Feasibility of late gadolinium enhancement (LGE) in ischemic cardiomyopathy using 2D-multisegment LGE combined with artificial intelligence reconstruction deep learning noise reduction algorithm. (15th November 2021)

• Record Type: Journal Article
• Authors: Muscogiuri, Giuseppe; Martini, Chiara; Gatti, Marco; Dell'Aversana, Serena; Ricci, Francesca; Guglielmo, Marco; Baggiano, Andrea; Fusini, Laura; Bracciani, Aurora; Scafuri, Stefano; Andreini, Daniele; Mushtaq, Saima; Conte, Edoardo; Gripari, Paola; Annoni, Andrea Daniele; Formenti, Alberto; Mancini, Maria Elisabetta; Bonfanti, Lorenzo; Guaricci, Andrea Igoren; Janich, Martin A.; Rabbat, Mark G.; Pompilio, Giulio; Pepi, Mauro; Pontone, Gianluca
• Is Part Of: International journal of cardiology. Volume 343(2021)
• Page Start: 164
• Page End: 170
• Publication Date: 2021-11-15
• Subjects: Ischemic cardiomyopathy -- Late gadolinium enhancement -- Image noise -- Artificial intelligence -- Deep learning reconstruction; 2D-MSLGE 2D multiple segmented inversion recovery gradient echo late gadolinium enhancement -- 2D-SSLGE 2D single segmented inversion recovery gradient echo late gadolinium enhancement -- NR artificial intelligence reconstruction deep learning noise reduction -- CMR cardiac magnetic resonance -- CNN convolutional neural network -- CNR contrast to noise ratio -- ICM ischemic cardiomyopathy -- LGE late gadolinium enhancement -- SCMR society of cardiovascular magnetic resonance -- SD standard deviation -- SIC Italian society of cardiology -- SNR signal to noise ratio; Cardiology -- Periodicals; Electronic journals; 616.12
• DOI: 10.1016/j.ijcard.2021.09.012
• Languages: English
• ISSNs: 0167-5273

Abstract

Abstract: Background: Despite the low spatial resolution of 2D-multisegment late gadolinium enhancement (2D-MSLGE) sequences, it may be useful in uncooperative patients instead of standard 2D single segmented inversion recovery gradient echo late gadolinium enhancement sequences (2D-SSLGE). The aim of the study is to assess the feasibility and comparison of 2D-MSLGE reconstructed with artificial intelligence reconstruction deep learning noise reduction (NR) algorithm compared to standard 2D-SSLGE in consecutive patients with ischemic cardiomyopathy (ICM). Methods: Fifty-seven patients with known ICM referred for a clinically indicated CMR were enrolled in this study. 2D-MSLGE were reconstructed using a growing level of NR (0%, 25%, 50%, 75%and 100%). Subjective image quality, signal to noise ratio (SNR) and contrast to noise ratio (CNR) were evaluated in each dataset and compared to standard 2D-SSLGE. Moreover, diagnostic accuracy, LGE mass and scan time were compared between 2D-MSLGE with NR and 2D-SSLGE. Results: The application of NR reconstruction ≥50% to 2D-MSLGE provided better subjective image quality, CNR and SNR compared to 2D-SSLGE ( p < 0.01). The best compromise in terms of subjective and objective image quality was observed for values of 2D-MSLGE 75%, while no differences were found in terms of LGE quantification between 2D-MSLGE versus 2D-SSLGE, regardless the NR applied. The sensitivity, specificity, negative predictive value, positive predictive value and accuracy of 2D-MSLGE NR 75% were 87.77%, 96.27%, 96.13%, 88.16% and 94.22%, respectively. Time of acquisition of 2D-MSLGE was significantly shorter compared to 2D-SSLGE ( p < 0.01). Conclusion: When compared to standard 2D-SSLGE, the application of NR reconstruction to 2D-MSLGE provides superior image quality with similar diagnostic accuracy. Highlights: NR technique improves image quality of late gadolinium enhancement. 2D-MSLGE reconstructed with NR 75% provide better image quality compared to 2D-SSLGE. NR reconstruction on 2D-MSLGE has not impact in terms of diagnostic accuracy.