Developing an Echocardiography-Based, Automatic Deep Learning Framework for the Differentiation of Increased Left Ventricular Wall Thickness Etiologies

Abstract

Aims Increased 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 to 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: CA: 0.90, HCM: 0.93, 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.

Echocardiography-Based Deep Learning Model to Differentiate Constrictive Pericarditis and Restrictive Cardiomyopathy

“…Deep learning models could be overfitted when only a small sample size is available for training 20 . To address the training sample size limitation in diseases with a lower prevalence, our group proposed a frame-based approach for echocardiography data augmentation 21 . In this work, we proposed a relatively simple deep learning approach based on the standard apical 4 chambers (A4C) TTE view to differentiate CP from RCM since A4C view shows ventricular septal motion, mitral annulus motion, and left ventricular filling pattern.…”

Challenges and solutions of echocardiography generalization for deep learning: a study in patients with constrictive pericarditis

“…Transthoracic echocardiography (TTE) is one of the most widely available imaging modalities in clinical cardiology, and it has been used as the first-line screening tool in various cardiac conditions 1 – 5 In addition to its availability, TTE has the advantages of having a high temporal resolution and being radiation free. Despite its importance in TTE echo studies for clinical phenotyping, there is also significant variance in the human interpretation of echocardiogram images that could impact diagnosis and clinical care.…”