OBJECTIVE: To explore the brain effect mechanism and the correlation between brain functional imaging and cognitive function in treatment of depressive disorder (DD) with transcutaneous auricular vagus nerve stimulation (taVNS) based on the resting-state functional magenetic reasonance imaging (rs-fMRI). METHODS: Thirty-two DD patients were included in a depression group and 32 subjects of healthy condition were enrolled in a normal group. In the depression group, the taVNS was applied to bilateral Xin (CO₁₅) and Shen (CO₁₀), at disperse-dense wave, 4 Hz/20 Hz in frequency and current intensity ≤20 mA depending on patient's tolerance, 30 min each time, twice daily. The duration of treatment consisted of 8 weeks. The patients of two groups were undertaken rs-fMRI scanning. The scores of Hamilton depression scale (HAMD), Hamilton anxiety scale (HAMA) and Wisconsin card sorting test (WCST) were observed in the normal group at baseline and the depression group before and after treatment separately. The differential brain regions were observed before and after treatment in the two groups and the value of degree centrality (DC) of fMRI was obtained. Their correlation was analyzed in terms of HAMD, HAMA and WCST scores. RESULTS: The scores of HAMD and HAMA in the depression group were all higher than those in the normal group (P<0.05). After treatment, the scores of HAMD and HAMA were lower than those before treatment in the depression group; the scores of total responses, response errors and perseverative errors of WCST were all lower than those before treatment (P<0.05). The brain regions with significant differences included the left inferior temporal gyrus, the left cerebellar peduncles region 1, the left insula, the right putamen, the bilateral supplementary motor area and the right middle frontal gyrus. After treatment, the value of DC in left supplementary motor area was negatively correlated to HAMD and HAMA scores respectively (r=-0.324, P=0.012; r=-0.310, P=0.015); the value of DC in left cerebellar peduncles region 1 was negatively correlated to the total responses of WCST (r=-0.322, P=0.013), and the left insula was positively correlated to the total responses of WCST (r=0.271, P=0.036). CONCLUSION The taVNS can modulate the intensity of the functional activities of some brain regions so as to relieve depressive symptoms and improve cognitive function.
Humans ; Depression/therapy* ; Magnetic Resonance Imaging/methods* ; Vagus Nerve Stimulation/methods* ; Brain/diagnostic imaging* ; Transcutaneous Electric Nerve Stimulation/methods* ; Vagus Nerve

Recently, deep learning has achieved impressive results in medical image tasks. However, this method usually requires large-scale annotated data, and medical images are expensive to annotate, so it is a challenge to learn efficiently from the limited annotated data. Currently, the two commonly used methods are transfer learning and self-supervised learning. However, these two methods have been little studied in multimodal medical images, so this study proposes a contrastive learning method for multimodal medical images. The method takes images of different modalities of the same patient as positive samples, which effectively increases the number of positive samples in the training process and helps the model to fully learn the similarities and differences of lesions on images of different modalities, thus improving the model's understanding of medical images and diagnostic accuracy. The commonly used data augmentation methods are not suitable for multimodal images, so this paper proposes a domain adaptive denormalization method to transform the source domain images with the help of statistical information of the target domain. In this study, the method is validated with two different multimodal medical image classification tasks: in the microvascular infiltration recognition task, the method achieves an accuracy of (74.79 ± 0.74)% and an F1 score of (78.37 ± 1.94)%, which are improved as compared with other conventional learning methods; for the brain tumor pathology grading task, the method also achieves significant improvements. The results show that the method achieves good results on multimodal medical images and can provide a reference solution for pre-training multimodal medical images.
Humans ; Algorithms ; Brain/diagnostic imaging* ; Brain Neoplasms/diagnostic imaging* ; Recognition, Psychology

PURPOSE: Child head injury under impact scenarios (e.g. falls, vehicle crashes, etc.) is an important topic in the field of injury biomechanics. The head of piglet was commonly used as the surrogate to investigate the biomechanical response and mechanisms of pediatric head injuries because of the similar cellular structures and material properties. However, up to date, piglet head models with accurate geometry and material properties, which have been validated by impact experiments, are seldom. We aim to develop such a model for future research. METHODS: In this study, first, the detailed anatomical structures of the piglet head, including the skull, suture, brain, pia mater, dura mater, cerebrospinal fluid, scalp and soft tissue, were constructed based on CT scans. Then, a structured butterfly method was adopted to mesh the complex geometries of the piglet head to generate high-quality elements and each component was assigned corresponding constitutive material models. Finally, the guided drop tower tests were conducted and the force-time histories were ectracted to validate the piglet head finite element model. RESULTS: Simulations were conducted on the developed finite element model under impact conditions and the simulation results were compared with the experimental data from the guided drop tower tests and the published literature. The average peak force and duration of the guide drop tower test were similar to that of the simulation, with an error below 10%. The inaccuracy was below 20%. The average peak force and duration reported in the literature were comparable to those of the simulation, with the exception of the duration for an impact energy of 11 J. The results showed that the model was capable to capture the response of the pig head. CONCLUSION This study can provide an effective tool for investigating child head injury mechanisms and protection strategies under impact loading conditions.
Animals ; Swine ; Finite Element Analysis ; Skull/injuries* ; Craniocerebral Trauma/diagnostic imaging* ; Brain ; Biomechanical Phenomena ; Scalp

