• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

一种使用机器学习的用于腰椎间盘突出症的全自动磁共振成像（MRI）引导决策支持系统。

A fully automatic MRI-guided decision support system for lumbar disc herniation using machine learning.

作者信息

Zhang Di, Du Jiawei, Shi Jiaxiao, Zhang Yundong, Jia Siyue, Liu Xingyu, Wu Yu, An Yicheng, Zhu Shibo, Pan Dayu, Zhang Wei, Zhang Yiling, Feng Shiqing

机构信息

Department of Orthopaedics Tianjin Medical University General Hospital Tianjin People's Republic of China.

Beijing Longwood Valley Company Beijing People's Republic of China.

出版信息

JOR Spine. 2024 May 30;7(2):e1342. doi: 10.1002/jsp2.1342. eCollection 2024 Jun.

DOI:10.1002/jsp2.1342
PMID:38817341
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11137648/
Abstract

BACKGROUND

Normalized decision support system for lumbar disc herniation (LDH) will improve reproducibility compared with subjective clinical diagnosis and treatment. Magnetic resonance imaging (MRI) plays an essential role in the evaluation of LDH. This study aimed to develop an MRI-based decision support system for LDH, which evaluates lumbar discs in a reproducible, consistent, and reliable manner.

METHODS

The research team proposed a system based on machine learning that was trained and tested by a large, manually labeled data set comprising 217 patients' MRI scans (3255 lumbar discs). The system analyzes the radiological features of identified discs to diagnose herniation and classifies discs by Pfirrmann grade and MSU classification. Based on the assessment, the system provides clinical advice.

RESULTS

Eventually, the accuracy of the diagnosis process reached 95.83%. An 83.5% agreement was observed between the system's prediction and the ground-truth in the Pfirrmann grade. In the case of MSU classification, 95.0% precision was achieved. With the assistance of this system, the accuracy, interpretation efficiency and interrater agreement among surgeons were improved substantially.

CONCLUSION

This system showed considerable accuracy and efficiency, and therefore could serve as an objective reference for the diagnosis and treatment procedure in clinical practice.

摘要

背景

与主观的临床诊断和治疗相比，标准化的腰椎间盘突出症（LDH）决策支持系统将提高可重复性。磁共振成像（MRI）在LDH的评估中起着至关重要的作用。本研究旨在开发一种基于MRI的LDH决策支持系统，该系统以可重复、一致且可靠的方式评估腰椎间盘。

方法

研究团队提出了一种基于机器学习的系统，该系统由一个包含217例患者MRI扫描（3255个腰椎间盘）的大型手动标注数据集进行训练和测试。该系统分析已识别椎间盘的放射学特征以诊断椎间盘突出，并根据Pfirrmann分级和MSU分类对椎间盘进行分类。基于评估结果，该系统提供临床建议。

结果

最终，诊断过程的准确率达到95.83%。在Pfirrmann分级中，该系统的预测与真实情况之间的一致性为83.5%。在MSU分类方面，精度达到了95.0%。在该系统的辅助下，外科医生的诊断准确率、解读效率和评分者间一致性均得到了显著提高。

结论

该系统显示出相当高的准确性和效率，因此可为临床实践中的诊断和治疗程序提供客观参考。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b24b/11137648/c12ea7cb917f/JSP2-7-e1342-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b24b/11137648/f6fa9f5b54ab/JSP2-7-e1342-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b24b/11137648/c795a10c20d5/JSP2-7-e1342-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b24b/11137648/1ae3c8bd678f/JSP2-7-e1342-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b24b/11137648/4cdc3119a7ed/JSP2-7-e1342-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b24b/11137648/158927021502/JSP2-7-e1342-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b24b/11137648/a20ce6c80652/JSP2-7-e1342-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b24b/11137648/a4f0257a745c/JSP2-7-e1342-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b24b/11137648/d2d609ca5015/JSP2-7-e1342-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b24b/11137648/c12ea7cb917f/JSP2-7-e1342-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b24b/11137648/f6fa9f5b54ab/JSP2-7-e1342-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b24b/11137648/c795a10c20d5/JSP2-7-e1342-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b24b/11137648/1ae3c8bd678f/JSP2-7-e1342-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b24b/11137648/4cdc3119a7ed/JSP2-7-e1342-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b24b/11137648/158927021502/JSP2-7-e1342-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b24b/11137648/a20ce6c80652/JSP2-7-e1342-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b24b/11137648/a4f0257a745c/JSP2-7-e1342-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b24b/11137648/d2d609ca5015/JSP2-7-e1342-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b24b/11137648/c12ea7cb917f/JSP2-7-e1342-g002.jpg

