利用无监督领域适应性自动进行心血管磁共振心肌瘢痕量化。

IF 3.7 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING European Radiology Experimental Pub Date : 2024-08-14 DOI:10.1186/s41747-024-00497-3
Richard Crawley, Sina Amirrajab, Didier Lustermans, Robert J Holtackers, Sven Plein, Mitko Veta, Marcel Breeuwer, Amedeo Chiribiri, Cian M Scannell
{"title":"利用无监督领域适应性自动进行心血管磁共振心肌瘢痕量化。","authors":"Richard Crawley, Sina Amirrajab, Didier Lustermans, Robert J Holtackers, Sven Plein, Mitko Veta, Marcel Breeuwer, Amedeo Chiribiri, Cian M Scannell","doi":"10.1186/s41747-024-00497-3","DOIUrl":null,"url":null,"abstract":"<p><p>Quantification of myocardial scar from late gadolinium enhancement (LGE) cardiovascular magnetic resonance (CMR) images can be facilitated by automated artificial intelligence (AI)-based analysis. However, AI models are susceptible to domain shifts in which the model performance is degraded when applied to data with different characteristics than the original training data. In this study, CycleGAN models were trained to translate local hospital data to the appearance of a public LGE CMR dataset. After domain adaptation, an AI scar quantification pipeline including myocardium segmentation, scar segmentation, and computation of scar burden, previously developed on the public dataset, was evaluated on an external test set including 44 patients clinically assessed for ischemic scar. The mean ± standard deviation Dice similarity coefficients between the manual and AI-predicted segmentations in all patients were similar to those previously reported: 0.76 ± 0.05 for myocardium and 0.75 ± 0.32 for scar, 0.41 ± 0.12 for scar in scans with pathological findings. Bland-Altman analysis showed a mean bias in scar burden percentage of -0.62% with limits of agreement from -8.4% to 7.17%. These results show the feasibility of deploying AI models, trained with public data, for LGE CMR quantification on local clinical data using unsupervised CycleGAN-based domain adaptation. RELEVANCE STATEMENT: Our study demonstrated the possibility of using AI models trained from public databases to be applied to patient data acquired at a specific institution with different acquisition settings, without additional manual labor to obtain further training labels.</p>","PeriodicalId":36926,"journal":{"name":"European Radiology Experimental","volume":null,"pages":null},"PeriodicalIF":3.7000,"publicationDate":"2024-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11324636/pdf/","citationCount":"0","resultStr":"{\"title\":\"Automated cardiovascular MR myocardial scar quantification with unsupervised domain adaptation.\",\"authors\":\"Richard Crawley, Sina Amirrajab, Didier Lustermans, Robert J Holtackers, Sven Plein, Mitko Veta, Marcel Breeuwer, Amedeo Chiribiri, Cian M Scannell\",\"doi\":\"10.1186/s41747-024-00497-3\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Quantification of myocardial scar from late gadolinium enhancement (LGE) cardiovascular magnetic resonance (CMR) images can be facilitated by automated artificial intelligence (AI)-based analysis. However, AI models are susceptible to domain shifts in which the model performance is degraded when applied to data with different characteristics than the original training data. In this study, CycleGAN models were trained to translate local hospital data to the appearance of a public LGE CMR dataset. After domain adaptation, an AI scar quantification pipeline including myocardium segmentation, scar segmentation, and computation of scar burden, previously developed on the public dataset, was evaluated on an external test set including 44 patients clinically assessed for ischemic scar. The mean ± standard deviation Dice similarity coefficients between the manual and AI-predicted segmentations in all patients were similar to those previously reported: 0.76 ± 0.05 for myocardium and 0.75 ± 0.32 for scar, 0.41 ± 0.12 for scar in scans with pathological findings. Bland-Altman analysis showed a mean bias in scar burden percentage of -0.62% with limits of agreement from -8.4% to 7.17%. These results show the feasibility of deploying AI models, trained with public data, for LGE CMR quantification on local clinical data using unsupervised CycleGAN-based domain adaptation. RELEVANCE STATEMENT: Our study demonstrated the possibility of using AI models trained from public databases to be applied to patient data acquired at a specific institution with different acquisition settings, without additional manual labor to obtain further training labels.</p>\",\"PeriodicalId\":36926,\"journal\":{\"name\":\"European Radiology Experimental\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":3.7000,\"publicationDate\":\"2024-08-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11324636/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"European Radiology Experimental\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1186/s41747-024-00497-3\",\"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}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"European Radiology Experimental","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1186/s41747-024-00497-3","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

