Cargando…

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

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...

Descripción completa

Detalles Bibliográficos
Autores principales: Li, James, Chao, Chieh-Ju, Jeong, Jiwoong Jason, Farina, Juan Maria, Seri, Amith R., Barry, Timothy, Newman, Hana, Campany, Megan, Abdou, Merna, O’Shea, Michael, Smith, Sean, Abraham, Bishoy, Hosseini, Seyedeh Maryam, Wang, Yuxiang, Lester, Steven, Alsidawi, Said, Wilansky, Susan, Steidley, Eric, Rosenthal, Julie, Ayoub, Chadi, Appleton, Christopher P., Shen, Win-Kuang, Grogan, Martha, Kane, Garvan C., Oh, Jae K., Patel, Bhavik N., Arsanjani, Reza, Banerjee, Imon
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9964852/
https://www.ncbi.nlm.nih.gov/pubmed/36826967
http://dx.doi.org/10.3390/jimaging9020048
_version_ 1784896611443277824
author Li, James
Chao, Chieh-Ju
Jeong, Jiwoong Jason
Farina, Juan Maria
Seri, Amith R.
Barry, Timothy
Newman, Hana
Campany, Megan
Abdou, Merna
O’Shea, Michael
Smith, Sean
Abraham, Bishoy
Hosseini, Seyedeh Maryam
Wang, Yuxiang
Lester, Steven
Alsidawi, Said
Wilansky, Susan
Steidley, Eric
Rosenthal, Julie
Ayoub, Chadi
Appleton, Christopher P.
Shen, Win-Kuang
Grogan, Martha
Kane, Garvan C.
Oh, Jae K.
Patel, Bhavik N.
Arsanjani, Reza
Banerjee, Imon
author_facet Li, James
Chao, Chieh-Ju
Jeong, Jiwoong Jason
Farina, Juan Maria
Seri, Amith R.
Barry, Timothy
Newman, Hana
Campany, Megan
Abdou, Merna
O’Shea, Michael
Smith, Sean
Abraham, Bishoy
Hosseini, Seyedeh Maryam
Wang, Yuxiang
Lester, Steven
Alsidawi, Said
Wilansky, Susan
Steidley, Eric
Rosenthal, Julie
Ayoub, Chadi
Appleton, Christopher P.
Shen, Win-Kuang
Grogan, Martha
Kane, Garvan C.
Oh, Jae K.
Patel, Bhavik N.
Arsanjani, Reza
Banerjee, Imon
author_sort Li, James
collection PubMed
description 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.
format Online
Article
Text
id pubmed-9964852
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-99648522023-02-26 Developing an Echocardiography-Based, Automatic Deep Learning Framework for the Differentiation of Increased Left Ventricular Wall Thickness Etiologies Li, James Chao, Chieh-Ju Jeong, Jiwoong Jason Farina, Juan Maria Seri, Amith R. Barry, Timothy Newman, Hana Campany, Megan Abdou, Merna O’Shea, Michael Smith, Sean Abraham, Bishoy Hosseini, Seyedeh Maryam Wang, Yuxiang Lester, Steven Alsidawi, Said Wilansky, Susan Steidley, Eric Rosenthal, Julie Ayoub, Chadi Appleton, Christopher P. Shen, Win-Kuang Grogan, Martha Kane, Garvan C. Oh, Jae K. Patel, Bhavik N. Arsanjani, Reza Banerjee, Imon J Imaging Article 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. MDPI 2023-02-18 /pmc/articles/PMC9964852/ /pubmed/36826967 http://dx.doi.org/10.3390/jimaging9020048 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Li, James
Chao, Chieh-Ju
Jeong, Jiwoong Jason
Farina, Juan Maria
Seri, Amith R.
Barry, Timothy
Newman, Hana
Campany, Megan
Abdou, Merna
O’Shea, Michael
Smith, Sean
Abraham, Bishoy
Hosseini, Seyedeh Maryam
Wang, Yuxiang
Lester, Steven
Alsidawi, Said
Wilansky, Susan
Steidley, Eric
Rosenthal, Julie
Ayoub, Chadi
Appleton, Christopher P.
Shen, Win-Kuang
Grogan, Martha
Kane, Garvan C.
Oh, Jae K.
Patel, Bhavik N.
Arsanjani, Reza
Banerjee, Imon
Developing an Echocardiography-Based, Automatic Deep Learning Framework for the Differentiation of Increased Left Ventricular Wall Thickness Etiologies
title Developing an Echocardiography-Based, Automatic Deep Learning Framework for the Differentiation of Increased Left Ventricular Wall Thickness Etiologies
title_full Developing an Echocardiography-Based, Automatic Deep Learning Framework for the Differentiation of Increased Left Ventricular Wall Thickness Etiologies
title_fullStr Developing an Echocardiography-Based, Automatic Deep Learning Framework for the Differentiation of Increased Left Ventricular Wall Thickness Etiologies
title_full_unstemmed Developing an Echocardiography-Based, Automatic Deep Learning Framework for the Differentiation of Increased Left Ventricular Wall Thickness Etiologies
title_short Developing an Echocardiography-Based, Automatic Deep Learning Framework for the Differentiation of Increased Left Ventricular Wall Thickness Etiologies
title_sort developing an echocardiography-based, automatic deep learning framework for the differentiation of increased left ventricular wall thickness etiologies
