Automated Segmentation and Connectivity Analysis for Normal Pressure Hydrocephalus.

IF 5 Q1 ENGINEERING, BIOMEDICAL BME frontiers Pub Date : 2022-01-09 eCollection Date: 2022-01-01 DOI:10.34133/2022/9783128
Angela Zhang, Amil Khan, Saisidharth Majeti, Judy Pham, Christopher Nguyen, Peter Tran, Vikram Iyer, Ashutosh Shelat, Jefferson Chen, B S Manjunath
{"title":"Automated Segmentation and Connectivity Analysis for Normal Pressure Hydrocephalus.","authors":"Angela Zhang,&nbsp;Amil Khan,&nbsp;Saisidharth Majeti,&nbsp;Judy Pham,&nbsp;Christopher Nguyen,&nbsp;Peter Tran,&nbsp;Vikram Iyer,&nbsp;Ashutosh Shelat,&nbsp;Jefferson Chen,&nbsp;B S Manjunath","doi":"10.34133/2022/9783128","DOIUrl":null,"url":null,"abstract":"<p><p><i>Objective and Impact Statement</i>. We propose an automated method of predicting Normal Pressure Hydrocephalus (NPH) from CT scans. A deep convolutional network segments regions of interest from the scans. These regions are then combined with MRI information to predict NPH. To our knowledge, this is the first method which automatically predicts NPH from CT scans and incorporates diffusion tractography information for prediction. <i>Introduction</i>. Due to their low cost and high versatility, CT scans are often used in NPH diagnosis. No well-defined and effective protocol currently exists for analysis of CT scans for NPH. Evans' index, an approximation of the ventricle to brain volume using one 2D image slice, has been proposed but is not robust. The proposed approach is an effective way to quantify regions of interest and offers a computational method for predicting NPH. <i>Methods</i>. We propose a novel method to predict NPH by combining regions of interest segmented from CT scans with connectome data to compute features which capture the impact of enlarged ventricles by excluding fiber tracts passing through these regions. The segmentation and network features are used to train a model for NPH prediction. <i>Results</i>. Our method outperforms the current state-of-the-art by 9 precision points and 29 recall points. Our segmentation model outperforms the current state-of-the-art in segmenting the ventricle, gray-white matter, and subarachnoid space in CT scans. <i>Conclusion</i>. Our experimental results demonstrate that fast and accurate volumetric segmentation of CT brain scans can help improve the NPH diagnosis process, and network properties can increase NPH prediction accuracy.</p>","PeriodicalId":72430,"journal":{"name":"BME frontiers","volume":null,"pages":null},"PeriodicalIF":5.0000,"publicationDate":"2022-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10521674/pdf/","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"BME frontiers","FirstCategoryId":"1087","ListUrlMain":"https://doi.org/10.34133/2022/9783128","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2022/1/1 0:00:00","PubModel":"eCollection","JCR":"Q1","JCRName":"ENGINEERING, BIOMEDICAL","Score":null,"Total":0}
引用次数: 2

Abstract

Objective and Impact Statement. We propose an automated method of predicting Normal Pressure Hydrocephalus (NPH) from CT scans. A deep convolutional network segments regions of interest from the scans. These regions are then combined with MRI information to predict NPH. To our knowledge, this is the first method which automatically predicts NPH from CT scans and incorporates diffusion tractography information for prediction. Introduction. Due to their low cost and high versatility, CT scans are often used in NPH diagnosis. No well-defined and effective protocol currently exists for analysis of CT scans for NPH. Evans' index, an approximation of the ventricle to brain volume using one 2D image slice, has been proposed but is not robust. The proposed approach is an effective way to quantify regions of interest and offers a computational method for predicting NPH. Methods. We propose a novel method to predict NPH by combining regions of interest segmented from CT scans with connectome data to compute features which capture the impact of enlarged ventricles by excluding fiber tracts passing through these regions. The segmentation and network features are used to train a model for NPH prediction. Results. Our method outperforms the current state-of-the-art by 9 precision points and 29 recall points. Our segmentation model outperforms the current state-of-the-art in segmenting the ventricle, gray-white matter, and subarachnoid space in CT scans. Conclusion. Our experimental results demonstrate that fast and accurate volumetric segmentation of CT brain scans can help improve the NPH diagnosis process, and network properties can increase NPH prediction accuracy.

Abstract Image

Abstract Image

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
常压脑积水的自动分割和连通性分析。
目标和影响声明。我们提出了一种通过CT扫描预测正常压力性脑积水(NPH)的自动方法。深度卷积网络从扫描中分割出感兴趣的区域。然后将这些区域与MRI信息相结合以预测NPH。据我们所知,这是第一种从CT扫描中自动预测NPH并结合扩散束成像信息进行预测的方法。介绍由于其低成本和高通用性,CT扫描经常用于NPH诊断。目前还没有明确有效的方案来分析NPH的CT扫描。Evans指数是使用一个2D图像切片对心室与大脑体积的近似值,已被提出,但并不稳健。所提出的方法是量化感兴趣区域的有效方法,并为预测NPH提供了一种计算方法。方法。我们提出了一种预测NPH的新方法,通过将CT扫描分割的感兴趣区域与连接体数据相结合,计算通过排除穿过这些区域的纤维束来捕捉心室增大影响的特征。分割和网络特征用于训练NPH预测的模型。后果我们的方法比目前最先进的方法高出9个精度点和29个召回点。我们的分割模型在CT扫描中分割心室、灰质和蛛网膜下腔方面优于目前最先进的分割模型。结论我们的实验结果表明,快速准确的CT脑扫描体积分割有助于改善NPH的诊断过程,网络特性可以提高NPH的预测精度。
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
CiteScore
7.10
自引率
0.00%
发文量
0
审稿时长
16 weeks
期刊最新文献
A Janus Adhesive Hydrogel with Integrated Attack and Defense for Bacteria Killing and Antifouling. Cationized Decalcified Bone Matrix for Infected Bone Defect Treatment. Functional Neural Networks in Human Brain Organoids. What Is the Magical Cavitation Bubble: A Holistic Perspective to Trigger Advanced Bubbles, Nano-Sonocatalysts, and Cellular Sonosensitizers. Synergistic Assembly of 1DZnO and Anti-CYFRA 21-1: A Physicochemical Approach to Optical Biosensing.
×
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