Improving Sensitivity of Arterial Spin Labeling Perfusion MRI in Alzheimer's Disease Using Transfer Learning of Deep Learning-Based ASL Denoising.

BACKGROUND: Arterial spin labeling (ASL) perfusion magnetic resonance imaging (MRI) denoising through deep learning (DL) often faces insufficient training data from patients. One solution is to train DL models using healthy subjects' data which are more widely available and transfer them to patients' data. PURPOSE: To evaluate the transferability of a DL-based ASL MRI denoising method (DLASL). STUDY TYPE: Retrospective. SUBJECTS: Four hundred and twenty-eight subjects (189 females) from three cohorts. FIELD STRENGTH/SEQUENCE: 3 T two-dimensional (2D) echo-planar imaging (EPI)-based pseudo-continuous ASL (PCASL) and 2D EPI-based pulsed ASL (PASL) sequences. ASSESSMENT: DLASL was trained using young healthy adults' PCASL data (Dataset 1: 250/30 subjects as training/validation set) and was directly transferred (DTF) to PCASL data from Dataset 2 (45 subjects test set) of normal controls (NC) and Alzheimer's disease (AD) groups. DLASL was fine-tuned (DLASLFT) and tested on PASL data from Dataset 3 (103 subjects test set) of NC and AD. An existing non-DL method (NonDL) was used for comparison. Cerebral blood flow (CBF) images from ASL MRI were compared between NC and AD to assess characteristic hypoperfusion (lower CBF) patterns in AD. CBF image quality and CBF map sensitivity for detecting hypoperfusion using peak t-value and suprathreshold cluster size are outcome measures. STATISTICAL TESTS: Paired t-test, two-sample t-test, one-way analysis of variance, and Tukey honestly significant difference, and linear mixed-effects models were used. P < 0.05 was considered statistically significant. RESULTS: Mean contrast-to-noise ratio (CNR) of Dataset 2 showed that DTF outperformed NonDL (AD: 3.38 vs. 2.64, NC: 3.80 vs. 3.36). On Dataset 3, DLASLFT outperformed NonDL measured by mean CNR (AD: 2.45 vs. 1.87, NC: 2.54 vs. 2.17) and mean radiologic score (2.86 vs. 2.44). Image quality improvement was significant on both test sets. DTF and DLASLFT improved sensitivity for detecting AD-related hypoperfusion patterns compared with NonDL. DATA CONCLUSION: We demonstrated the DLASL's transferability across different ASL sequences and different populations. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY: Stage 2.

Accelerating GluCEST imaging using deep learning for B0 correction.

PURPOSE: Glutamate weighted Chemical Exchange Saturation Transfer (GluCEST) MRI is a noninvasive technique for mapping parenchymal glutamate in the brain. Because of the sensitivity to field (B0 ) inhomogeneity, the total acquisition time is prolonged due to the repeated image acquisitions at several saturation offset frequencies, which can cause practical issues such as increased sensitivity to patient motions. Because GluCEST signal is derived from the small z-spectrum difference, it often has a low signal-to-noise-ratio (SNR). We proposed a novel deep learning (DL)-based algorithm armed with wide activation neural network blocks to address both issues. METHODS: B0 correction based on reduced saturation offset acquisitions was performed for the positive and negative sides of the z-spectrum separately. For each side, a separate deep residual network was trained to learn the nonlinear mapping from few CEST-weighted images acquired at different ppm values to the one at 3 ppm (where GluCEST peaks) in the same side of the z-spectrum. RESULTS: All DL-based methods outperformed the "traditional" method visually and quantitatively. The wide activation blocks-based method showed the highest performance in terms of Structural Similarity Index (SSIM) and peak signal-to-noise ratio (PSNR), which were 0.84 and 25dB respectively. SNR increases in regions of interest were over 8dB. CONCLUSION: We demonstrated that the new DL-based method can reduce the entire GluCEST imaging time by ˜50% and yield higher SNR than current state-of-the-art.

