AI-based fully automatic image analysis: Optimal abdominal and thoracic segmentation volumes for estimating total muscle volume on computed tomography scans

IF 2.5 Q3 ENDOCRINOLOGY & METABOLISM Osteoporosis and Sarcopenia Pub Date : 2024-06-01 DOI:10.1016/j.afos.2024.04.001
Thomas Ying , Pablo Borrelli , Lars Edenbrandt , Olof Enqvist , Reza Kaboteh , Elin Trägårdh , Johannes Ulén , Henrik Kjölhede
{"title":"AI-based fully automatic image analysis: Optimal abdominal and thoracic segmentation volumes for estimating total muscle volume on computed tomography scans","authors":"Thomas Ying ,&nbsp;Pablo Borrelli ,&nbsp;Lars Edenbrandt ,&nbsp;Olof Enqvist ,&nbsp;Reza Kaboteh ,&nbsp;Elin Trägårdh ,&nbsp;Johannes Ulén ,&nbsp;Henrik Kjölhede","doi":"10.1016/j.afos.2024.04.001","DOIUrl":null,"url":null,"abstract":"<div><h3>Objectives</h3><p>Evaluation of sarcopenia from computed tomography (CT) is often based on measuring skeletal muscle area on a single transverse slice. Automatic segmentation of muscle volume has a lower variance and may be a better proxy for the total muscle volume than single-slice areas. The aim of the study was to determine which abdominal and thoracic anatomical volumes were best at predicting the total muscle volume.</p></div><div><h3>Methods</h3><p>A cloud-based artificial intelligence tool (<span>recomia.org</span><svg><path></path></svg>) was used to segment all skeletal muscle of the torso of 994 patients who had performed whole-torso CT 2008–2020 for various clinical indications. Linear regression models for several anatomical volumes and single-slice areas were compared with regard to predicting the total torso muscle volume.</p></div><div><h3>Results</h3><p>The muscle volume from the tip of the coccyx and 25 cm cranially was the best of the abdominal volumes and was significantly better than the L3 slice muscle area (R<sup>2</sup> 0.935 vs 0.830, P &lt; 0.0001). For thoracic volumes, the muscle volume between the top of the sternum to the lower bound of the Th12 vertebra showed the best correlation with the total volume, significantly better than the Th12 slice muscle area (R<sup>2</sup> 0.892 vs 0.775, P &lt; 0.0001). Adjusting for body height improved the correlation slightly for all measurements but did not significantly change the ordering.</p></div><div><h3>Conclusions</h3><p>We identified muscle volumes that can be reliably segmented by automated image analysis which is superior to single slice areas in predicting total muscle volume.</p></div>","PeriodicalId":19701,"journal":{"name":"Osteoporosis and Sarcopenia","volume":null,"pages":null},"PeriodicalIF":2.5000,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S240552552400061X/pdfft?md5=7590e8e315832561e5fca36a44997630&pid=1-s2.0-S240552552400061X-main.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Osteoporosis and Sarcopenia","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S240552552400061X","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENDOCRINOLOGY & METABOLISM","Score":null,"Total":0}
引用次数: 0

Abstract

Objectives

Evaluation of sarcopenia from computed tomography (CT) is often based on measuring skeletal muscle area on a single transverse slice. Automatic segmentation of muscle volume has a lower variance and may be a better proxy for the total muscle volume than single-slice areas. The aim of the study was to determine which abdominal and thoracic anatomical volumes were best at predicting the total muscle volume.

Methods

A cloud-based artificial intelligence tool (recomia.org) was used to segment all skeletal muscle of the torso of 994 patients who had performed whole-torso CT 2008–2020 for various clinical indications. Linear regression models for several anatomical volumes and single-slice areas were compared with regard to predicting the total torso muscle volume.

Results

The muscle volume from the tip of the coccyx and 25 cm cranially was the best of the abdominal volumes and was significantly better than the L3 slice muscle area (R2 0.935 vs 0.830, P < 0.0001). For thoracic volumes, the muscle volume between the top of the sternum to the lower bound of the Th12 vertebra showed the best correlation with the total volume, significantly better than the Th12 slice muscle area (R2 0.892 vs 0.775, P < 0.0001). Adjusting for body height improved the correlation slightly for all measurements but did not significantly change the ordering.

Conclusions

We identified muscle volumes that can be reliably segmented by automated image analysis which is superior to single slice areas in predicting total muscle volume.

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
基于人工智能的全自动图像分析:估计计算机断层扫描总肌肉体积的最佳腹部和胸部分割体积
目的通过计算机断层扫描(CT)评估肌肉疏松症通常基于测量单个横向切片上的骨骼肌面积。自动分割肌肉体积的方差较小,可能比单片面积更能代表肌肉的总体积。研究的目的是确定哪些腹部和胸部解剖容积最能预测肌肉总体积。方法使用基于云的人工智能工具(recomia.org)对 2008-2020 年期间因各种临床适应症接受全躯干 CT 检查的 994 名患者的躯干所有骨骼肌进行分割。结果从尾骨顶端到头颅 25 厘米处的肌肉体积是腹部体积中最好的,明显优于 L3 切片肌肉面积(R2 0.935 vs 0.830,P <0.0001)。在胸腔容积方面,胸骨顶部到第 12 节脊椎下缘之间的肌肉容积与总容积的相关性最好,明显优于第 12 节切片肌肉面积(R2 0.892 vs 0.775,P < 0.0001)。结论我们确定了可通过自动图像分析进行可靠分割的肌肉体积,在预测肌肉总体积方面优于单切片面积。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
Osteoporosis and Sarcopenia
Osteoporosis and Sarcopenia Orthopedics, Sports Medicine and Rehabilitation, Endocrinology, Diabetes and Metabolism, Obstetrics, Gynecology and Women's Health, Geriatrics and Gerontology
自引率
5.00%
发文量
23
审稿时长
66 days
期刊最新文献
Does intradiscal steroid injection accelerate the histological degeneration of the human disc? Surgery for spinal deformity with osteoporosis: Achieving successful fusion Verification of grip strength as an evaluation tool for locomotive syndrome in rheumatoid arthritis Effects of whole-body vibration on bone properties in type 2 diabetes model rats Choice of cemented or uncemented stems for displaced femoral neck fractures
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1