SPINEPS--采用多类语义和实例分割的两阶段方法对 T2 加权磁共振图像进行全脊柱自动分割。

IF 4.7 2区 医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING
European Radiology Pub Date : 2025-03-01 Epub Date: 2024-10-29 DOI:10.1007/s00330-024-11155-y
Hendrik Möller, Robert Graf, Joachim Schmitt, Benjamin Keinert, Hanna Schön, Matan Atad, Anjany Sekuboyina, Felix Streckenbach, Florian Kofler, Thomas Kroencke, Stefanie Bette, Stefan N Willich, Thomas Keil, Thoralf Niendorf, Tobias Pischon, Beate Endemann, Bjoern Menze, Daniel Rueckert, Jan S Kirschke
{"title":"SPINEPS--采用多类语义和实例分割的两阶段方法对 T2 加权磁共振图像进行全脊柱自动分割。","authors":"Hendrik Möller, Robert Graf, Joachim Schmitt, Benjamin Keinert, Hanna Schön, Matan Atad, Anjany Sekuboyina, Felix Streckenbach, Florian Kofler, Thomas Kroencke, Stefanie Bette, Stefan N Willich, Thomas Keil, Thoralf Niendorf, Tobias Pischon, Beate Endemann, Bjoern Menze, Daniel Rueckert, Jan S Kirschke","doi":"10.1007/s00330-024-11155-y","DOIUrl":null,"url":null,"abstract":"<p><strong>Objectives: </strong>Introducing SPINEPS, a deep learning method for semantic and instance segmentation of 14 spinal structures (ten vertebra substructures, intervertebral discs, spinal cord, spinal canal, and sacrum) in whole-body sagittal T2-weighted turbo spin echo images.</p><p><strong>Material and methods: </strong>This local ethics committee-approved study utilized a public dataset (train/test 179/39 subjects, 137 female), a German National Cohort (NAKO) subset (train/test 1412/65 subjects, mean age 53, 694 female), and an in-house dataset (test 10 subjects, mean age 70, 5 female). SPINEPS is a semantic segmentation model, followed by a sliding window approach utilizing a second model to create instance masks from the semantic ones. Segmentation evaluation metrics included the Dice score and average symmetrical surface distance (ASSD). Statistical significance was assessed using the Wilcoxon signed-rank test.</p><p><strong>Results: </strong>On the public dataset, SPINEPS outperformed a nnUNet baseline on every structure and metric (e.g., an average over vertebra instances: dice 0.933 vs 0.911, p < 0.001, ASSD 0.21 vs 0.435, p < 0.001). SPINEPS trained on automated annotations of the NAKO achieves an average global Dice score of 0.918 on the combined NAKO and in-house test split. Adding the training data from the public dataset outperforms this (average instance-wise Dice score over the vertebra substructures 0.803 vs 0.778, average global Dice score 0.931 vs 0.918).</p><p><strong>Conclusion: </strong>SPINEPS offers segmentation of 14 spinal structures in T2w sagittal images. It provides a semantic mask and an instance mask separating the vertebrae and intervertebral discs. This is the first publicly available algorithm to enable this segmentation.</p><p><strong>Key points: </strong>Question No publicly available automatic approach can yield semantic and instance segmentation masks for the whole spine (including posterior elements) in T2-weighted sagittal TSE images. Findings Segmenting semantically first and then instance-wise outperforms a baseline trained directly on instance segmentation. The developed model produces high-resolution MRI segmentations for the whole spine. Clinical relevance This study introduces an automatic approach to whole spine segmentation, including posterior elements, in arbitrary fields of view T2w sagittal MR images, enabling easy biomarker extraction, automatic localization of pathologies and degenerative diseases, and quantifying analyses as downstream research.</p>","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":"1178-1189"},"PeriodicalIF":4.7000,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11836161/pdf/","citationCount":"0","resultStr":"{\"title\":\"SPINEPS-automatic whole spine segmentation of T2-weighted MR images using a two-phase approach to multi-class semantic and instance segmentation.