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

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.

How Artificial Intelligence Can Enhance the Diagnosis of Cardiac Amyloidosis: A Review of Recent Advances and Challenges

“…Furthermore, AI-ECG models are able to predict CA over six months before clinical diagnosis [11]. Similarly, AI-echocardiography models are highly accurate, with AUCs ranging from 0.84 to 1.00 [28,47,48]. In one study, an AI-echocardiography model outperformed human experts in differentiating CA from other conditions [28].…”

“…A total of 586 patients were used for the final analysis (194 HCM, 201 CA, and 191 HTN/others), with a mean age of 55.0 years. Among the individual view-dependent models used in this study, the A4C model had the best performance (AUC: HCM = 0.94, CA = 0.73, and HTN/other = 0.87) with the final fusion model outperforming all the view-dependent models (AUC: HCM = 0.93, CA = 0.90, and HTN/other = 0.92), indicating the potential of this model in the diagnosis and workup of these pathologies that result in increased left-ventricular wall thickness, including CA [48]. As with the previous study, this study is limited by its single-center and retrospective nature and the possibility of referral bias given that patients were identified at a tertiary referral center; these may limit the potential for the generalization of these results.…”

“…In another single-center study by Li et al, investigators retrospectively studied an echocardiography-based automatic DL framework to differentiate increased LV wall thickness etiologies [48]. A total of 586 patients were used for the final analysis (194 HCM, 201 CA, and 191 HTN/others), with a mean age of 55.0 years.…”

ConFormer: A Novel Collection of Deep Learning Models to Assist Cardiologists in the Assessment of Cardiac Function

“…While most studies use two views, Li et al used six views (AP2, AP3, AP4, PLAX, PSAX-M, PSAX-V) to optimize a pre-trained InceptionResnetV2 model to train a meta-learner under a fusion architecture. They classified important etiologies (HCM, CA and HTN/others) of increased LV wall thickness [18].…”

Multimodality Imaging for Diagnosing Transthyretin Cardiac Amyloidosis

“…However, the noninvasive techniques improve patient acceptance of work-up to diagnose CA. Echocardiography provides clues like increased left ventricular thickness, prompting further investigations [2]. Strain imaging through echocardiography could be useful to know the cause of left ventricular hypertrophy.…”