TY - JOUR
T1 - Developing an Echocardiography-Based, Automatic Deep Learning Framework for the Differentiation of Increased Left Ventricular Wall Thickness Etiologies
AU - Li, James
AU - Chao, Chieh Ju
AU - Jeong, Jiwoong Jason
AU - Farina, Juan Maria
AU - Seri, Amith R.
AU - Barry, Timothy
AU - Newman, Hana
AU - Campany, Megan
AU - Abdou, Merna
AU - O’Shea, Michael
AU - Smith, Sean
AU - Abraham, Bishoy
AU - Hosseini, Seyedeh Maryam
AU - Wang, Yuxiang
AU - Lester, Steven
AU - Alsidawi, Said
AU - Wilansky, Susan
AU - Steidley, Eric
AU - Rosenthal, Julie
AU - Ayoub, Chadi
AU - Appleton, Christopher P
AU - Shen, Win-Kuang
AU - Grogan, Martha
AU - Kane, Garvan C.
AU - Oh, Jae K.
AU - Patel, Bhavik N.
AU - Arsanjani, Reza
AU - Banerjee, Imon
N1 - Publisher Copyright:
© 2023 by the authors.
PY - 2023/2
Y1 - 2023/2
N2 - 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.
AB - 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.
KW - deep learning
KW - echocardiography
KW - LV wall thickness
UR - http://www.scopus.com/inward/record.url?scp=85148697479&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85148697479&partnerID=8YFLogxK
U2 - 10.3390/jimaging9020048
DO - 10.3390/jimaging9020048
M3 - Article
AN - SCOPUS:85148697479
SN - 2313-433X
VL - 9
JO - Journal of Imaging
JF - Journal of Imaging
IS - 2
M1 - 48
ER -