Abnormal Global Cortical Responses in Drug-Naïve Patients With Schizophrenia Following Orbitofrontal Cortex Stimulation: A Concurrent Transcranial Magnetic Stimulation-Electroencephalography Study.

BACKGROUND: Abnormalities in cortical excitability and plasticity have been considered to underlie the pathophysiology of schizophrenia. Transcranial magnetic stimulation combined with electroencephalography (TMS-EEG) can provide a direct evaluation of cortical responses to TMS. Here, we employed TMS-EEG to investigate cortical responses to orbitofrontal cortex (OFC) stimulation in schizophrenia. METHODS: In total, we recruited 92 drug-naïve patients with first-episode schizophrenia and 51 age- and sex-matched healthy individuals. For each participant, one session of 1-Hz repetitive TMS (rTMS) was delivered to the right OFC, and TMS-EEG data were obtained to explore the change in cortical-evoked activities before and immediately after rTMS during the eyes-closed state. The MATRICS Consensus Cognitive Battery was used to assess neurocognitive performance. RESULTS: The cortical responses indexed by global mean field amplitudes (i.e., P30, N45, and P60) were larger in patients with schizophrenia than in healthy control participants at baseline. Furthermore, after one session of 1-Hz rTMS over the right OFC, the N100 amplitude was significantly reduced in the healthy control group but not in the schizophrenia group. In the healthy control participants, there was a significant correlation between modulation of P60 amplitude by rTMS and working memory; however, this correlation was absent in patients with schizophrenia. CONCLUSIONS: Aberrant global cortical responses following right OFC stimulation were found in patients with drug-naïve first-episode schizophrenia, supporting its significance in the primary pathophysiology of schizophrenia.

Repetitive transcranial magnetic stimulation can improve negative symptoms and/or neurocognitive impairments in the first psychosis episode: A randomized controlled trial.

OBJECTIVE: Negative symptoms and neurocognitive impairments in psychosis correlate with their severity. Currently, there is no satisfactory treatment. We aimed to evaluate and compare the effects of repetitive transcranial magnetic stimulation(rTMS) on negative symptoms and neurocognitive impairments in patients in first-episode of psychosis(FEP) in a randomized controlled trial(RCT). METHOD: This is a single-site RCT of 85 patients with FEP. Patients were randomized to receive a 4-week course of active(n = 45) or sham rTMS(n = 40). Factor analysis was applied to a cross-sectional dataset of 744 FEP patients who completed negative symptom evaluation and neurocognitive battery tests. Two independent dimensions were generated and used for the K-means cluster analysis to produce sub-clusters. rTMS of 1-Hz was delivered to the right orbitofrontal(OFC) cortex. RESULTS: Two distinct dimensional factors of neurocognitive functions(factor-1) and negative symptoms(factor-2), and three clusters with distinctive features were generated. Significant improvements in factor-1 and factor-2 were observed after 4-weeks of rTMS treatment in both the active and sham rTMS groups. The repeated-measures analysis of variance revealed a significant effect of time×group(F = 5.594, p = 0.021, η2 = 0.073) on factor-2, but no effect of time×group on factor-1. Only improvements in negative symptoms were significantly different between the active and sham rTMS groups(p = 0.028). Patients in cluster-3 characterized by extensive negative symptoms, showed greater improvement in the active rTMS group than in the sham rTMS group. CONCLUSIONS: The 1-Hz right OFC cortex rTMS is more effective in reducing negative symptoms than neurocognitive impairments. It is especially effective in patients with dominantly negative symptoms in FEP.

Abnormal Static and Dynamic Local Functional Connectivity in First-Episode Schizophrenia: A Resting-State fMRI Study.

