Cargando…

Deep learning-based left ventricular segmentation demonstrates improved performance on respiratory motion-resolved whole-heart reconstructions

INTRODUCTION: Deep learning (DL)-based segmentation has gained popularity for routine cardiac magnetic resonance (CMR) image analysis and in particular, delineation of left ventricular (LV) borders for LV volume determination. Free-breathing, self-navigated, whole-heart CMR exams provide high-resolu...

Descripción completa

Detalles Bibliográficos
Autores principales: Yang, Yitong, Shah, Zahraw, Jacob, Athira J., Hair, Jackson, Chitiboi, Teodora, Passerini, Tiziano, Yerly, Jerome, Di Sopra, Lorenzo, Piccini, Davide, Hosseini, Zahra, Sharma, Puneet, Sahu, Anurag, Stuber, Matthias, Oshinski, John N.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10365088/
https://www.ncbi.nlm.nih.gov/pubmed/37492382
http://dx.doi.org/10.3389/fradi.2023.1144004
_version_ 1785076978529861632
author Yang, Yitong
Shah, Zahraw
Jacob, Athira J.
Hair, Jackson
Chitiboi, Teodora
Passerini, Tiziano
Yerly, Jerome
Di Sopra, Lorenzo
Piccini, Davide
Hosseini, Zahra
Sharma, Puneet
Sahu, Anurag
Stuber, Matthias
Oshinski, John N.
author_facet Yang, Yitong
Shah, Zahraw
Jacob, Athira J.
Hair, Jackson
Chitiboi, Teodora
Passerini, Tiziano
Yerly, Jerome
Di Sopra, Lorenzo
Piccini, Davide
Hosseini, Zahra
Sharma, Puneet
Sahu, Anurag
Stuber, Matthias
Oshinski, John N.
author_sort Yang, Yitong
collection PubMed
description INTRODUCTION: Deep learning (DL)-based segmentation has gained popularity for routine cardiac magnetic resonance (CMR) image analysis and in particular, delineation of left ventricular (LV) borders for LV volume determination. Free-breathing, self-navigated, whole-heart CMR exams provide high-resolution, isotropic coverage of the heart for assessment of cardiac anatomy including LV volume. The combination of whole-heart free-breathing CMR and DL-based LV segmentation has the potential to streamline the acquisition and analysis of clinical CMR exams. The purpose of this study was to compare the performance of a DL-based automatic LV segmentation network trained primarily on computed tomography (CT) images in two whole-heart CMR reconstruction methods: (1) an in-line respiratory motion-corrected (Mcorr) reconstruction and (2) an off-line, compressed sensing-based, multi-volume respiratory motion-resolved (Mres) reconstruction. Given that Mres images were shown to have greater image quality in previous studies than Mcorr images, we hypothesized that the LV volumes segmented from Mres images are closer to the manual expert-traced left ventricular endocardial border than the Mcorr images. METHOD: This retrospective study used 15 patients who underwent clinically indicated 1.5 T CMR exams with a prototype ECG-gated 3D radial phyllotaxis balanced steady state free precession (bSSFP) sequence. For each reconstruction method, the absolute volume difference (AVD) of the automatically and manually segmented LV volumes was used as the primary quantity to investigate whether 3D DL-based LV segmentation generalized better on Mcorr or Mres 3D whole-heart images. Additionally, we assessed the 3D Dice similarity coefficient between the manual and automatic LV masks of each reconstructed 3D whole-heart image and the sharpness of the LV myocardium-blood pool interface. A two-tail paired Student’s t-test (alpha = 0.05) was used to test the significance in this study. RESULTS & DISCUSSION: The AVD in the respiratory Mres reconstruction was lower than the AVD in the respiratory Mcorr reconstruction: 7.73 ± 6.54 ml vs. 20.0 ± 22.4 ml, respectively (n = 15, p-value = 0.03). The 3D Dice coefficient between the DL-segmented masks and the manually segmented masks was higher for Mres images than for Mcorr images: 0.90 ± 0.02 vs. 0.87 ± 0.03 respectively, with a p-value = 0.02. Sharpness on Mres images was higher than on Mcorr images: 0.15 ± 0.05 vs. 0.12 ± 0.04, respectively, with a p-value of 0.014 (n = 15). CONCLUSION: We conclude that the DL-based 3D automatic LV segmentation network trained on CT images and fine-tuned on MR images generalized better on Mres images than on Mcorr images for quantifying LV volumes.
