skin Neoplasms - pathology; Deep learning; Dermatoscopic images; Skin lesion classification; Convolutional neural networks (CNN); Data Augmentation; Image Preprocessing
• DOI: 10.1186/s12880-024-01356-8
• ISSN: 1471-2342

Skin cancer stands as one of the foremost challenges in oncology, with its early detection being crucial for successful treatment outcomes. Traditional diagnostic methods depend on dermatologist expertise, creating a need for more reliable, automated tools. This study explores deep learning, particularly Convolutional Neural Networks (CNNs), to enhance the accuracy and efficiency of skin cancer diagnosis. Leveraging the HAM10000 dataset, a comprehensive collection of dermatoscopic images encompassing a diverse range of skin lesions, this study introduces a sophisticated CNN model tailored for the nuanced task of skin lesion classification. The model's architecture is intricately designed with multiple convolutional, pooling, and dense layers, aimed at capturing the complex visual features of skin lesions. To address the challenge of class imbalance within the dataset, an innovative data augmentation strategy is employed, ensuring a balanced representation of each lesion category during training. Furthermore, this study introduces a CNN model with optimized layer configuration and data augmentation, significantly boosting diagnostic precision in skin cancer detection. The model's learning process is optimized using the Adam optimizer, with parameters fine-tuned over 50 epochs and a batch size of 128 to enhance the model's ability to discern subtle patterns in the image data. A Model Checkpoint callback ensures the preservation of the best model iteration for future use. The proposed model demonstrates an accuracy of 97.78% with a notable precision of 97.9%, recall of 97.9%, and an F2 score of 97.8%, underscoring its potential as a robust tool in the early detection and classification of skin cancer, thereby supporting clinical decision-making and contributing to improved patient outcomes in dermatology.