Fully automated AI-based cardiac motion parameter extraction - application to mitral and tricuspid valves on long-axis cine MR images.

PURPOSE: In cardiac MRI, valve motion parameters can be useful for the diagnosis of cardiac dysfunction. In this study, a fully automated AI-based valve tracking system was developed and evaluated on 2- or 4-chamber view cine series on a large cardiac MR dataset. Automatically derived motion parameters include atrioventricular plane displacement (AVPD), velocities (AVPV), mitral or tricuspid annular plane systolic excursion (MAPSE, TAPSE), or longitudinal shortening (LS). METHOD: Two sequential neural networks with an intermediate processing step are applied to localize the target and track the landmarks throughout the cardiac cycle. Initially, a localisation network is used to perform heatmap regression of the target landmarks, such as mitral, tricuspid valve annulus as well as apex points. Then, a registration network is applied to track these landmarks using deformation fields. Based on these outputs, motion parameters were derived. RESULTS: The accuracy of the system resulted in deviations of 1.44 ± 1.32 mm, 1.51 ± 1.46 cm/s, 2.21 ± 1.81 mm, 2.40 ± 1.97 mm, 2.50 ± 2.06 mm for AVPD, AVPV, MAPSE, TAPSE and LS, respectively. Application on a large patient database (N = 5289) revealed a mean MAPSE and LS of 9.5 ± 3.0 mm and 15.9 ± 3.9 % on 2-chamber and 4-chamber views, respectively. A mean TAPSE and LS of 13.4 ± 4.7 mm and 21.4 ± 6.9 % was measured. CONCLUSION: The results demonstrate the versatility of the proposed system for automatic extraction of various valve-related motion parameters.

Ex vivo evaluation of the Ozaki procedure in comparison with the native aortic valve and prosthetic valves.

OBJECTIVES: We investigated the hydrodynamic performance and cusp kinematics of the Ozaki neocuspidized aortic valve in comparison with the native aortic and prosthetic valves in an ex vivo study. METHODS: Native aortic valves of swine hearts were replaced by aortic valve substitutes, and their hydrodynamic performance (effective orifice area and mean pressure gradient) was evaluated in a mock circulation under defined conditions. The following aortic valve substitutes were investigated: native aortic valve, Ozaki valve, Perimount Magna Ease, Trifecta and St. Jude Medical Masters. All prosthetic valves had a labelled size of 21 mm. RESULTS: The Ozaki valve and native aortic valve showed a similar and significantly larger orifice area than all investigated prosthetic valves particularly at high flow rates. There was no significant difference between the Ozaki valve and the native aortic valve. The native aortic valve and Ozaki valve showed a similar increase in orifice area with increasing flow through the valve while prosthetic valves showed a markedly weaker increase. Similarly, the native and Ozaki valve showed a similar increase in mPG with forward flow which was weaker than prosthetic valves. Cusp kinematics were similar between the native and Ozaki valve, whilst prosthetic valves were clearly distinguishable from them. CONCLUSIONS: The Ozaki procedure showed excellent hydrodynamic performance compared to prosthetic valves and showed similar cusp motion characteristics to the native aortic valve. Our results suggest that the Ozaki neocuspidized valve behaves physiologically in many aspects, which may contribute to beneficial clinical outcomes.