Multimodal data fusion reveals functional and neurochemical correlates of Parkinson's disease.

BACKGROUND: Neurotransmitter deficits and spatial associations among neurotransmitter distribution, brain activity, and clinical features in Parkinson's disease (PD) remain unclear. Better understanding of neurotransmitter impairments in PD may provide potential therapeutic targets. Therefore, we aimed to investigate the spatial relationship between PD-related patterns and neurotransmitter deficits. METHODS: We included 59 patients with PD and 41 age- and sex-matched healthy controls (HCs). The voxel-wise mean amplitude of the low-frequency fluctuation (mALFF) was calculated and compared between the two groups. The JuSpace toolbox was used to test whether spatial patterns of mALFF alterations in patients with PD were associated with specific neurotransmitter receptor/transporter densities. RESULTS: Compared to HCs, patients with PD showed reduced mALFF in the sensorimotor- and visual-related regions. In addition, mALFF alteration patterns were significantly associated with the spatial distribution of the serotonergic, dopaminergic, noradrenergic, glutamatergic, cannabinoid, and acetylcholinergic neurotransmitter systems (p < 0.05, false discovery rate-corrected). CONCLUSIONS: Our results revealed abnormal brain activity patterns and specific neurotransmitter deficits in patients with PD, which may provide new insights into the mechanisms and potential targets for pharmacotherapy.

A ResNet mini architecture for brain age prediction.

The brain presents age-related structural and functional changes in the human life, with different extends between subjects and groups. Brain age prediction can be used to evaluate the development and aging of human brain, as well as providing valuable information for neurodevelopment and disease diagnosis. Many contributions have been made for this purpose, resorting to different machine learning methods. To solve this task and reduce memory resource consumption, we develop a mini architecture of only 10 layers by modifying the deep residual neural network (ResNet), named ResNet mini architecture. To support the ResNet mini architecture in brain age prediction, the brain age dataset (OpenNeuro #ds000228) that consists of 155 study participants (three classes) and the Alzheimer MRI preprocessed dataset that consists of 6400 images (four classes) are employed. We compared the performance of the ResNet mini architecture with other popular networks using the two considered datasets. Experimental results show that the proposed architecture exhibits generality and robustness with high accuracy and less parameter number.

A multi-view fusion lightweight network for CRSwNPs prediction on CT images.

Accurate preoperative differentiation of the chronic rhinosinusitis (CRS) endotype between eosinophilic CRS (eCRS) and non-eosinophilic CRS (non-eCRS) is an important topic in predicting postoperative outcomes and administering personalized treatment. To this end, we have constructed a sinus CT dataset, which comprises CT scan data and pathological biopsy results from 192 patients of chronic rhinosinusitis with nasal polyps (CRSwNP), treated at the Second Affiliated Hospital of Shantou University Medical College between 2020 and 2022. To differentiate CRSwNP endotype on preoperative CT and improve efficiency at the same time, we developed a multi-view fusion model that contains a mini-architecture with each network of 10 layers by modifying the deep residual neural network. The proposed model is trained on a training set and evaluated on a test set. The multi-view deep learning fusion model achieved the area under the receiver-operating characteristics curve (AUC) of 0.991, accuracy of 0.965 and F1-Score of 0.970 in test set. We compared the performance of the mini-architecture with other lightweight networks on the same Sinus CT dataset. The experimental results demonstrate that the developed ResMini architecture contribute to competitive CRSwNP endotype identification modeling in terms of accuracy and parameter number.

NMR and MS reveal characteristic metabolome atlas and optimize esophageal squamous cell carcinoma early detection.

Metabolic changes precede malignant histology. However, it remains unclear whether detectable characteristic metabolome exists in esophageal squamous cell carcinoma (ESCC) tissues and biofluids for early diagnosis. Here, we conduct NMR- and MS-based metabolomics on 1,153 matched ESCC tissues, normal mucosae, pre- and one-week post-operative sera and urines from 560 participants across three hospitals, with machine learning and WGCNA. Aberrations in 'alanine, aspartate and glutamate metabolism' proved to be prevalent throughout the ESCC evolution, consistently identified by NMR and MS, and reflected in 16 serum and 10 urine metabolic signatures in both discovery and validation sets. NMR-based simplified panels of any five serum or urine metabolites outperform clinical serological tumor markers (AUC = 0.984 and 0.930, respectively), and are effective in distinguishing early-stage ESCC in test set (serum accuracy = 0.994, urine accuracy = 0.879). Collectively, NMR-based biofluid screening can reveal characteristic metabolic events of ESCC and be feasible for early detection (ChiCTR2300073613).

