• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

基于深度特征和局部方向模式技术的新型肥厚型心肌病诊断指标

Novel Hypertrophic Cardiomyopathy Diagnosis Index Using Deep Features and Local Directional Pattern Techniques.

作者信息

Gudigar Anjan, Raghavendra U, Samanth Jyothi, Dharmik Chinmay, Gangavarapu Mokshagna Rohit, Nayak Krishnananda, Ciaccio Edward J, Tan Ru-San, Molinari Filippo, Acharya U Rajendra

机构信息

Department of Instrumentation and Control Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal 576104, India.

Department of Cardiovascular Technology, Manipal College of Health Professions, Manipal Academy of Higher Education, Manipal 576104, India.

出版信息

J Imaging. 2022 Apr 6;8(4):102. doi: 10.3390/jimaging8040102.

DOI:10.3390/jimaging8040102
PMID:35448229
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC9030738/
Abstract

Hypertrophic cardiomyopathy (HCM) is a genetic disorder that exhibits a wide spectrum of clinical presentations, including sudden death. Early diagnosis and intervention may avert the latter. Left ventricular hypertrophy on heart imaging is an important diagnostic criterion for HCM, and the most common imaging modality is heart ultrasound (US). The US is operator-dependent, and its interpretation is subject to human error and variability. We proposed an automated computer-aided diagnostic tool to discriminate HCM from healthy subjects on US images. We used a local directional pattern and the ResNet-50 pretrained network to classify heart US images acquired from 62 known HCM patients and 101 healthy subjects. Deep features were ranked using Student’s t-test, and the most significant feature (SigFea) was identified. An integrated index derived from the simulation was defined as 100·log10(SigFea/2) in each subject, and a diagnostic threshold value was empirically calculated as the mean of the minimum and maximum integrated indices among HCM and healthy subjects, respectively. An integrated index above a threshold of 0.5 separated HCM from healthy subjects with 100% accuracy in our test dataset.

摘要

肥厚型心肌病（HCM）是一种遗传性疾病，临床表现多样，包括猝死。早期诊断和干预可能避免猝死。心脏成像显示的左心室肥厚是HCM的重要诊断标准，最常用的成像方式是心脏超声（US）。超声检查依赖操作者，其解读容易出现人为误差和差异。我们提出了一种自动化计算机辅助诊断工具，用于在超声图像上区分HCM患者和健康受试者。我们使用局部方向模式和预训练的ResNet-50网络对从62例已知HCM患者和101例健康受试者获取的心脏超声图像进行分类。使用学生t检验对深度特征进行排序，确定最显著特征（SigFea）。将模拟得出的综合指数定义为每个受试者的100·log10（SigFea/2），并根据经验分别计算HCM患者和健康受试者中最小和最大综合指数的平均值作为诊断阈值。在我们的测试数据集中，综合指数高于0.5的阈值可将HCM患者与健康受试者准确区分，准确率达100%。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/041d/9030738/c9a692d6b16f/jimaging-08-00102-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/041d/9030738/fd75c1ec85d7/jimaging-08-00102-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/041d/9030738/9d2c7a4443bb/jimaging-08-00102-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/041d/9030738/6a041511a5fa/jimaging-08-00102-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/041d/9030738/48d91684732b/jimaging-08-00102-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/041d/9030738/f74b62da938a/jimaging-08-00102-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/041d/9030738/f252949b5f9f/jimaging-08-00102-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/041d/9030738/4ace9213116f/jimaging-08-00102-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/041d/9030738/5a378182ad29/jimaging-08-00102-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/041d/9030738/0e1c513ff00e/jimaging-08-00102-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/041d/9030738/940b8502c0cb/jimaging-08-00102-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/041d/9030738/53d88ea22663/jimaging-08-00102-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/041d/9030738/b4614caeec4d/jimaging-08-00102-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/041d/9030738/c9a692d6b16f/jimaging-08-00102-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/041d/9030738/fd75c1ec85d7/jimaging-08-00102-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/041d/9030738/9d2c7a4443bb/jimaging-08-00102-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/041d/9030738/6a041511a5fa/jimaging-08-00102-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/041d/9030738/48d91684732b/jimaging-08-00102-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/041d/9030738/f74b62da938a/jimaging-08-00102-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/041d/9030738/f252949b5f9f/jimaging-08-00102-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/041d/9030738/4ace9213116f/jimaging-08-00102-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/041d/9030738/5a378182ad29/jimaging-08-00102-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/041d/9030738/0e1c513ff00e/jimaging-08-00102-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/041d/9030738/940b8502c0cb/jimaging-08-00102-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/041d/9030738/53d88ea22663/jimaging-08-00102-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/041d/9030738/b4614caeec4d/jimaging-08-00102-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/041d/9030738/c9a692d6b16f/jimaging-08-00102-g013.jpg

