White matter structural topologic efficiency predicts individual resistance to sleep deprivation.

BACKGROUND: Sleep deprivation (SD) is commonplace in modern society and there are large individual differences in the vulnerability to SD. We aim to identify the structural network differences based on diffusion tensor imaging (DTI) that contribute to the individual different vulnerability to SD. METHODS: The number of psychomotor vigilance task (PVT) lapses was used to classify 49 healthy subjects on the basis of whether they were vulnerable or resistant to SD. DTI and graph theory approaches were used to investigate the topologic organization differences of the brain structural connectome between SD-vulnerable and -resistant individuals. We measured the level of global efficiency and clustering in rich club and non-rich club organizations. RESULTS: We demonstrated that participants vulnerable to SD had less global efficiency, network strength, and local efficiency but longer shortest path length compared with participants resistant to SD. Lower efficiency was mainly distributed in the right insula, bilateral thalamus, bilateral frontal, temporal, and temporal lobes. Furthermore, a disrupted subnetwork was observed that consisted of widespread connections. Moreover, the vulnerable group showed significantly decreased strength of the rich club compared with the resistant group. The strength of rich club connectivity was found to be correlated negatively with PVT performance (r = -0.395, p = 0.005). We further tested the reliability of the results. CONCLUSION: The findings revealed that individual differences in resistance to SD are related to disrupted topologic efficiency connectome pattern, and our study may provide potential connectome-based biomarkers for the early detection of the vulnerable degree to SD.

The restoration ability of a short nap after sleep deprivation on the brain cognitive function: A dynamic functional connectivity analysis.

AIMS: The brain function impairment induced by sleep deprivation (SD) is temporary and can be fully reversed with sufficient sleep. However, in many cases, long-duration recovery sleep is not feasible. Thus, this study aimed to investigate whether a short nap after SD is sufficient to restore brain function. METHODS: The data of 38 subjects, including resting state functional magnetic resonance imaging data collected at three timepoints (before SD, after 30 h of SD, and after a short nap following SD) and psychomotor vigilance task (PVT) data, were collected. Dynamic functional connectivity (DFC) analysis was used to evaluate changes in brain states among three timepoints, and four DFC states were distinguished across the three timepoints. RESULTS: Before SD, state 2 (a resting-like FC matrix) was dominant (48.26%). However, after 30 h SD, the proportion of state 2 dramatically decreased, and state 3 (still resting-like, but FCs were weakened) became dominant (40.92%). The increased proportion of state 3 positively correlated with a larger PVT "lapse" time. After a nap, the proportions of states 2 and 3 significantly increased and decreased, respectively, and the change in proportion of state 2 negatively correlated with the change in PVT "lapse" time. CONCLUSIONS: Taken together, the results indicated that, after a nap, the cognitive function impairment caused by SD may be reversed to some extent. Additionally, DFC differed among timepoints, which was also associated with the extent of cognitive function impairment after SD (state 3) and the extent of recovery therefrom after a nap (state 2).

Association of Objective Sleep Characteristics and Incident Angina Pectoris: A Longitudinal Analysis from the Sleep Heart Health Study.

Purpose: While prior research has highlighted a significant association between sleep characteristics and angina pectoris (AP) incidence, the link between sleep efficiency (SE) and angina remains unexplored. This study seeks to elucidate the relationship between AP and objectively quantified SE. Patients and Methods: We examined a cohort of 2990 participants (1320 males and 1670 females; mean age 63.69 ± 13.2 years) from the Sleep Heart Health Study. The main exposure variable was SE, as determined by baseline home polysomnography, while the primary outcome was the first incidence of angina pectoris (AP) during the period between the baseline polysomnography and the end of follow-up. A multivariate Cox regression model was utilized, controlling for factors such as age, gender, BMI, smoking and alcohol consumption habits, diabetes, hypertension, sleep duration, triglycerides, cholesterol, high-density lipoprotein, apnea-hypopnea index, nocturnal oxygen saturation, to analyze the relationship between SE and AP. Results: During an average follow-up of 11 years, 284 patients developed AP. The unadjusted Kaplan-Meier analysis identified the 2nd quartile of SE as having the lowest AP risk. The multivariate Cox proportional hazards model demonstrated a higher risk of AP in quartile 1 (HR, 1.679; 95% CI, 1.109-2.542; P <0.014) and quartile 3 (HR, 1.503; 95% CI, 1.037-2.179; P <0.031), compared to quartile 2 of SE. Upon stratified analysis, this relationship was particularly pronounced in hypertensive individuals. Conclusion: Our results highlight the critical role of optimal sleep efficiency in mitigating the risk of angina pectoris, especially among hypertensive individuals.