Repurposing of the PET Probe Prototype PiB for Label and Radiation-Free CEST MRI Molecular Imaging of Amyloid.

Positron emission tomography (PET) probes are specific and sensitive while suffering from radiation risk. It is worthwhile to explore the chemical emission saturation transfer (CEST) effects of the probe prototypes and repurpose them for CEST imaging to avoid radiation. In this study, we used 11C-PiB as an example of a PET probe for detecting amyloid and tested the feasibility of repurposing this PET probe prototype, PiB, for CEST imaging. After optimizing the parameters through preliminary phantom experiments, we used APP/PS1 transgenic mice and age-matched C57 mice for in vivo CEST magnetic resonance imaging (MRI) of amyloid. Furthermore, the pathological assessment was conducted on the same brain slices to evaluate the correlation between the CEST MRI signal abnormality and ß-amyloid deposition detected by immunohistochemical staining. In our results, the Z-spectra revealed an apparent CEST effect that peaked at approximately 6 ppm. APP/PS1 mice as young as 9 months injected with PiB showed a significantly higher CEST effect compared to the control groups. The hyperintense region was correlated with the Aß deposition shown by pathological staining. In conclusion, repurposing the PET probe prototype for CEST MRI imaging is feasible and enables label- and radiation-free detection of the amyloid while maintaining the sensitivity and specificity of the ligand. This study opens the door to developing CEST probes based on PET probe prototypes.

Imaging of brain clearance pathways via MRI assessment of the glymphatic system.

Glymphatic clearance dysfunction may play an important role in a variety of neurodegenerative diseases and the progression of ageing. However, in vivo imaging of the glymphatic system is challenging. In this study, we describe an MRI method based on chemical exchange saturation transfer (CEST) of the Angiopep-2 probe to visualize the clearance function of the glymphatic system. We injected rats with Angiopep-2 via the tail vein and performed in vivo MRI at 7 T to track differences in Angiopep-2 signal changes; we then applied the same principles in a bilateral deep cervical lymph node ligation rat model and in ageing rats. We demonstrated the feasibility of Angiopep-2 CEST for visualizing the clearance function of the glymphatic system. Finally, a pathological assessment was performed. Within the model group, the deep cervical lymph node ligation group and the ageing group showed higher CEST signal than the control group. We conclude that this new MRI method can visualize clearance in the glymphatic system.

γ-Aminobutyric acid as a biomarker of the lateralizing and monitoring drug effect in patients with magnetic resonance imaging-negative temporal lobe epilepsy.

Introduction: Despite verifying proton magnetic resonance spectroscopy (1H-MRS) for focal localization in magnetic resonance imaging (MRI)-negative temporal lobe epilepsy (TLE), it is necessary to illustrate metabolic changes and screen for effective biomarkers for monitoring therapeutic effect. We used 1H-MRS to investigate the role of metabolic levels in MRI-negative TLE. Materials and methods: Thirty-seven patients (n = 37, 14 women) and 20 healthy controls (n = 20, 11 women) were investigated by 1H-MRS. We compared the metabolite level changes in the epileptic and contralateral sides on the mesial temporal and dorsolateral prefrontal cortices and analyzed their association with clinical symptoms. Results: γ-Aminobutyric acid (GABA) levels were significantly lower on the epileptic side (2.292 ± 0.890) than in the contralateral side (2.662 ± 0.742, p = 0.029*) in patients on the mesial temporal lobe. N-acetylaspartate (NAA) levels were significantly lower on the epileptic side (7.284 ± 1.314) than on the contralateral side (7.655 ± 1.549, p = 0.034*). NAA + N-acetylaspartylglutamate levels were significantly lower on the epileptic side (7.668 ± 1.406) than on the contralateral side (8.086 ± 1.675, p = 0.032*). Glutamate levels were significantly lower on the epileptic side (7.773 ± 1.428) than on the contralateral side (8.245 ± 1.616, p = 0.040*). Moreover, a significant negative correlation was found between GABA levels in the epileptic mesial temporal lobe and tonic-clonic seizure frequency (r = -0.338, p = 0.046*). Conclusion: γ-Aminobutyric acid (GABA) is a potential biomarker for lateralization and monitoring seizure frequency in MRI-negative TLE.

