Machine learning approaches are increasingly being applied to neuroimaging data from patients with psychiatric disorders to extract brain-based features for diagnosis and prognosis. The goal of this review is to discuss recent practices for evaluating machine learning applications to obsessive-compulsive and related disorders and to advance a novel strategy of building machine learning models based on a set of core brain regions for better performance, interpretability, and generalizability. Specifically, we argue that a core set of co-altered brain regions (namely 'core regions') comprising areas central to the underlying psychopathology enables the efficient construction of a predictive model to identify distinct symptom dimensions/clusters in individual patients. Hypothesis-driven and data-driven approaches are further introduced showing how core regions are identified from the entire brain. We demonstrate a broadly applicable roadmap for leveraging this core set-based strategy to accelerate the pursuit of neuroimaging-based markers for diagnosis and prognosis in a variety of psychiatric disorders.
Humans ; Obsessive-Compulsive Disorder/epidemiology* ; Brain/pathology* ; Neuroimaging/methods* ; Machine Learning ; Comorbidity ; Magnetic Resonance Imaging/methods*

Advances in radionuclide tracers have allowed for more accurate imaging that reflects the actions of numerous neurotransmitters, energy metabolism utilization, inflammation, and pathological protein accumulation. All of these achievements in molecular brain imaging have broadened our understanding of brain function in Parkinson's disease (PD). The implementation of molecular imaging has supported more accurate PD diagnosis as well as assessment of therapeutic outcome and disease progression. Moreover, molecular imaging is well suited for the detection of preclinical or prodromal PD cases. Despite these advances, future frontiers of research in this area will focus on using multi-modalities combining positron emission tomography and magnetic resonance imaging along with causal modeling with complex algorithms.
Brain ; diagnostic imaging ; Humans ; Molecular Imaging ; methods ; trends ; Neuroimaging ; methods ; trends ; Parkinson Disease ; diagnostic imaging

Adult ; Female ; Humans ; Magnetic Resonance Imaging ; Neuroimaging ; methods ; Pituitary Neoplasms ; diagnosis

Repetitive transcranial magnetic stimulation (rTMS) has been applied in a variety of diseases due to the clinical effects through the plasticity of the brain. The effects of TMS appear differently depending on the methods of stimulation. Single pulse TMS depolarizes and discharges nerves temporally under the cortex areas stimulated, whereas rTMS induces long-lasting effects of nerves stimulated. According to the intensity of stimulation, the direction of coil and stimulation frequency, rTMS can increase or decrease the excitability of the corticospinal tract and has been verified as techniques to treat a variety of neuropsychiatric disorders. In rTMS studies using electroencephalogram (EEG), changes in brain waves have been measured before and after TMS or simultaneously during TMS. In these studies, low frequency (< or =1 Hz) rTMS, high-frequency (5-25 Hz) rTMS, theta burst stimulation, paired association stimulation have been studied and somatosensory, visual, cognitive, and motor potentials and oscillatory activities were measured and compared before and after TMS. Combined with neurophysiological and, neuroimaging methods, TMS techniques could be used to study cortical excitability, cortical inhibition and excitement, and the cortical plasticity of local areas and neural network. In particular, because simultaneous measurement during TMS as well as measurement before and after TMS is possible, EEG could be very useful to determine the effects of TMS compared to other brain imaging tools.
Brain ; Brain Waves ; Electroencephalography* ; Methods ; Neuroimaging ; Plastics ; Pyramidal Tracts ; Transcranial Magnetic Stimulation*

Adult ; Extracorporeal Membrane Oxygenation ; methods ; Female ; Humans ; Near Drowning ; complications ; diagnostic imaging ; therapy ; Neuroimaging ; Treatment Outcome

A novel medical automatic image segmentation strategy based on guided filtering and multi-atlas is proposed to achieve accurate, smooth, robust, and reliable segmentation. This framework consists of 4 elements: the multi-atlas registration, which uses the atlas prior information; the label fusion, in which the similarity measure of the registration is used as the weight to fuse the warped label; the guided filtering, which uses the local information of the target image to correct the registration errors; and the threshold approaches used to obtain the segment result. The experimental results showed part among the 15 brain MRI images used to segment the hippocampus region, the proposed method achieved a median Dice coefficient of 86% on the left hippocampus and 87.4% on the right hippocampus. Compared with the traditional label fusion algorithm, the proposed algorithm outperforms the common brain image segmentation methods with a good efficiency and accuracy.
Algorithms ; Hippocampus ; anatomy & histology ; Humans ; Image Processing, Computer-Assisted ; methods ; Magnetic Resonance Imaging ; Neuroimaging ; Software