Cognitive impairment after sleep deprivation: The role of precuneus related connectivity on the intra-individual variability changes.

OBJECTIVE: Intra-individual variability (IIV) in cognitive performance is thought to reflect the efficiency with which attentional resources are allocated in different circumstances requiring cognitive control. IIV in cognitive performance is associated with the strength of the negative correlation between task-positive network and default mode network (DMN) activity. In this study, we investigated the impact of sleep deprivation (SD) on functional connectivity (FC) between the DMN and psychomotor vigilance task-related network (PVT-RN), and its relationship with IIV in cognitive performance. METHODS: Two analyses, network-level independent component analysis (NL-ICA) and region-level (RL)-ICA, were employed to compare the coefficient of variation (CV) of the PVT between normal sleep and SD conditions across 67 healthy participants. RESULTS: After SD, in NL-ICA, the FC between the PVT-RN and DMN was positively correlated with the CV of the PVT, as well as the changes therein, compared with normal sleep. Using a mask derived from the DMN and PVT-RN, the RL-ICA revealed that 12 edges/connections between DMN and PVT independent components were associated with the CV of the PVT, with nine of these connections involving the precuneus. CONCLUSIONS: These findings suggest that the precuneus may play a crucial role in the interactions of various brain functions during the PVT, with the connections between the precuneus and frontoparietal and somatosensory networks being significantly altered after SD. Moreover, following SD, weakened negative FC between the precuneus and bilateral inferior parietal lobule may disrupt the balance between cognitive and executive control functions, leading to a decline in cognitive performance.

Ultra-high b-Value DWI in predicting progression risk of locally advanced rectal cancer: a comparative study with routine DWI.

BACKGROUND: The prognosis prediction of locally advanced rectal cancer (LARC) was important to individualized treatment, we aimed to investigate the performance of ultra-high b-value DWI (UHBV-DWI) in progression risk prediction of LARC and compare with routine DWI. METHODS: This retrospective study collected patients with rectal cancer from 2016 to 2019. Routine DWI (b = 0, 1000 s/mm2) and UHBV-DWI (b = 0, 1700 ~ 3500 s/mm2) were processed with mono-exponential model to generate ADC and ADCuh, respectively. The performance of the ADCuh was compared with ADC in 3-year progression free survival (PFS) assessment using time-dependent ROC and Kaplan-Meier curve. Prognosis model was constructed with ADCuh, ADC and clinicopathologic factors using multivariate COX proportional hazard regression analysis. The prognosis model was assessed with time-dependent ROC, decision curve analysis (DCA) and calibration curve. RESULTS: A total of 112 patients with LARC (TNM-stage II-III) were evaluated. ADCuh performed better than ADC for 3-year PFS assessment (AUC = 0.754 and 0.586, respectively). Multivariate COX analysis showed that ADCuh and ADC were independent factors for 3-year PFS (P < 0.05). Prognostic model 3 (TNM-stage + extramural venous invasion (EMVI) + ADCuh) was superior than model 2 (TNM-stage + EMVI + ADC) and model 1 (TNM-stage + EMVI) for 3-year PFS prediction (AUC = 0.805, 0.719 and 0.688, respectively). DCA showed that model 3 had higher net benefit than model 2 and model 1. Calibration curve demonstrated better agreement of model 1 than model 2 and model 1. CONCLUSIONS: ADCuh from UHBV-DWI performed better than ADC from routine DWI in predicting prognosis of LARC. The model based on combination of ADCuh, TNM-stage and EMVI could help to indicate progression risk before treatment.

