Recently, deep learning technologies have rapidly expanded into medical image analysis, including both disease detection and classification. As far as we know, migraine is a disabling and common neurological disorder, typically characterized by unilateral, throbbing and pulsating headaches. Unfortunately, a large number of migraineurs do not receive the accurate diagnosis when using traditional diagnostic criteria based on the guidelines of the International Headache Society. As such, there is substantial interest in developing automated methods to assist in the diagnosis of migraine. To the best of our knowledge, no studies have evaluated the potential of deep learning technologies in assisting with the classification of migraine patients. Here, we used deep learning methods in combination with three functional measures (the amplitude of low-frequency fluctuations, regional homogeneity and regional functional correlation strength) based on rs-fMRI data to distinguish not only between migraineurs and healthy controls, but also between the two subtypes of migraine. We employed 21 migraine patients without aura, 15 migraineurs with aura, and 28 healthy controls. Compared with the traditional support vector machine classifier, which has an accuracy of 83.67%, our Inception module-based convolutional neural network approach showed a significant improvement in classification output (over 86.18%). Our data also indicate that the Inception module-based CNN performs better than the AlexNet-based CNN (Inception module-based CNN reached an accuracy of 99.25%). Finally, we also found that regional functional correlation strength (RFCS) could be regarded as the optimum input out of the three indices (ALFF, ReHo, RFCS). Overall, our study shows that combining the three functional measures of rs-fMRI with deep learning classification is a powerful method to distinguish between migraineurs and healthy individuals. Our data also highlight that deep learning-based frameworks could be used to develop more complicated models or systems to aid in clinical decision making in the future.

Magnetic resonance imaging (MRI) is by nature a multi-modality technique that provides complementary information about different aspects of diseases. So far no attempts have been reported to assess the potential of multi-modal MRI in discriminating individuals with and without migraine, so in this study, we proposed a classification approach to examine whether or not the integration of multiple MRI features could improve the classification performance between migraine patients without aura (MWoA) and healthy controls. Twenty-one MWoA patients and 28 healthy controls participated in this study. Resting-state functional MRI data was acquired to derive three functional measures: the amplitude of low-frequency fluctuations, regional homogeneity and regional functional correlation strength; and structural MRI data was obtained to measure the regional gray matter volume. For each measure, the values of 116 pre-defined regions of interest were extracted as classification features. Features were first selected and combined by a multi-kernel strategy; then a support vector machine classifier was trained to distinguish the subjects at individual level. The performance of the classifier was evaluated using a leave-one-out cross-validation method, and the final classification accuracy obtained was 83.67% (with a sensitivity of 92.86% and a specificity of 71.43%). The anterior cingulate cortex, prefrontal cortex, orbitofrontal cortex and the insula contributed the most discriminative features. In general, our proposed framework shows a promising classification capability for MWoA by integrating information from multiple MRI features.

Post-traumatic stress disorder (PTSD) is a debilitating psychiatric disorder. It can be difficult to discern the symptoms of PTSD and obtain an accurate diagnosis. Different magnetic resonance imaging (MRI) modalities focus on different aspects, which may provide complementary information for PTSD discrimination. However, none of the published studies assessed the diagnostic potential of multimodal MRI in identifying individuals with and without PTSD. In the current study, we investigated whether the complementary information conveyed by multimodal MRI scans could be combined to improve PTSD classification performance. Structural and resting-state functional MRI scans were conducted on 17 PTSD patients, 20 trauma-exposed controls without PTSD (TEC) and 20 non-traumatized healthy controls (HC). Gray matter volume, amplitude of low-frequency fluctuations and regional homogeneity were extracted as classification features, and in order to integrate the information of structural and functional MRI data, the extracted features were combined by a multi-kernel combination strategy. Then a support vector machine classifier was trained to distinguish the subjects at individual level. The performance of the classifier was evaluated using the leave-one-out cross-validation method. In the pairwise comparison of PTSD, TEC and HC groups, classification accuracies obtained by the proposed approach were 2.70%, 2.50% and 2.71% higher than the best single feature way, with the accuracies of 89.19%, 90.00% and 67.57% for PTSD versus HC, TEC versus HC and PTSD versus TEC respectively. The proposed approach could improve PTSD identification at individual level. Additionally, it provides preliminary support to develop the multimodal MRI method as a clinical diagnostic aid.

The knee osteoarthritis (KOA) pain is the most common form of arthritis pain affecting millions of people worldwide. Long-term KOA pain causes motor impairment and affects affective and cognitive functions. However, little is known about the structural and functional abnormalities induced by long-term KOA pain. In this work, high-resolution structural magnetic resonance imaging (sMRI) and resting-state functional MRI (rs-fMRI) data were acquired in patients with KOA and age-, sex-matched healthy controls (HC). Gray matter volume (GMV) and fractional amplitude of low-frequency fluctuation (fALFF) were used to study the structural and functional abnormalities in patients with KOA. Compared with HC, patients with KOA showed reduced GMV in bilateral insula and bilateral hippocampus, and reduced fALFF in left cerebellum, precentral gyrus, and the right superior occipital gyrus. Patients with KOA also showed increased fALFF in left insula and bilateral hippocampus. In addition, the abnormal GMV in left insula and fALFF in left fusiform were closely correlated with the pain severity or disease duration. These results indicated that long KOA pain leads to brain structural and functional impairments in motor, visual, cognitive, and affective functions that related to brain areas. Our findings may facilitate to understand the neural basis of KOA pain and the future therapy to relieve disease symptoms.

Primary objective: To investigate the epidemiological characteristics of paediatric inpatients with traumatic brain injury (TBI) in China. Research design: The Chinese Trauma Database (CTD), a nationwide register system based on hospital admission data, contains diagnosis and treatment information for trauma inpatients in over 200 military-managed public-service hospitals in China. Using the ICD-9 coding, the data for children with TBI aged 0–17 years between 2001 and 2007 were retrieved. Methods and procedures: The demographic characteristics, admission time, injury cause, severity and treatment outcomes of paediatric inpatients with TBI were analysed. Main outcomes and results: A total of 26,028 paediatric inpatients with TBI (69.52% male, 30.48% female) were included in the CTD. Motor vehicle traffic (MVT) accidents, falls and assaults were the primary causes of injury. Falls were the leading cause of TBI in children aged 0–4 years, and MVT was the leading cause of TBI in children aged 5–17 years. According to the abbreviated injury scale, 37.20% of the TBI cases were mild, 25.15% were moderate, 24.81% were severe and 12.84% were critically severe. Conclusion: Chinese authorities should develop targeted measures to reduce children injuries based on the leading causes of TBI in the different age groups, particularly MVT, falls and assaults.