loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock
Multi-class Semantic Segmentation of Skin Lesions via Fully Convolutional Networks

Topics: Impact of AI on Healthcare; Improving the interpretability of computational algorithms used in the biomedical and healthcare setting; Increasing the translation and trust of computational algorithms and tools for predicting patient/disease outcomes and supporting clinical decision making

Authors: Manu Goyal 1 ; Moi Hoon Yap 2 and Saeed Hassanpour 3

Affiliations: 1 Department of Biomedical Data Science, Dartmouth College, Hanover, NH, U.S.A. ; 2 Visual Computing Lab, Manchester Metropolitan University, Manchester, U.K. ; 3 Departments of Biomedical Data Science, Computer Science and Epidemiology, Dartmouth College, Hanover, NH, U.S.A.

Keyword(s): Skin Cancer, Fully Convolutional Networks, Multi-class Segmentation, Lesion Diagnosis.

Abstract: Melanoma is clinically difficult to distinguish from common benign skin lesions, particularly melanocytic naevus and seborrhoeic keratosis. The dermoscopic appearance of these lesions has huge intra-class variations and high inter-class visual similarities. Most current research is focusing on single-class segmentation irrespective of classes of skin lesions. In this work, we evaluate the performance of deep learning on multi-class segmentation of ISIC-2017 challenge dataset, which consists of 2,750 dermoscopic images. We propose an end-to-end solution using fully convolutional networks (FCNs) for multi-class semantic segmentation to automatically segment the melanoma, seborrhoeic keratosis and naevus. To improve the performance of FCNs, transfer learning and a hybrid loss function are used. We evaluate the performance of the deep learning segmentation methods for multi-class segmentation and lesion diagnosis (with post-processing method) on the testing set of the ISIC-2017 challenge dataset. The results showed that the two-tier level transfer learning FCN-8s achieved the overall best result with Dice score of 78.5% in a naevus category, 65.3% in melanoma, and 55.7% in seborrhoeic keratosis in multi-class segmentation and Accuracy of 84.62% for recognition of melanoma in lesion diagnosis. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 18.217.98.175

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Goyal, M.; Yap, M. and Hassanpour, S. (2020). Multi-class Semantic Segmentation of Skin Lesions via Fully Convolutional Networks. In Proceedings of the 13th International Joint Conference on Biomedical Engineering Systems and Technologies - C2C; ISBN 978-989-758-398-8; ISSN 2184-4305, SciTePress, pages 290-295. DOI: 10.5220/0009380302900295

@conference{c2c20,
author={Manu Goyal. and Moi Hoon Yap. and Saeed Hassanpour.},
title={Multi-class Semantic Segmentation of Skin Lesions via Fully Convolutional Networks},
booktitle={Proceedings of the 13th International Joint Conference on Biomedical Engineering Systems and Technologies - C2C},
year={2020},
pages={290-295},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0009380302900295},
isbn={978-989-758-398-8},
issn={2184-4305},
}

TY - CONF

JO - Proceedings of the 13th International Joint Conference on Biomedical Engineering Systems and Technologies - C2C
TI - Multi-class Semantic Segmentation of Skin Lesions via Fully Convolutional Networks
SN - 978-989-758-398-8
IS - 2184-4305
AU - Goyal, M.
AU - Yap, M.
AU - Hassanpour, S.
PY - 2020
SP - 290
EP - 295
DO - 10.5220/0009380302900295
PB - SciTePress