Prognostic value of multi b-value DWI in patients with locally advanced rectal cancer.

OBJECTIVES: To evaluate the potential of multi b-value DWI in predicting the prognosis of patients with locally advanced rectal cancer (LARC). METHODS: From 2015 to 2019, a total of 161 patients with LARC were enrolled and randomly sampled into a training set (n = 113) and validation set (n = 48). Multi b-value DWI (b = 0~1500 s/mm2) scans were postprocessed to generate functional parameters, including apparent diffusion coefficient (ADC), Dt, Dp, f, distributed diffusion coefficient (DDC), and α. Histogram features of each functional parameter were submitted into Least absolute shrinkage and selection operator (LASSO) and stepwise multivariate COX analysis to generate DWI_score based on the training set. The prognostic model was constructed with functional parameter, DWI_score, and clinicopathologic factors by using univariate and multivariate COX analysis on the training set and verified on the validation set. RESULTS: Multivariate COX analysis revealed that DWI_score was an independent indicator for 5-year progression-free survival (PFS, HR = 5.573, p < 0.001), but not for overall survival (OS, HR = 2.177, p = 0.051). No mean value of functional parameters was correlated with PFS or OS. Prognostic model for 5-year PFS based on DWI_score, TNM-stage, mesorectal fascia (MRF), and extramural venous invasion (EMVI) showed good performance both in the training set (AUC = 0.819) and validation set (AUC = 0.815). CONCLUSIONS: The DWI_score based on histogram features of multi b-value DWI functional parameters was an independent factor for PFS of LARC and the prognostic model with a combination of DWI_score and clinicopathologic factors could indicate the progression risk before treatment. KEY POINTS: • Mean value of functional parameters obtained from multi b-value DWI might not be useful to assess the prognosis of LARC. • The DWI_score based on histogram features of multi b-value DWI functional parameters was an independent prognosis factor for PFS of LARC. • Prognostic model based on DWI_score and clinicopathologic factors could indicate the progression risk of LARC before treatment.

Corrigendum: Classifying Vulnerability to Sleep Deprivation Using Resting-State Functional MRI Graph Theory Metrics.

[This corrects the article DOI: 10.3389/fnins.2021.660365.].

Predicting Attentional Vulnerability to Sleep Deprivation: A Multivariate Pattern Analysis of DTI Data.

Background: Large individual differences exist in sleep deprivation (SD) induced sustained attention deterioration. Several brain imaging studies have suggested that the activities within frontal-parietal network, cortico-thalamic connections, and inter-hemispheric connectivity might underlie the neural correlates of vulnerability/resistance to SD. However, those traditional approaches are based on average estimates of differences at the group level. Currently, a neuroimaging marker that can reliably predict this vulnerability at the individual level is lacking. Methods: Efficient transfer of information relies on the integrity of white matter (WM) tracts in the human brain, we therefore applied machine learning approach to investigate whether the WM diffusion metrics can predict vulnerability to SD. Forty-nine participants completed the psychomotor vigilance task (PVT) both after resting wakefulness (RW) and after 24 h of sleep deprivation (SD). The number of PVT lapse (reaction time > 500 ms) was calculated for both RW condition and SD condition and participants were categorized as vulnerable (24 participants) or resistant (25 participants) to SD according to the change in the number of PVT lapses between the two conditions. Diffusion tensor imaging were acquired to extract four multitype WM features at a regional level: fractional anisotropy, mean diffusivity, axial diffusivity, and radial diffusivity. A linear support vector machine (LSVM) learning approach using leave-one-out cross-validation (LOOCV) was performed to assess the discriminative power of WM features in SD-vulnerable and SD-resistant participants. Results: LSVM analysis achieved a correct classification rate of 83.67% (sensitivity: 87.50%; specificity: 80.00%; and area under the receiver operating characteristic curve: 0.85) for differentiating SD-vulnerable from SD-resistant participants. WM fiber tracts that contributed most to the classification model were primarily commissural pathways (superior longitudinal fasciculus), projection pathways (posterior corona radiata, anterior limb of internal capsule) and association pathways (body and genu of corpus callosum). Furthermore, we found a significantly negative correlation between changes in PVT lapses and the LSVM decision value. Conclusion: These findings suggest that WM fibers connecting (1) regions within frontal-parietal attention network, (2) the thalamus to the prefrontal cortex, and (3) the left and right hemispheres contributed the most to classification accuracy.

