Multi-Model Segmentation Algorithm for Rotator Cuff Injury Based on MRI Images

This paper proposes an AI-based diagnostic method using MRI images for rotator cuff injuries to assist in treatment by segmenting tear areas and assessing tear severity. A multi-model deep learning network based on Unet + FPN architecture was developed to automatically segment rotator cuff injury im...

Full description

Saved in:
Bibliographic Details
Main Authors: Mengqi Li, Jingchao Fang, Haonan Hou, Li Yuan, Jin Guo, Zhenlong Liu
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Bioengineering
Subjects:
Online Access:https://www.mdpi.com/2306-5354/12/3/218
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849342574916009984
author Mengqi Li
Jingchao Fang
Haonan Hou
Li Yuan
Jin Guo
Zhenlong Liu
author_facet Mengqi Li
Jingchao Fang
Haonan Hou
Li Yuan
Jin Guo
Zhenlong Liu
author_sort Mengqi Li
collection DOAJ
description This paper proposes an AI-based diagnostic method using MRI images for rotator cuff injuries to assist in treatment by segmenting tear areas and assessing tear severity. A multi-model deep learning network based on Unet + FPN architecture was developed to automatically segment rotator cuff injury images and determine tear grades. A dataset of 376 patients with 5640 images was used for training, with an additional 94 patients and 1410 images reserved for testing. To optimize segmentation, a tailored matching strategy was applied, achieving an Intersection over Union (IoU) of 0.79 ± 0.01 and a Dice coefficient of 0.75 ± 0.01, indicating high accuracy in segmenting tear areas. For tear severity indicators, the accuracy of estimating retraction (ER) reached 0.92 ± 0.02, and the accuracy of estimating stop tear width (ESTW) reached 0.79 ± 0.01. As the first AI algorithm specifically developed for diagnosing rotator cuff injuries, this platform demonstrates promising accuracy in both tear segmentation and severity assessment, aiming to support doctors in providing efficient, accurate diagnoses of rotator cuff tears.
format Article
id doaj-art-02e4128b3e8f4e7c9c5c784e688d76a1
institution Kabale University
issn 2306-5354
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Bioengineering
spelling doaj-art-02e4128b3e8f4e7c9c5c784e688d76a12025-08-20T03:43:21ZengMDPI AGBioengineering2306-53542025-02-0112321810.3390/bioengineering12030218Multi-Model Segmentation Algorithm for Rotator Cuff Injury Based on MRI ImagesMengqi Li0Jingchao Fang1Haonan Hou2Li Yuan3Jin Guo4Zhenlong Liu5Department of Sports Medicine, Peking University Third Hospital, Institute of Sports Medicine of Peking University, Beijing 100191, ChinaDepartment of Radiology, Peking University Third Hospital, Beijing 100191, ChinaSchool of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing 100083, ChinaSchool of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing 100083, ChinaSchool of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing 100083, ChinaDepartment of Sports Medicine, Peking University Third Hospital, Institute of Sports Medicine of Peking University, Beijing 100191, ChinaThis paper proposes an AI-based diagnostic method using MRI images for rotator cuff injuries to assist in treatment by segmenting tear areas and assessing tear severity. A multi-model deep learning network based on Unet + FPN architecture was developed to automatically segment rotator cuff injury images and determine tear grades. A dataset of 376 patients with 5640 images was used for training, with an additional 94 patients and 1410 images reserved for testing. To optimize segmentation, a tailored matching strategy was applied, achieving an Intersection over Union (IoU) of 0.79 ± 0.01 and a Dice coefficient of 0.75 ± 0.01, indicating high accuracy in segmenting tear areas. For tear severity indicators, the accuracy of estimating retraction (ER) reached 0.92 ± 0.02, and the accuracy of estimating stop tear width (ESTW) reached 0.79 ± 0.01. As the first AI algorithm specifically developed for diagnosing rotator cuff injuries, this platform demonstrates promising accuracy in both tear segmentation and severity assessment, aiming to support doctors in providing efficient, accurate diagnoses of rotator cuff tears.https://www.mdpi.com/2306-5354/12/3/218MRIrotator cuff injurydeep learningAI segmentationmulti-model mechanism
spellingShingle Mengqi Li
Jingchao Fang
Haonan Hou
Li Yuan
Jin Guo
Zhenlong Liu
Multi-Model Segmentation Algorithm for Rotator Cuff Injury Based on MRI Images
Bioengineering
MRI
rotator cuff injury
deep learning
AI segmentation
multi-model mechanism
title Multi-Model Segmentation Algorithm for Rotator Cuff Injury Based on MRI Images
title_full Multi-Model Segmentation Algorithm for Rotator Cuff Injury Based on MRI Images
title_fullStr Multi-Model Segmentation Algorithm for Rotator Cuff Injury Based on MRI Images
title_full_unstemmed Multi-Model Segmentation Algorithm for Rotator Cuff Injury Based on MRI Images
title_short Multi-Model Segmentation Algorithm for Rotator Cuff Injury Based on MRI Images
title_sort multi model segmentation algorithm for rotator cuff injury based on mri images
topic MRI
rotator cuff injury
deep learning
AI segmentation
multi-model mechanism
url https://www.mdpi.com/2306-5354/12/3/218
work_keys_str_mv AT mengqili multimodelsegmentationalgorithmforrotatorcuffinjurybasedonmriimages
AT jingchaofang multimodelsegmentationalgorithmforrotatorcuffinjurybasedonmriimages
AT haonanhou multimodelsegmentationalgorithmforrotatorcuffinjurybasedonmriimages
AT liyuan multimodelsegmentationalgorithmforrotatorcuffinjurybasedonmriimages
AT jinguo multimodelsegmentationalgorithmforrotatorcuffinjurybasedonmriimages
AT zhenlongliu multimodelsegmentationalgorithmforrotatorcuffinjurybasedonmriimages