{"title":"一种利用机器学习和 J-ACCESS 数据库开发的新型算法可从心肌灌注单光子发射断层扫描图像中估算出缺陷评分。","authors":"Keisuke Kiso, Kenichi Nakajima, Yukitaka Nimura, Tsunehiko Nishimura","doi":"10.1007/s12149-024-01971-z","DOIUrl":null,"url":null,"abstract":"<div><h3>Background</h3><p>Stress myocardial perfusion single-photon emission computed tomography (SPECT) imaging (MPI) has been used to diagnose and predict the prognoses of patients with coronary artery disease (CAD). An ongoing multicenter collaboration established a Japanese database (J-ACCESS) in 2001 that includes a risk model and expert interpretations. The present study aimed to develop a novel algorithm using machine learning (ML) and resources from the J-ACCESS database to aid SPECT image interpretation.</p><h3>Methods</h3><p>We analyzed data from 1288 patients in J-ACCESS 3 and 4 databases. Three-dimensional (3D) stereoscopic images of left ventricular myocardial perfusion were reconstructed with linear transformation from the original short-axis data. Segments were extracted from U-Net, then features were extracted from each segment during the ML process. We estimated segmental scores based on weighted features obtained from fully connected layers. Correlations between segment scores interpreted by nuclear cardiology experts and estimated by ML were evaluated using a 17-segment model, summed stress (SSS), summed rest (SRS), and summed difference (SDS) scores, and ratios (%) of summed different scores (%SDS).</p><h3>Results</h3><p>The complete concordance rate of scores assessed by the experts and estimated by ML was 79.6%. The underestimated and overestimated rates were 10.3% and 10.0%, respectively. Associations between defect scores assessed by experts and ML were close, with correlation coefficients (<i>r</i>) of 0.923, 0.917, 0.842 and 0.853 for SSS, SRS, SDS, %SDS, respectively (<i>p</i> < 0.0001 for all).</p><h3>Conclusions</h3><p>We created a new algorithm to estimate MPI scores using ML and the J-ACCESS database. This algorithm should provide accurate MPI interpretation even in facilities without specialist nuclear cardiologists, and might facilitate therapeutic decision-making and predict prognoses.</p></div>","PeriodicalId":8007,"journal":{"name":"Annals of Nuclear Medicine","volume":null,"pages":null},"PeriodicalIF":2.5000,"publicationDate":"2024-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s12149-024-01971-z.pdf","citationCount":"0","resultStr":"{\"title\":\"A novel algorithm developed using machine learning and a J-ACCESS database can estimate defect scores from myocardial perfusion single-photon emission tomography images\",\"authors\":\"Keisuke Kiso, Kenichi Nakajima, Yukitaka Nimura, Tsunehiko Nishimura\",\"doi\":\"10.1007/s12149-024-01971-z\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><h3>Background</h3><p>Stress myocardial perfusion single-photon emission computed tomography (SPECT) imaging (MPI) has been used to diagnose and predict the prognoses of patients with coronary artery disease (CAD). An ongoing multicenter collaboration established a Japanese database (J-ACCESS) in 2001 that includes a risk model and expert interpretations. The present study aimed to develop a novel algorithm using machine learning (ML) and resources from the J-ACCESS database to aid SPECT image interpretation.</p><h3>Methods</h3><p>We analyzed data from 1288 patients in J-ACCESS 3 and 4 databases. Three-dimensional (3D) stereoscopic images of left ventricular myocardial perfusion were reconstructed with linear transformation from the original short-axis data. Segments were extracted from U-Net, then features were extracted from each segment during the ML process. We estimated segmental scores based on weighted features obtained from fully connected layers. Correlations between segment scores interpreted by nuclear cardiology experts and estimated by ML were evaluated using a 17-segment model, summed stress (SSS), summed rest (SRS), and summed difference (SDS) scores, and ratios (%) of summed different scores (%SDS).</p><h3>Results</h3><p>The complete concordance rate of scores assessed by the experts and estimated by ML was 79.6%. The underestimated and overestimated rates were 10.3% and 10.0%, respectively. Associations between defect scores assessed by experts and ML were close, with correlation coefficients (<i>r</i>) of 0.923, 0.917, 0.842 and 0.853 for SSS, SRS, SDS, %SDS, respectively (<i>p</i> < 0.0001 for all).