e-space
Manchester Metropolitan University's Research Repository

    Interpretability of a deep learning based approach for the classification of skin lesions into main anatomic body sites

    Jaworek-Korjakowska, Joanna, Brodzicki, Andrzej, Cassidy, Bill ORCID logoORCID: https://orcid.org/0000-0003-3741-8120, Kendrick, Connah and Yap, Moi Hoon ORCID logoORCID: https://orcid.org/0000-0001-7681-4287 (2021) Interpretability of a deep learning based approach for the classification of skin lesions into main anatomic body sites. Cancers, 13 (23). 6048. ISSN 2072-6694

    [img]
    Preview
    Published Version
    Available under License Creative Commons Attribution.

    Download (8MB) | Preview

    Abstract

    Over the past few decades, different clinical diagnostic algorithms have been proposed to diagnose malignant melanoma in its early stages. Furthermore, the detection of skin moles driven by current deep learning based approaches yields impressive results in the classification of malignant melanoma. However, in all these approaches, the researchers do not take into account the origin of the skin lesion. It has been observed that the specific criteria for in situ and early invasive melanoma highly depend on the anatomic site of the body. To address this problem, we propose a deep learning architecture based framework to classify skin lesions into the three most important anatomic sites, including the face, trunk and extremities, and acral lesions. In this study, we take advantage of pretrained networks, including VGG19, ResNet50, Xception, DenseNet121, and EfficientNetB0, to calculate the features with an adjusted and densely connected classifier. Furthermore, we perform in depth analysis on database, architecture, and result regarding the effectiveness of the proposed framework. Experiments confirm the ability of the developed algorithms to classify skin lesions into the most important anatomical sites with 91.45% overall accuracy for the EfficientNetB0 architecture, which is a state-of-the-art result in this domain.

    Impact and Reach

    Statistics

    Activity Overview
    6 month trend
    83Downloads
    6 month trend
    20Hits

    Additional statistics for this dataset are available via IRStats2.

    Altmetric

    Repository staff only

    Edit record Edit record