The importance of identifying functional Val158Met polymorphism in catechol-O- Methyltransferase when assessing MRI-based volumetric measurements in major depressive disorder

Gray Matter Volume Abnormality in Chronic Pain Patients With Depressive Symptoms: A Systemic Review and Meta-Analysis of Voxel-Based Morphometry Studies

Background

Gray matter volume (GMV) alteration in specific brain regions has been widely regarded as one of the most important neuroplasticity features in chronic pain patients with depressive symptoms (CP-D). However, the consistent and significant results were still lacking. Thus, further exploration was suggested to be performed.

Objectives

This study aimed to comprehensively collect the voxel-based morphometry (VBM) studies on GMV alteration between CP-D and healthy controls (HCs). And a systemic review and meta-analysis were made to explore the characteristic brain regions in chronic pain and depression comorbidity.

Methods

Search of PubMed, MEDLINE, Web of Science, and Cochrane Library databases updated to July 13, 2021. The altered GMV between CP-D and HCs in VBM studies was included in this meta-analysis. In total, 18 studies (20 datasets) and 1320 participants (520 patients and 800 HCs) were included. The significant coordinate information (x, y, z) reported in standard space and the effect size (t-value or z-score) were extracted and analyzed by anisotropic effect size-signed differential mapping (AES-SDM) 5.15 software.

Results

According to the main analysis results, CP-D showed significant and consistent increased GMV in the left hippocampus (HIP. L) and decreased GMV in the medial part of the left superior frontal gyrus (SFG. L, BA 10) compared to HCs. Subgroup analysis showed significant decreased GMV in the medial orbital part of SFG.R (BA 10) in neuropathic pain, as well as significant increased GMV in the right parahippocampal gyrus (PHG.R, BA 35), left hippocampus (HIP.L, BA 20), and right middle frontal gyrus (MFG.R) in musculoskeletal pain. Furthermore, meta-regression showed a positive relationship between the decreased GMV in the medial part of SFG.L and the percentage of female patients.

Conclusion

GMV abnormality in specific brain areas (e.g., HIP.L and SFG) was robust and reproducible, which could be significantly involved in this comorbidity disease. The findings in this study may be a valuable reference for future research.

Systematic Review Registration

[www.crd.york.ac.uk/prospero/].

Full-count PET recovery from low-count image using a dilated convolutional neural network

PURPOSE

Positron emission tomography (PET) is an essential technique in many clinical applications that allows for quantitative imaging at the molecular level. This study aims to develop a denoising method using a novel dilated convolutional neural network (CNN) to recover full-count images from low-count images.

METHODS

We adopted similar hierarchical structures as the conventional U-Net and incorporated dilated kernels in each convolution to allow the network to observe larger, more robust features within the image without the requirement of downsampling and upsampling internal representations. Our dNet was trained alongside a U-Net for comparison. Both models were evaluated using a leave-one-out cross-validation procedure on a dataset of 35 subjects (~3500 slabs), which were obtained from an ongoing ¹⁸ F-Fluorodeoxyglucose (FDG) study. Low-count PET data (10% count) were generated by randomly selecting one-tenth of all events in the associated listmode file. Analysis was done on the static image from the last 10 minutes of emission data. Both low-count PET and full-count PET were reconstructed using ordered subset expectation maximization (OSEM). Objective image quality metrics, including mean absolute percent error (MAPE), peak signal-to-noise ratio (PSNR), and structural similarity index metric (SSIM), were used to analyze the deep learning methods. Both deep learning methods were further compared to a traditional Gaussian filtering method. Further, region of interest (ROI) quantitative analysis was also used to compare U-Net and dNet architectures.

RESULTS

Both the U-Net and our proposed network were successfully trained to synthesize full-count PET images from the generated low-count PET images. Compared to low-count PET and Gaussian filtering, both deep learning methods improved MAPE, PSNR, and SSIM. Our dNet also systematically outperformed U-Net on all three metrics (MAPE: 4.99 ± 0.68 vs 5.31 ± 0.76, P < 0.01; PSNR: 31.55 ± 1.31 dB vs 31.05 ± 1.39, P < 0.01; SSIM: 0.9513 ± 0.0154 vs 0.9447 ± 0.0178, P < 0.01). ROI quantification showed greater quantitative improvements using dNet over U-Net.

CONCLUSION

This study proposed a novel approach of using dilated convolutions for recovering full-count PET images from low-count PET images.