format Online
Article
Text
id pubmed-10365088
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-103650882023-07-25 Deep learning-based left ventricular segmentation demonstrates improved performance on respiratory motion-resolved whole-heart reconstructions Yang, Yitong Shah, Zahraw Jacob, Athira J. Hair, Jackson Chitiboi, Teodora Passerini, Tiziano Yerly, Jerome Di Sopra, Lorenzo Piccini, Davide Hosseini, Zahra Sharma, Puneet Sahu, Anurag Stuber, Matthias Oshinski, John N. Front Radiol Radiology INTRODUCTION: Deep learning (DL)-based segmentation has gained popularity for routine cardiac magnetic resonance (CMR) image analysis and in particular, delineation of left ventricular (LV) borders for LV volume determination. Free-breathing, self-navigated, whole-heart CMR exams provide high-resolution, isotropic coverage of the heart for assessment of cardiac anatomy including LV volume. The combination of whole-heart free-breathing CMR and DL-based LV segmentation has the potential to streamline the acquisition and analysis of clinical CMR exams. The purpose of this study was to compare the performance of a DL-based automatic LV segmentation network trained primarily on computed tomography (CT) images in two whole-heart CMR reconstruction methods: (1) an in-line respiratory motion-corrected (Mcorr) reconstruction and (2) an off-line, compressed sensing-based, multi-volume respiratory motion-resolved (Mres) reconstruction. Given that Mres images were shown to have greater image quality in previous studies than Mcorr images, we hypothesized that the LV volumes segmented from Mres images are closer to the manual expert-traced left ventricular endocardial border than the Mcorr images. METHOD: This retrospective study used 15 patients who underwent clinically indicated 1.5 T CMR exams with a prototype ECG-gated 3D radial phyllotaxis balanced steady state free precession (bSSFP) sequence. For each reconstruction method, the absolute volume difference (AVD) of the automatically and manually segmented LV volumes was used as the primary quantity to investigate whether 3D DL-based LV segmentation generalized better on Mcorr or Mres 3D whole-heart images. Additionally, we assessed the 3D Dice similarity coefficient between the manual and automatic LV masks of each reconstructed 3D whole-heart image and the sharpness of the LV myocardium-blood pool interface. A two-tail paired Student’s t-test (alpha = 0.05) was used to test the significance in this study. RESULTS & DISCUSSION: The AVD in the respiratory Mres reconstruction was lower than the AVD in the respiratory Mcorr reconstruction: 7.73 ± 6.54 ml vs. 20.0 ± 22.4 ml, respectively (n = 15, p-value = 0.03). The 3D Dice coefficient between the DL-segmented masks and the manually segmented masks was higher for Mres images than for Mcorr images: 0.90 ± 0.02 vs. 0.87 ± 0.03 respectively, with a p-value = 0.02. Sharpness on Mres images was higher than on Mcorr images: 0.15 ± 0.05 vs. 0.12 ± 0.04, respectively, with a p-value of 0.014 (n = 15). CONCLUSION: We conclude that the DL-based 3D automatic LV segmentation network trained on CT images and fine-tuned on MR images generalized better on Mres images than on Mcorr images for quantifying LV volumes. Frontiers Media S.A. 2023-06-02 /pmc/articles/PMC10365088/ /pubmed/37492382 http://dx.doi.org/10.3389/fradi.2023.1144004 Text en © 2023 Yang, Shah, Jacob, Hair, Chitiboi, Passerini, Yerly, Di Sopra, Piccini, Hosseini, Sharma, Sahu, Stuber and Oshinski. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) (https://creativecommons.org/licenses/by/4.0/) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Radiology
Yang, Yitong
Shah, Zahraw
Jacob, Athira J.