相似文献

1
Novel Hypertrophic Cardiomyopathy Diagnosis Index Using Deep Features and Local Directional Pattern Techniques.基于深度特征和局部方向模式技术的新型肥厚型心肌病诊断指标
J Imaging. 2022 Apr 6;8(4):102. doi: 10.3390/jimaging8040102.
2
Radiomic Analysis of Myocardial Native T Imaging Discriminates Between Hypertensive Heart Disease and Hypertrophic Cardiomyopathy.心肌固有 T 成像的放射组学分析可区分高血压性心脏病与肥厚型心肌病。
JACC Cardiovasc Imaging. 2019 Oct;12(10):1946-1954. doi: 10.1016/j.jcmg.2018.11.024. Epub 2019 Jan 16.
3
The diagnostic value of multiparameter cardiovascular magnetic resonance for early detection of light-chain amyloidosis from hypertrophic cardiomyopathy patients.多参数心血管磁共振对肥厚型心肌病患者早期检测轻链淀粉样变性的诊断价值。
Front Cardiovasc Med. 2022 Oct 18;9:1017097. doi: 10.3389/fcvm.2022.1017097. eCollection 2022.
4
Gender-specific clinical characteristics of deep Q waves in hypertrophic cardiomyopathy.肥厚型心肌病中深Q波的性别特异性临床特征
Gend Med. 2007 Sep;4(3):274-83. doi: 10.1016/s1550-8579(07)80046-5.
5
Hypertrophic Cardiomyopathy: Genetics, Pathogenesis, Clinical Manifestations, Diagnosis, and Therapy.肥厚型心肌病：遗传学、发病机制、临床表现、诊断与治疗
Circ Res. 2017 Sep 15;121(7):749-770. doi: 10.1161/CIRCRESAHA.117.311059.
6
T1 Mapping in Discrimination of Hypertrophic Phenotypes: Hypertensive Heart Disease and Hypertrophic Cardiomyopathy: Findings From the International T1 Multicenter Cardiovascular Magnetic Resonance Study.T1 Mapping在肥厚型表型鉴别中的应用：高血压性心脏病和肥厚型心肌病：国际T1多中心心血管磁共振研究结果
Circ Cardiovasc Imaging. 2015 Dec;8(12). doi: 10.1161/CIRCIMAGING.115.003285.
7
Prognostic value of intra-left ventricular electromechanical asynchrony in patients with mild hypertrophic cardiomyopathy compared with power athletes.轻度肥厚型心肌病患者与职业运动员相比，左心室内机电失同步的预后价值。
Br J Sports Med. 2006 Mar;40(3):244-50; discussion 244-50. doi: 10.1136/bjsm.2005.022194.
8
Impact of cardiac magnetic resonance on the diagnosis of hypertrophic cardiomyopathy - a 10-year experience with over 1000 patients.心脏磁共振成像对肥厚型心肌病诊断的影响——10 年 1000 多例患者的经验。
Eur Radiol. 2021 Mar;31(3):1194-1205. doi: 10.1007/s00330-020-07207-8. Epub 2020 Sep 2.
9
Intelligent diagnosis of left ventricular hypertrophy using transthoracic echocardiography videos.经胸超声心动图视频左心室肥厚的智能诊断。
Comput Methods Programs Biomed. 2022 Nov;226:107182. doi: 10.1016/j.cmpb.2022.107182. Epub 2022 Oct 12.
10
Genetic diagnosis of hypertrophic cardiomyopathy using mass spectrometry DNA arrays and high resolution melting.使用质谱DNA阵列和高分辨率熔解技术对肥厚型心肌病进行基因诊断。
Rev Port Cardiol. 2011 Jan;30(1):7-18.

