TIIS (한국인터넷정보학회)
Current Result Document :
| 한글제목(Korean Title) |
Skin Lesion Image Segmentation Based on Adversarial Networks |
| 영문제목(English Title) |
Skin Lesion Image Segmentation Based on Adversarial Networks |
| 저자(Author) |
Ning Wang
Yanjun Peng
Yuanhong Wang
Meiling Wang
|
| 원문수록처(Citation) |
VOL 12 NO. 06 PP. 2826 ~ 2840 (2018. 06) |
한글내용
(Korean Abstract) |
|
영문내용
(English Abstract) |
Traditional methods based active contours or region merging are powerless in processing images with blurring border or hair occlusion. In this paper, a structure based convolutional neural networks is proposed to solve segmentation of skin lesion image. The structure mainly consists of two networks which are segmentation net and discrimination net. The segmentation net is designed based U-net that used to generate the mask of lesion, while the discrimination net is designed with only convolutional layers that used to determine whether input image is from ground truth labels or generated images. Images were obtained from “Skin Lesion Analysis Toward Melanoma Detection” challenge which was hosted by ISBI 2016 conference. We achieved segmentation average accuracy of 0.97, dice coefficient of 0.94 and Jaccard index of 0.89 which outperform the other existed state-of-the-art segmentation networks, including winner of ISBI 2016 challenge for skin melanoma segmentation.
|
| 키워드(Keyword) |
Skin lesion
image segmentation
convolutional neural networks
adversarial network
|
| 파일첨부 |
PDF 다운로드
|
