Dermoscopic image segmentation via multistage fully convolutional networks

Bi, Lei, Kim, Jinman, Ahn, Euijoon, Kumar, Ashnil, Fulham, Michael, and Feng, Dagan (2017) Dermoscopic image segmentation via multistage fully convolutional networks. IEEE Transactions on Biomedical Engineering, 64 (9). pp. 2065-2074.

[img] PDF (Published Version) - Published Version
Restricted to Repository staff only

View at Publisher Website: https://doi.org/10.1109/TBME.2017.271277...
184


Abstract

Objective: Segmentation of skin lesions is an important step in the automated computer aided diagnosis of melanoma. However, existing segmentation methods have a tendency to over- or under-segment the lesions and perform poorly when the lesions have fuzzy boundaries, low contrast with the background, inhomogeneous textures, or contain artifacts. Furthermore, the performance of these methods are heavily reliant on the appropriate tuning of a large number of parameters as well as the use of effective preprocessing techniques, such as illumination correction and hair removal.

Methods: We propose to leverage fully convolutional networks (FCNs) to automatically segment the skin lesions. FCNs are a neural network architecture that achieves object detection by hierarchically combining low-level appearance information with high-level semantic information. We address the issue of FCN producing coarse segmentation boundaries for challenging skin lesions (e.g., those with fuzzy boundaries and/or low difference in the textures between the foreground and the background) through a multistage segmentation approach in which multiple FCNs learn complementary visual characteristics of different skin lesions; early stage FCNs learn coarse appearance and localization information while late-stage FCNs learn the subtle characteristics of the lesion boundaries. We also introduce a new parallel integration method to combine the complementary information derived from individual segmentation stages to achieve a final segmentation result that has accurate localization and well-defined lesion boundaries, even for the most challenging skin lesions.

Results: We achieved an average Dice coefficient of 91.18% on the ISBI 2016 Skin Lesion Challenge dataset and 90.66% on the PH2 dataset.

Conclusion and Significance: Our extensive experimental results on two well-established public benchmark datasets demonstrate that our method is more effective than other state-of-the-art methods for skin lesion segmentation.

Item ID: 72036
Item Type: Article (Research - C1)
ISSN: 1558-2531
Copyright Information: © 2017 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission
Date Deposited: 22 Feb 2022 02:36
FoR Codes: 46 INFORMATION AND COMPUTING SCIENCES > 4603 Computer vision and multimedia computation > 460306 Image processing @ 60%
46 INFORMATION AND COMPUTING SCIENCES > 4603 Computer vision and multimedia computation > 460308 Pattern recognition @ 40%
SEO Codes: 22 INFORMATION AND COMMUNICATION SERVICES > 2204 Information systems, technologies and services > 220403 Artificial intelligence @ 60%
22 INFORMATION AND COMMUNICATION SERVICES > 2204 Information systems, technologies and services > 220404 Computer systems @ 40%
More Statistics

Actions (Repository Staff Only)

Item Control Page Item Control Page