Diagnosis of melanoma from dermoscopic images using a deep depthwise separable residual convolutional network. Issue 12 (14th August 2019)

• Record Type: Journal Article
• Authors: Sarkar, Rahul; Chatterjee, Chandra Churh; Hazra, Animesh
• Is Part Of: IET image processing. Volume 13:Issue 12(2019)
• Page Start: 2130
• Page End: 2142
• Publication Date: 2019-08-14
• Subjects: cancer -- diseases -- skin -- image enhancement -- image colour analysis -- medical image processing -- image classification -- discrete wavelet transforms -- gradient methods -- image filtering -- cellular biophysics -- image denoising -- convolutional neural nets; deep depthwise separable residual convolutional network -- skin cancers -- melanocyte cells -- deep depthwise separable residual convolutional algorithm -- binary melanoma classification -- dermoscopic skin lesion image dataset -- multiple channel image matrix -- multiple colour spaces -- noise removal -- nonlocal means filter -- gradient weighted class activation maps -- multiple skin lesion image datasets -- MED‐NODE datasets -- efficient disease diagnosis -- malignant cell growth -- area under receiver operating characteristic score -- contrast‐limited adaptive histogram equilisation -- discrete wavelet transform algorithm -- lesion detection -- lesion classification ability -- saliency maps -- melanoma diagnosis; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2018.6669
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : Melanoma is one of the four major types of skin cancers caused by malignant growth in the melanocyte cells. It is the rarest one, accounting to only 1% of all skin cancer cases. However, it is the deadliest among all the skin cancer types. Owing to its rarity, efficient diagnosis of the disease becomes rather difficult. Here, a deep depthwise separable residual convolutional algorithm is introduced to perform binary melanoma classification on a dermoscopic skin lesion image dataset. Prior to training the model with the dataset noise removal from the images using non‐local means filter is performed followed by enhancement using contrast‐limited adaptive histogram equilisation over discrete wavelet transform algorithm. Images are fed to the model as multi‐channel image matrices with channels chosen across multiple color spaces based on their ability to optimize the performance of the model. Proper lesion detection and classification ability of the model are tested by monitoring the gradient weighted class activation maps and saliency maps, respectively. Dynamic effectiveness of the model is shown through its performance in multiple skin lesion image datasets. The proposed model achieved an ACC of 99.50% on international skin imaging collaboration (ISIC), 96.77% on PH2, 94.44% on DermIS and 95.23% on MED‐NODE datasets.