A Dermoscopic Skin Lesion Classification Technique Using YOLO-CNN and Traditional Feature Model

• Published in: Arabian journal for science and engineering (2011) Vol. 46; no. 10; pp. 9797 - 9808
• Main Authors: Nersisson, Ruban, Iyer, Tharun J., Joseph Raj, Alex Noel, Rajangam, Vijayarajan
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.10.2021; Springer Nature B.V
• Subjects: Artificial neural networks; Cancer; Classification; Engineering; Feature extraction; Humanities and Social Sciences; Lesions; multidisciplinary; Research Article-Electrical Engineering; Science; Skin cancer; YOLO; Feature fusion; Dermoscopic skin lesions; Transfer learning; Convolutional neural network
• ISSN: 2193-567X; 1319-8025; 2191-4281
• DOI: 10.1007/s13369-021-05571-1

Skin cancer is one of the most deadly diseases around the world, wherein one of the three cancers is skin cancer. Early detection of skin cancer is paramount for better treatment planning. This paper investigates a Convolutional Neural Network (CNN), specifically, You Only Look Once (YOLO), to extract features from the skin lesions. The features, obtained from the CNN, are concatenated with traditional features like texture and colour features extracted from the lesion region of the input images. Later, the concatenated features are fed to a Fully Connected Network, which is trained with the specific ground truths to achieve higher classification accuracy. The proposed method improves the detection and classification of skin lesions when compared with other models and YOLO without traditional features. The performance measures of the fusion network are able to achieve the accuracy of 94%, precision of 0.85, recall of 0.88, and area under the curve of 0.95.