Alan Romero-Pacheco, Nidiyare Hevia-Montiel, Blanca Vazquez, Fernando Arámbula Cosío, Jorge Perez-Gonzalez
{"title":"基于深度学习的超声心动图左心室心肌应变估计。","authors":"Alan Romero-Pacheco, Nidiyare Hevia-Montiel, Blanca Vazquez, Fernando Arámbula Cosío, Jorge Perez-Gonzalez","doi":"10.1117/1.JMI.12.5.054002","DOIUrl":null,"url":null,"abstract":"<p><strong>Purpose: </strong>We present a deep-learning-based methodology for estimating deformation in 2D echocardiograms. The goal is to automatically estimate the longitudinal strain of the left ventricle (LV) walls in images affected by speckle noise and acoustic occlusions.</p><p><strong>Approach: </strong>The proposed methodology integrates algorithms for converting sparse to dense flow, a Res-UNet architecture for automatic myocardium segmentation, flow estimation using a global motion aggregation network, and the computation of longitudinal strain curves and the global longitudinal strain (GLS) index. The approach was evaluated using two echocardiographic datasets in apical four-chamber view, both modified with noise and acoustic shadows. The CAMUS dataset ( <math><mrow><mi>N</mi> <mo>=</mo> <mn>250</mn></mrow> </math> ) was used for LV wall segmentation, whereas a synthetic image database ( <math><mrow><mi>N</mi> <mo>=</mo> <mn>2037</mn></mrow> </math> ) was employed for flow estimation.</p><p><strong>Results: </strong>Among the main performance metrics achieved are 98% [96 to 99] of correlation in the conversion from sparse to dense flow, a Dice index of <math><mrow><mn>88.2</mn> <mo>%</mo> <mo>±</mo> <mn>3.8</mn> <mo>%</mo></mrow> </math> for myocardial segmentation, an endpoint error of 0.133 [0.13 to 0.14] pixels in flow estimation, and an error of 1.34% [0.94 to 2.09] in the estimation of the GLS index.</p><p><strong>Conclusions: </strong>The results demonstrate improvements over previously reported performances while maintaining stability in echocardiograms with acoustic shadows. This methodology could be useful in clinical practice for the analysis of echocardiograms with noise artifacts and acoustic occlusions. Our code and trained models are publicly available at https://github.com/ArBioIIMAS/echo-gma.</p>","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":"12 5","pages":"054002"},"PeriodicalIF":1.7000,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12476231/pdf/","citationCount":"0","resultStr":"{\"title\":\"Deep-learning-based estimation of left ventricle myocardial strain from echocardiograms with occlusion artifacts.\",\"authors\":\"Alan Romero-Pacheco, Nidiyare Hevia-Montiel, Blanca Vazquez, Fernando Arámbula Cosío, Jorge Perez-Gonzalez\",\"doi\":\"10.1117/1.JMI.12.5.054002\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Purpose: </strong>We present a deep-learning-based methodology for estimating deformation in 2D echocardiograms. The goal is to automatically estimate the longitudinal strain of the left ventricle (LV) walls in images affected by speckle noise and acoustic occlusions.</p><p><strong>Approach: </strong>The proposed methodology integrates algorithms for converting sparse to dense flow, a Res-UNet architecture for automatic myocardium segmentation, flow estimation using a global motion aggregation network, and the computation of longitudinal strain curves and the global longitudinal strain (GLS) index. The approach was evaluated using two echocardiographic datasets in apical four-chamber view, both modified with noise and acoustic shadows. The CAMUS dataset ( <math><mrow><mi>N</mi> <mo>=</mo> <mn>250</mn></mrow> </math> ) was used for LV wall segmentation, whereas a synthetic image database ( <math><mrow><mi>N</mi> <mo>=</mo> <mn>2037</mn></mrow> </math> ) was employed for flow estimation.</p><p><strong>Results: </strong>Among the main performance metrics achieved are 98% [96 to 99] of correlation in the conversion from sparse to dense flow, a Dice index of <math><mrow><mn>88.2</mn> <mo>%</mo> <mo>±</mo> <mn>3.8</mn> <mo>%</mo></mrow> </math> for myocardial segmentation, an endpoint error of 0.133 [0.13 to 0.14] pixels in flow estimation, and an error of 1.34% [0.94 to 2.09] in the estimation of the GLS index.</p><p><strong>Conclusions: </strong>The results demonstrate improvements over previously reported performances while maintaining stability in echocardiograms with acoustic shadows. This methodology could be useful in clinical practice for the analysis of echocardiograms with noise artifacts and acoustic occlusions. Our code and trained models are publicly available at https://github.com/ArBioIIMAS/echo-gma.</p>\",\"PeriodicalId\":47707,\"journal\":{\"name\":\"Journal of Medical Imaging\",\"volume\":\"12 5\",\"pages\":\"054002\"},\"PeriodicalIF\":1.7000,\"publicationDate\":\"2025-09-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12476231/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Medical Imaging\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1117/1.JMI.12.5.054002\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2025/9/27 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q3\",\"JCRName\":\"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Medical Imaging","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1117/1.JMI.12.5.054002","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/9/27 0:00:00","PubModel":"Epub","JCR":"Q3","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}
Deep-learning-based estimation of left ventricle myocardial strain from echocardiograms with occlusion artifacts.
Purpose: We present a deep-learning-based methodology for estimating deformation in 2D echocardiograms. The goal is to automatically estimate the longitudinal strain of the left ventricle (LV) walls in images affected by speckle noise and acoustic occlusions.
Approach: The proposed methodology integrates algorithms for converting sparse to dense flow, a Res-UNet architecture for automatic myocardium segmentation, flow estimation using a global motion aggregation network, and the computation of longitudinal strain curves and the global longitudinal strain (GLS) index. The approach was evaluated using two echocardiographic datasets in apical four-chamber view, both modified with noise and acoustic shadows. The CAMUS dataset ( ) was used for LV wall segmentation, whereas a synthetic image database ( ) was employed for flow estimation.
Results: Among the main performance metrics achieved are 98% [96 to 99] of correlation in the conversion from sparse to dense flow, a Dice index of for myocardial segmentation, an endpoint error of 0.133 [0.13 to 0.14] pixels in flow estimation, and an error of 1.34% [0.94 to 2.09] in the estimation of the GLS index.
Conclusions: The results demonstrate improvements over previously reported performances while maintaining stability in echocardiograms with acoustic shadows. This methodology could be useful in clinical practice for the analysis of echocardiograms with noise artifacts and acoustic occlusions. Our code and trained models are publicly available at https://github.com/ArBioIIMAS/echo-gma.
期刊介绍:
JMI covers fundamental and translational research, as well as applications, focused on medical imaging, which continue to yield physical and biomedical advancements in the early detection, diagnostics, and therapy of disease as well as in the understanding of normal. The scope of JMI includes: Imaging physics, Tomographic reconstruction algorithms (such as those in CT and MRI), Image processing and deep learning, Computer-aided diagnosis and quantitative image analysis, Visualization and modeling, Picture archiving and communications systems (PACS), Image perception and observer performance, Technology assessment, Ultrasonic imaging, Image-guided procedures, Digital pathology, Biomedical applications of biomedical imaging. JMI allows for the peer-reviewed communication and archiving of scientific developments, translational and clinical applications, reviews, and recommendations for the field.