摘要

通过基于人工智能(AI)的自动分析,可以对晚期钆增强(LGE)心血管磁共振(CMR)图像中的心肌瘢痕进行量化。然而,人工智能模型容易受到领域偏移的影响,当应用于与原始训练数据具有不同特征的数据时,模型的性能就会下降。在本研究中,对 CycleGAN 模型进行了训练,以将本地医院数据转换为公共 LGE CMR 数据集的外观。经过领域适应后,在外部测试集(包括 44 名临床评估为缺血性瘢痕的患者)上评估了之前在公共数据集上开发的人工智能瘢痕量化管道,包括心肌分割、瘢痕分割和瘢痕负担计算。所有患者的人工分段与人工智能预测分段之间的平均±标准偏差骰子相似系数与之前报告的相似:心肌为 0.76 ± 0.05,瘢痕为 0.75 ± 0.32,在有病理结果的扫描中,瘢痕为 0.41 ± 0.12。Bland-Altman分析显示,瘢痕负荷百分比的平均偏差为-0.62%,一致性范围为-8.4%至7.17%。这些结果表明,利用基于 CycleGAN 的无监督领域自适应技术,在本地临床数据上部署使用公共数据训练的 LGE CMR 定量人工智能模型是可行的。相关性声明:我们的研究证明了使用公共数据库训练的人工智能模型应用于特定机构以不同采集设置获取的患者数据的可能性,而无需额外的人工劳动来获取进一步的训练标签。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

摘要图片

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
Automated cardiovascular MR myocardial scar quantification with unsupervised domain adaptation.

Quantification of myocardial scar from late gadolinium enhancement (LGE) cardiovascular magnetic resonance (CMR) images can be facilitated by automated artificial intelligence (AI)-based analysis. However, AI models are susceptible to domain shifts in which the model performance is degraded when applied to data with different characteristics than the original training data. In this study, CycleGAN models were trained to translate local hospital data to the appearance of a public LGE CMR dataset. After domain adaptation, an AI scar quantification pipeline including myocardium segmentation, scar segmentation, and computation of scar burden, previously developed on the public dataset, was evaluated on an external test set including 44 patients clinically assessed for ischemic scar. The mean ± standard deviation Dice similarity coefficients between the manual and AI-predicted segmentations in all patients were similar to those previously reported: 0.76 ± 0.05 for myocardium and 0.75 ± 0.32 for scar, 0.41 ± 0.12 for scar in scans with pathological findings. Bland-Altman analysis showed a mean bias in scar burden percentage of -0.62% with limits of agreement from -8.4% to 7.17%. These results show the feasibility of deploying AI models, trained with public data, for LGE CMR quantification on local clinical data using unsupervised CycleGAN-based domain adaptation. RELEVANCE STATEMENT: Our study demonstrated the possibility of using AI models trained from public databases to be applied to patient data acquired at a specific institution with different acquisition settings, without additional manual labor to obtain further training labels.

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 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
期刊最新文献
Dark-field radiography for the detection of bone microstructure changes in osteoporotic human lumbar spine specimens. Amide proton transfer-weighted CEST MRI for radiotherapy target delineation of glioblastoma: a prospective pilot study. Deep learning-based segmentation of kidneys and renal cysts on T2-weighted MRI from patients with autosomal dominant polycystic kidney disease. Probing clarity: AI-generated simplified breast imaging reports for enhanced patient comprehension powered by ChatGPT-4o. Transfer learning classification of suspicious lesions on breast ultrasound: is there room to avoid biopsies of benign lesions?
×
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