Role of Imaging Modalities and N-Acetylcysteine Treatment in Sepsis-Associated Encephalopathy.

Sepsis-associated encephalopathy is a severe systemic infection complication. Although early stages involve pathophysiological changes, detection using conventional imaging is challenging. Glutamate chemical exchange saturation transfer and diffusion kurtosis imaging can noninvasively investigate cellular and molecular events in early disease stages using magnetic resonance imaging (MRI). N-Acetylcysteine, an antioxidant and precursor of glutathione, regulates neurotransmitter glutamate metabolism and participates in neuroinflammation. We investigated the protective role of n-acetylcysteine in sepsis-associated encephalopathy using a rat model and monitored changes in brain using magnetic resonance (MR) molecular imaging. Bacterial lipopolysaccharide was injected intraperitoneally to induce a sepsis-associated encephalopathy model. Behavioral performance was assessed using the open-field test. Tumor necrosis factor α and glutathione levels were detected biochemically. Imaging was performed using a 7.0-T MRI scanner. Protein expression, cellular damage, and changes in blood-brain barrier permeability were assessed using western blotting, pathological staining, and Evans blue staining, respectively. Lipopolysaccharide-induced rats showed reduced anxiety and depression after treatment with n-acetylcysteine. MR molecular imaging can identify pathological processes at different disease stages. Furthermore, rats treated with n-acetylcysteine showed increased glutathione levels and decreased tumor necrosis factor α, suggesting enhanced antioxidant capacity and inhibition of inflammatory processes, respectively. Western blot analysis showed reduced expression of nuclear factor kappa B (p50) protein after treatment, suggesting that n-acetylcysteine inhibits inflammation via this signaling pathway. Finally, n-acetylcysteine-treated rats showed reduced cellular damage by pathology and reduced extravasation of their blood-brain barrier by Evans Blue staining. Thus, n-acetylcysteine might be a therapeutic option for sepsis-associated encephalopathy and other neuroinflammatory diseases. Furthermore, noninvasive "dynamic visual monitoring" of physiological and pathological changes related to sepsis-associated encephalopathy was achieved using MR molecular imaging for the first time, providing a more sensitive imaging basis for early diagnosis, identification, and prognosis.

Neurochemical and microstructural alterations in bipolar and depressive disorders: A multimodal magnetic resonance imaging study.

Aims: Depression in bipolar disorder (BD) is often misdiagnosed as unipolar depression (UD), leading to mistreatments and poor clinical outcomes in many bipolar patients. Herein, we report direct comparisons between medication-free patients with BD and those with UD in terms of the microstructure and neurometabolites in eight brain regions. Methods: A total of 20 patients with BD, 30 with UD patients, and 20 matched healthy controls (HCs) underwent 3.0T magnetic resonance imaging with chemical exchange saturation transfer (CEST) for glutamate (Glu; GluCEST) imaging, multivoxel magnetic resonance spectroscopy, and diffusion kurtosis imaging. Results: Compared with HCs, patients with UD showed significantly lower levels of multiple metabolites, GluCEST% values, and diffusional kurtosis [mean kurtosis (MK)] values in most brain regions. In contrast, patients with BD presented significantly higher levels of Glu in their bilateral ventral prefrontal white matter (VPFWM), higher choline (Cho)-containing compounds in their left VPFWM and anterior cingulate cortex (ACC), and higher GluCEST% values in their bilateral VPFWM and ACC; moreover, reduced MK in these patients was more prominent in the left VPFWM and left thalamus. Conclusion: The findings demonstrated that both patients with UD and BD have abnormal microstructure and metabolic alterations, and the changes are not completely consistent in the prefrontal lobe region. Elevated Glu, Cho, and GluCEST% in the ACC and VPFWM of patients with UD and BD may help in differentiating between these two disorders. Our findings support the significance for the microstructural integrity and brain metabolic changes of the prefrontal lobe region in BD and UD.