</p><h3>Conclusions</h3><p>We created a new algorithm to estimate MPI scores using ML and the J-ACCESS database. This algorithm should provide accurate MPI interpretation even in facilities without specialist nuclear cardiologists, and might facilitate therapeutic decision-making and predict prognoses.</p></div>\",\"PeriodicalId\":8007,\"journal\":{\"name\":\"Annals of Nuclear Medicine\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.5000,\"publicationDate\":\"2024-08-29\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://link.springer.com/content/pdf/10.1007/s12149-024-01971-z.pdf\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Annals of Nuclear Medicine\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://link.springer.com/article/10.1007/s12149-024-01971-z\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Annals of Nuclear Medicine","FirstCategoryId":"3","ListUrlMain":"https://link.springer.com/article/10.1007/s12149-024-01971-z","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}
引用次数: 0
摘要
背景：应激心肌灌注单光子发射计算机断层扫描（SPECT）成像（MPI）已被用于诊断和预测冠状动脉疾病（CAD）患者的预后。2001 年，一项正在进行的多中心合作建立了一个日本数据库（J-ACCESS），其中包括一个风险模型和专家解释。本研究旨在利用机器学习（ML）和 J-ACCESS 数据库的资源开发一种新型算法，以辅助 SPECT 图像解读：我们分析了 J-ACCESS 3 和 4 数据库中 1288 名患者的数据。左心室心肌灌注的三维（3D）立体图像是根据原始短轴数据通过线性变换重建的。从 U-Net 中提取分段，然后在 ML 过程中从每个分段中提取特征。我们根据全连接层获得的加权特征来估算分段得分。使用 17 个节段模型、应力总和（SSS）、静息总和（SRS）和差异总和（SDS）得分以及不同得分总和的比率（%）评估了核心脏病学专家解释的节段得分与 ML 估算的得分之间的相关性：结果：专家评估得分与 ML 估算得分的完全一致率为 79.6%。低估率和高估率分别为 10.3% 和 10.0%。专家评估的缺陷评分与 ML 估计的评分之间的相关性很接近，SSS、SRS、SDS 和 %SDS 的相关系数（r）分别为 0.923、0.917、0.842 和 0.853（p 结论：专家评估的缺陷评分与 ML 估计的评分之间的相关性很接近，SSS、SRS、SDS 和 %SDS 的相关系数（r）分别为 0.923、0.917、0.842 和 0.853：我们利用 ML 和 J-ACCESS 数据库创建了一种估算 MPI 评分的新算法。即使在没有专业核心脏病专家的医疗机构中，该算法也能提供准确的 MPI 解读，并有助于做出治疗决策和预测预后。
A novel algorithm developed using machine learning and a J-ACCESS database can estimate defect scores from myocardial perfusion single-photon emission tomography images
Background
Stress myocardial perfusion single-photon emission computed tomography (SPECT) imaging (MPI) has been used to diagnose and predict the prognoses of patients with coronary artery disease (CAD). An ongoing multicenter collaboration established a Japanese database (J-ACCESS) in 2001 that includes a risk model and expert interpretations. The present study aimed to develop a novel algorithm using machine learning (ML) and resources from the J-ACCESS database to aid SPECT image interpretation.
Methods
We analyzed data from 1288 patients in J-ACCESS 3 and 4 databases. Three-dimensional (3D) stereoscopic images of left ventricular myocardial perfusion were reconstructed with linear transformation from the original short-axis data. Segments were extracted from U-Net, then features were extracted from each segment during the ML process. We estimated segmental scores based on weighted features obtained from fully connected layers. Correlations between segment scores interpreted by nuclear cardiology experts and estimated by ML were evaluated using a 17-segment model, summed stress (SSS), summed rest (SRS), and summed difference (SDS) scores, and ratios (%) of summed different scores (%SDS).
Results
The complete concordance rate of scores assessed by the experts and estimated by ML was 79.6%. The underestimated and overestimated rates were 10.3% and 10.0%, respectively. Associations between defect scores assessed by experts and ML were close, with correlation coefficients (r) of 0.923, 0.917, 0.842 and 0.853 for SSS, SRS, SDS, %SDS, respectively (p < 0.0001 for all).
Conclusions
We created a new algorithm to estimate MPI scores using ML and the J-ACCESS database. This algorithm should provide accurate MPI interpretation even in facilities without specialist nuclear cardiologists, and might facilitate therapeutic decision-making and predict prognoses.
期刊介绍：
Annals of Nuclear Medicine is an official journal of the Japanese Society of Nuclear Medicine. It develops the appropriate application of radioactive substances and stable nuclides in the field of medicine.
The journal promotes the exchange of ideas and information and research in nuclear medicine and includes the medical application of radionuclides and related subjects. It presents original articles, short communications, reviews and letters to the editor.
京公网安备 11010802042870号
京ICP备2023020795号-1
分享
求助内容：
应助结果提醒方式：
扫码关注我们
