Combined conventional factors and the radiomics signature of coronary plaque texture could improve cardiac risk prediction.

OBJECTIVES: This study aims to investigate how radiomics analysis can help understand the association between plaque texture, epicardial adipose tissue (EAT), and cardiovascular risk. Working with a Photon-counting CT, which exhibits enhanced feature stability, offers the potential to advance radiomics analysis and enable its integration into clinical routines. METHODS: Coronary plaques were manually segmented in this retrospective, single-centre study and radiomic features were extracted using pyradiomics. The study population was divided into groups according to the presence of high-risk plaques (HRP), plaques with at least 50% stenosis, plaques with at least 70% stenosis, or triple-vessel disease. A combined group with patients exhibiting at least one of these risk factors was formed. Random forest feature selection identified differentiating features for the groups. EAT thickness and density were measured and compared with feature selection results. RESULTS: A total number of 306 plaques from 61 patients (mean age 61 years +/- 8.85 [standard deviation], 13 female) were analysed. Plaques of patients with HRP features or relevant stenosis demonstrated a higher presence of texture heterogeneity through various radiomics features compared to patients with only an intermediate stenosis degree. While EAT thickness did not significantly differ, affected patients showed significantly higher mean densities in the 50%, HRP, and combined groups, and insignificantly higher densities in the 70% and triple-vessel groups. CONCLUSION: The combination of a higher EAT density and a more heterogeneous plaque texture might offer an additional tool in identifying patients with an elevated risk of cardiovascular events. CLINICAL RELEVANCE STATEMENT: Cardiovascular disease is the leading cause of mortality globally. Plaque composition and changes in the EAT are connected to cardiac risk. A better understanding of the interrelation of these risk indicators can lead to improved cardiac risk prediction. KEY POINTS: Cardiac plaque composition and changes in the EAT are connected to cardiac risk. Higher EAT density and more heterogeneous plaque texture are related to traditional risk indicators. Radiomics texture analysis conducted on PCCT scans can help identify patients with elevated cardiac risk.

Parallel-stream fusion of scan-specific and scan-general priors for learning deep MRI reconstruction in low-data regimes.

Magnetic resonance imaging (MRI) is an essential diagnostic tool that suffers from prolonged scan times. Reconstruction methods can alleviate this limitation by recovering clinically usable images from accelerated acquisitions. In particular, learning-based methods promise performance leaps by employing deep neural networks as data-driven priors. A powerful approach uses scan-specific (SS) priors that leverage information regarding the underlying physical signal model for reconstruction. SS priors are learned on each individual test scan without the need for a training dataset, albeit they suffer from computationally burdening inference with nonlinear networks. An alternative approach uses scan-general (SG) priors that instead leverage information regarding the latent features of MRI images for reconstruction. SG priors are frozen at test time for efficiency, albeit they require learning from a large training dataset. Here, we introduce a novel parallel-stream fusion model (PSFNet) that synergistically fuses SS and SG priors for performant MRI reconstruction in low-data regimes, while maintaining competitive inference times to SG methods. PSFNet implements its SG prior based on a nonlinear network, yet it forms its SS prior based on a linear network to maintain efficiency. A pervasive framework for combining multiple priors in MRI reconstruction is algorithmic unrolling that uses serially alternated projections, causing error propagation under low-data regimes. To alleviate error propagation, PSFNet combines its SS and SG priors via a novel parallel-stream architecture with learnable fusion parameters. Demonstrations are performed on multi-coil brain MRI for varying amounts of training data. PSFNet outperforms SG methods in low-data regimes, and surpasses SS methods with few tens of training samples. On average across tasks, PSFNet achieves 3.1 dB higher PSNR, 2.8% higher SSIM, and 0.3 × lower RMSE than baselines. Furthermore, in both supervised and unsupervised setups, PSFNet requires an order of magnitude lower samples compared to SG methods, and enables an order of magnitude faster inference compared to SS methods. Thus, the proposed model improves deep MRI reconstruction with elevated learning and computational efficiency.

A Transfer-Learning Approach for Accelerated MRI Using Deep Neural Networks.

PURPOSE: Neural networks have received recent interest for reconstruction of undersampled MR acquisitions. Ideally, network performance should be optimized by drawing the training and testing data from the same domain. In practice, however, large datasets comprising hundreds of subjects scanned under a common protocol are rare. The goal of this study is to introduce a transfer-learning approach to address the problem of data scarcity in training deep networks for accelerated MRI. METHODS: Neural networks were trained on thousands (upto 4 thousand) of samples from public datasets of either natural images or brain MR images. The networks were then fine-tuned using only tens of brain MR images in a distinct testing domain. Domain-transferred networks were compared to networks trained directly in the testing domain. Network performance was evaluated for varying acceleration factors (4-10), number of training samples (0.5-4k), and number of fine-tuning samples (0-100). RESULTS: The proposed approach achieves successful domain transfer between MR images acquired with different contrasts (T1 - and T2 -weighted images) and between natural and MR images (ImageNet and T1 - or T2 -weighted images). Networks obtained via transfer learning using only tens of images in the testing domain achieve nearly identical performance to networks trained directly in the testing domain using thousands (upto 4 thousand) of images. CONCLUSION: The proposed approach might facilitate the use of neural networks for MRI reconstruction without the need for collection of extensive imaging datasets.

Spatially informed voxelwise modeling for naturalistic fMRI experiments.

Voxelwise modeling (VM) is a powerful framework to predict single voxel responses evoked by a rich set of stimulus features present in complex natural stimuli. However, because VM disregards correlations across neighboring voxels, its sensitivity in detecting functional selectivity can be diminished in the presence of high levels of measurement noise. Here, we introduce spatially-informed voxelwise modeling (SPIN-VM) to take advantage of response correlations in spatial neighborhoods of voxels. To optimally utilize shared information, SPIN-VM performs regularization across spatial neighborhoods in addition to model features, while still generating single-voxel response predictions. We demonstrated the performance of SPIN-VM on a rich dataset from a natural vision experiment. Compared to VM, SPIN-VM yields higher prediction accuracies and better capture locally congruent information representations across cortex. These results suggest that SPIN-VM offers improved performance in predicting single-voxel responses and recovering coherent information representations.