相似文献

1
A fully automatic MRI-guided decision support system for lumbar disc herniation using machine learning.一种使用机器学习的用于腰椎间盘突出症的全自动磁共振成像（MRI）引导决策支持系统。
JOR Spine. 2024 May 30;7(2):e1342. doi: 10.1002/jsp2.1342. eCollection 2024 Jun.
2
A novel classification based on magnetic resonance imaging for individualized surgical strategies of lumbar disc herniation.一种基于磁共振成像的腰椎间盘突出症个体化手术策略的新分类。
Arch Orthop Trauma Surg. 2023 Aug;143(8):4833-4842. doi: 10.1007/s00402-023-04810-4. Epub 2023 Feb 14.
3
Disc degeneration contributes to the denser bone in the subendplate but not in the vertebral body in patients with lumbar spinal stenosis or disc herniation.在腰椎管狭窄症或椎间盘突出症患者中，椎间盘退变导致终板下骨质密度增加，但椎体骨质密度未增加。
Spine J. 2023 Jan;23(1):64-71. doi: 10.1016/j.spinee.2022.09.010. Epub 2022 Oct 3.
4
A Deep Learning Model for the Accurate and Reliable Classification of Disc Degeneration Based on MRI Data.基于 MRI 数据的用于 discs 退变准确可靠分类的深度学习模型。
Invest Radiol. 2021 Feb 1;56(2):78-85. doi: 10.1097/RLI.0000000000000709.
5
Analysis of the influence of species, intervertebral disc height and Pfirrmann classification on failure load of an injured disc using a novel disc herniation model.采用新型椎间盘突出模型分析种属、椎间盘高度和 Pfirrmann 分级对损伤椎间盘失效负荷的影响。
Spine J. 2021 Apr;21(4):698-707. doi: 10.1016/j.spinee.2020.10.030. Epub 2020 Nov 3.
6
Development and application of AI assisted automatic reconstruction of axial lumbar disc CT images and diagnosis of lumbar disc herniation.人工智能辅助腰椎间盘CT图像自动重建及腰椎间盘突出症诊断的开发与应用
Eur J Radiol. 2025 Apr;185:112003. doi: 10.1016/j.ejrad.2025.112003. Epub 2025 Feb 13.
7
Deep Learning for Lumbar Disc Herniation Diagnosis and Treatment Decision-Making Using Magnetic Resonance Imagings: A Retrospective Study.利用磁共振成像的深度学习在腰椎间盘突出症诊断及治疗决策中的应用：一项回顾性研究
World Neurosurg. 2025 Mar;195:123728. doi: 10.1016/j.wneu.2025.123728. Epub 2025 Feb 26.
8
Automatic Grading of Disc Herniation, Central Canal Stenosis and Nerve Roots Compression in Lumbar Magnetic Resonance Image Diagnosis.腰椎磁共振成像诊断中椎间盘突出、椎管狭窄和神经根受压的自动分级。
Front Endocrinol (Lausanne). 2022 Jun 6;13:890371. doi: 10.3389/fendo.2022.890371. eCollection 2022.
9
Congenital diaphragmatic hernia: automatic lung and liver MRI segmentation with nnU-Net, reproducibility of pyradiomics features, and a machine learning application for the classification of liver herniation.先天性膈疝：使用nnU-Net进行肺和肝脏的自动MRI分割、影像组学特征的可重复性以及用于肝脏疝分类的机器学习应用
Eur J Pediatr. 2024 May;183(5):2285-2300. doi: 10.1007/s00431-024-05476-9. Epub 2024 Feb 28.
10
Bone morphogenic protein-2 signaling in human disc degeneration and correlation to the Pfirrmann MRI grading system.骨形态发生蛋白-2 信号在人类椎间盘退变中的作用及其与 Pfirrmann MRI 分级系统的相关性。
Spine J. 2021 Jul;21(7):1205-1216. doi: 10.1016/j.spinee.2021.03.002. Epub 2021 Mar 5.