Avatrombopag for the treatment of thrombocytopenia in children's patients following allogeneic hematopoietic stem-cell transplantation: A pilot study.

Thrombocytopenia following allogeneic hematopoietic stem cell transplantation (allo-HSCT) is a common and life-threatening complication. Thus, new prevention and treatment strategies for post-HSCT thrombocytopenia are urgently required. In recent studies, thrombopoietin receptor agonists (TPO-RA) for treating post-HSCT thrombocytopenia indicated efficiency and safety. The improved effect of post-HSCT thrombocytopenia in adults was found in the administration of avatrombopag which was a new TPO-RA. However, there was no relevant study in the children's cohort. Herein, we retrospectively analyzed the effect of avatrombopag in post-HSCT thrombocytopenia in children. As a result, the overall response rate (ORR) and complete response rate (CRR) were 91% and 78%, respectively. Furthermore, both cumulative ORR and CRR were significantly lower in the poor graft function (PGF)/secondary failure of platelet recovery (SFPR) group compared to the engraftment-promotion group (86.7% vs. 100%, p = 0.002 and 65.0% vs. 100%, p < 0.001, respectively). Achieving OR required a median of 16 days in the PGF/SFPR group while 7 days in the engraftment-promotion group (p = 0.003). Grade III-IV acute graft vs. host disease and inadequate megakaryocytes were identified as risk factors of CRR only in univariate analysis (p = 0.03 and p = 0.01, respectively). No severe adverse events were documented. Conclusively, avatrombopag is an alternatively efficient and safe agent for treating post-HSCT thrombocytopenia in children.

Applying Rituximab During the Conditioning Regimen Prevents Epstein-Barr Virus Infection Following Allogeneic Hematopoietic Stem Cell Transplant in a Children's Cohort: A Retrospective Case-Control Study.

INTRODUCTION: Since hematopoietic stem cell transplant (HSCT) is an important therapy for malignant and non-malignant pediatric diseases, improving transplant-related mortality remains a challenge. Currently, rituximab, a monoclonal antibody of anti-CD20, is widely used for several post-HSCT complications. However, few studies have focused on the application of rituximab before HSCT. METHODS: We conducted a retrospective case-control study from January 2019 to July 2021 to determine this effect in a single center. Forty-eight patients were included in the rituximab group, with a one-to-one ratio matched to the control group. RESULTS: Both the occurrence rate and cumulative incidence rate of Epstein-Barr virus (EBV) infection were significantly lower in the rituximab group than in the without-rituximab group (10.4% vs. 33.3%, p = 0.014 and 12.2% vs. 39.3% p = 0.0026, respectively). Furthermore, without the application of rituximab was identified as a risk factor for post-HSCT EBV infection via both univariate [hazard ratio (HR) = 4.17, 95%CI (1.52-11.43), p = 0.005] and multivariate analyses [HR = 4.65, 95%CI (1.66-13.0), p = 0.003]. Although the overall survival (OS) probability of the rituximab group was comparable to the without-rituximab group, a markedly improved OS of the rituximab group was found in the malignant disease subgroup (78.9% vs. 42.1%, p = 0.032). The outcomes of graft-versus-host disease, neutrophil and platelet engraftment, other viral infections, and the reconstitution of lymphocytes showed no significant differences between the two groups. CONCLUSIONS: The administration of rituximab before HSCT may prevent EBV infection following HSCT.

POCS-Augmented CycleGAN for MR Image Reconstruction.

Recent years have seen increased research interest in replacing the computationally intensive Magnetic resonance (MR) image reconstruction process with deep neural networks. We claim in this paper that the traditional image reconstruction methods and deep learning (DL) are mutually complementary and can be combined to achieve better image reconstruction quality. To test this hypothesis, a hybrid DL image reconstruction method was proposed by combining a state-of-the-art deep learning network, namely a generative adversarial network with cycle loss (CycleGAN), with a traditional data reconstruction algorithm: Projection Onto Convex Set (POCS). The output of the first iteration's training results of the CycleGAN was updated by POCS and used as the extra training data for the second training iteration of the CycleGAN. The method was validated using sub-sampled Magnetic resonance imaging data. Compared with other state-of-the-art, DL-based methods (e.g., U-Net, GAN, and RefineGAN) and a traditional method (compressed sensing), our method showed the best reconstruction results.