Sleep Stage Classification Based on Multi-Centers: Comparison Between Different Ages, Mental Health Conditions and Acquisition Devices.

Purpose: To investigate the general sleep stage classification performance of deep learning networks, three datasets, across different age groups, mental health conditions, and acquisition devices, comprising adults (SHHS) and children without mental health conditions (CCSHS), and subjects with mental health conditions (XJ), were included in this study. Methods: A long short-term memory (LSTM) network was used to evaluate the effect of different ages, mental health conditions, and acquisition devices on the sleep stage classification performance and the general performance. Results: Results showed that the age and different mental health conditions may affect the sleep stage classification performance of the network. The same acquisition device using different parameters may not have an obvious effect on the classification performance. When using a single dataset and two datasets for training, the network performed better only on the training dataset. When training was conducted with three datasets, the network performed well for all datasets with a Cohen's Kappa of 0.8192 and 0.8472 for the SHHS and CCSHS, respectively, but performed relatively worse (0.6491) for the XJ, which indicated the complexity effect of different mental health conditions on the sleep stage classification task. Moreover, the performance of the network trained using three datasets was similar for each dataset to that of the network trained using a single dataset and tested on the same dataset. Conclusion: These results suggested that when more datasets across different age groups, mental health conditions, and acquisition devices (ie, more datasets with different feature distributions for each sleep stage) are used for training, the general performance of a deep learning network will be superior for sleep stage classification tasks with varied conditions.

Improved interobserver agreement on nodule type and Lung-RADS classification of subsolid nodules using computer-aided solid component measurement.

PURPOSE: The Lung CT Screening Reporting and Data System (Lung-RADS) classification of subsolid nodules (SSNs) can be challenging due to limited interobserver agreement in determining the type and size of the nodule. Our study aimed to assess the effect of a computer-aided method on the interobserver agreement of Lung-RADS classification for SSNs. MATERIALS AND METHODS: This study consisted of 156 SSNs in 121 patients who underwent initial CT screening for lung cancer. Three independent readers determined the nodule type and measured the size of the entire nodule as well as the solid component, first without and then assisted by a semi-automated computer-aided tool. They assigned to each nodule the corresponding Lung-RADS 1.1 category. Agreement in size measurements was assessed by intraclass correlation coefficient (ICC) and Bland-Altman indexes, while agreement in nodule type and Lung-RADS was determined using Fleiss kappa statistics. The relationship between final diagnosis of the nodules and Lung-RADS classifications was also evaluated. RESULTS: Among the 156 nodules, manual size measurement reached an ICC of 0.994, and 48 nodules contained solid component measured by all the three readers both manually and semi-automatically. ICCs for the solid component measurement were 0.952, 0.997 and 0.996 for manual diameter, semi- automated diameter and volume measurement, respectively. Bias and 95% limits of agreement for average diameter of solid component were smaller with semi-automated measurements than with manual measurements. Kappa values of semi-automated assessment for nodule type (0.974) and Lung-RADS classification (0.958 for diameter and 0.952 for volume) were higher than with the manual measurements (0.783 for nodule type and 0.652 for Lung-RADS classification). Compared to manual work, the semi-automated assessment identified more 4B nodules among the 26 pathologically confirmed invasive adenocarcinomas (IACs). CONCLUSION: Semi-automated assessment could improve the interobserver agreement of nodule type and Lung-RADS classification for SSNs, and be inclined to classify SSNs corresponding to pathologically confirmed IACs into higher risk categories.