本文引用的文献

1
The Essence of Clinical Practice Guidelines for Lumbar Disc Herniation, 2021: 3. Diagnosis.《2021年腰椎间盘突出症临床实践指南精粹：3. 诊断》
Spine Surg Relat Res. 2022 Jul 27;6(4):325-328. doi: 10.22603/ssrr.2022-0044. eCollection 2022.
2
Clinical Reporting of Magnetic Resonance Imaging, the Way Forward for Patients With Lumbar Disc Herniation: A Prospective Correlational Study.磁共振成像的临床报告：腰椎间盘突出症患者的未来之路——一项前瞻性相关性研究
Cureus. 2022 Jul 25;14(7):e27232. doi: 10.7759/cureus.27232. eCollection 2022 Jul.
3
Choroid automatic segmentation and thickness quantification on swept-source optical coherence tomography images of highly myopic patients.
高度近视患者扫频源光学相干断层扫描图像中脉络膜的自动分割与厚度定量分析
Ann Transl Med. 2022 Jun;10(11):620. doi: 10.21037/atm-21-6736.
4
Spine-GFlow: A hybrid learning framework for robust multi-tissue segmentation in lumbar MRI without manual annotation.脊柱-GFlow：一种无需手动标注的腰椎 MRI 多组织分割稳健混合学习框架。
Comput Med Imaging Graph. 2022 Jul;99:102091. doi: 10.1016/j.compmedimag.2022.102091. Epub 2022 Jun 16.
5
High-Accuracy Nodal Staging of Head and Neck Cancer With USPIO-Enhanced MRI: A New Reading Algorithm Based on Node-to-Node Matched Histopathology.超顺磁氧化铁增强 MRI 对头颈癌的高精度淋巴结分期：一种基于淋巴结-淋巴结配对组织病理学的新阅读算法。
Invest Radiol. 2022 Dec 1;57(12):810-818. doi: 10.1097/RLI.0000000000000902. Epub 2022 Jul 1.
6
Improved Productivity Using Deep Learning-assisted Reporting for Lumbar Spine MRI.深度学习辅助报告在腰椎 MRI 中的应用提高了生产力。
Radiology. 2022 Oct;305(1):160-166. doi: 10.1148/radiol.220076. Epub 2022 Jun 14.
7
Deep learning-based high-accuracy quantitation for lumbar intervertebral disc degeneration from MRI.基于深度学习的 MRI 腰椎间盘退变高精度定量分析
Nat Commun. 2022 Feb 11;13(1):841. doi: 10.1038/s41467-022-28387-5.
8
MRI Characteristics at a Mean of Thirteen Years After Lumbar Disc Herniation Surgery in Adolescents: A Case-Control Study.青少年腰椎间盘突出症手术后平均13年的MRI特征：一项病例对照研究
JB JS Open Access. 2021 Nov 19;6(4). doi: 10.2106/JBJS.OA.21.00081. eCollection 2021 Oct-Dec.
9
DGMSNet: Spine segmentation for MR image by a detection-guided mixed-supervised segmentation network.DGMSNet：一种通过检测引导的混合监督分割网络对磁共振图像进行脊柱分割的方法
Med Image Anal. 2022 Jan;75:102261. doi: 10.1016/j.media.2021.102261. Epub 2021 Oct 27.
10
Adjuvant surgical decision-making system for lumbar intervertebral disc herniation after percutaneous endoscopic lumber discectomy: a retrospective nonlinear multiple logistic regression prediction model based on a large sample.经皮内镜腰椎间盘切除术治疗腰椎间盘突出症后辅助手术决策系统：基于大样本的回顾性非线性多因素 logistic 回归预测模型。
Spine J. 2021 Dec;21(12):2035-2048. doi: 10.1016/j.spinee.2021.07.012. Epub 2021 Jul 20.