Deep learning to reconstruct quasi-steady-state chemical exchange saturation transfer from a non-steady-state experiment.

The insufficiently long RF saturation duration and relaxation delay in chemical exchange saturation transfer (CEST)-MRI experiments may result in underestimation of CEST measurements. To maintain the CEST effect without prolonging the saturation duration and reach quasi-steady state (QUASS), a deep learning method was developed to reconstruct a QUASS CEST image pixel by pixel from non-steady-state CEST acquired in experiments. In this work, we established a tumor-bearing rat model on a 7 T horizontal bore small-animal MRI scanner, allowing ground-truth generation, after which a bidirectional long short-term memory network was formulated and trained on simulated CEST Z-spectra to reconstruct the QUASS CEST; finally, the ground truth yielded by experiments was used to evaluate the performance of the reconstruction model by comparing the estimates with the ground truth. For quantitation evaluation, linear regression analysis, structural similarity index (SSIM) and peak signal-to-noise ratio (peak SNR) were used to assess the proposed model in the QUASS CEST reconstruction. In the linear regression analysis of in vivo data, the coefficient of determination for six different representative frequency offsets was at least R2 = 0.9521. Using the SSIM and peak SNR as evaluation metrics, the reconstruction accuracies of in vivo QUASS CEST were found to be 0.9991 and 46.7076, respectively. Experimental results demonstrate that the proposed model provides a robust and accurate solution for QUASS CEST reconstruction using a deep learning mechanism.

Efficacy and safety of proton beam therapy for rhabdomyosarcoma: a systematic review and meta-analysis.

OBJECTIVE: This study aimed to evaluate and conduct a meta-analysis on the efficacy and safety of proton beam therapy (PBT) for rhabdomyosarcoma (RMS). METHODS: We searched for articles using PubMed, Embase, Cochrane Library, and Web of Science databases from their inception to December 22, 2022. Two researchers independently screened literature and extracted data. Statistical analyses were performed using STATA version 14.0. RESULTS: We got 675 candidate articles, of which 11 studies were included in our study according to the inclusion and exclusion criteria. Of the 544 RMS patients who received PBT. The local control (LC) rate at 1, 2, 3, 4, and 5 years were 96% (95% confidence interval (CI) 0.91-1.01), 93% (95% CI 0.86-1.00), 78% (95% CI 0.71-0.85), 85% (95% CI 0.78-0.92), and 84% (95% CI 0.74-0.95), respectively. The progression-free survival (PFS) rate at 1, 2, 3, 4, and 5 years were 82% (95% CI 0.72-0.92), 73% (95% CI 0.61-0.84), 63% (95% CI 0.47-0.79), 64% (95% CI 0.54-0.74), and 76% (95% CI 0.59-0.94), respectively. The overall survival (OS) rate at 1, 2, 3, 4, and 5 years were 93% (95% CI 0.86-1.00), 85% (95% CI 0.76-0.95), 80% (95% CI 0.63-0.96), 71% (95% CI 0.62-0.80), and 82% (95% CI 0.71-0.94), respectively. Acute and late toxicities were mainly grades 1 to 2 in all studies. CONCLUSION: As an advantageous RT technique, PBT is an emerging option for patients with RMS, particularly children and adolescents patients. The data showed that PBT is a feasible, safe, and effective modality for RMS, showing promising LC, OS, PFS, and lower acute and late toxicities. PROSPERO registration number: CRD42022329154.

Quantitative morphometric changes in vascular mild cognitive impairment patients: early diagnosis of dementia.