Classifying Vulnerability to Sleep Deprivation Using Resting-State Functional MRI Graph Theory Metrics.

Sleep deprivation (SD) has become very common in contemporary society, where people work around the clock. SD-induced cognitive deficits show large inter-individual differences and are trait-like with known neural correlates. However, few studies have used neuroimaging to predict vulnerability to SD. Here, resting state functional magnetic resonance imaging (fMRI) data and psychomotor vigilance task (PVT) data were collected from 60 healthy subjects after resting wakefulness and after one night of SD. The number of PVT lapses was then used to classify participants on the basis of whether they were vulnerable or resilient to SD. We explored the viability of graph-theory-based degree centrality to accurately classify vulnerability to SD. Compared with during resting wakefulness, widespread changes in degree centrality (DC) were found after SD, indicating significant reorganization of sleep homeostasis with respect to activity in resting state brain network architecture. Support vector machine (SVM) analysis using leave-one-out cross-validation achieved a correct classification rate of 84.75% [sensitivity 82.76%, specificity 86.67%, and area under the receiver operating characteristic curve (AUC) 0.94] for differentiating vulnerable subjects from resilient subjects. Brain areas that contributed most to the classification model were mainly located within the sensorimotor network, default mode network, and thalamus. Furthermore, we found a significantly negative correlation between changes in PVT lapses and DC in the thalamus after SD. These findings suggest that resting-state network measures combined with a machine learning algorithm could have broad potential applications in screening vulnerability to SD.

The Construction of a Risk Prediction Model Based on Neural Network for Pre-operative Acute Ischemic Stroke in Acute Type A Aortic Dissection Patients.

Objective: To establish a pre-operative acute ischemic stroke risk (AIS) prediction model using the deep neural network in patients with acute type A aortic dissection (ATAAD). Methods: Between January 2015 and February 2019, 300 ATAAD patients diagnosed by aorta CTA were analyzed retrospectively. Patients were divided into two groups according to the presence or absence of pre-operative AIS. Pre-operative AIS risk prediction models based on different machine learning algorithm was established with clinical, transthoracic echocardiography (TTE) and CTA imaging characteristics as input. The performance of the difference models was evaluated using the receiver operating characteristic (ROC), precision-recall curve (PRC) and decision curve analysis (DCA). Results: Pre-operative AIS was detected in 86 of 300 patients with ATAAD (28.7%). The cohort was split into a training (211, 70% patients) and validation cohort (89, 30% patients) according to stratified sampling strategy. The constructed deep neural network model had the best performance on the discrimination of AIS group compare with other machine learning model, with an accuracy of 0.934 (95% CI: 0.891-0.963), 0.921 (95% CI: 0.845-0.968), sensitivity of 0.934, 0.960, specificity of 0.933, 0.906, and AUC of 0.982 (95% CI: 0.967-0.997), 0.964 (95% CI: 0.932-0.997) in the training and validation cohort, respectively. Conclusion: The established risk prediction model based on the deep neural network method may have the big potential to evaluate the risk of pre-operative AIS in patients with ATAAD.

Predicting Disease-Free Survival With Multiparametric MRI-Derived Radiomic Signature in Cervical Cancer Patients Underwent CCRT.

