Multiple skin lesions diagnostics via integrated deep convolutional networks for segmentation and classification

• Published in: Computer methods and programs in biomedicine Vol. 190; p. 105351
• Main Authors: Al-masni, Mohammed A., Kim, Dong-Hyun, Kim, Tae-Seong
• Format: Journal Article
• Language: English
• Published: Ireland Elsevier B.V 01.07.2020
• Subjects: CAD; Classification; CNN; Deep learning; Dermoscopy; Diagnosis, Computer-Assisted - methods; Humans; Image Interpretation, Computer-Assisted - methods; ISIC; Machine Learning; Melanoma; Neural Networks, Computer; Segmentation; Skin lesion; Skin Neoplasms - classification; Skin Neoplasms - diagnosis; Deep learning; CNN; Skin lesion; Segmentation; ISIC; CAD; Classification; Melanoma
• ISSN: 0169-2607; 1872-7565; 1872-7565
• DOI: 10.1016/j.cmpb.2020.105351

•An integrated two-stage diagnostic model for skin lesion boundary segmentation and multiple skin diseases classification is proposed.•Segmentation of skin lesion boundaries was performed using a full resolution convolutional network (FrCN) segmentator.•Four well-established classifiers are evaluated: Inception-v3, ResNet-50, Inception-ResNet-v2, and DenseNet-201, to distinguish between different skin diseases.•The proposed work was trained and evaluated using three different datasets: two classes of ISIC 2016; three classes of ISIC 2017; and seven classes of ISIC 2018.•Proper rebalancing, segmentation, and augmentation of the datasets are investigated. Computer automated diagnosis of various skin lesions through medical dermoscopy images remains a challenging task. In this work, we propose an integrated diagnostic framework that combines a skin lesion boundary segmentation stage and a multiple skin lesions classification stage. Firstly, we segment the skin lesion boundaries from the entire dermoscopy images using deep learning full resolution convolutional network (FrCN). Then, a convolutional neural network classifier (i.e., Inception-v3, ResNet-50, Inception-ResNet-v2, and DenseNet-201) is applied on the segmented skin lesions for classification. The former stage is a critical prerequisite step for skin lesion diagnosis since it extracts prominent features of various types of skin lesions. A promising classifier is selected by testing well-established classification convolutional neural networks. The proposed integrated deep learning model has been evaluated using three independent datasets (i.e., International Skin Imaging Collaboration (ISIC) 2016, 2017, and 2018, which contain two, three, and seven types of skin lesions, respectively) with proper balancing, segmentation, and augmentation. In the integrated diagnostic system, segmented lesions improve the classification performance of Inception-ResNet-v2 by 2.72% and 4.71% in terms of the F1-score for benign and malignant cases of the ISIC 2016 test dataset, respectively. The classifiers of Inception-v3, ResNet-50, Inception-ResNet-v2, and DenseNet-201 exhibit their capability with overall weighted prediction accuracies of 77.04%, 79.95%, 81.79%, and 81.27% for two classes of ISIC 2016, 81.29%, 81.57%, 81.34%, and 73.44% for three classes of ISIC 2017, and 88.05%, 89.28%, 87.74%, and 88.70% for seven classes of ISIC 2018, respectively, demonstrating the superior performance of ResNet-50. The proposed integrated diagnostic networks could be used to support and aid dermatologists for further improvement in skin cancer diagnosis. [Display omitted]