Vascular mild cognitive impairment (VMCI) is an early and reversible stage of dementia. Volume differences in regional gray matter may reveal the development and prognosis of VMCI. This study selected 2 of the most common types of VMCI, namely, periventricular white matter hyperintensities (PWMH, n = 14) and strategic single infarctions (SSI, n = 10), and used the voxel-based morphometry method to quantify their morphological characteristics. Meanwhile, age- and sex-matched healthy volunteers were included (n = 16). All the participants were neuropsychologically tested to characterize their cognitive function and underwent whole-brain magnetic resonance imaging scanning. Our results showed that the volumes of the bilateral temporal lobes and bilateral frontal gray matter were obviously diminished in the PWMH group. The atrophy volume difference was 4,086 voxels in the left temporal lobe, 4,154 voxels in the right temporal lobe, 1,718 voxels in the left frontal lobe, and 1,141 voxels in the right frontal lobe (P ≤ 0.001). Moreover, the characteristics of the gray matter atrophy associated with the PWMH were more similar to those associated with Alzheimer's disease than SSI, which further revealed the susceptibility for escalation from PWMH to dementia. In conclusion, PWMH patients and SSI patients have different morphological characteristics, which explain the different prognoses of VMCI.

Angiopep-2, an MRI Biomarker, Dynamically Monitors Amyloid Deposition in Early Alzheimer's Disease.

The reliable and dynamic detection of amyloid ß-protein (Aß) deposition using imaging technology is necessary for preclinical Alzheimer's disease (AD), which may significantly improve prognosis. The present study aimed to evaluate the feasibility of applying angiopep-2 (ANG), a chemical exchange saturation transfer-magnetic resonance imaging (CEST-MRI) biomarker, for monitoring Aß deposition in vivo. ANG exerted a good chemical exchange saturation transfer (CEST) effect and displayed a moderate binding affinity to Aß1-42 in vitro. Six-month-old mice with AD injected with ANG exhibited a significantly enhanced CEST effect than controls in vivo; this effect gradually became more apparent at 8, 10, and 12 months. Spatial learning impairment caused by abundant Aß deposition (representing mild cognitive impairment in AD patients) develops at 12 months in APPswe/PSEN1dE9 (line 85) AD mice. To conclude, the CEST of ANG could display very earlier age-related Aß pathological progress in mice with AD, consistent with immunohistochemistry. ANG has extraordinary potential for clinical transformation as an imaging biomarker to diagnose early AD and track its progress dynamically and nonradiationally.

Voxel-based morphometry and a deep learning model for the diagnosis of early Alzheimer's disease based on cerebral gray matter changes.

This study aimed to analyse cerebral grey matter changes in mild cognitive impairment (MCI) using voxel-based morphometry and to diagnose early Alzheimer's disease using deep learning methods based on convolutional neural networks (CNNs) evaluating these changes. Participants (111 MCI, 73 normal cognition) underwent 3-T structural magnetic resonance imaging. The obtained images were assessed using voxel-based morphometry, including extraction of cerebral grey matter, analyses of statistical differences, and correlation analyses between cerebral grey matter and clinical cognitive scores in MCI. The CNN-based deep learning method was used to extract features of cerebral grey matter images. Compared to subjects with normal cognition, participants with MCI had grey matter atrophy mainly in the entorhinal cortex, frontal cortex, and bilateral frontotemporal lobes (p < 0.0001). This atrophy was significantly correlated with the decline in cognitive scores (p < 0.01). The accuracy, sensitivity, and specificity of the CNN model for identifying participants with MCI were 80.9%, 88.9%, and 75%, respectively. The area under the curve of the model was 0.891. These findings demonstrate that research based on brain morphology can provide an effective way for the clinical, non-invasive, objective evaluation and identification of early Alzheimer's disease.

3.0 T multi-parametric MRI reveals metabolic and microstructural abnormalities in the posterior visual pathways in patients with thyroid eye disease.

