Developing an Echocardiography-Based, Automatic Deep Learning Framework for the Differentiation of Increased Left Ventricular Wall Thickness Etiologies
-
Published:2023-02-18
Issue:2
Volume:9
Page:48
-
ISSN:2313-433X
-
Container-title:Journal of Imaging
-
language:en
-
Short-container-title:J. Imaging
Author:
Li James12, Chao Chieh-Ju3ORCID, Jeong Jiwoong Jason12, Farina Juan Maria1ORCID, Seri Amith R.1, Barry Timothy1ORCID, Newman Hana1, Campany Megan1, Abdou Merna1, O’Shea Michael1, Smith Sean1ORCID, Abraham Bishoy1, Hosseini Seyedeh Maryam1, Wang Yuxiang1, Lester Steven1, Alsidawi Said1ORCID, Wilansky Susan1, Steidley Eric1, Rosenthal Julie1, Ayoub Chadi1, Appleton Christopher P.1, Shen Win-Kuang1, Grogan Martha3, Kane Garvan C.3, Oh Jae K.3, Patel Bhavik N.1, Arsanjani Reza1ORCID, Banerjee Imon12
Affiliation:
1. Mayo Clinic Arizona, Scottsdale, AZ 85054, USA 2. School of Computing and Augmented Intelligence, Arizona State University, Phoenix, AZ 85281, USA 3. Mayo Clinic Rochester, Rochester, MN 55905, USA
Abstract
Aims:Increased left ventricular (LV) wall thickness is frequently encountered in transthoracic echocardiography (TTE). While accurate and early diagnosis is clinically important, given the differences in available therapeutic options and prognosis, an extensive workup is often required to establish the diagnosis. We propose the first echo-based, automated deep learning model with a fusion architecture to facilitate the evaluation and diagnosis of increased left ventricular (LV) wall thickness. Methods and Results: Patients with an established diagnosis of increased LV wall thickness (hypertrophic cardiomyopathy (HCM), cardiac amyloidosis (CA), and hypertensive heart disease (HTN)/others) between 1/2015 and 11/2019 at Mayo Clinic Arizona were identified. The cohort was divided into 80%/10%/10% for training, validation, and testing sets, respectively. Six baseline TTE views were used to optimize a pre-trained InceptionResnetV2 model. Each model output was used to train a meta-learner under a fusion architecture. Model performance was assessed by multiclass area under the receiver operating characteristic curve (AUROC). A total of 586 patients were used for the final analysis (194 HCM, 201 CA, and 191 HTN/others). The mean age was 55.0 years, and 57.8% were male. Among the individual view-dependent models, the apical 4-chamber model had the best performance (AUROC: HCM: 0.94, CA: 0.73, and HTN/other: 0.87). The final fusion model outperformed all the view-dependent models (AUROC: HCM: 0.93, CA: 0.90, and HTN/other: 0.92). Conclusion: The echo-based InceptionResnetV2 fusion model can accurately classify the main etiologies of increased LV wall thickness and can facilitate the process of diagnosis and workup.
Subject
Electrical and Electronic Engineering,Computer Graphics and Computer-Aided Design,Computer Vision and Pattern Recognition,Radiology, Nuclear Medicine and imaging
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|