引用本文的文献

1
Grid-Based Structural and Dimensional Skin Cancer Classification with Self-Featured Optimized Explainable Deep Convolutional Neural Networks.基于网格的结构化和尺寸皮肤癌分类的自特征优化可解释深度卷积神经网络。
Int J Mol Sci. 2024 Jan 26;25(3):1546. doi: 10.3390/ijms25031546.
2
Automated detection of pain levels using deep feature extraction from shutter blinds-based dynamic-sized horizontal patches with facial images.基于百叶窗式动态尺寸水平斑块和面部图像的深度学习特征提取自动检测疼痛等级。
Sci Rep. 2022 Oct 14;12(1):17297. doi: 10.1038/s41598-022-21380-4.

本文引用的文献

1
A novel augmented deep transfer learning for classification of COVID-19 and other thoracic diseases from X-rays.一种用于从X光片中对新冠肺炎及其他胸部疾病进行分类的新型增强深度迁移学习方法。
Neural Comput Appl. 2021;33(20):14037-14048. doi: 10.1007/s00521-021-06044-0. Epub 2021 Apr 29.
2
A deep learning approach for the automatic recognition of prosthetic mitral valve in echocardiographic images.一种用于在超声心动图像中自动识别人工二尖瓣的深度学习方法。
Comput Biol Med. 2021 Jun;133:104388. doi: 10.1016/j.compbiomed.2021.104388. Epub 2021 Apr 14.
3
Artificial intelligence-based myocardial texture analysis in etiological differentiation of left ventricular hypertrophy.
基于人工智能的心肌纹理分析在左心室肥厚病因鉴别中的应用
Ann Transl Med. 2021 Jan;9(2):108. doi: 10.21037/atm-20-4891.
4
Distinct hypertrophic cardiomyopathy genotypes result in convergent sarcomeric proteoform profiles revealed by top-down proteomics.不同肥厚型心肌病基因型导致的相似肌节蛋白构象表型可通过自上而下的蛋白质组学技术揭示。
Proc Natl Acad Sci U S A. 2020 Oct 6;117(40):24691-24700. doi: 10.1073/pnas.2006764117. Epub 2020 Sep 23.
5
Radiomics in Echocardiography: Deep Learning and Echocardiographic Analysis.超声心动图中的放射组学：深度学习与超声心动图分析。
Curr Cardiol Rep. 2020 Jul 9;22(9):89. doi: 10.1007/s11886-020-01348-4.
6
Evaluation of deep learning detection and classification towards computer-aided diagnosis of breast lesions in digital X-ray mammograms.深度学习在数字乳腺X线摄影中对乳腺病变计算机辅助诊断的检测与分类评估。
Comput Methods Programs Biomed. 2020 Nov;196:105584. doi: 10.1016/j.cmpb.2020.105584. Epub 2020 Jun 4.
7
Hypertrophic cardiomyopathy.肥厚型心肌病
Int J Cardiol Heart Vasc. 2020 Mar 25;27:100503. doi: 10.1016/j.ijcha.2020.100503. eCollection 2020 Apr.
8
Computer-aided diagnosis of congestive heart failure using ECG signals - A review.基于心电图信号的充血性心力衰竭计算机辅助诊断——综述。
Phys Med. 2019 Jun;62:95-104. doi: 10.1016/j.ejmp.2019.05.004. Epub 2019 May 10.
9
Fully Automated Echocardiogram Interpretation in Clinical Practice.临床实践中的全自动超声心动图解读。
Circulation. 2018 Oct 16;138(16):1623-1635. doi: 10.1161/CIRCULATIONAHA.118.034338.
10
Deep Convolutional Neural Networks for breast cancer screening.深度学习卷积神经网络在乳腺癌筛查中的应用。
Comput Methods Programs Biomed. 2018 Apr;157:19-30. doi: 10.1016/j.cmpb.2018.01.011. Epub 2018 Jan 11.