Introduction: We aim to explore the microstructural and metabolic changes in visual pathways in patients with thyroid eye disease (TED) using 3T multi-parametric MRI. Methods: Thirty-four TED patients (inactive group = 20; active group = 14; acute group = 18; chronic group = 16) and 12 healthy controls (HC) were recruited from November 2020 to July 2021. Proton magnetic resonance spectroscopy (1H-MRS), glutamate chemical exchange saturation transfer (GluCEST) and diffusion kurtosis imaging (DKI) were performed on 3.0T MR scanner. Data analysis and group comparisons were performed after MR data processing. Results: As compare to HC group, the levels of total choline (tCh) in optic radiation (OR) in active group ([1.404 ± 0.560] vs. [1.022 ± 0.260]; p < 0.05), together with tCh ([1.415 ± 0.507] vs. [1.022 ± 0.260]; p < 0.05) in OR in acute group were significantly increased. Glutamine (Gln) levels were higher in OR in the chronic group than those in HCs and were positively correlated with the levels of thyroglobulin antibody (TgAb), thyroid peroxidase antibody (TPOAb), free triiodothyronine (FT3) and FT4 in chronic group. Glutamate (Glu) levels by 1H-MRS did not show significant differences between any two groups. Interestingly, MTRasym (3.0 ppm) was higher in OL in inactive group, active group, acute group and chronic group than those in HCs, and was positively correlated with Glu levels in OL in 1H-MRS. Fractional anisotropy (FA) values from DKI in OR in acute group were significantly lower than those in HCs. Discussion: Our initial study demonstrate that GluCEST performs better than 1H-MRS to monitor Glu alterations in visual pathway in TED patients. Changes of brain glutamine levels in TED patients are closely related to their associated hormones alterations, indicating that disease injury status could be reflected through non-invasive metabolites detection by brain 1H-MRS. FA is the most sensitive DKI index to reveal the visual pathway impairment in TED patients. Altogether, our study revealed that 3T multiparametric MR techniques are useful to demonstrate metabolic and microstructural alterations in visual pathways in TED patients. We found that damage to visual pathways occurs in mild TED cases, which not only offers a new approach to the diagnosis of dysthyroid optic neuropathy, but also demonstrates neuropathy in TED is a gradual and continuous spatio-emporal progression.

Deep learning for dense Z-spectra reconstruction from CEST images at sparse frequency offsets.

A direct way to reduce scan time for chemical exchange saturation transfer (CEST)-magnetic resonance imaging (MRI) is to reduce the number of CEST images acquired in experiments. In some scenarios, a sufficient number of CEST images acquired in experiments was needed to estimate parameters for quantitative analysis, and this prolonged the scan time. For that, we aim to develop a general deep-learning framework to reconstruct dense CEST Z-spectra from experimentally acquired images at sparse frequency offsets so as to reduce the number of experimentally acquired CEST images and achieve scan time reduction. The main innovation works are outlined as follows: (1) a general sequence-to-sequence (seq2seq) framework is proposed to reconstruct dense CEST Z-spectra from experimentally acquired images at sparse frequency offsets; (2) we create a training set from wide-ranging simulated Z-spectra instead of experimentally acquired CEST data, overcoming the limitation of the time and labor consumption in manual annotation; (3) a new seq2seq network that is capable of utilizing information from both short-range and long-range is developed to improve reconstruction ability. One of our intentions is to establish a simple and efficient framework, i.e., traditional seq2seq can solve the reconstruction task and obtain satisfactory results. In addition, we propose a new seq2seq network that includes the short- and long-range ability to boost dense CEST Z-spectra reconstruction. The experimental results demonstrate that the considered seq2seq models can accurately reconstruct dense CEST images from experimentally acquired images at 11 frequency offsets so as to reduce the scan time by at least 2/3, and our new seq2seq network contributes to competitive advantage.

Amide Proton Transfer-Weighted Imaging Detects Hippocampal Proteostasis Disturbance Induced by Sleep Deprivation at 7.0 T MRI.

Sleep deprivation leads to hippocampal injury. Proteostasis disturbance is an important mechanism linking sleep deprivation and hippocampal injury. However, identifying noninvasive imaging biomarkers for hippocampal proteostasis disturbance remains challenging. Amide proton transfer-weighted (APTw) imaging is a chemical exchange saturation transfer technique based on the amide protons in proteins and peptides. We aimed to explore the ability of APTw imaging in detecting sleep deprivation-induced hippocampal proteostasis disturbance and its biological significance, as well as its biological basis. In vitro, the feasibility of APTw imaging in detecting changes of the protein state was evaluated, demonstrating that APTw imaging can detect alterations in the protein concentration, conformation, and aggregation state. In vivo, the hippocampal APTw signal declined with increased sleep deprivation time and was significantly lower in sleep-deprived rats than that in normal rats. This signal was positively correlated with the number of surviving neurons counted in Nissl staining and negatively correlated with the expression of glucose-regulated protein 78 evaluated in immunohistochemistry. Differentially expressed proteins in proteostasis network pathways were identified in the hippocampi of normal rats and sleep-deprived rats via mass spectrometry proteomics analysis, providing the biological basis for the change of the hippocampal APTw signal in sleep-deprived rats. These findings demonstrate that APTw imaging can detect hippocampal proteostasis disturbance induced by sleep deprivation and reflect the extent of neuronal injury and endoplasmic reticulum stress.