Prognostic biomarkers that can reliably predict the disease-free survival (DFS) of locally advanced cervical cancer (LACC) are needed for identifying those patients at high risk for progression, who may benefit from a more aggressive treatment. In the present study, we aimed to construct a multiparametric MRI-derived radiomic signature for predicting DFS of LACC patients who underwent concurrent chemoradiotherapy (CCRT). METHODS: This multicenter retrospective study recruited 263 patients with International Federation of Gynecology and Obetrics (FIGO) stage IB-IVA treated with CCRT for whom pretreatment MRI scans were performed. They were randomly divided into two groups: primary cohort (n = 178) and validation cohort (n = 85). The LASSO regression and Cox proportional hazard regression were conducted to construct the radiomic signature (RS). According to the cutoff of the RS value, patients were dichotomized into low- and high-risk groups. Pearson's correlation and Kaplan-Meier analysis were conducted to evaluate the association between the RS and DFS. The RS, the clinical model incorporating FIGO stage and lymph node metastasis by the multivariate Cox proportional hazard model, and a combined model incorporating RS and clinical model were constructed to estimate DFS individually. RESULTS: The final radiomic signature consisted of four radiomic features: T2W_wavelet-LH_ glszm_Size Zone NonUniformity, ADC_wavelet-HL-first order_ Median, ADC_wavelet-HH-glrlm_Long Run Low Gray Level Emphasis, and ADC_wavelet _LL_gldm_Large Dependence High Gray Emphasis. Higher RS was significantly associated with worse DFS in the primary and validation cohorts (both p<0.001). The RS demonstrated better prognostic performance in predicting DFS than the clinical model in both cohorts (C-index, 0.736-0.758 for RS, and 0.603-0.649 for clinical model). However, the combined model showed no significant improvement (C-index, 0.648, 95% CI, 0.571-0.685). CONCLUSIONS: The present study indicated that the multiparametric MRI-derived radiomic signature could be used as a non-invasive prognostic tool for predicting DFS in LACC patients.

Baseline Brain Gray Matter Volume as a Predictor of Acupuncture Outcome in Treating Migraine.

Background: The present study aimed to investigate the use of imaging biomarkers to predict the outcome of acupuncture in patients with migraine without aura (MwoA). Methods: Forty-one patients with MwoA received 4 weeks of acupuncture treatment and two brain imaging sessions at the Beijing Traditional Chinese Medicine Hospital affiliated with Capital Medical University. Patients kept a headache diary for 4 weeks before treatment and during acupuncture treatment. Responders were defined as those with at least a 50% reduction in the number of migraine days. The machine learning method was used to distinguish responders from non-responders based on pre-treatment brain gray matter (GM) volume. Longitudinal changes in GM predictive regions were also analyzed. Results: After 4 weeks of acupuncture, 19 patients were classified as responders. Based on 10-fold cross-validation for the selection of GM features, the linear support vector machine produced a classification model with 73% sensitivity, 85% specificity, and 83% accuracy. The area under the receiver operating characteristic curve was 0.7871. This classification model included 10 GM areas that were mainly distributed in the frontal, temporal, parietal, precuneus, and cuneus gyri. The reduction in the number of migraine days was correlated with baseline GM volume in the cuneus, parietal, and frontal gyri in all patients. Moreover, the left cuneus showed a longitudinal increase in GM volume in responders. Conclusion: The results suggest that pre-treatment brain structure could be a novel predictor of the outcome of acupuncture in the treatment of MwoA. Imaging features could be a useful tool for the prediction of acupuncture efficacy, which would enable the development of a personalized medicine strategy.

Predicting responses to electroconvulsive therapy in schizophrenia patients undergoing antipsychotic treatment: Baseline functional connectivity among regions with strong electric field distributions.

This study explored imaging predictors of electroconvulsive therapy (ECT) outcome in schizophrenia patients based on pre-treatment functional connectivity (FC) within regions with strong ECT electric fields distribution. Forty-seven patients received standard antipsychotic drugs combined with ECT as well as two brain imaging sessions. Regions of interest (ROI) with strong electric field distribution were determined by ECT simulation. Using baseline functional connectivity between ROIs, a model was constructed to predict the percentage reduction of Positive and Negative Syndrome Scale (PANSS) scores. The strong electric fields were distributed in the orbital prefrontal lobe, medial temporal lobe, and other parts of the temporal lobe. Ten functional connectivity features within the electric field distribution areas showed a predictive ability for ECT outcome. The correlation coefficient between the predictive and real values of cross-validation was 0.7165. Among the predictive features, ECT induced a significant decrease in functional connectivity between the right amygdala and the left hippocampus. These results suggest that pretreatment functional connectivity patterns in brain regions with strong electric field distributions during ECT could be potential predictors of the efficacy of ECT augmentation in schizophrenia. These findings may help to improve individualized clinical treatment in the future.

