Deep Residual Network with Regularized Fisher Framework for Detection of Melanoma

Mandal, Bappaditya

Abstract

Of all the skin cancer that is prevalent, melanoma has the highest mortality rates. Melanoma becomes life threatening when it penetrates deep into the dermis layer unless detected at an early stage, it becomes fatal since it has a tendency to migrate to other parts of our body. This paper presents an automated non-invasive methodology to assist the clinicians and dermatologists for detection of melanoma. Unlike conventional computational methods which require (expensive) domain expertise for segmentation and hand crafted feature computation and/or selection, a deep convolutional neural network based regularized discriminant learning framework which extracts low dimensional discriminative features for melanoma detection is proposed. Our approach minimizes the whole of within-class variance information and maximizes the total class variance information. The importance of various subspaces arising in the within-class scatter matrix followed by dimensionality reduction using total class variance information are analyzed for melanoma detection. Experimental results on ISBI 2016, MED-NODE, PH2 and the recent ISBI 2017 databases show the efficacy of our proposed approach as compared to other state-of-the-art methodologies.

Citation

Mandal, B. (2018). Deep Residual Network with Regularized Fisher Framework for Detection of Melanoma. IET Computer Vision, 1096-1104. https://doi.org/10.1049/iet-cvi.2018.5238

• Acceptance Date: Jun 18, 2018
• Publication Date: Dec 1, 2018
• Journal: IET Computer Vision
• Print ISSN: 1751-9632
• Publisher: Institution of Engineering and Technology (IET)
• Pages: 1096-1104
• DOI: https://doi.org/10.1049/iet-cvi.2018.5238
• Keywords: image segmentation, cancer, learning (artificial intelligence), medical image processing, image classification, feature extraction, neural nets, skin, within-class variance information, total class variance information, melanoma detection, residual networ
• Publisher URL: http://dx.doi.org/10.1049/iet-cvi.2018.5238