Automated detection of intracranial artery stenosis and occlusion in magnetic resonance angiography: A preliminary study based on deep learning.

BACKGROUND AND OBJECTIVES: Intracranial atherosclerotic stenosis of a major intracranial artery is the common cause of ischemic stroke. We evaluate the feasibility of using deep learning to automatically detect intracranial arterial steno-occlusive lesions from time-of-flight magnetic resonance angiography. METHODS: In a retrospective study, magnetic resonance images with radiological reports of intracranial arterial stenosis and occlusion were extracted. The images were randomly divided into a training set and a test set. The manual annotation of lesions with a bounding box labeled "moderate stenosis," "severe stenosis," "occlusion," and "absence of signal" was considered as ground truth. A deep learning algorithm based on you only look once version 5 (YOLOv5) detection model was developed with the training set, and its sensitivity and positive predictive values to detect lesions were evaluated in the test set. RESULTS: A dataset of 200 examinations consisted of a total of 411 lesions-242 moderate stenoses, 84 severe stenoses, 70 occlusions, and 15 absence of signal. The magnetic resonance images contained 291 lesions in the training set and 120 lesions in the test set. The sensitivity and positive predictive values were 64.2 and 83.7%, respectively. The detection sensitivity in relation to the location was greatest in the internal carotid artery (86.2%). CONCLUSIONS: Applying deep learning algorithms in the automated detection of intracranial arterial steno-occlusive lesions from time-of-flight magnetic resonance angiography is feasible and has great potential.

Combined Application of Quantitative Susceptibility Mapping and Diffusion Kurtosis Imaging Techniques to Investigate the Effect of Iron Deposition on Microstructural Changes in the Brain in Parkinson's Disease.

Objectives: Brain iron deposition and microstructural changes in brain tissue are associated with Parkinson's disease (PD). However, the correlation between these factors in Parkinson's disease has been little studied. This study aimed to use quantitative susceptibility mapping combined with diffusion kurtosis imaging to investigate the effects of iron deposition on microstructural tissue alterations in the brain. Methods: Quantitative susceptibility mapping and diffusion kurtosis imaging were performed on 24 patients with early PD, 13 patients with advanced PD, and 25 healthy controls. The mean values of magnetic susceptibility and diffusion kurtosis were calculated for the bilateral substantia nigra, red nucleus, putamen, globus pallidus, and caudate nucleus, and compared between the groups. Correlation analyses between the diffusion kurtosis of each nucleus and its magnetic susceptibility parameters in PD patients and healthy controls were performed. Results: The study found a significant increase in iron deposition in the substantia nigra, red nucleus, putamen and globus pallidus, bilaterally, in patients with PD. Mean kurtosis values were increased in the substantia nigra but decreased in the globus pallidus; axial kurtosis values were decreased in both the substantia nigra and red nucleus; radial kurtosis values were increased in the substantia nigra but showed an opposite trend in the globus pallidus and caudate nucleus. In the substantia nigra of patients with PD, magnetic susceptibility was positively correlated with mean and radial kurtosis values, and negatively correlated with axial kurtosis. None of these correlations were significantly different in the control group. In the putamen, magnetic susceptibility was positively correlated with mean, axial, and radial kurtosis only in patients with advanced-stage PD. Conclusion: Our study provides new evidence for brain iron content and microstructural alterations in patients with PD. Iron deposition may be a common mechanism for microstructural alterations in the substantia nigra and putamen of patients with PD. Tracking the dynamic changes in iron content and microstructure throughout the course of PD will help us to better understand the dynamics of iron metabolism and microstructural alterations in the pathogenesis of PD and to develop new approaches to monitor and treat PD.