Mechanisms of Cell Adhesion Molecules in Endocrine-Related Cancers: A Concise Outlook.

Chemotherapy is a critical treatment for endocrine-related cancers; however, chemoresistance and disease recurrence remain a challenge. The interplay between cancer cells and the tumor microenvironment via cell adhesion molecules (CAMs) promotes drug resistance, known as cell adhesion-mediated drug resistance (CAM-DR). CAMs are cell surface molecules that facilitate cell-to-cell or cell-to-extracellular matrix binding. CAMs exert an adhesion effect and trigger intracellular signaling that regulates cancer cell stemness maintenance, survival, proliferation, metastasis, epithelial-mesenchymal transition, and drug resistance. To understand these mechanisms, this review focuses on the role of CD44, cadherins, selectins, and integrins in CAM-DR in endocrine-related cancers.

Features of cytomegalovirus infection and evaluation of cytomegalovirus-specific T cells therapy in children's patients following allogeneic hematopoietic stem cell transplantation: A retrospective single-center study.

Cytomegalovirus (CMV) infection remains a critical cause of mortality after allogeneic hematopoietic stem cell transplantation (allo-HSCT), despite improvement by pre-emptive antivirus treatment. CMV-specific cytotoxic T lymphocytes (CMV-CTL) are universally used and proven well-tolerance after allo-HSCT in adult clinical trials. However, it is not comprehensively evaluated in children's patients. Herein, we conducted a retrospective study to determine the risk factors of CMV infection and evaluation of CMV-CTL in children patients who underwent allo-HSCT. As result, a significantly poor 5-year overall survival was found in the CMV infection group (87.3 vs. 94.6%, p=0.01). Haploidentical HSCT (haplo-HSCT) was identified as an independent risk factor for CMV infection through both univariate and multivariate analyses (p<0.001, p=0.027, respectively). Furthermore, the cumulative incidence of CMV infection was statistically higher in the haplo-HSCT group compared to the HLA-matched donor group (44.2% vs. 21.6%, p<0.001). Finally, the overall response rate of CMV-CTL was 89.7% (26/29 patients) in CMV infection after allo-HSCT. We concluded that CMV infection following allo-HSCT correlated with increased mortality in children's patients, and haplo-HSCT was an independent risk factor for CMV infection. Adoptive CMV-CTL cell therapy was safe and effective in pediatric patients with CMV infection.

Medial septum glutamatergic neurons control wakefulness through a septo-hypothalamic circuit.

The medial septum (MS) is involved in arousal-based behaviors and modulates general anesthesia response. However, the role of MS in wakefulness control remains unknown. Here, combining double fluorescence in situ hybridization and optrode recording, we showed that MS glutamatergic neurons exhibited higher activities preferentially during wakefulness. Activating these neurons, either optogenetically or chemogenetically, strongly promoted wakefulness, mainly through the transition from non-rapid eye movement (NREM) sleep to wakefulness. In contrast, inactivation of these neurons reduced wakefulness by the transition from wakefulness to NREM sleep. Furthermore, both rabies-mediated monosynaptic retrograde and anterograde tracing showed that MS glutamatergic neurons monosynaptically innervated lateral hypothalamus (LH) glutamatergic neurons, which were also wake-active as well as wake-promoting. Activating MS-derived glutamatergic terminals in LH enhanced wakefulness, whereas silencing MS glutamatergic neurons destabilized the wake-active preference of LH glutamatergic neurons. These results reveal a vital role of MS glutamatergic neurons in wakefulness control and depict a novel septo-hypothalamic circuit for wakefulness.