Dynamic functional connectivity (FC) analyses have provided ample information on the disturbances of global functional brain organization in patients with schizophrenia. However, our understanding about the dynamics of local FC in never-treated first episode schizophrenia (FES) patients is still rudimentary. Dynamic Regional Phase Synchrony (DRePS), a newly developed dynamic local FC analysis method that could quantify the instantaneous phase synchronization in local spatial scale, overcomes the limitations of commonly used sliding-window methods. The current study performed a comprehensive examination on both the static and dynamic local FC alterations in FES patients (N = 74) from healthy controls (HCs, N = 41) with resting-state functional magnetic resonance imaging using DRePS, and compared the static local FC metrics derived from DRePS with those calculated from two commonly used regional homogeneity (ReHo) analysis methods that are defined based on Kendall's coefficient of concordance (KCC-ReHo) and frequency coherence (Cohe-ReHo). Symptom severities of FES patients were assessed with a set of clinical scales. Cognitive functions of FES patients and HCs were assessed with the MATRICS consensus cognitive battery. Group-level analysis revealed that compared with HCs, FES patients exhibited increased static local FC in right superior, middle temporal gyri, hippocampus, parahippocampal gyrus, putamen, and bilateral caudate nucleus. Nonetheless, the dynamic local FC metrics did not show any significant differences between the two groups. The associations between all local FC metrics and clinical characteristics manifested scores were explored using a relevance vector machine. Results showed that the Global Assessment of Functioning score highest in past year and the Brief Visuospatial Memory Test-Revised task score were statistically significantly predicted by a combination of all static and dynamic features. The diagnostic abilities of different local FC metrics and their combinations were compared by the classification performance of linear support vector machine classifiers. Results showed that the inclusion of zero crossing ratio of DRePS, one of the dynamic local FC metrics, alongside static local FC metrics improved the classification accuracy compared to using static metrics alone. These results enrich our understanding of the neurocognitive mechanisms underlying schizophrenia, and demonstrate the potential of developing diagnostic biomarker for schizophrenia based on DRePS.

Low-frequency repetitive transcranial magnetic stimulation over the right orbitofrontal cortex for patients with first-episode schizophrenia: A randomized, double-blind, sham-controlled trial.

Repetitive transcranial magnetic stimulation (rTMS) has been used in the treatment of patients with schizophrenia. The conventional targets of rTMS treatment are the dorsolateral prefrontal cortex (DLPFC) and temporoparietal cortex (TPC). However, the efficacy of these two treatment strategies was quite heterogeneous. Structural and functional abnormalities of the orbitofrontal cortex (OFC) in schizophrenia are closely related to negative symptoms. We sought to determine whether 1 Hz rTMS over the right OFC is effective in treating patients with first-episode schizophrenia. In this study, eighty-nine patients with drug-naïve, first-episode schizophrenia were randomly divided into the rTMS (n = 47) or sham stimulation (n = 42) groups, with both groups receiving twenty sessions of 1 Hz rTMS treatment. The PANSS was assessed at baseline, day 10, and day 20, and MATRICS Consensus Cognitive Battery (MCCB) was implemented to assess the cognitive impairment at baseline and day 20. Results showed that patients in the active rTMS group had more improvement in clinical symptoms and cognitive deficits than patients in sham group at day 20. In conclusion, 1 Hz rTMS over OFC can improve psychotic symptoms and cognitive functions in schizophrenic patients. Our study provides a new alternative for the treatment of negative symptoms and cognitive deficits in schizophrenia.

Increased theta-low gamma phase-amplitude coupling in resting electroencephalography after intermittent theta burst stimulation.

OBJECTIVE: Intermittent theta burst stimulation (iTBS) is based on the phase-amplitude coupling (PAC) pattern. We aimed to investigate the effect of iTBS on PAC in resting electroencephalography (EEG), which may provide insight into the underlying mechanism. METHODS: Twenty-one healthy volunteers were recruited and received both active and sham neuroimaging-guided iTBS on two separate days, which was precisely delivered to the right superior temporal gyrus. On each experimental day, resting EEG was recorded before and after stimulation for each participant. PACs across electrodes and frequency bands were calculated and compared to investigate the effect of iTBS. RESULTS: Theta (4-6 Hz) -low gamma (45-55 Hz) PAC over the stimulation site had a significant interaction effect, which increased after the active iTBS but did not differ after the sham iTBS. No significant interaction effect occurred in other cross-frequency couplings such as delta-low gamma, alpha-low gamma, delta-high gamma, theta-high gamma, or alpha-high gamma PAC in the region of interest. CONCLUSION: iTBS selectively modulated theta-low gamma PAC at the stimulation area, which exhibited both region- and frequency- specificity. This suggests that PAC may be a bridge connecting external neuromodulation to internal neuroplasticity.

Deep learning-based multiomics integration model for predicting axillary lymph node metastasis in breast cancer.

