Render U-Net: A Unique Perspective on Render to Explore Accurate Medical Image Segmentation
Organ lesions have a high mortality rate, and pose a serious threat to people’s lives. Segmenting organs accurately is helpful for doctors to diagnose. There is a demand for the advanced segmentation model for medical images. However, most segmentation models directly migrated from natural image seg...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-09-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/10/18/6439 |
id |
doaj-c7395ec6dc6549d2b37ef41755f7758e |
---|---|
record_format |
Article |
spelling |
doaj-c7395ec6dc6549d2b37ef41755f7758e2020-11-25T03:28:48ZengMDPI AGApplied Sciences2076-34172020-09-01106439643910.3390/app10186439Render U-Net: A Unique Perspective on Render to Explore Accurate Medical Image SegmentationChen Li0Wei Chen1Yusong Tan2College of Computer, National University of Defense Technology, Changsha 410073, ChinaCollege of Computer, National University of Defense Technology, Changsha 410073, ChinaCollege of Computer, National University of Defense Technology, Changsha 410073, ChinaOrgan lesions have a high mortality rate, and pose a serious threat to people’s lives. Segmenting organs accurately is helpful for doctors to diagnose. There is a demand for the advanced segmentation model for medical images. However, most segmentation models directly migrated from natural image segmentation models. These models usually ignore the importance of the boundary. To solve this difficulty, in this paper, we provided a unique perspective on rendering to explore accurate medical image segmentation. We adapt a subdivision-based point-sampling method to get high-quality boundaries. In addition, we integrated the attention mechanism and nested U-Net architecture into the proposed network Render U-Net.Render U-Net was evaluated on three public datasets, including LiTS, CHAOS, and DSB. This model obtained the best performance on five medical image segmentation tasks.https://www.mdpi.com/2076-3417/10/18/6439semantic segmentationrenderingmedical imageartificial intelligencedeep learning |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Chen Li Wei Chen Yusong Tan |
spellingShingle |
Chen Li Wei Chen Yusong Tan Render U-Net: A Unique Perspective on Render to Explore Accurate Medical Image Segmentation Applied Sciences semantic segmentation rendering medical image artificial intelligence deep learning |
author_facet |
Chen Li Wei Chen Yusong Tan |
author_sort |
Chen Li |
title |
Render U-Net: A Unique Perspective on Render to Explore Accurate Medical Image Segmentation |
title_short |
Render U-Net: A Unique Perspective on Render to Explore Accurate Medical Image Segmentation |
title_full |
Render U-Net: A Unique Perspective on Render to Explore Accurate Medical Image Segmentation |
title_fullStr |
Render U-Net: A Unique Perspective on Render to Explore Accurate Medical Image Segmentation |
title_full_unstemmed |
Render U-Net: A Unique Perspective on Render to Explore Accurate Medical Image Segmentation |
title_sort |
render u-net: a unique perspective on render to explore accurate medical image segmentation |
publisher |
MDPI AG |
series |
Applied Sciences |
issn |
2076-3417 |
publishDate |
2020-09-01 |
description |
Organ lesions have a high mortality rate, and pose a serious threat to people’s lives. Segmenting organs accurately is helpful for doctors to diagnose. There is a demand for the advanced segmentation model for medical images. However, most segmentation models directly migrated from natural image segmentation models. These models usually ignore the importance of the boundary. To solve this difficulty, in this paper, we provided a unique perspective on rendering to explore accurate medical image segmentation. We adapt a subdivision-based point-sampling method to get high-quality boundaries. In addition, we integrated the attention mechanism and nested U-Net architecture into the proposed network Render U-Net.Render U-Net was evaluated on three public datasets, including LiTS, CHAOS, and DSB. This model obtained the best performance on five medical image segmentation tasks. |
topic |
semantic segmentation rendering medical image artificial intelligence deep learning |
url |
https://www.mdpi.com/2076-3417/10/18/6439 |
work_keys_str_mv |
AT chenli renderunetauniqueperspectiveonrendertoexploreaccuratemedicalimagesegmentation AT weichen renderunetauniqueperspectiveonrendertoexploreaccuratemedicalimagesegmentation AT yusongtan renderunetauniqueperspectiveonrendertoexploreaccuratemedicalimagesegmentation |
_version_ |
1724582708058783744 |