\",\"authors\":\"Hendrik Möller, Robert Graf, Joachim Schmitt, Benjamin Keinert, Hanna Schön, Matan Atad, Anjany Sekuboyina, Felix Streckenbach, Florian Kofler, Thomas Kroencke, Stefanie Bette, Stefan N Willich, Thomas Keil, Thoralf Niendorf, Tobias Pischon, Beate Endemann, Bjoern Menze, Daniel Rueckert, Jan S Kirschke\",\"doi\":\"10.1007/s00330-024-11155-y\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Objectives: </strong>Introducing SPINEPS, a deep learning method for semantic and instance segmentation of 14 spinal structures (ten vertebra substructures, intervertebral discs, spinal cord, spinal canal, and sacrum) in whole-body sagittal T2-weighted turbo spin echo images.</p><p><strong>Material and methods: </strong>This local ethics committee-approved study utilized a public dataset (train/test 179/39 subjects, 137 female), a German National Cohort (NAKO) subset (train/test 1412/65 subjects, mean age 53, 694 female), and an in-house dataset (test 10 subjects, mean age 70, 5 female). SPINEPS is a semantic segmentation model, followed by a sliding window approach utilizing a second model to create instance masks from the semantic ones. Segmentation evaluation metrics included the Dice score and average symmetrical surface distance (ASSD). Statistical significance was assessed using the Wilcoxon signed-rank test.</p><p><strong>Results: </strong>On the public dataset, SPINEPS outperformed a nnUNet baseline on every structure and metric (e.g., an average over vertebra instances: dice 0.933 vs 0.911, p < 0.001, ASSD 0.21 vs 0.435, p < 0.001). SPINEPS trained on automated annotations of the NAKO achieves an average global Dice score of 0.918 on the combined NAKO and in-house test split. Adding the training data from the public dataset outperforms this (average instance-wise Dice score over the vertebra substructures 0.803 vs 0.778, average global Dice score 0.931 vs 0.918).</p><p><strong>Conclusion: </strong>SPINEPS offers segmentation of 14 spinal structures in T2w sagittal images. It provides a semantic mask and an instance mask separating the vertebrae and intervertebral discs. This is the first publicly available algorithm to enable this segmentation.</p><p><strong>Key points: </strong>Question No publicly available automatic approach can yield semantic and instance segmentation masks for the whole spine (including posterior elements) in T2-weighted sagittal TSE images. Findings Segmenting semantically first and then instance-wise outperforms a baseline trained directly on instance segmentation. The developed model produces high-resolution MRI segmentations for the whole spine. Clinical relevance This study introduces an automatic approach to whole spine segmentation, including posterior elements, in arbitrary fields of view T2w sagittal MR images, enabling easy biomarker extraction, automatic localization of pathologies and degenerative diseases, and quantifying analyses as downstream research.</p>\",\"PeriodicalId\":12076,\"journal\":{\"name\":\"European Radiology\",\"volume\":\" \",\"pages\":\"1178-1189\"},\"PeriodicalIF\":4.7000,\"publicationDate\":\"2025-03-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11836161/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"European Radiology\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1007/s00330-024-11155-y\",\"RegionNum\":2,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/10/29 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q1\",\"JCRName\":\"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"European Radiology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1007/s00330-024-11155-y","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/10/29 0:00:00","PubModel":"Epub","JCR":"Q1","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}
引用次数: 0

