Estimating the volume of penumbra in rodents using DTI and stack-based ensemble machine learning framework.

IF 3.7 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING
Duen-Pang Kuo, Yung-Chieh Chen, Yi-Tien Li, Sho-Jen Cheng, Kevin Li-Chun Hsieh, Po-Chih Kuo, Chen-Yin Ou, Cheng-Yu Chen
{"title":"Estimating the volume of penumbra in rodents using DTI and stack-based ensemble machine learning framework.","authors":"Duen-Pang Kuo, Yung-Chieh Chen, Yi-Tien Li, Sho-Jen Cheng, Kevin Li-Chun Hsieh, Po-Chih Kuo, Chen-Yin Ou, Cheng-Yu Chen","doi":"10.1186/s41747-024-00455-z","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>This study investigates the potential of diffusion tensor imaging (DTI) in identifying penumbral volume (PV) compared to the standard gadolinium-required perfusion-diffusion mismatch (PDM), utilizing a stack-based ensemble machine learning (ML) approach with enhanced explainability.</p><p><strong>Methods: </strong>Sixteen male rats were subjected to middle cerebral artery occlusion. The penumbra was identified using PDM at 30 and 90 min after occlusion. We used 11 DTI-derived metrics and 14 distance-based features to train five voxel-wise ML models. The model predictions were integrated using stack-based ensemble techniques. ML-estimated and PDM-defined PVs were compared to evaluate model performance through volume similarity assessment, the Pearson correlation analysis, and Bland-Altman analysis. Feature importance was determined for explainability.</p><p><strong>Results: </strong>In the test rats, the ML-estimated median PV was 106.4 mL (interquartile range 44.6-157.3 mL), whereas the PDM-defined median PV was 102.0 mL (52.1-144.9 mL). These PVs had a volume similarity of 0.88 (0.79-0.96), a Pearson correlation coefficient of 0.93 (p < 0.001), and a Bland-Altman bias of 2.5 mL (2.4% of the mean PDM-defined PV), with 95% limits of agreement ranging from -44.9 to 49.9 mL. Among the features used for PV prediction, the mean diffusivity was the most important feature.</p><p><strong>Conclusions: </strong>Our study confirmed that PV can be estimated using DTI metrics with a stack-based ensemble ML approach, yielding results comparable to the volume defined by the standard PDM. The model explainability enhanced its clinical relevance. Human studies are warranted to validate our findings.</p><p><strong>Relevance statement: </strong>The proposed DTI-based ML model can estimate PV without the need for contrast agent administration, offering a valuable option for patients with kidney dysfunction. It also can serve as an alternative if perfusion map interpretation fails in the clinical setting.</p><p><strong>Key points: </strong>• Penumbral volume can be estimated by DTI combined with stack-based ensemble ML. • Mean diffusivity was the most important feature used for predicting penumbral volume. • The proposed approach can be beneficial for patients with kidney dysfunction.</p>","PeriodicalId":36926,"journal":{"name":"European Radiology Experimental","volume":null,"pages":null},"PeriodicalIF":3.7000,"publicationDate":"2024-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11093947/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"European Radiology Experimental","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1186/s41747-024-00455-z","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}
引用次数: 0

Abstract

Background: This study investigates the potential of diffusion tensor imaging (DTI) in identifying penumbral volume (PV) compared to the standard gadolinium-required perfusion-diffusion mismatch (PDM), utilizing a stack-based ensemble machine learning (ML) approach with enhanced explainability.

Methods: Sixteen male rats were subjected to middle cerebral artery occlusion. The penumbra was identified using PDM at 30 and 90 min after occlusion. We used 11 DTI-derived metrics and 14 distance-based features to train five voxel-wise ML models. The model predictions were integrated using stack-based ensemble techniques. ML-estimated and PDM-defined PVs were compared to evaluate model performance through volume similarity assessment, the Pearson correlation analysis, and Bland-Altman analysis. Feature importance was determined for explainability.

Results: In the test rats, the ML-estimated median PV was 106.4 mL (interquartile range 44.6-157.3 mL), whereas the PDM-defined median PV was 102.0 mL (52.1-144.9 mL). These PVs had a volume similarity of 0.88 (0.79-0.96), a Pearson correlation coefficient of 0.93 (p < 0.001), and a Bland-Altman bias of 2.5 mL (2.4% of the mean PDM-defined PV), with 95% limits of agreement ranging from -44.9 to 49.9 mL. Among the features used for PV prediction, the mean diffusivity was the most important feature.

Conclusions: Our study confirmed that PV can be estimated using DTI metrics with a stack-based ensemble ML approach, yielding results comparable to the volume defined by the standard PDM. The model explainability enhanced its clinical relevance. Human studies are warranted to validate our findings.

Relevance statement: The proposed DTI-based ML model can estimate PV without the need for contrast agent administration, offering a valuable option for patients with kidney dysfunction. It also can serve as an alternative if perfusion map interpretation fails in the clinical setting.

Key points: • Penumbral volume can be estimated by DTI combined with stack-based ensemble ML. • Mean diffusivity was the most important feature used for predicting penumbral volume. • The proposed approach can be beneficial for patients with kidney dysfunction.

Abstract Image

利用 DTI 和基于堆栈的集合机器学习框架估算啮齿动物半影的体积。
背景:与标准的钆要求灌注-弥散不匹配(PDM)相比,本研究利用一种基于堆栈的集合机器学习(ML)方法,利用增强的可解释性,研究了弥散张量成像(DTI)在识别半影体积(PV)方面的潜力:16只雄性大鼠接受了大脑中动脉闭塞治疗。方法:16 只雄性大鼠在大脑中动脉闭塞后 30 分钟和 90 分钟使用 PDM 鉴定半影。我们使用 11 个 DTI 衍生指标和 14 个基于距离的特征来训练五个体素 ML 模型。模型预测使用基于堆栈的集合技术进行整合。通过容积相似性评估、皮尔逊相关分析和布兰德-阿尔特曼分析,对 ML 估算的 PV 和 PDM 定义的 PV 进行比较,以评估模型的性能。确定了特征的重要性,以便进行解释:在测试大鼠中,ML 估算的中位 PV 为 106.4 mL(四分位距为 44.6-157.3 mL),而 PDM 定义的中位 PV 为 102.0 mL(52.1-144.9 mL)。这些 PV 的容积相似度为 0.88(0.79-0.96),皮尔逊相关系数为 0.93(p 结论:PV 与 PDM 的容积相似度为 0.88(0.79-0.96),皮尔逊相关系数为 0.93:我们的研究证实,使用基于堆栈的集合 ML 方法,可以利用 DTI 指标估算出 PV,其结果与标准 PDM 所定义的体积相当。模型的可解释性增强了其临床相关性。为了验证我们的研究结果,有必要进行人体研究:所提出的基于 DTI 的 ML 模型无需使用造影剂即可估算 PV,为肾功能不全的患者提供了一种有价值的选择。该模型还可作为临床灌注图解读失败时的替代方法:- 要点:通过 DTI 结合基于堆栈的集合 ML,可以估算半影容积。- 平均扩散率是预测半影体积的最重要特征。- 建议的方法对肾功能不全患者有益。
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 求助全文
来源期刊
European Radiology Experimental
European Radiology Experimental Medicine-Radiology, Nuclear Medicine and Imaging
CiteScore
6.70
自引率
2.60%
发文量
56
审稿时长
18 weeks
×
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