Humans ; Water ; Rivers ; Skull/anatomy & histology* ; Brain/diagnostic imaging* ; Forensic Medicine ; Forensic Anthropology

OBJECTIVES: To explore a new method for electroencephalography (EEG) background analysis in neonates with hypoxic-ischemic encephalopathy (HIE) and its relationship with clinical grading and head magnetic resonance imaging (MRI) grading. METHODS: A retrospective analysis was performed for the video electroencephalography (vEEG) and amplitude-integrated electroencephalography (aEEG) monitoring data within 24 hours after birth of neonates diagnosed with HIE from January 2016 to August 2022. All items of EEG background analysis were enrolled into an assessment system and were scored according to severity to obtain the total EEG score. The correlations of total EEG score with total MRI score and total Sarnat score (TSS, used to evaluate clinical gradings) were analyzed by Spearman correlation analysis. The total EEG score was compared among the neonates with different clinical gradings and among the neonates with different head MRI gradings. The receiver operating characteristic (ROC) curve and the area under thecurve (AUC) were used to evaluate the value of total EEG score in diagnosing moderate/severe head MRI abnormalities and clinical moderate/severe HIE, which was then compared with the aEEG grading method. RESULTS: A total of 50 neonates with HIE were included. The total EEG score was positively correlated with the total head MRI score and TSS (r_s=0.840 and 0.611 respectively, P<0.001). There were significant differences in the total EEG score between different clinical grading groups and different head MRI grading groups (P<0.05). The total EEG score and the aEEG grading method had an AUC of 0.936 and 0.617 respectively in judging moderate/severe head MRI abnormalities (P<0.01) and an AUC of 0.887 and 0.796 respectively in judging clinical moderate/severe HIE (P>0.05). The total EEG scores of ≤6 points, 7-13 points, and ≥14 points were defined as mild, moderate, and severe EEG abnormalities respectively, which had the best consistency with clinical grading and head MRI grading (P<0.05). CONCLUSIONS The new EEG background scoring method can quantitatively reflect the severity of brain injury and can be used for the judgment of brain function in neonates with HIE.
Infant, Newborn ; Humans ; Hypoxia-Ischemia, Brain/diagnostic imaging* ; Retrospective Studies ; Brain Injuries ; Electroencephalography ; ROC Curve

Humans ; Huntington Disease/diagnostic imaging* ; Brain/diagnostic imaging* ; Brain Mapping ; Magnetic Resonance Imaging

Humans ; Brain/diagnostic imaging* ; Head

INTRODUCTION: Detection of neurological conditions is of high importance in the current context of increasingly ageing populations. Imaging of the retina and the optic nerve head represents a unique opportunity to detect brain diseases, but requires specific human expertise. We review the current outcomes of artificial intelligence (AI) methods applied to retinal imaging for the detection of neurological and neuro-ophthalmic conditions. METHOD: Current and emerging concepts related to the detection of neurological conditions, using AI-based investigations of the retina in patients with brain disease were examined and summarised. RESULTS: Papilloedema due to intracranial hypertension can be accurately identified with deep learning on standard retinal imaging at a human expert level. Emerging studies suggest that patients with Alzheimer's disease can be discriminated from cognitively normal individuals, using AI applied to retinal images. CONCLUSION Recent AI-based systems dedicated to scalable retinal imaging have opened new perspectives for the detection of brain conditions directly or indirectly affecting retinal structures. However, further validation and implementation studies are required to better understand their potential value in clinical practice.
Humans ; Artificial Intelligence ; Brain/diagnostic imaging* ; Retina ; Optic Disk ; Aging

Connectome/methods* ; Magnetic Resonance Imaging/methods* ; Brain/diagnostic imaging* ; Head ; Brain Mapping/methods* ; Nerve Net

Gray Matter/diagnostic imaging* ; Cerebral Cortex ; Brain ; Magnetic Resonance Imaging