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9964852/
https://www.ncbi.nlm.nih.gov/pubmed/36826967
http://dx.doi.org/10.3390/jimaging9020048
work_keys_str_mv AT lijames developinganechocardiographybasedautomaticdeeplearningframeworkforthedifferentiationofincreasedleftventricularwallthicknessetiologies
AT chaochiehju developinganechocardiographybasedautomaticdeeplearningframeworkforthedifferentiationofincreasedleftventricularwallthicknessetiologies
AT jeongjiwoongjason developinganechocardiographybasedautomaticdeeplearningframeworkforthedifferentiationofincreasedleftventricularwallthicknessetiologies
AT farinajuanmaria developinganechocardiographybasedautomaticdeeplearningframeworkforthedifferentiationofincreasedleftventricularwallthicknessetiologies
AT seriamithr developinganechocardiographybasedautomaticdeeplearningframeworkforthedifferentiationofincreasedleftventricularwallthicknessetiologies
AT barrytimothy developinganechocardiographybasedautomaticdeeplearningframeworkforthedifferentiationofincreasedleftventricularwallthicknessetiologies
AT newmanhana developinganechocardiographybasedautomaticdeeplearningframeworkforthedifferentiationofincreasedleftventricularwallthicknessetiologies
AT campanymegan developinganechocardiographybasedautomaticdeeplearningframeworkforthedifferentiationofincreasedleftventricularwallthicknessetiologies
AT abdoumerna developinganechocardiographybasedautomaticdeeplearningframeworkforthedifferentiationofincreasedleftventricularwallthicknessetiologies
AT osheamichael developinganechocardiographybasedautomaticdeeplearningframeworkforthedifferentiationofincreasedleftventricularwallthicknessetiologies
AT smithsean developinganechocardiographybasedautomaticdeeplearningframeworkforthedifferentiationofincreasedleftventricularwallthicknessetiologies
AT abrahambishoy developinganechocardiographybasedautomaticdeeplearningframeworkforthedifferentiationofincreasedleftventricularwallthicknessetiologies
AT hosseiniseyedehmaryam developinganechocardiographybasedautomaticdeeplearningframeworkforthedifferentiationofincreasedleftventricularwallthicknessetiologies
AT wangyuxiang developinganechocardiographybasedautomaticdeeplearningframeworkforthedifferentiationofincreasedleftventricularwallthicknessetiologies
AT lestersteven developinganechocardiographybasedautomaticdeeplearningframeworkforthedifferentiationofincreasedleftventricularwallthicknessetiologies
AT alsidawisaid developinganechocardiographybasedautomaticdeeplearningframeworkforthedifferentiationofincreasedleftventricularwallthicknessetiologies
AT wilanskysusan developinganechocardiographybasedautomaticdeeplearningframeworkforthedifferentiationofincreasedleftventricularwallthicknessetiologies
AT steidleyeric developinganechocardiographybasedautomaticdeeplearningframeworkforthedifferentiationofincreasedleftventricularwallthicknessetiologies
AT rosenthaljulie developinganechocardiographybasedautomaticdeeplearningframeworkforthedifferentiationofincreasedleftventricularwallthicknessetiologies
AT ayoubchadi developinganechocardiographybasedautomaticdeeplearningframeworkforthedifferentiationofincreasedleftventricularwallthicknessetiologies
AT appletonchristopherp developinganechocardiographybasedautomaticdeeplearningframeworkforthedifferentiationofincreasedleftventricularwallthicknessetiologies
AT shenwinkuang developinganechocardiographybasedautomaticdeeplearningframeworkforthedifferentiationofincreasedleftventricularwallthicknessetiologies
AT groganmartha developinganechocardiographybasedautomaticdeeplearningframeworkforthedifferentiationofincreasedleftventricularwallthicknessetiologies
AT kanegarvanc developinganechocardiographybasedautomaticdeeplearningframeworkforthedifferentiationofincreasedleftventricularwallthicknessetiologies
AT ohjaek developinganechocardiographybasedautomaticdeeplearningframeworkforthedifferentiationofincreasedleftventricularwallthicknessetiologies
AT patelbhavikn developinganechocardiographybasedautomaticdeeplearningframeworkforthedifferentiationofincreasedleftventricularwallthicknessetiologies
AT arsanjanireza developinganechocardiographybasedautomaticdeeplearningframeworkforthedifferentiationofincreasedleftventricularwallthicknessetiologies
AT banerjeeimon developinganechocardiographybasedautomaticdeeplearningframeworkforthedifferentiationofincreasedleftventricularwallthicknessetiologies