Detection of malignant melanoma in H&E-stained images using deep learning techniques. (December 2021)

• Record Type: Journal Article
• Authors: Alheejawi, Salah; Berendt, Richard; Jha, Naresh; Maity, Santi P.; Mandal, Mrinal
• Is Part Of: Tissue & cell. Volume 73(2021)
• Publication Date: 2021-12
• Subjects: Histopathological image analysis -- Nuclear segmentation -- Melanoma detection -- Deep learning; Cytology -- Periodicals; 571.5
• DOI: 10.1016/j.tice.2021.101659
• Languages: English
• ISSNs: 0040-8166

Abstract

Highlights: Novel technique for detecting malignant melanoma in whole slide skin image. The proposed technique is based on a deep learning network. The nuclei segmentation accuracy is over 94 %. The detected melanoma region has a Dice score of over 85 %. Abstract: Histopathological images are widely used to diagnose diseases including skin cancer. As digital histopathological images are typically of very large size, in the order of several billion pixels, automated identification of all abnormal cell nuclei and their distribution within multiple tissue sections would assist rapid comprehensive diagnostic assessment. In this paper, we propose a deep learning-based technique to segment the melanoma regions in Hematoxylin and Eosin (H&E) stained histopathological images. In this technique, the nuclei in the image are first segmented using a Convolutional Neural Network (CNN). The segmented nuclei are then used to generate melanoma region masks. Experimental results with a small melanoma dataset show that the proposed method can potentially segment the nuclei with more than 94 % accuracy and segment the melanoma regions with a Dice coefficient of around 85 %. The proposed technique also has a small execution time making it suitable for clinical diagnosis with a fast turnaround time.