Quantification of viable left atrial (LA) tissue is a reliable information which should be used to support therapy selection in atrial fibrillation (AF) patients. Late gadolinium-enhanced magnetic resonance imaging (LGE-MRI) is employed for the non-invasive assessment of LA fibrotic tissue. Unfortunately, the analysis of LGE-MRI relies on manual tracing of LA boundaries. This task is time-consuming and prone to high inter-observer variability. Therefore, an automatic approach for LA wall detection would be very helpful. In this study, we compared the performance of different deep architectures - U-Net and attention U-Net (AttnU-Net) - and different loss functions - Dice loss (DL) and focal Tversky loss (FTL) to automatically detect LA boundaries from LGE-MRI data. In addition, AttnU-Net was trained without deep supervision (DS) and multi-scale inputs (MI), with DS and with DS+MI. No statistically significant differences were found training the networks with DL or FTL. U-Net was the best-performing algorithm overall, outperforming significantly AttnU-Net with a Dice Coefficient of 0.9015±0.0308 (mean ± standard deviation). However, no significant differences were found between U-Net and AttnU-Net DS/DS+MI. Based on these results, using a DL or FTL does not affect the performance and U-Net was the best-performing solution.

Borra D., Portas D., Andalo A., Fabbri C., Corsi C. (2020). Performance Comparison of Deep Learning Approaches for Left Atrium Segmentation from LGE-MRI Data. IEEE Computer Society [10.22489/CinC.2020.306].

Performance Comparison of Deep Learning Approaches for Left Atrium Segmentation from LGE-MRI Data

Borra D.;Fabbri C.;Corsi C.
2020

Abstract

Quantification of viable left atrial (LA) tissue is a reliable information which should be used to support therapy selection in atrial fibrillation (AF) patients. Late gadolinium-enhanced magnetic resonance imaging (LGE-MRI) is employed for the non-invasive assessment of LA fibrotic tissue. Unfortunately, the analysis of LGE-MRI relies on manual tracing of LA boundaries. This task is time-consuming and prone to high inter-observer variability. Therefore, an automatic approach for LA wall detection would be very helpful. In this study, we compared the performance of different deep architectures - U-Net and attention U-Net (AttnU-Net) - and different loss functions - Dice loss (DL) and focal Tversky loss (FTL) to automatically detect LA boundaries from LGE-MRI data. In addition, AttnU-Net was trained without deep supervision (DS) and multi-scale inputs (MI), with DS and with DS+MI. No statistically significant differences were found training the networks with DL or FTL. U-Net was the best-performing algorithm overall, outperforming significantly AttnU-Net with a Dice Coefficient of 0.9015±0.0308 (mean ± standard deviation). However, no significant differences were found between U-Net and AttnU-Net DS/DS+MI. Based on these results, using a DL or FTL does not affect the performance and U-Net was the best-performing solution.
2020
Computing in Cardiology
1
4
Borra D., Portas D., Andalo A., Fabbri C., Corsi C. (2020). Performance Comparison of Deep Learning Approaches for Left Atrium Segmentation from LGE-MRI Data. IEEE Computer Society [10.22489/CinC.2020.306].
Borra D.; Portas D.; Andalo A.; Fabbri C.; Corsi C.
File in questo prodotto:
Eventuali allegati, non sono esposti

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/11585/811120
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 1
social impact