Deep Learning Image Reconstruction Algorithm for CCTA: Image Quality Assessment and Clinical Application.

OBJECTIVE: The increasing number of coronary computed tomography angiography (CCTA) requests raised concerns about dose exposure. New dose reduction strategies based on artificial intelligence have been proposed to overcome limitations of iterative reconstruction (IR) algorithms. Our prospective study sought to explore the added value of deep-learning image reconstruction (DLIR) in comparison with a hybrid IR algorithm (adaptive statistical iterative reconstruction-veo [ASiR-V]) in CCTA, even in clinical challenging scenarios, as obesity, heavily calcified vessels and coronary stents. METHODS: We prospectively included 103 consecutive patients who underwent CCTA. Data sets were reconstructed with ASiR-V and DLIR. For each reconstruction signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) was calculated, and qualitative assessment was made with a four-point Likert scale by two independent and blinded radiologists with different expertise. RESULTS: Both SNR and CNR were significantly higher in DLIR (SNR-DLIR median value [interquartile range] of 13.89 [11.06-16.35] and SNR-ASiR-V 25.42 [22.46-32.22], P < 0.001; CNR-DLIR 16.84 [9.83-27.08] vs CNR-ASiR-V 10.09 [5.69-13.5], P < 0.001).Median qualitative score was 4 for DLIR images versus 3 for ASiR-V ( P < 0.001), with a good interreader reliability [intraclass correlation coefficient(2,1)e intraclass correlation coefficient(3,1) 0.60 for DLIR and 0.62 and 0.73 for ASiR-V].In the obese and in the "calcifications and stents" groups, DLIR showed significantly higher values of SNR (24.23 vs 11.11, P < 0.001 and 24.55 vs 14.09, P < 0.001, respectively) and CNR (16.08 vs 8.04, P = 0.008 and 17.31 vs 10.14, P = 0.003) and image quality. CONCLUSIONS: Deep-learning image reconstruction in CCTA allows better SNR, CNR, and qualitative assessment than ASiR-V, with an added value in the most challenging clinical scenarios.

Multi-modality Imaging Evaluation of a Rare and Complex Case of Single Ventricle Physiology; the important role of Cardiac MR.

Congenital heart diseases (CHD) represent a major clinical and diagnostic challenge for correct abnormality identification and subsequent successful therapy; even more challenging is following-up patient health after multiple post-interventional corrections often required in complex cardio-vascular abnormalities. We describe a multi-modality imaging evaluation of a complex congenital cardio-vascular diseases, underlining the relevance of cardiac magnetic resonance to non invasively solve some issues related to postsurgical changes.

Vieussens' ring coronary collateral circulation: a natural bypass history.

"Vieussens' ring" or "arterial circle of Vieussens" is a crucial hetero-coronaric pathway, bridging proximal right coronary artery (RCA) and left anterior descending artery (LAD) when a hemodynamically stenosis is established in the either of the vessel. In detail such coronary collateral circulation is usually supplied by branches of the conus artery. We present a case of a 62-year-old man who was admitted to our emergency department complaining of chest pain. Coronary angiography showed LAD occlusion at the mid tract with delayed and slight opacification of its distal segment sustained by Vieussens' ring. Coronary computed tomography angiography (CCTA) was subsequently performed which confirmed the presence of such natural bypass and evaluated its relationship with adjacent structures. Imaging, particularly CCTAoffers a valid tool in assessing the hetero-coronaric collateral vessel. Due to its high spatial resolution it may provide many information about the coronary anatomy by delineating their origin, course and termination.

Aliased Flow Signal Planimetry by Cardiovascular Magnetic Resonance Imaging for Grading Aortic Stenosis Severity: A Prospective Pilot Study.

Objectives: Transthoracic echocardiography (TTE) is the standard technique for assessing aortic stenosis (AS), with effective orifice area (EOA) recommended for grading severity. EOA is operator-dependent, influenced by a number of pitfalls and requires multiple measurements introducing independent and random sources of error. We tested the diagnostic accuracy and precision of aliased orifice area planimetry (AOAcmr), a new, simple, non-invasive technique for grading of AS severity by low-VENC phase-contrast cardiovascular magnetic resonance (CMR) imaging. Methods: Twenty-two consecutive patients with mild, moderate, or severe AS and six age- and sex-matched healthy controls had TTE and CMR examinations on the same day. We performed analysis of agreement and correlation among (i) AOAcmr; (ii) geometric orifice area (GOAcmr) by direct CMR planimetry; (iii) EOAecho by TTE-continuity equation; and (iv) the "gold standard" multimodality EOA (EOAhybrid) obtained by substituting CMR LVOT area into Doppler continuity equation. Results: There was excellent pairwise positive linear correlation among AOAcmr, EOAhybrid, GOAcmr, and EOAecho (p < 0.001); AOAcmr had the highest correlation with EOAhybrid (R 2 = 0.985, p < 0.001). There was good agreement between methods, with the lowest bias (0.019) for the comparison between AOAcmr and EOAhybrid. AOAcmr yielded excellent intra- and inter-rater reliability (intraclass correlation coefficient: 0.997 and 0.998, respectively). Conclusions: Aliased orifice area planimetry by 2D phase contrast imaging is a simple, reproducible, accurate "one-stop shop" CMR method for grading AS, potentially useful when echocardiographic severity assessment is inconclusive or discordant. Larger studies are warranted to confirm and validate these promising preliminary results.