Sleep Stage Classification Using Time-Frequency Spectra From Consecutive Multi-Time Points.

Sleep stage classification is an open challenge in the field of sleep research. Considering the relatively small size of datasets used by previous studies, in this paper we used the Sleep Heart Health Study dataset from the National Sleep Research Resource database. A long short-term memory (LSTM) network using a time-frequency spectra of several consecutive 30 s time points as an input was used to perform the sleep stage classification. Four classical convolutional neural networks (CNNs) using a time-frequency spectra of a single 30 s time point as an input were used for comparison. Results showed that, when considering the temporal information within the time-frequency spectrum of a single 30 s time point, the LSTM network had a better classification performance than the CNNs. Moreover, when additional temporal information was taken into consideration, the classification performance of the LSTM network gradually increased. It reached its peak when temporal information from three consecutive 30 s time points was considered, with a classification accuracy of 87.4% and a Cohen's Kappa coefficient of 0.8216. Compared with CNNs, our results indicate that for sleep stage classification, the temporal information within the data or the features extracted from the data should be considered. LSTM networks take this temporal information into account, and thus, may be more suitable for sleep stage classification.

Predicting response to electroconvulsive therapy combined with antipsychotics in schizophrenia using multi-parametric magnetic resonance imaging.

Electroconvulsive therapy (ECT) has been shown to be effective in schizophrenia, particularly when rapid symptom reduction is needed or in cases of resistance to drug treatment. However, there are no markers available to predict response to ECT. Here, we examine whether multi-parametric magnetic resonance imaging (MRI)-based radiomic features can predict response to ECT for individual patients. A total of 57 treatment-resistant schizophrenia patients, or schizophrenia patients with an acute episode or suicide attempts were randomly divided into primary (42 patients) and test (15 patients) cohorts. We collected T1-weighted structural MRI and diffusion MRI for 57 patients before receiving ECT and extracted 600 radiomic features for feature selection and prediction. To predict a continuous improvement in symptoms (ΔPANSS), the prediction process was performed with a support vector regression model based on a leave-one-out cross-validation framework in primary cohort and was tested in test cohort. The multi-parametric MRI-based radiomic model, including four structural MRI feature from left inferior frontal gyrus, right insula, left middle temporal gyrus and right superior temporal gyrus respectively and six diffusion MRI features from tracts connecting frontal or temporal gyrus possessed a low root mean square error of 15.183 in primary cohort and 14.980 in test cohort. The Pearson's correlation coefficients between predicted and actual values were 0.671 and 0.777 respectively. These results demonstrate that multi-parametric MRI-based radiomic features may predict response to ECT for individual patients. Such features could serve as prognostic neuroimaging biomarkers that provide a critical step toward individualized treatment response prediction in schizophrenia.

Abnormal Resting-State Functional Connectivity in the Whole Brain in Lifelong Premature Ejaculation Patients Based on Machine Learning Approach.

Recent neuroimaging studies have indicated that abnormalities in brain structure and function may play an important role in the etiology of lifelong premature ejaculation (LPE). LPE patients have exhibited aberrant cortical structure, altered brain network function and abnormal brain activation in response to erotic pictures. However, it remains unclear whether resting-state whole brain functional connectivity (FC) is altered in LPE patients. Machine learning analysis has the advantage of screening the best classification features from high-throughput data (such as FC), which has the potential to identify the pathophysiological targets of disease by establishing classification indicators for patients and healthy controls (HCs). Therefore, the supported vector machine based classification model using FC as features was used in the present study to confirm the most specific FCs that distinguish LPE patients from healthy controls. After feature selection, the remained features were used to build the classification model, with an accuracy 0.85 ± 0.14, sensitivity of 0.92 ± 0.18, specificity of 0.72 ± 0.30, and recall index of 0.85 ± 0.17 across 1000 testing groups (100 times 10-folds cross validation). After that, two-sample t-tests with family-wise error correction were used to compare these features that occur more than 500 times during training steps between LPE patients and HCs. Four FCs, (1) between left medial part of orbital frontal cortex (mOFC) and right mOFC, (2) between the left rectus and right postcentral gyrus, (3) between the right insula and left pallidum, and (4) between the right middle part of temporal pole and right inferior part of temporal gyrus showed significant group difference. These results demonstrate that resting-state brain FC might be a discriminating feature to distinguish LPE patients from HCs. These classification features, especially the FC between bilateral mOFC, provide underlying abnormal central functional targets in LPE etiology, which offers a novel alternative target for future intervention in LPE treatment.

