Validation of deep learning techniques for quality augmentation in diffusion MRI for clinical studies.

The objective of this study is to evaluate the efficacy of deep learning (DL) techniques in improving the quality of diffusion MRI (dMRI) data in clinical applications. The study aims to determine whether the use of artificial intelligence (AI) methods in medical images may result in the loss of critical clinical information and/or the appearance of false information. To assess this, the focus was on the angular resolution of dMRI and a clinical trial was conducted on migraine, specifically between episodic and chronic migraine patients. The number of gradient directions had an impact on white matter analysis results, with statistically significant differences between groups being drastically reduced when using 21 gradient directions instead of the original 61. Fourteen teams from different institutions were tasked to use DL to enhance three diffusion metrics (FA, AD and MD) calculated from data acquired with 21 gradient directions and a b-value of 1000 s/mm2. The goal was to produce results that were comparable to those calculated from 61 gradient directions. The results were evaluated using both standard image quality metrics and Tract-Based Spatial Statistics (TBSS) to compare episodic and chronic migraine patients. The study results suggest that while most DL techniques improved the ability to detect statistical differences between groups, they also led to an increase in false positive. The results showed that there was a constant growth rate of false positives linearly proportional to the new true positives, which highlights the risk of generalization of AI-based tasks when assessing diverse clinical cohorts and training using data from a single group. The methods also showed divergent performance when replicating the original distribution of the data and some exhibited significant bias. In conclusion, extreme caution should be exercised when using AI methods for harmonization or synthesis in clinical studies when processing heterogeneous data in clinical studies, as important information may be altered, even when global metrics such as structural similarity or peak signal-to-noise ratio appear to suggest otherwise.

A microstructure estimation Transformer inspired by sparse representation for diffusion MRI.

Diffusion magnetic resonance imaging (dMRI) is an important tool in characterizing tissue microstructure based on biophysical models, which are typically multi-compartmental models with mathematically complex and highly non-linear forms. Resolving microstructures from these models with conventional optimization techniques is prone to estimation errors and requires dense sampling in the q-space with a long scan time. Deep learning based approaches have been proposed to overcome these limitations. Motivated by the superior performance of the Transformer in feature extraction than the convolutional structure, in this work, we present a learning-based framework based on Transformer, namely, a Microstructure Estimation Transformer with Sparse Coding (METSC) for dMRI-based microstructural parameter estimation. To take advantage of the Transformer while addressing its limitation in large training data requirement, we explicitly introduce an inductive bias-model bias into the Transformer using a sparse coding technique to facilitate the training process. Thus, the METSC is composed with three stages, an embedding stage, a sparse representation stage, and a mapping stage. The embedding stage is a Transformer-based structure that encodes the signal in a high-level space to ensure the core voxel of a patch is represented effectively. In the sparse representation stage, a dictionary is constructed by solving a sparse reconstruction problem that unfolds the Iterative Hard Thresholding (IHT) process. The mapping stage is essentially a decoder that computes the microstructural parameters from the output of the second stage, based on the weighted sum of normalized dictionary coefficients where the weights are also learned. We tested our framework on two dMRI models with downsampled q-space data, including the intravoxel incoherent motion (IVIM) model and the neurite orientation dispersion and density imaging (NODDI) model. The proposed method achieved up to 11.25 folds of acceleration while retaining high fitting accuracy for NODDI fitting, reducing the mean squared error (MSE) up to 70% compared with the previous q-space learning approach. METSC outperformed the other state-of-the-art learning-based methods, including the model-free and model-based methods. The network also showed robustness against noise and generalizability across different datasets. The superior performance of METSC indicates its potential to improve dMRI acquisition and model fitting in clinical applications.

Inversion-Recovery-Prepared Oscillating Gradient Sequence Improves Diffusion-Time Dependency Measurements in the Human Brain.

