基于深度学习的先天性心脏病快速三维全心建模方法

IF 1.9 4区医学 Q3 CARDIAC & CARDIOVASCULAR SYSTEMS

Cardiology Pub Date : 2024-10-11 DOI:10.1159/000541980

Haiping Huang, Yisheng Wu

{"title":"基于深度学习的先天性心脏病快速三维全心建模方法","authors":"Haiping Huang, Yisheng Wu","doi":"10.1159/000541980","DOIUrl":null,"url":null,"abstract":"Introduction: This study aims to develop a deep learning-based method for generating three-dimensional heart mesh models for patients with congenital heart disease by integrating medical imaging and clinical diagnostic information.Methods: A deep learning model was trained using CT and cardiac MRI (CMR) images, along with clinical data from 110 patients. The web-based platform automatically outputs STL files for 3D printing and Unity 3D OBJ files for virtual reality (VR) applications upon uploading the medical images and diagnostic information. The models were tested on three congenital heart disease cases, with corresponding 3D printed and VR heart models generated.Results: The 3D printed and VR heart models received high praise from professional doctors for their anatomical accuracy and clarity. Evaluations indicated that the proposed method effectively and rapidly reconstructs complex congenital heart disease structures, proving useful for preoperative planning and diagnostic support.Conclusion: The 3D modeling approach has the potential to enhance the precision of surgical planning and diagnosis for congenital heart disease. Future studies should explore larger datasets and training models for different types of congenital heart disease to validate the model's broad applicability.","PeriodicalId":9391,"journal":{"name":"Cardiology","volume":null,"pages":null},"PeriodicalIF":1.9000,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A Deep Learning-Based Method for Rapid 3D Whole-Heart Modeling in Congenital Heart Disease.\",\"authors\":\"Haiping Huang, Yisheng Wu\",\"doi\":\"10.1159/000541980\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Introduction: This study aims to develop a deep learning-based method for generating three-dimensional heart mesh models for patients with congenital heart disease by integrating medical imaging and clinical diagnostic information.Methods: A deep learning model was trained using CT and cardiac MRI (CMR) images, along with clinical data from 110 patients. The web-based platform automatically outputs STL files for 3D printing and Unity 3D OBJ files for virtual reality (VR) applications upon uploading the medical images and diagnostic information. The models were tested on three congenital heart disease cases, with corresponding 3D printed and VR heart models generated.Results: The 3D printed and VR heart models received high praise from professional doctors for their anatomical accuracy and clarity. Evaluations indicated that the proposed method effectively and rapidly reconstructs complex congenital heart disease structures, proving useful for preoperative planning and diagnostic support.Conclusion: The 3D modeling approach has the potential to enhance the precision of surgical planning and diagnosis for congenital heart disease. Future studies should explore larger datasets and training models for different types of congenital heart disease to validate the model's broad applicability.\",\"PeriodicalId\":9391,\"journal\":{\"name\":\"Cardiology\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.9000,\"publicationDate\":\"2024-10-11\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Cardiology\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1159/000541980\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"CARDIAC & CARDIOVASCULAR SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Cardiology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1159/000541980","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"CARDIAC & CARDIOVASCULAR SYSTEMS","Score":null,"Total":0}

引用次数: 0

摘要

简介：本研究旨在开发一种基于深度学习的方法，通过整合医学影像和临床诊断信息生成先天性心脏病患者的三维心脏网格模型：本研究旨在开发一种基于深度学习的方法，通过整合医学影像和临床诊断信息，为先天性心脏病患者生成三维心脏网状模型：方法：使用 CT 和心脏核磁共振成像（CMR）图像以及 110 名患者的临床数据训练深度学习模型。基于网络的平台在上传医学影像和诊断信息后，会自动输出用于三维打印的 STL 文件和用于虚拟现实（VR）应用的 Unity 3D OBJ 文件。这些模型在三个先天性心脏病病例上进行了测试，并生成了相应的 3D 打印和 VR 心脏模型：结果：3D 打印和 VR 心脏模型的解剖准确性和清晰度得到了专业医生的高度评价。评估结果表明，所提出的方法能有效、快速地重建复杂的先天性心脏病结构，对术前规划和诊断支持非常有用：结论：三维建模方法有望提高先天性心脏病手术规划和诊断的精确度。未来的研究应针对不同类型的先天性心脏病探索更大的数据集和训练模型，以验证该模型的广泛适用性。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

A Deep Learning-Based Method for Rapid 3D Whole-Heart Modeling in Congenital Heart Disease.

Introduction: This study aims to develop a deep learning-based method for generating three-dimensional heart mesh models for patients with congenital heart disease by integrating medical imaging and clinical diagnostic information.

Methods: A deep learning model was trained using CT and cardiac MRI (CMR) images, along with clinical data from 110 patients. The web-based platform automatically outputs STL files for 3D printing and Unity 3D OBJ files for virtual reality (VR) applications upon uploading the medical images and diagnostic information. The models were tested on three congenital heart disease cases, with corresponding 3D printed and VR heart models generated.

Results: The 3D printed and VR heart models received high praise from professional doctors for their anatomical accuracy and clarity. Evaluations indicated that the proposed method effectively and rapidly reconstructs complex congenital heart disease structures, proving useful for preoperative planning and diagnostic support.

Conclusion: The 3D modeling approach has the potential to enhance the precision of surgical planning and diagnosis for congenital heart disease. Future studies should explore larger datasets and training models for different types of congenital heart disease to validate the model's broad applicability.

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

Cardiology 医学-心血管系统

CiteScore

3.40

自引率

5.30%

发文量

审稿时长

1.5 months

期刊介绍： ''Cardiology'' features first reports on original clinical, preclinical and fundamental research as well as ''Novel Insights from Clinical Experience'' and topical comprehensive reviews in selected areas of cardiovascular disease. ''Editorial Comments'' provide a critical but positive evaluation of a recent article. Papers not only describe but offer critical appraisals of new developments in non-invasive and invasive diagnostic methods and in pharmacologic, nutritional and mechanical/surgical therapies. Readers are thus kept informed of current strategies in the prevention, recognition and treatment of heart disease. Special sections in a variety of subspecialty areas reinforce the journal''s value as a complete record of recent progress for all cardiologists, internists, cardiac surgeons, clinical physiologists, pharmacologists and professionals in other areas of medicine interested in current activity in cardiovascular diseases.