Background Segmentation of cardiovascular magnetic resonance (CMR) images is an essential step for evaluating dimensional and functional ventricular parameters as ejection fraction (EF) but may be limited by artifacts, which represent the major challenge to automatically derive clinical information. The aim of this study is to investigate the accuracy of a deep learning (DL) approach for automatic segmentation of cardiac structures from CMR images characterized by magnetic susceptibility artifact in patient with cardiac implanted electronic devices (CIED). Methods In this retrospective study, 230 patients (100 with CIED) who underwent clinically indicated CMR were used to developed and test a DL model. A novel convolutional neural network was proposed to extract the left ventricle (LV) and right (RV) ventricle endocardium and LV epicardium. In order to perform a successful segmentation, it is important the network learns to identify salient image regions even during local magnetic field inhomogeneities. The proposed network takes advantage from a spatial attention module to selectively process the most relevant information and focus on the structures of interest. To improve segmentation, especially for images with artifacts, multiple loss functions were minimized in unison. Segmentation results were assessed against manual tracings and commercial CMR analysis software cvi(42)(Circle Cardiovascular Imaging, Calgary, Alberta, Canada). An external dataset of 56 patients with CIED was used to assess model generalizability. Results In the internal datasets, on image with artifacts, the median Dice coefficients for end-diastolic LV cavity, LV myocardium and RV cavity, were 0.93, 0.77 and 0.87 and 0.91, 0.82, and 0.83 in end-systole, respectively. The proposed method reached higher segmentation accuracy than commercial software, with performance comparable to expert inter-observer variability (bias +/- 95%LoA): LVEF 1 +/- 8% vs 3 +/- 9%, RVEF - 2 +/- 15% vs 3 +/- 21%. In the external cohort, EF well correlated with manual tracing (intraclass correlation coefficient: LVEF 0.98, RVEF 0.93). The automatic approach was significant faster than manual segmentation in providing cardiac parameters (approximately 1.5 s vs 450 s). Conclusions Experimental results show that the proposed method reached promising performance in cardiac segmentation from CMR images with susceptibility artifacts and alleviates time consuming expert physician contour segmentation.

Cardiovascular magnetic resonance images with susceptibility artifacts: artificial intelligence with spatial-attention for ventricular volumes and mass assessment / M. Penso, M. Babbaro, S. Moccia, M. Guglielmo, M.L. Carerj, C.M. Giacari, M. Chiesa, R. Maragna, M.G. Rabbat, A. Barison, N. Martini, M. Pepi, E.G. Caiani, G. Pontone. - In: JOURNAL OF CARDIOVASCULAR MAGNETIC RESONANCE. - ISSN 1097-6647. - 24:1(2022 Nov 28), pp. 62.1-62.14. [10.1186/s12968-022-00899-5]

Cardiovascular magnetic resonance images with susceptibility artifacts: artificial intelligence with spatial-attention for ventricular volumes and mass assessment

G. Pontone
Co-ultimo
2022

Abstract

Background Segmentation of cardiovascular magnetic resonance (CMR) images is an essential step for evaluating dimensional and functional ventricular parameters as ejection fraction (EF) but may be limited by artifacts, which represent the major challenge to automatically derive clinical information. The aim of this study is to investigate the accuracy of a deep learning (DL) approach for automatic segmentation of cardiac structures from CMR images characterized by magnetic susceptibility artifact in patient with cardiac implanted electronic devices (CIED). Methods In this retrospective study, 230 patients (100 with CIED) who underwent clinically indicated CMR were used to developed and test a DL model. A novel convolutional neural network was proposed to extract the left ventricle (LV) and right (RV) ventricle endocardium and LV epicardium. In order to perform a successful segmentation, it is important the network learns to identify salient image regions even during local magnetic field inhomogeneities. The proposed network takes advantage from a spatial attention module to selectively process the most relevant information and focus on the structures of interest. To improve segmentation, especially for images with artifacts, multiple loss functions were minimized in unison. Segmentation results were assessed against manual tracings and commercial CMR analysis software cvi(42)(Circle Cardiovascular Imaging, Calgary, Alberta, Canada). An external dataset of 56 patients with CIED was used to assess model generalizability. Results In the internal datasets, on image with artifacts, the median Dice coefficients for end-diastolic LV cavity, LV myocardium and RV cavity, were 0.93, 0.77 and 0.87 and 0.91, 0.82, and 0.83 in end-systole, respectively. The proposed method reached higher segmentation accuracy than commercial software, with performance comparable to expert inter-observer variability (bias +/- 95%LoA): LVEF 1 +/- 8% vs 3 +/- 9%, RVEF - 2 +/- 15% vs 3 +/- 21%. In the external cohort, EF well correlated with manual tracing (intraclass correlation coefficient: LVEF 0.98, RVEF 0.93). The automatic approach was significant faster than manual segmentation in providing cardiac parameters (approximately 1.5 s vs 450 s). Conclusions Experimental results show that the proposed method reached promising performance in cardiac segmentation from CMR images with susceptibility artifacts and alleviates time consuming expert physician contour segmentation.
Cardiac magnetic resonance; Cardiac segmentation; Cardioverter-defibrillators; Deep learning; Pacemaker; Susceptibility artifacts
Settore MED/11 - Malattie dell'Apparato Cardiovascolare
28-nov-2022
Article (author)
File in questo prodotto:
File Dimensione Formato  
Cardiovascular.pdf

accesso aperto

Descrizione: Research
Tipologia: Publisher's version/PDF
Dimensione 2.08 MB
Formato Adobe PDF
2.08 MB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2434/954691
Citazioni
  • ???jsp.display-item.citation.pmc??? 0
  • Scopus 6
  • ???jsp.display-item.citation.isi??? 5
social impact