Attention-Guided Network with Densely Connected Convolution for Skin Lesion Segmentation
The automatic segmentation of skin lesions is considered to be a key step in the diagnosis and treatment of skin lesions, which is essential to improve the survival rate of patients. However, due to the low contrast, the texture and boundary are difficult to distinguish, which makes the accurate seg...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-05-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/21/10/3462 |
id |
doaj-e979a34046464b0d84969a9018d9a112 |
---|---|
record_format |
Article |
spelling |
doaj-e979a34046464b0d84969a9018d9a1122021-06-01T00:12:02ZengMDPI AGSensors1424-82202021-05-01213462346210.3390/s21103462Attention-Guided Network with Densely Connected Convolution for Skin Lesion SegmentationShengxin Tao0Yun Jiang1Simin Cao2Chao Wu3Zeqi Ma4College of Computer Science and Engineering, Northwest Normal University, Lanzhou 730070, ChinaCollege of Computer Science and Engineering, Northwest Normal University, Lanzhou 730070, ChinaCollege of Computer Science and Engineering, Northwest Normal University, Lanzhou 730070, ChinaCollege of Computer Science and Engineering, Northwest Normal University, Lanzhou 730070, ChinaCollege of Computer Science and Engineering, Northwest Normal University, Lanzhou 730070, ChinaThe automatic segmentation of skin lesions is considered to be a key step in the diagnosis and treatment of skin lesions, which is essential to improve the survival rate of patients. However, due to the low contrast, the texture and boundary are difficult to distinguish, which makes the accurate segmentation of skin lesions challenging. To cope with these challenges, this paper proposes an attention-guided network with densely connected convolution for skin lesion segmentation, called CSAG and DCCNet. In the last step of the encoding path, the model uses densely connected convolution to replace the ordinary convolutional layer. A novel attention-oriented filter module called Channel Spatial Fast Attention-guided Filter (CSFAG for short) was designed and embedded in the skip connection of the CSAG and DCCNet. On the ISIC-2017 data set, a large number of ablation experiments have verified the superiority and robustness of the CSFAG module and Densely Connected Convolution. The segmentation performance of CSAG and DCCNet is compared with other latest algorithms, and very competitive results have been achieved in all indicators. The robustness and cross-data set performance of our method was tested on another publicly available data set PH2, further verifying the effectiveness of the model.https://www.mdpi.com/1424-8220/21/10/3462deep convolutional neural networkskin lesion segmentationattention mechanismcomputer-aided diagnosis |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Shengxin Tao Yun Jiang Simin Cao Chao Wu Zeqi Ma |
spellingShingle |
Shengxin Tao Yun Jiang Simin Cao Chao Wu Zeqi Ma Attention-Guided Network with Densely Connected Convolution for Skin Lesion Segmentation Sensors deep convolutional neural network skin lesion segmentation attention mechanism computer-aided diagnosis |
author_facet |
Shengxin Tao Yun Jiang Simin Cao Chao Wu Zeqi Ma |
author_sort |
Shengxin Tao |
title |
Attention-Guided Network with Densely Connected Convolution for Skin Lesion Segmentation |
title_short |
Attention-Guided Network with Densely Connected Convolution for Skin Lesion Segmentation |
title_full |
Attention-Guided Network with Densely Connected Convolution for Skin Lesion Segmentation |
title_fullStr |
Attention-Guided Network with Densely Connected Convolution for Skin Lesion Segmentation |
title_full_unstemmed |
Attention-Guided Network with Densely Connected Convolution for Skin Lesion Segmentation |
title_sort |
attention-guided network with densely connected convolution for skin lesion segmentation |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2021-05-01 |
description |
The automatic segmentation of skin lesions is considered to be a key step in the diagnosis and treatment of skin lesions, which is essential to improve the survival rate of patients. However, due to the low contrast, the texture and boundary are difficult to distinguish, which makes the accurate segmentation of skin lesions challenging. To cope with these challenges, this paper proposes an attention-guided network with densely connected convolution for skin lesion segmentation, called CSAG and DCCNet. In the last step of the encoding path, the model uses densely connected convolution to replace the ordinary convolutional layer. A novel attention-oriented filter module called Channel Spatial Fast Attention-guided Filter (CSFAG for short) was designed and embedded in the skip connection of the CSAG and DCCNet. On the ISIC-2017 data set, a large number of ablation experiments have verified the superiority and robustness of the CSFAG module and Densely Connected Convolution. The segmentation performance of CSAG and DCCNet is compared with other latest algorithms, and very competitive results have been achieved in all indicators. The robustness and cross-data set performance of our method was tested on another publicly available data set PH2, further verifying the effectiveness of the model. |
topic |
deep convolutional neural network skin lesion segmentation attention mechanism computer-aided diagnosis |
url |
https://www.mdpi.com/1424-8220/21/10/3462 |
work_keys_str_mv |
AT shengxintao attentionguidednetworkwithdenselyconnectedconvolutionforskinlesionsegmentation AT yunjiang attentionguidednetworkwithdenselyconnectedconvolutionforskinlesionsegmentation AT simincao attentionguidednetworkwithdenselyconnectedconvolutionforskinlesionsegmentation AT chaowu attentionguidednetworkwithdenselyconnectedconvolutionforskinlesionsegmentation AT zeqima attentionguidednetworkwithdenselyconnectedconvolutionforskinlesionsegmentation |
_version_ |
1721415611149451264 |