Identification of the significant pathways of Banxia Houpu decoction in the treatment of depression based on network pharmacology.

Banxia Houpu decoction (BXHPD) has been used to treat depression in clinical practice for centuries. However, the pharmacological mechanisms of BXHPD still remain unclear. Network Pharmacology (NP) approach was used to explore the potential molecular mechanisms of BXHPD in treating depression. Potential active compounds of BXHPD were obtained from the Traditional Chinese Medicine Systems Pharmacology Database and Analysis Platform Database. STRING database was used to build a interaction network between the active compounds and target genes associated with depression. The topological features of nodes were visualized and calculated. Significant pathways and biological functions were identified using Gene Ontology and Kyoto Encyclopedia of Genes and Genomes analyses. A total of 44 active compounds were obtained from BXHPD, and 121 potential target genes were considered to be therapeutically relevant. Pathway analysis indicated that MAPK signaling pathway, ErbB signaling pathway, HIF-1 signaling pathway and PI3K-Akt pathway were significant pathways in depression. They were mainly involved in promoting nerve growth and nutrition and alleviating neuroinflammatory conditions. The result provided some potential ways for modern medicine in the treatment of depression.

Denoising arterial spin labeling perfusion MRI with deep machine learning.

PURPOSE: Arterial spin labeling (ASL) perfusion MRI is a noninvasive technique for measuring cerebral blood flow (CBF) in a quantitative manner. A technical challenge in ASL MRI is data processing because of the inherently low signal-to-noise-ratio (SNR). Deep learning (DL) is an emerging machine learning technique that can learn a nonlinear transform from acquired data without using any explicit hypothesis. Such a high flexibility may be particularly beneficial for ASL denoising. In this paper, we proposed and validated a DL-based ASL MRI denoising algorithm (DL-ASL). METHODS: The DL-ASL network was constructed using convolutional neural networks (CNNs) with dilated convolution and wide activation residual blocks to explicitly take the inter-voxel correlations into account, and preserve spatial resolution of input image during model learning. RESULTS: DL-ASL substantially improved the quality of ASL CBF in terms of SNR. Based on retrospective analyses, DL-ASL showed a high potential of reducing 75% of the original acquisition time without sacrificing CBF measurement quality. CONCLUSION: DL-ASL achieved improved denoising performance for ASL MRI as compared with current routine methods in terms of higher PSNR, SSIM and Radiologic scores. With the help of DL-ASL, much fewer repetitions may be prescribed in ASL MRI, resulting in a great reduction of the total acquisition time.

Priors-guided slice-wise adaptive outlier cleaning for arterial spin labeling perfusion MRI.

BACKGROUND: Due to the low signal-to-noise-ratio (SNR) and unavoidable head motions, the pairwise subtraction perfusion signal extraction process in arterial spin labeling (ASL) perfusion MRI can produce extreme outliers. COMPARISON WITH EXISTING METHODS: We previously proposed an adaptive outlier cleaning (AOC) algorithm for ASL MRI. While it performed well even for clinical ASL data, two issues still exist. One is that if the reference is already dominated by noise, outlier cleaning using low correlation with the mean as a rejection criterion will actually reject the less noisy samples but keep the more noisy ones. The other is that it is sub-optimal to reject the entire outlier volumes without considering the quality of each constituent slices. To address both problems, a prior-guided and slice-wise AOC algorithm was proposed in this study. NEW METHODS: The reference of AOC was initiated to be a pseudo cerebral blood flow (CBF) map based on prior knowledge and outlier rejection was performed at each slice. ASL data from the ADNI database (www.adni-info.org) were used to validate the method. Image preprocessing was performed using ASLtbx. RESULTS: The proposed method outperformed the original AOC and SCORE in terms of higher SNR and test-retest stability of the resultant CBF maps. CONCLUSION: ASL CBF can be substantially improved using prior-guided and slice-wise outlier rejection. The proposed method will benefit the ever since increasing ASL user community for both clinical and scientific brain research.