Share Email Print
cover

Proceedings Paper

ASNet: An adaptive scale network for skin lesion segmentation in dermoscopy images
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Dermoscopy is a non-invasive dermatology imaging and widely used in dermatology clinic. In order to screen and detect melanoma automatically, skin lesion segmentation in dermoscopy images is of great significance. In this paper, we propose an adaptive scale network (ASNet) for skin lesion segmentation in dermoscopy images. A ResNet34 with pretrained weights is applied as the encoder to extract more representative features. A novel adaptive scale module is designed and inserted into the top of the encoder path to dynamically fuse multi-scale information, which can self-learn based on spatial attention mechanism. Our proposed method is 5-fold cross-validated on a public dataset from Challenge Lesion Boundary Segmentation in ISIC-2018, which includes 2594 images from different types of skin lesion with different resolutions. The Jaccard coefficient, Dice coefficient and Accuracy are 82.15±0.328%, 88.880.390% and 96.00±0.228%, respectively. Experimental results show the effectiveness of the proposed ASNet.

Paper Details

Date Published: 28 February 2020
PDF: 6 pages
Proc. SPIE 11317, Medical Imaging 2020: Biomedical Applications in Molecular, Structural, and Functional Imaging, 113170W (28 February 2020); doi: 10.1117/12.2549178
Show Author Affiliations
Liangjiu Zhu, Soochow Univ. (China)
Shuanglang Feng, Soochow Univ. (China)
Weifang Zhu, Soochow Univ. (China)
Minjiang Univ. (China)
Xinjian Chen, Soochow Univ. (China)


Published in SPIE Proceedings Vol. 11317:
Medical Imaging 2020: Biomedical Applications in Molecular, Structural, and Functional Imaging
Andrzej Krol; Barjor S. Gimi, Editor(s)

© SPIE. Terms of Use
Back to Top
PREMIUM CONTENT
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?
close_icon_gray