Major advances have been made over the past few decades in identifying and managing disorders of consciousness (DOC) in patients with acquired brain injury (ABI), bringing the transformation from a conceptualized definition to a complex clinical scenario worthy of scientific exploration. Given the continuously-evolving framework of precision medicine that integrates valuable behavioral assessment tools, sophisticated neuroimaging, and electrophysiological techniques, a considerably higher diagnostic accuracy rate of DOC may now be reached. During the treatment of patients with DOC, a variety of intervention methods are available, including amantadine and transcranial direct current stimulation, which have both provided class II evidence, zolpidem, which is also of high quality, and non-invasive stimulation, which appears to be more encouraging than pharmacological therapy. However, heterogeneity is profoundly ingrained in study designs, and only rare schemes have been recommended by authoritative institutions. There is still a lack of an effective clinical protocol for managing patients with DOC following ABI. To advance future clinical studies on DOC, we present a comprehensive review of the progress in clinical identification and management as well as some challenges in the pathophysiology of DOC. We propose a preliminary clinical decision protocol, which could serve as an ideal reference tool for many medical institutions.
Humans ; Transcranial Direct Current Stimulation/methods* ; Consciousness Disorders/etiology* ; Brain Injuries/complications* ; Consciousness ; Neuroimaging

Understanding the connection between brain and behavior in animals requires precise monitoring of their behaviors in three-dimensional (3-D) space. However, there is no available three-dimensional behavior capture system that focuses on rodents. Here, we present MouseVenue3D, an automated and low-cost system for the efficient capture of 3-D skeleton trajectories in markerless rodents. We improved the most time-consuming step in 3-D behavior capturing by developing an automatic calibration module. Then, we validated this process in behavior recognition tasks, and showed that 3-D behavioral data achieved higher accuracy than 2-D data. Subsequently, MouseVenue3D was combined with fast high-resolution miniature two-photon microscopy for synchronous neural recording and behavioral tracking in the freely-moving mouse. Finally, we successfully decoded spontaneous neuronal activity from the 3-D behavior of mice. Our findings reveal that subtle, spontaneous behavior modules are strongly correlated with spontaneous neuronal activity patterns.
Animals ; Behavior, Animal ; Brain/diagnostic imaging* ; Imaging, Three-Dimensional/methods* ; Mice ; Neuroimaging ; Rodentia

Neuroimaging has opened new opportunities to study the neural correlates of consciousness, and provided additional information concerning diagnosis, prognosis, and therapeutic interventions in patients with disorders of consciousness. Here, we aim to review neuroimaging studies in chronic disorders of consciousness from the viewpoint of the brain network, focusing on positron emission tomography, functional MRI, functional near-infrared spectroscopy, electrophysiology, and diffusion MRI. To accelerate basic research on disorders of consciousness and provide a panoramic view of unconsciousness, we propose that it is urgent to integrate different techniques at various spatiotemporal scales, and to merge fragmented findings into a uniform "Brainnetome" (Brain-net-ome) research framework.
Animals ; Brain ; physiology ; Chronic Disease ; Consciousness ; physiology ; Consciousness Disorders ; physiopathology ; Humans ; Neuroimaging ; methods ; Persistent Vegetative State

PURPOSE: Although quantification of amyloid positron emission tomography (PET) is important for evaluating patients with cognitive impairment, its routine clinical use is hampered by complicated preprocessing steps and required MRI. Here, we suggested a one-step quantification based on deep learning using native-space amyloid PET images of different radiotracers acquired from multiple centers.METHODS: Amyloid PET data of the Alzheimer Disease Neuroimaging Initiative (ADNI) were used for this study. A training/validation consists of 850 florbetapir PET images. Three hundred sixty-six florbetapir and 89 florbetaben PET images were used as test sets to evaluate the model. Native-space amyloid PET images were used as inputs, and the outputs were standardized uptake value ratios (SUVRs) calculated by the conventional MR-based method.RESULTS: The mean absolute errors (MAEs) of the composite SUVR were 0.040, 0.060, and 0.050 of training/validation and test sets for florbetapir PETand a test set for florbetaben PET, respectively. The agreement of amyloid positivity measured by Cohen's kappa for test sets of florbetapir and florbetaben PET were 0.87 and 0.89, respectively.CONCLUSION: We suggest a one-step quantification method for amyloid PET via a deep learning model. The model is highly reliable to quantify the amyloid PET regardless of multicenter images and various radiotracers.
Alzheimer Disease ; Amyloid ; Cognition Disorders ; Humans ; Learning ; Magnetic Resonance Imaging ; Methods ; Neuroimaging ; Positron-Emission Tomography