Association Between Connectivity of Hippocampal Sub-Regions and Auditory Verbal Hallucinations in Schizophrenia.

Background: Hippocampal dysconnectivity has been detected in schizophrenia patients with auditory verbal hallucinations (AVHs). Neuroanatomical evidence has indicated distinct sub-regions in the hippocampus, but which sub-regions within the hippocampus may emerge dysfunction in the brain network, and the relationship between connection strength and the severity of this debilitating disorder have yet to be revealed. Masked independent component analysis (mICA), i.e., ICA restricted to a defined region of interest, can provide insight into observing local functional connectivity in a particular brain region. We aim to map out the sub-regions in the hippocampus with dysconnectivity linked to AVHs in schizophrenia. Methods: In this functional magnetic resonance imaging study of schizophrenia patients with (n = 57) and without (n = 83) AVHs, and 71 healthy controls, we first examined hippocampal connectivity using mICA, and then the correlation between connection metric and clinical severity was generated. Results: As compared with patients without AVHs, mICA showed a group of hyper-connections for the left middle part, as well as another group of hypo-connections for the bilateral antero-lateral and right antero-medial parts in patients with AVHs. Connectivity was linked to the clinical symptoms scores in the sample of patients with AVHs. Conclusion: These findings demonstrate that the left middle part is more densely connected, but the bilateral antero-lateral and right antero-medial parts are more sparsely connected in schizophrenia patients with AVHs. The findings in the present study show proof of precious location in the hippocampus mediating the neural mechanism behind AVHs in schizophrenia.

Radiomics signature: A potential biomarker for the prediction of MGMT promoter methylation in glioblastoma.

BACKGROUND: In glioblastoma (GBM), promoter methylation of the DNA repair gene O-methylguanine-DNA methyltransferase (MGMT) is associated with beneficial chemotherapy. PURPOSE/HYPOTHESIS: To analyze radiomics features for utilizing the full potential of medical imaging as biomarkers of MGMT promoter methylation. STUDY TYPE: Retrospective. POPULATION/SUBJECTS: In all, 98 GBM patients with known MGMT (48 methylated and 50 unmethylated tumors). FIELD STRENGTH/SEQUENCE: 3.0T magnetic resonance (MR) images, containing T1 -weighted image (T1 WI), T2 -weighted image (T2 WI), and enhanced T1 WI. ASSESSMENT: A region of interest (ROI) of the tumor was delineated. A total of 1665 radiomics features were extracted and quantized, and were reduced using least absolute shrinkage and selection operator (LASSO) regularization. STATISTICAL TESTING: After the support vector machine construction, accuracy, sensitivity, and specificity were computed for different sequences. An independent validation cohort containing 20 GBM patients was utilized to further evaluate the radiomics model performance. RESULTS: Radiomics features of T1 WI reached an accuracy of 67.54%. Enhanced T1 WI features reached an accuracy of 82.01%, while T2 WI reached an accuracy of 69.25%. The best classification system for predicting MGMT promoter methylation status originated from the combination of 36 T1 WI, T2 WI, and enhanced T1 WI images features, with an accuracy of 86.59%. Further validation on the independent cohort of 20 patients produced similar results, with an accuracy of 80%. DATA CONCLUSION: Our results provide further evidence that radiomics MR features could predict MGMT methylation status in preoperative GBM. Multiple imaging modalities together can yield putative noninvasive biomarkers for the identification of MGMT. LEVEL OF EVIDENCE: 4 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2018;47:1380-1387.