Deep learning based classification of facial dermatological disorders. (January 2021)

• Record Type: Journal Article
• Authors: Goceri, Evgin
• Is Part Of: Computers in biology and medicine. Volume 128(2021)
• Publication Date: 2021-01
• Subjects: Automated diagnosis -- Active contours -- Lesion segmentation -- Loss function -- DenseNet201 -- Skin disease; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2020.104118
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Common properties of dermatological diseases are mostly lesions with abnormal pattern and skin color (usually redness). Therefore, dermatology is one of the most appropriate areas in medicine for automated diagnosis from images using pattern recognition techniques to provide accurate, objective, early diagnosis and interventions. Also, automated techniques provide diagnosis without depending on location and time. In addition, the number of patients in dermatology departments and costs of dermatologist visits can be reduced. Therefore, in this work, an automated method is proposed to classify dermatological diseases from color digital photographs. Efficiency of the proposed approach is provided by 2 stages. In the 1st stage, lesions are detected and extracted by using a variational level set technique after noise reduction and intensity normalization steps. In the 2nd stage, lesions are classified using a pre-trained DenseNet201 architecture with an efficient loss function. In this study, five common facial dermatological diseases are handled since they also cause anxiety, depression and even suicide death. The main contributions provided by this work can be identified as follows: (i) A comprehensive survey about the state-of-the-art works on classifications of dermatological diseases using deep learning; (ii) A new fully automated lesion detection and segmentation based on level sets; (iii) A new adaptive, hybrid and non-symmetric loss function; (iv) Using a pre-trained DenseNet201 structure with the new loss function to classify skin lesions; (v) Comparative evaluations of ten convolutional networks for skin lesion classification. Experimental results indicate that the proposed approach can classify lesions with high performance (95.24% accuracy). Highlights: A new fully automated segmentation was proposed to detect and extract skin lesions. A new adaptive, hybrid and non-symmetric loss function was proposed. A pre-trained DenseNet201 model was used for lesion classification from photographs. Comparative performance analysis was performed for 10 CNN-based networks. High classification accuracy (95.24%) was obtained with the proposed DenseNet201.