StrainNet: Improved Myocardial Strain Analysis of Cine MRI by Deep Learning from DENSE.

Purpose: To develop a three-dimensional (two dimensions + time) convolutional neural network trained with displacement encoding with stimulated echoes (DENSE) data for displacement and strain analysis of cine MRI. Materials and Methods: In this retrospective multicenter study, a deep learning model (StrainNet) was developed to predict intramyocardial displacement from contour motion. Patients with various heart diseases and healthy controls underwent cardiac MRI examinations with DENSE between August 2008 and January 2022. Network training inputs were a time series of myocardial contours from DENSE magnitude images, and ground truth data were DENSE displacement measurements. Model performance was evaluated using pixelwise end-point error (EPE). For testing, StrainNet was applied to contour motion from cine MRI. Global and segmental circumferential strain (Ecc) derived from commercial feature tracking (FT), StrainNet, and DENSE (reference) were compared using intraclass correlation coefficients (ICCs), Pearson correlations, Bland-Altman analyses, paired t tests, and linear mixed-effects models. Results: The study included 161 patients (110 men; mean age, 61 years ± 14 [SD]), 99 healthy adults (44 men; mean age, 35 years ± 15), and 45 healthy children and adolescents (21 males; mean age, 12 years ± 3). StrainNet showed good agreement with DENSE for intramyocardial displacement, with an average EPE of 0.75 mm ± 0.35. The ICCs between StrainNet and DENSE and FT and DENSE were 0.87 and 0.72, respectively, for global Ecc and 0.75 and 0.48, respectively, for segmental Ecc. Bland-Altman analysis showed that StrainNet had better agreement than FT with DENSE for global and segmental Ecc. Conclusion: StrainNet outperformed FT for global and segmental Ecc analysis of cine MRI.Keywords: Image Postprocessing, MR Imaging, Cardiac, Heart, Pediatrics, Technical Aspects, Technology Assessment, Strain, Deep Learning, DENSE Supplemental material is available for this article. © RSNA, 2023.

Novel insights into in-vivo diffusion tensor cardiovascular magnetic resonance using computational modeling and a histology-based virtual microstructure.

PURPOSE: To develop histology-informed simulations of diffusion tensor cardiovascular magnetic resonance (DT-CMR) for typical in-vivo pulse sequences and determine their sensitivity to changes in extra-cellular space (ECS) and other microstructural parameters. METHODS: We synthesised the DT-CMR signal from Monte Carlo random walk simulations. The virtual tissue was based on porcine histology. The cells were thickened and then shrunk to modify ECS. We also created idealised geometries using cuboids in regular arrangement, matching the extra-cellular volume fraction (ECV) of 16-40%. The simulated voxel size was 2.8 × 2.8 × 8.0 mm3 for pulse sequences covering short and long diffusion times: Stejskal-Tanner pulsed-gradient spin echo, second-order motion-compensated spin echo, and stimulated echo acquisition mode (STEAM), with clinically available gradient strengths. RESULTS: The primary diffusion tensor eigenvalue increases linearly with ECV at a similar rate for all simulated geometries. Mean diffusivity (MD) varies linearly, too, but is higher for the substrates with more uniformly distributed ECS. Fractional anisotropy (FA) for the histology-based geometry is higher than the idealised geometry with low sensitivity to ECV, except for the long mixing time of the STEAM sequence. Varying the intra-cellular diffusivity (DIC ) results in large changes of MD and FA. Varying extra-cellular diffusivity or using stronger gradients has minor effects on FA. Uncertainties of the primary eigenvector orientation are reduced using STEAM. CONCLUSIONS: We found that the distribution of ECS has a measurable impact on DT-CMR parameters. The observed sensitivity of MD and FA to ECV and DIC has potentially interesting applications for interpreting in-vivo DT-CMR parameters.

Assessment of Myocardial Microstructural Dynamics by In Vivo Diffusion Tensor Cardiac Magnetic Resonance.

BACKGROUND: Cardiomyocytes are organized in microstructures termed sheetlets that reorientate during left ventricular thickening. Diffusion tensor cardiac magnetic resonance (DT-CMR) may enable noninvasive interrogation of in vivo cardiac microstructural dynamics. Dilated cardiomyopathy (DCM) is a condition of abnormal myocardium with unknown sheetlet function. OBJECTIVES: This study sought to validate in vivo DT-CMR measures of cardiac microstructure against histology, characterize microstructural dynamics during left ventricular wall thickening, and apply the technique in hypertrophic cardiomyopathy (HCM) and DCM. METHODS: In vivo DT-CMR was acquired throughout the cardiac cycle in healthy swine, followed by in situ and ex vivo DT-CMR, then validated against histology. In vivo DT-CMR was performed in 19 control subjects, 19 DCM, and 13 HCM patients. RESULTS: In swine, a DT-CMR index of sheetlet reorientation (E2A) changed substantially (E2A mobility ∼46°). E2A changes correlated with wall thickness changes (in vivo r2 = 0.75; in situ r2 = 0.89), were consistently observed under all experimental conditions, and accorded closely with histological analyses in both relaxed and contracted states. The potential contribution of cyclical strain effects to in vivo E2A was ∼17%. In healthy human control subjects, E2A increased from diastole (18°) to systole (65°; p < 0.001; E2A mobility = 45°). HCM patients showed significantly greater E2A in diastole than control subjects did (48°; p < 0.001) with impaired E2A mobility (23°; p < 0.001). In DCM, E2A was similar to control subjects in diastole, but systolic values were markedly lower (40°; p < 0.001) with impaired E2A mobility (20°; p < 0.001). CONCLUSIONS: Myocardial microstructure dynamics can be characterized by in vivo DT-CMR. Sheetlet function was abnormal in DCM with altered systolic conformation and reduced mobility, contrasting with HCM, which showed reduced mobility with altered diastolic conformation. These novel insights significantly improve understanding of contractile dysfunction at a level of noninvasive interrogation not previously available in humans.

