Cargando…

Spine Medical Image Segmentation Based on Deep Learning

The aim was to further explore the clinical value of deep learning algorithm in the field of spinal medical image segmentation, and this study designed an improved U-shaped network (BN-U-Net) algorithm and applied it to the spinal MRI medical image segmentation of 22 research objects. The applicatio...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhang, Qingfeng, Du, Yun, Wei, Zhiqiang, Liu, Hengping, Yang, Xiaoxia, Zhao, Dongfang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Hindawi 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8694979/
https://www.ncbi.nlm.nih.gov/pubmed/34956558
http://dx.doi.org/10.1155/2021/1917946
_version_ 1784619479471226880
author Zhang, Qingfeng
Du, Yun
Wei, Zhiqiang
Liu, Hengping
Yang, Xiaoxia
Zhao, Dongfang
author_facet Zhang, Qingfeng
Du, Yun
Wei, Zhiqiang
Liu, Hengping
Yang, Xiaoxia
Zhao, Dongfang
author_sort Zhang, Qingfeng
collection PubMed
description The aim was to further explore the clinical value of deep learning algorithm in the field of spinal medical image segmentation, and this study designed an improved U-shaped network (BN-U-Net) algorithm and applied it to the spinal MRI medical image segmentation of 22 research objects. The application value of this algorithm in MRI image processing was comprehensively evaluated by accuracy (Acc), sensitivity (Sen), specificity (Spe), and area under curve (AUC). The results show that the image processing time of fully convolutional network (FCN) algorithm and U-Net algorithm is greater than 6 min, while the processing time of BN-U-Net algorithm is only 5–10 s, and the processing time is significantly shortened (P < 0.05). The Acc, Sen, and Spe results of BN-U-Net segmentation algorithm were 94.54 ± 3.56%, 88.76 ± 2.67%, and 86.27 ± 6.23%, respectively, which were significantly improved compared with FCN algorithm and U-Net algorithm (P < 0.05). In summary, the improved U-Net network algorithm used in this study significantly improves the quality of spinal MRI images by automatic segmentation of MRI images, which is worthy of further promotion in the field of spinal medical image segmentation.
format Online
Article
Text
id pubmed-8694979
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Hindawi
record_format MEDLINE/PubMed
spelling pubmed-86949792021-12-23 Spine Medical Image Segmentation Based on Deep Learning Zhang, Qingfeng Du, Yun Wei, Zhiqiang Liu, Hengping Yang, Xiaoxia Zhao, Dongfang J Healthc Eng Research Article The aim was to further explore the clinical value of deep learning algorithm in the field of spinal medical image segmentation, and this study designed an improved U-shaped network (BN-U-Net) algorithm and applied it to the spinal MRI medical image segmentation of 22 research objects. The application value of this algorithm in MRI image processing was comprehensively evaluated by accuracy (Acc), sensitivity (Sen), specificity (Spe), and area under curve (AUC). The results show that the image processing time of fully convolutional network (FCN) algorithm and U-Net algorithm is greater than 6 min, while the processing time of BN-U-Net algorithm is only 5–10 s, and the processing time is significantly shortened (P < 0.05). The Acc, Sen, and Spe results of BN-U-Net segmentation algorithm were 94.54 ± 3.56%, 88.76 ± 2.67%, and 86.27 ± 6.23%, respectively, which were significantly improved compared with FCN algorithm and U-Net algorithm (P < 0.05). In summary, the improved U-Net network algorithm used in this study significantly improves the quality of spinal MRI images by automatic segmentation of MRI images, which is worthy of further promotion in the field of spinal medical image segmentation. Hindawi 2021-12-15 /pmc/articles/PMC8694979/ /pubmed/34956558 http://dx.doi.org/10.1155/2021/1917946 Text en Copyright © 2021 Qingfeng Zhang et al. https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Research Article
Zhang, Qingfeng
Du, Yun
Wei, Zhiqiang
Liu, Hengping
Yang, Xiaoxia
Zhao, Dongfang
Spine Medical Image Segmentation Based on Deep Learning
title Spine Medical Image Segmentation Based on Deep Learning
title_full Spine Medical Image Segmentation Based on Deep Learning
title_fullStr Spine Medical Image Segmentation Based on Deep Learning
title_full_unstemmed Spine Medical Image Segmentation Based on Deep Learning
title_short Spine Medical Image Segmentation Based on Deep Learning
title_sort spine medical image segmentation based on deep learning
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8694979/
https://www.ncbi.nlm.nih.gov/pubmed/34956558
http://dx.doi.org/10.1155/2021/1917946
work_keys_str_mv AT zhangqingfeng spinemedicalimagesegmentationbasedondeeplearning
AT duyun spinemedicalimagesegmentationbasedondeeplearning
AT weizhiqiang spinemedicalimagesegmentationbasedondeeplearning
AT liuhengping spinemedicalimagesegmentationbasedondeeplearning
AT yangxiaoxia spinemedicalimagesegmentationbasedondeeplearning
AT zhaodongfang spinemedicalimagesegmentationbasedondeeplearning