Paper Info
Title
Skin Lesion Segmentation Via Dense Connected Deconvolutional Network
Abstract
Dermoscopy imaging analysis is a routine procedure for diagnosis and treatment of skin lesions. Segmentation is the very first step to demarcate skin lesions for further quantitative analysis. However, it is a challenging task due to various changes from different viewpoints and scales of skin lesions. To handle these challenges, we devise a new dense deconvolutional network (DDN) for skin lesion segmentation based on encoding module and decoding module. Our devised network consists of convolution unit, dense deconvolutional layer (DDL) and chained residual pooling block. DDL is adopted to restore the high resolution of the original input by upsampling, while the chained residual pooling is utilized to fuse multi-level features. Also, the hierarchical supervision is added to capture low level detailed boundary information. The DDN is trained in an end-to-end manner and free of prior knowledge and complicated post-processing procedures. With fusing the local and global contextual information, the high-resolution prediction output is obtained. The validation on the public ISBI 2016 and 2017 skin lesion challenge dataset demonstrates the effectiveness of our proposed method.
Year
DOI
Venue
2018
10.1109/ICPR.2018.8545136
2018 24TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR)
Keywords
Field
DocType
Skin lesion segmentation, Dermoscopy image, Dense deconvolutional layer, Chained residual pooling
Residual,Computer vision,Pattern recognition,Convolution,Segmentation,Computer science,Pooling,Artificial intelligence,Image restoration,Decoding methods,Upsampling,Encoding (memory)
Conference
ISSN
Citations 
PageRank 
1051-4651
1
0.35
References 
Authors
0
8
Name
Order
Citations
PageRank
Hang Li13821.94
Xinzi He210.35
Zhen Yu3374.31
Feng Zhou411013.95
Jie-Zhi Cheng510213.00
Limin Huang611.02
Tianfu Wang738255.46
Bai Ying Lei811924.99