Beat-to-beat respiratory motion correction with near 100% efficiency: a quantitative assessment using high-resolution coronary artery imaging.

This study quantitatively assesses the effectiveness of retrospective beat-to-beat respiratory motion correction (B2B-RMC) at near 100% efficiency using high-resolution coronary artery imaging. Three-dimensional (3D) spiral images were obtained in a coronary respiratory motion phantom with B2B-RMC and navigator gating. In vivo, targeted 3D coronary imaging was performed in 10 healthy subjects using B2B-RMC spiral and navigator gated balanced steady-state free-precession (nav-bSSFP) techniques. Vessel diameter and sharpness in proximal and mid arteries were used as a measure of respiratory motion compensation effectiveness and compared between techniques. Phantom acquisitions with B2B-RMC were sharper than those acquired with navigator gating (B2B-RMC vs. navigator gating: 1.01±0.02 mm(-1) vs. 0.86±0.08 mm(-1), P<.05). In vivo B2B-RMC respiratory efficiency was significantly and substantially higher (99.7%±0.5%) than nav-bSSFP (44.0%±8.9%, P<.0001). Proximal and mid vessel sharpnesses were similar (B2B-RMC vs. nav-bSSFP, proximal: 1.00±0.14 mm(-1) vs. 1.08±0.11 mm(-1), mid: 1.01±0.11 mm(-1) vs. 1.05±0.12 mm(-1); both P=not significant [ns]). Mid vessel diameters were not significantly different (2.85±0.39 mm vs. 2.80±0.35 mm, P=ns), but proximal B2B-RMC diameters were slightly higher (2.85±0.38 mm vs. 2.70±0.34 mm, P<.05), possibly due to contrast differences. The respiratory efficiency of B2B-RMC is less variable and significantly higher than navigator gating. Phantom and in vivo vessel sharpness and diameter values suggest that respiratory motion compensation is equally effective.

Syrian hamster embryo (SHE) assay (pH 6.7) coupled with infrared spectroscopy and chemometrics towards toxicological assessment.

The Syrian hamster embryo (SHE) assay (pH 6.7) is an in vitro candidate to replace in vivo carcinogenicity tests. However, the conventional method of visual scoring of foci (non-transformed vs. transformed colonies) can be time-consuming and is open to subjectivity. Infrared (IR) spectroscopy has the potential to provide objective assessment of such SHE colonies with the added advantage of potentially providing mechanistic information. In this study, SHE cells were treated with one of eight different chemical regimens, allowed in culture to attach and form foci on IR-reflective glass slides; these were subsequently interrogated by attenuated total reflection (ATR) Fourier-transform IR (FTIR) spectroscopy. Derived mid-IR spectra (n = 13,406) were subjected to chemometric analysis focusing primarily on the extraction of biochemical information related to test agent treatment and/or morphological transformation. The use of ATR-FTIR spectroscopy with chemometrics to analyze the SHE assay is a novel approach to toxicological assessment.

Interlaboratory assessment of the GreenScreen HC GADD45a-GFP genotoxicity screening assay: an enabling study for independent validation as an alternative method.

Sixteen coded compounds were blind-tested at 4 laboratories using the recently described GADD45a-GFP genotoxicity assay. The compounds were chosen to include non-genotoxic compounds as well as weak and strong genotoxins. None of the compounds required metabolic activation in order to exhibit genotoxic effects. The participating laboratories included 2 global pharmaceutical companies, a global consumer goods company and the Gentronix laboratory in Manchester. Each compound was tested 4 times on different days following a protocol previously described. The tests were carried out after a 3-day training period from the parent lab (Manchester). Following the exclusion of data from tests with positive control failures and data series with 'spikes', 92% of assays gave the correct result: non-genotoxins giving negative results and genotoxins giving positive results. There were no randomly distributed problems suggesting that differences between the results from different sites reflected the use of different instruments, procedural differences and operator experience. In naïve operator laboratories the quality of data improved with operator practice. It was concluded that simple clarification of the protocol would provide the level of reliability required for widespread use of the assay in hazard assessment.