SACNet: Shuffling atrous convolutional U‐Net for medical image segmentation
Abstract Medical images exhibit multi‐granularity and high obscurity along boundaries. As representative work, the U‐Net and its variants exhibit two shortcomings on medical image segmentation: (a) they expand the range of reception fields by applying addition or concatenate operators to features wi...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2023-03-01
|
Series: | IET Image Processing |
Subjects: | |
Online Access: | https://doi.org/10.1049/ipr2.12709 |
_version_ | 1811159591598161920 |
---|---|
author | Shaofan Wang Yukun Liu Yanfeng Sun Baocai Yin |
author_facet | Shaofan Wang Yukun Liu Yanfeng Sun Baocai Yin |
author_sort | Shaofan Wang |
collection | DOAJ |
description | Abstract Medical images exhibit multi‐granularity and high obscurity along boundaries. As representative work, the U‐Net and its variants exhibit two shortcomings on medical image segmentation: (a) they expand the range of reception fields by applying addition or concatenate operators to features with different reception fields, which disrupts the distribution of the essential feature of objects; (b) they utilize the downsampling or atrous convolution to characterize multi‐granular features of objects, which can obtain a large range of reception fields but leads to blur boundaries of objects. A Shuffling Atrous Convolutional U‐Net (SACNet) for circumventing those issues is proposed. The significant component of SACNet is the Shuffling Atrous Convolution (SAC) module, which fuses different atrous convolutional layers together by using a shuffle concatenate operation, so that the features from the same channel (which correspond to the same attribute of objects) are merged together. Besides the SAC modules, SACNet utilizes an EP module during the fine and medium levels to enhance the boundaries of objects, and utilizes a Transformer module during the coarse level to capture an overall correlation of pixels. Experiments on three medical image segmentation tasks: abdominal organ, cardiac, and skin lesion segmentation demonstrate that, SACNet outperforms several state‐of‐the‐art methods and facilitates easy transplant to other semantic segmentation tasks. |
first_indexed | 2024-04-10T05:43:50Z |
format | Article |
id | doaj.art-072f75270ce04787b3482465fe89932e |
institution | Directory Open Access Journal |
issn | 1751-9659 1751-9667 |
language | English |
last_indexed | 2024-04-10T05:43:50Z |
publishDate | 2023-03-01 |
publisher | Wiley |
record_format | Article |
series | IET Image Processing |
spelling | doaj.art-072f75270ce04787b3482465fe89932e2023-03-06T04:27:52ZengWileyIET Image Processing1751-96591751-96672023-03-011741236125210.1049/ipr2.12709SACNet: Shuffling atrous convolutional U‐Net for medical image segmentationShaofan Wang0Yukun Liu1Yanfeng Sun2Baocai Yin3Beijing Institute of Artificial Intelligence, Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Faculty of Information Technology Beijing University of Technology Beijing ChinaBeijing Institute of Artificial Intelligence, Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Faculty of Information Technology Beijing University of Technology Beijing ChinaBeijing Institute of Artificial Intelligence, Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Faculty of Information Technology Beijing University of Technology Beijing ChinaBeijing Institute of Artificial Intelligence, Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Faculty of Information Technology Beijing University of Technology Beijing ChinaAbstract Medical images exhibit multi‐granularity and high obscurity along boundaries. As representative work, the U‐Net and its variants exhibit two shortcomings on medical image segmentation: (a) they expand the range of reception fields by applying addition or concatenate operators to features with different reception fields, which disrupts the distribution of the essential feature of objects; (b) they utilize the downsampling or atrous convolution to characterize multi‐granular features of objects, which can obtain a large range of reception fields but leads to blur boundaries of objects. A Shuffling Atrous Convolutional U‐Net (SACNet) for circumventing those issues is proposed. The significant component of SACNet is the Shuffling Atrous Convolution (SAC) module, which fuses different atrous convolutional layers together by using a shuffle concatenate operation, so that the features from the same channel (which correspond to the same attribute of objects) are merged together. Besides the SAC modules, SACNet utilizes an EP module during the fine and medium levels to enhance the boundaries of objects, and utilizes a Transformer module during the coarse level to capture an overall correlation of pixels. Experiments on three medical image segmentation tasks: abdominal organ, cardiac, and skin lesion segmentation demonstrate that, SACNet outperforms several state‐of‐the‐art methods and facilitates easy transplant to other semantic segmentation tasks.https://doi.org/10.1049/ipr2.12709convolutional neural netsmedical image processing |
spellingShingle | Shaofan Wang Yukun Liu Yanfeng Sun Baocai Yin SACNet: Shuffling atrous convolutional U‐Net for medical image segmentation IET Image Processing convolutional neural nets medical image processing |
title | SACNet: Shuffling atrous convolutional U‐Net for medical image segmentation |
title_full | SACNet: Shuffling atrous convolutional U‐Net for medical image segmentation |
title_fullStr | SACNet: Shuffling atrous convolutional U‐Net for medical image segmentation |
title_full_unstemmed | SACNet: Shuffling atrous convolutional U‐Net for medical image segmentation |
title_short | SACNet: Shuffling atrous convolutional U‐Net for medical image segmentation |
title_sort | sacnet shuffling atrous convolutional u net for medical image segmentation |
topic | convolutional neural nets medical image processing |
url | https://doi.org/10.1049/ipr2.12709 |
work_keys_str_mv | AT shaofanwang sacnetshufflingatrousconvolutionalunetformedicalimagesegmentation AT yukunliu sacnetshufflingatrousconvolutionalunetformedicalimagesegmentation AT yanfengsun sacnetshufflingatrousconvolutionalunetformedicalimagesegmentation AT baocaiyin sacnetshufflingatrousconvolutionalunetformedicalimagesegmentation |