Hair, Jackson
Chitiboi, Teodora
Passerini, Tiziano
Yerly, Jerome
Di Sopra, Lorenzo
Piccini, Davide
Hosseini, Zahra
Sharma, Puneet
Sahu, Anurag
Stuber, Matthias
Oshinski, John N.
Deep learning-based left ventricular segmentation demonstrates improved performance on respiratory motion-resolved whole-heart reconstructions
title Deep learning-based left ventricular segmentation demonstrates improved performance on respiratory motion-resolved whole-heart reconstructions
title_full Deep learning-based left ventricular segmentation demonstrates improved performance on respiratory motion-resolved whole-heart reconstructions
title_fullStr Deep learning-based left ventricular segmentation demonstrates improved performance on respiratory motion-resolved whole-heart reconstructions
title_full_unstemmed Deep learning-based left ventricular segmentation demonstrates improved performance on respiratory motion-resolved whole-heart reconstructions
title_short Deep learning-based left ventricular segmentation demonstrates improved performance on respiratory motion-resolved whole-heart reconstructions
title_sort deep learning-based left ventricular segmentation demonstrates improved performance on respiratory motion-resolved whole-heart reconstructions
topic Radiology
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10365088/
https://www.ncbi.nlm.nih.gov/pubmed/37492382
http://dx.doi.org/10.3389/fradi.2023.1144004
work_keys_str_mv AT yangyitong deeplearningbasedleftventricularsegmentationdemonstratesimprovedperformanceonrespiratorymotionresolvedwholeheartreconstructions
AT shahzahraw deeplearningbasedleftventricularsegmentationdemonstratesimprovedperformanceonrespiratorymotionresolvedwholeheartreconstructions
AT jacobathiraj deeplearningbasedleftventricularsegmentationdemonstratesimprovedperformanceonrespiratorymotionresolvedwholeheartreconstructions
AT hairjackson deeplearningbasedleftventricularsegmentationdemonstratesimprovedperformanceonrespiratorymotionresolvedwholeheartreconstructions
AT chitiboiteodora deeplearningbasedleftventricularsegmentationdemonstratesimprovedperformanceonrespiratorymotionresolvedwholeheartreconstructions
AT passerinitiziano deeplearningbasedleftventricularsegmentationdemonstratesimprovedperformanceonrespiratorymotionresolvedwholeheartreconstructions
AT yerlyjerome deeplearningbasedleftventricularsegmentationdemonstratesimprovedperformanceonrespiratorymotionresolvedwholeheartreconstructions
AT disopralorenzo deeplearningbasedleftventricularsegmentationdemonstratesimprovedperformanceonrespiratorymotionresolvedwholeheartreconstructions
AT piccinidavide deeplearningbasedleftventricularsegmentationdemonstratesimprovedperformanceonrespiratorymotionresolvedwholeheartreconstructions
AT hosseinizahra deeplearningbasedleftventricularsegmentationdemonstratesimprovedperformanceonrespiratorymotionresolvedwholeheartreconstructions
AT sharmapuneet deeplearningbasedleftventricularsegmentationdemonstratesimprovedperformanceonrespiratorymotionresolvedwholeheartreconstructions
AT sahuanurag deeplearningbasedleftventricularsegmentationdemonstratesimprovedperformanceonrespiratorymotionresolvedwholeheartreconstructions
AT stubermatthias deeplearningbasedleftventricularsegmentationdemonstratesimprovedperformanceonrespiratorymotionresolvedwholeheartreconstructions
AT oshinskijohnn deeplearningbasedleftventricularsegmentationdemonstratesimprovedperformanceonrespiratorymotionresolvedwholeheartreconstructions