摘要

目标:介绍SPINEPS,这是一种深度学习方法,用于在全身矢状位T2加权涡轮自旋回波图像中对14个脊柱结构(10个椎体下结构、椎间盘、脊髓、椎管和骶骨)进行语义和实例分割:这项经当地伦理委员会批准的研究使用了一个公共数据集(训练/测试179/39名受试者,137名女性)、一个德国国家队列(NAKO)子集(训练/测试1412/65名受试者,平均年龄53岁,694名女性)和一个内部数据集(测试10名受试者,平均年龄70岁,5名女性)。SPINEPS 是一个语义分割模型,然后采用滑动窗口方法,利用第二个模型从语义模型中创建实例掩码。分割评估指标包括骰子得分和平均对称表面距离(ASSD)。统计意义采用 Wilcoxon 符号秩检验进行评估:结果:在公共数据集上,SPINEPS 在每个结构和指标上的表现都优于 nnUNet 基准(例如,椎骨实例的平均值:骰子 0.933 vs 0.911,p 结论:SPINEPS 能够对 14 个椎骨实例进行分割:SPINEPS 可对 T2w 矢状图像中的 14 个脊柱结构进行分割。它提供了一个语义掩码和一个实例掩码,将椎骨和椎间盘分开。这是首个公开可用的分割算法:问题 目前还没有公开的自动方法能在 T2 加权矢状位 TSE 图像中生成整个脊柱(包括后方元素)的语义和实例分割掩模。研究结果 首先进行语义分割,然后进行实例分割的效果优于直接进行实例分割训练的基线。所开发的模型可对整个脊柱进行高分辨率 MRI 分割。临床相关性 本研究介绍了一种在任意视场 T2w 矢状磁共振图像中进行包括后部元素在内的全脊柱自动分割的方法,可轻松提取生物标记物、自动定位病变和退行性疾病,并作为下游研究进行量化分析。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
SPINEPS-automatic whole spine segmentation of T2-weighted MR images using a two-phase approach to multi-class semantic and instance segmentation.

Objectives: Introducing SPINEPS, a deep learning method for semantic and instance segmentation of 14 spinal structures (ten vertebra substructures, intervertebral discs, spinal cord, spinal canal, and sacrum) in whole-body sagittal T2-weighted turbo spin echo images.

Material and methods: This local ethics committee-approved study utilized a public dataset (train/test 179/39 subjects, 137 female), a German National Cohort (NAKO) subset (train/test 1412/65 subjects, mean age 53, 694 female), and an in-house dataset (test 10 subjects, mean age 70, 5 female). SPINEPS is a semantic segmentation model, followed by a sliding window approach utilizing a second model to create instance masks from the semantic ones. Segmentation evaluation metrics included the Dice score and average symmetrical surface distance (ASSD). Statistical significance was assessed using the Wilcoxon signed-rank test.

Results: On the public dataset, SPINEPS outperformed a nnUNet baseline on every structure and metric (e.g., an average over vertebra instances: dice 0.933 vs 0.911, p < 0.001, ASSD 0.21 vs 0.435, p < 0.001). SPINEPS trained on automated annotations of the NAKO achieves an average global Dice score of 0.918 on the combined NAKO and in-house test split. Adding the training data from the public dataset outperforms this (average instance-wise Dice score over the vertebra substructures 0.803 vs 0.778, average global Dice score 0.931 vs 0.918).

Conclusion: SPINEPS offers segmentation of 14 spinal structures in T2w sagittal images. It provides a semantic mask and an instance mask separating the vertebrae and intervertebral discs. This is the first publicly available algorithm to enable this segmentation.

Key points: Question No publicly available automatic approach can yield semantic and instance segmentation masks for the whole spine (including posterior elements) in T2-weighted sagittal TSE images. Findings Segmenting semantically first and then instance-wise outperforms a baseline trained directly on instance segmentation. The developed model produces high-resolution MRI segmentations for the whole spine. Clinical relevance This study introduces an automatic approach to whole spine segmentation, including posterior elements, in arbitrary fields of view T2w sagittal MR images, enabling easy biomarker extraction, automatic localization of pathologies and degenerative diseases, and quantifying analyses as downstream research.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
European Radiology
European Radiology 医学-核医学
CiteScore
11.60
自引率
8.50%
发文量
874
审稿时长
2-4 weeks
期刊介绍: European Radiology (ER) continuously updates scientific knowledge in radiology by publication of strong original articles and state-of-the-art reviews written by leading radiologists. A well balanced combination of review articles, original papers, short communications from European radiological congresses and information on society matters makes ER an indispensable source for current information in this field. This is the Journal of the European Society of Radiology, and the official journal of a number of societies. From 2004-2008 supplements to European Radiology were published under its companion, European Radiology Supplements, ISSN 1613-3749.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信