Neural network auto-segmentation of serial-block-face scanning electron microscopy images exhibit collagen fibril structural differences with tendon type and health

IF 2.1 3区 医学 Q2 ORTHOPEDICS Journal of Orthopaedic Research® Pub Date : 2024-08-23 DOI:10.1002/jor.25961
Ellen T. Bloom, Chandran R. Sabanayagam, Jamie M. Benson, Lily M. Lin, Jean L. Ross, Jeffrey L. Caplan, Dawn M. Elliott
{"title":"Neural network auto-segmentation of serial-block-face scanning electron microscopy images exhibit collagen fibril structural differences with tendon type and health","authors":"Ellen T. Bloom,&nbsp;Chandran R. Sabanayagam,&nbsp;Jamie M. Benson,&nbsp;Lily M. Lin,&nbsp;Jean L. Ross,&nbsp;Jeffrey L. Caplan,&nbsp;Dawn M. Elliott","doi":"10.1002/jor.25961","DOIUrl":null,"url":null,"abstract":"<p>A U-Net machine learning algorithm was adapted to automatically segment tendon collagen fibril cross-sections from serial block face scanning electron microscopy (SBF-SEM) and create three-dimensional (3D) renderings. We compared the performance of routine Otsu thresholding and U-Net for a positional tendon that has low fibril density (rat tail tendon), an energy-storing tendon that has high fibril density (rat plantaris tendon), and a high fibril density tendon hypothesized to have disorganized 3D ultrastructure (degenerated rat plantaris tendon). The area segmentation of the tail and healthy plantaris tendon had excellent accuracy for both the Otsu and U-Net, with an Intersection over Union (IoU) of 0.8. With degeneration, only the U-Net could accurately segment the area, whereas Otsu IoU was only 0.45. For boundary validation, the U-Net outperformed Otsu segmentation for all tendons. The fibril diameter from U-Net was within 10% of the manual segmentation, however, the Otsu underestimated the fibril diameter by 39% in healthy plantaris and by 84% in the degenerated plantaris. Fibril geometry was averaged across the entire image stack and compared across tendon types. The tail had a lower fibril area fraction (58%) and larger fibril diameter (0.31 µm) than the healthy plantaris (67% and 0.21 µm) and degenerated plantaris tendon (66% and 0.19 µm). This method can be applied to a large variety of tissues to quantify 3D collagen fibril structure.</p>","PeriodicalId":16650,"journal":{"name":"Journal of Orthopaedic Research®","volume":"43 1","pages":"5-13"},"PeriodicalIF":2.1000,"publicationDate":"2024-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Orthopaedic Research®","FirstCategoryId":"3","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/jor.25961","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ORTHOPEDICS","Score":null,"Total":0}
引用次数: 0

Abstract

A U-Net machine learning algorithm was adapted to automatically segment tendon collagen fibril cross-sections from serial block face scanning electron microscopy (SBF-SEM) and create three-dimensional (3D) renderings. We compared the performance of routine Otsu thresholding and U-Net for a positional tendon that has low fibril density (rat tail tendon), an energy-storing tendon that has high fibril density (rat plantaris tendon), and a high fibril density tendon hypothesized to have disorganized 3D ultrastructure (degenerated rat plantaris tendon). The area segmentation of the tail and healthy plantaris tendon had excellent accuracy for both the Otsu and U-Net, with an Intersection over Union (IoU) of 0.8. With degeneration, only the U-Net could accurately segment the area, whereas Otsu IoU was only 0.45. For boundary validation, the U-Net outperformed Otsu segmentation for all tendons. The fibril diameter from U-Net was within 10% of the manual segmentation, however, the Otsu underestimated the fibril diameter by 39% in healthy plantaris and by 84% in the degenerated plantaris. Fibril geometry was averaged across the entire image stack and compared across tendon types. The tail had a lower fibril area fraction (58%) and larger fibril diameter (0.31 µm) than the healthy plantaris (67% and 0.21 µm) and degenerated plantaris tendon (66% and 0.19 µm). This method can be applied to a large variety of tissues to quantify 3D collagen fibril structure.

Abstract Image

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
神经网络自动分割的序列块面扫描电子显微镜图像显示了胶原纤维结构与肌腱类型和健康状况的差异。
我们对 U-Net 机器学习算法进行了调整,以自动分割连续块面扫描电子显微镜(SBF-SEM)中的肌腱胶原纤维横截面,并创建三维(3D)渲染图。我们比较了常规大津阈值法和 U-Net 对于低纤维密度的定位肌腱(大鼠尾部肌腱)、高纤维密度的储能肌腱(大鼠足底肌腱)以及假定三维超微结构混乱的高纤维密度肌腱(退化的大鼠足底肌腱)的性能。大津网和 U-Net 对尾部和健康足底肌腱的区域分割具有极高的准确性,交集大于联合(IoU)为 0.8。在肌腱退化的情况下,只有 U-Net 可以准确分割区域,而 Otsu 的 IoU 只有 0.45。在边界验证中,U-Net 对所有肌腱的分割都优于 Otsu。U-Net得出的纤维直径与人工分割结果相差10%以内,但Otsu低估了健康足底肌纤维直径的39%,低估了退化足底肌纤维直径的84%。纤维几何形状是整个图像堆栈的平均值,并在不同肌腱类型之间进行比较。与健康足底肌腱(67% 和 0.21 µm)和退化足底肌腱(66% 和 0.19 µm)相比,尾部肌腱的纤维面积分数(58%)较低,纤维直径(0.31 µm)较大。这种方法可应用于多种组织,以量化三维胶原纤维结构。
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
Journal of Orthopaedic Research®
Journal of Orthopaedic Research® 医学-整形外科
CiteScore
6.10
自引率
3.60%
发文量
261
审稿时长
3-6 weeks
期刊介绍: The Journal of Orthopaedic Research is the forum for the rapid publication of high quality reports of new information on the full spectrum of orthopaedic research, including life sciences, engineering, translational, and clinical studies.
期刊最新文献
Synovial fluid dual-biomarker algorithm accurately differentiates osteoarthritis from inflammatory arthritis. Correction to "Optical Spectroscopic Determination of Human Meniscus Composition". Bilateral waveform analysis of gait biomechanics presurgery to 12 months following ACL reconstruction compared to controls. Issue Information - Cover Issue Information - Editorial Board and TOC
×
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