BACKGROUND: Oscillating gradient diffusion MRI (dMRI) enables measurements at a short diffusion-time (td ), but it is challenging for clinical systems. Particularly, the low b-value and low resolution may give rise to cerebrospinal fluid (CSF) contamination. PURPOSE: To assess the effect of CSF partial volume on td -dMRI measurements and efficacy of inversion-recovery (IR) prepared oscillating and pulsed gradient dMRI sequence to improve td -dMRI measurements in the human brain. STUDY TYPE: Prospective. SUBJECTS: Ten normal volunteers and six glioma patients. FIELD STRENGTH/SEQUENCE: A 3 T; three-dimensional (3D) IR-prepared oscillating gradient-prepared gradient spin-echo (GRASE) and two-dimensional (2D) IR-prepared oscillating gradient echo-planar imaging (EPI) sequences. ASSESSMENT: We assessed the td -dependent patterns of apparent diffusion coefficient (ADC) in several gray and white matter structures, including the hippocampal subfields (head, body, and tail), cortical gray matter, thalamus, and posterior white matter in normal volunteers. Pulsed gradient (0 Hz) and oscillating gradients at frequencies of 20 Hz, 40 Hz, and 60 Hz dMRI were acquired with GRASE and EPI sequences with or without the IR module. We also tested the td -dependency patterns in glioma patients using the EPI sequence with or without the IR module. STATISTICAL TESTS: The differences in ADC across the different td s were compared by one-way ANOVA followed by post hoc pairwise t-tests with Bonferroni correction. RESULTS: In the healthy subjects, brain regions that were possibly contaminated by CSF signals, such as the hippocampus (head, body, and tail) and cortical gray matter, td -dependent ADC changes were only significant with the IR-prepared 2D and 3D sequences but not with the non-IR sequences. In brain glioblastomas patients, significantly higher td -dependence was observed in the tumor region with the IR module than that without IR (slope = 0.0196 µm2 /msec2 vs. 0.0034 µm2 /msec2 ). CONCLUSION: The IR-prepared sequence effectively suppressed the CSF partial volume effect and significantly improved the td -dependent measurements in the human brain. EVIDENCE LEVEL: 1 TECHNICAL EFFICACY: Stage 1.

AFFIRM: Affinity Fusion-Based Framework for Iteratively Random Motion Correction of Multi-Slice Fetal Brain MRI.

Multi-slice magnetic resonance images of the fetal brain are usually contaminated by severe and arbitrary fetal and maternal motion. Hence, stable and robust motion correction is necessary to reconstruct high-resolution 3D fetal brain volume for clinical diagnosis and quantitative analysis. However, the conventional registration-based correction has a limited capture range and is insufficient for detecting relatively large motions. Here, we present a novel Affinity Fusion-based Framework for Iteratively Random Motion (AFFIRM) correction of the multi-slice fetal brain MRI. It learns the sequential motion from multiple stacks of slices and integrates the features between 2D slices and reconstructed 3D volume using affinity fusion, which resembles the iterations between slice-to-volume registration and volumetric reconstruction in the regular pipeline. The method accurately estimates the motion regardless of brain orientations and outperforms other state-of-the-art learning-based methods on the simulated motion-corrupted data, with a 48.4% reduction of mean absolute error for rotation and 61.3% for displacement. We then incorporated AFFIRM into the multi-resolution slice-to-volume registration and tested it on the real-world fetal MRI scans at different gestation stages. The results indicated that adding AFFIRM to the conventional pipeline improved the success rate of fetal brain super-resolution reconstruction from 77.2% to 91.9%.

JNK-dependent phosphorylation and nuclear translocation of EGR-1 promotes cardiomyocyte apoptosis.

Myocardial apoptosis induced by myocardial ischemia and hyperlipemia are the main causes of high mortality of cardiovascular diseases. It is not clear whether there is a common mechanism responsible for these two kinds of cardiomyocyte apoptosis. Previous studies demonstrated that early growth response protein 1 (EGR-1) has a pro-apoptotic effect on cardiomyocytes under various stress conditions. Here, we found that EGR-1 is also involved in cardiomyocyte apoptosis induced by both ischemia and high-fat, but how EGR-1 enters the nucleus and whether nuclear EGR-1 (nEGR-1) has a universal effect on cardiomyocyte apoptosis are still unknown. By analyzing the phosphorylation sites and nucleation information of EGR-1, we constructed different mutant plasmids to confirm that the nucleus location of EGR-1 requires Ser501 phosphorylation and regulated by JNK. Furthermore, the pro-apoptotic effect of nEGR-1 was further explored through genetic methods. The results showed that EGR-1 positively regulates the mRNA levels of apoptosis-related proteins (ATF2, CTCF, HAND2, ELK1), which may be the downstream targets of EGR-1 to promote the cardiomyocyte apoptosis. Our research announced the universal pro-apoptotic function of nEGR-1 and explored the mechanism of its nucleus location in cardiomyocytes, providing a new target for the "homotherapy for heteropathy" to cardiovascular diseases.