Aim: To develop a deep learning-based multiomics integration model. Materials & methods: Five types of omics data (mRNA, DNA methylation, miRNA, copy number variation and protein expression) were used to build a deep learning-based multiomics integration model via a deep neural network, incorporating an attention mechanism that adaptively considers the weights of multiomics features. Results: Compared with other methods, the deep learning-based multiomics integration model achieved remarkable results, with an area under the curve of 0.89 (95% CI: 0.863-0.910). Conclusion: The deep learning-based multiomics integration model achieved promising results and is an effective method for predicting axillary lymph node metastasis in breast cancer.

Development and Validation of a Nomogram for Predicting Axillary Lymph Node Metastasis in Breast Cancer.

BACKGROUND: Axillary lymph node (ALN) status is a key prognosis indicator for breast cancer patients. To develop an effective tool for predicting axillary lymph node metastasis in breast cancer, a nomogram was established based on mRNA expression data and clinicopathological characteristics. MATERIALS AND METHODS: A 1062 breast cancer patients with mRNA data and clinical information were obtained from The Cancer Genome Atlas (TCGA). We first analyzed the differentially expression genes (DEGs) between ALN positive and ALN negative patients. Then, logistic regression, least absolute shrinkage and selection operator (Lasso) regression, and backward stepwise regression were performed to select candidate mRNA biomarkers. The mRNA signature was constructed by the mRNA biomarkers and corresponding Lasso coefficients. The key clinical factors were obtained by Wilcoxon-Mann-Whitney U test or Pearson's χ2 test. Finally, the nomogram for predicting axillary lymph node metastasis was developed and evaluated by concordance index (C-index), calibration curve, decision curve analysis (DCA), and receptor operating characteristic (ROC) curve. Furthermore, the nomogram was externally validated using Gene Expression Omnibus (GEO) dataset. RESULTS: The nomogram for predicting ALN metastasis yielded a C-index of 0.728 (95% CI: 0.698-0.758) and an AUC of 0.728 (95% CI: 0.697-0.758) in the TCGA cohort. In the independent validation cohort, the C-index and AUC of the nomogram were up to 0.825 (95% CI: 0.695-0.955) and 0.810 (95% CI: 0.666-0.953), respectively. CONCLUSION: This nomogram could predict the risk of axillary lymph node metastasis in breast cancer and may provide a reference for clinicians to design individualized axillary lymph node management strategies.

Evaluation of Brain Source Localization Methods Based on Test-Retest Reliability With Multiple Session EEG Data.

OBJECTIVE: Various EEG source localization methods have been proposed for functional brain research. The evaluation and comparison of these methods are usually based on simulated data but not real EEG data, as the ground truth of source localization is unknown. In this study, we aim to evaluate source localization methods quantitatively under the real situation. METHODS: We examined the test-retest reliability of the source signals reconstructed from a public six-session EEG data of 16 subjects performing face recognition tasks by five mainstream methods, including weighted minimum norm estimation (WMN), dynamical Statistical Parametric Mapping (dSPM), Standardized LOw Resolution brain Electromagnetic TomogrAphy (sLORETA), dipole modeling and linearly constrained minimum variance (LCMV) beamformers. All methods were evaluated in terms of peak localization reliability and amplitude reliability of source signals. RESULTS: In the two brain regions responsible for static face recognition, all methods have promising peak localization reliability, with WMN showing the smallest peak dipole distance between session pairs. The spatial stability of source localization in the familiar face condition is better than those in the unfamiliar face and the scrambled face conditions in the face recognition areas in the right hemisphere. In addition, the test-retest reliability of source amplitude by all methods is good to excellent under the familiar face condition. CONCLUSION: Stable and reliable results for source localization can be obtained in the presence of evident EEG effects. Due to different levels of a priori knowledge, different source localization methods have different applicable scenarios. SIGNIFICANCE: These findings provide new evidence for the validity of source localization analysis and a new perspective for the evaluation of source localization methods on real EEG data.

The enhanced visible light driven photocatalytic activity of zinc porphyrin/g-C3N4 nanosheet for efficient bacterial infected wound healing.

Graphitic carbon nitride (g-C3N4) has received much attention as a metal-free polymeric two-dimensional photocatalyst for antibiotic-free antibacterial application. However, the weak photocatalytic antibacterial activity of pure g-C3N4 stimulated by visible light limits its applications. Herein, g-C3N4 is modified with Zinc (II) meso-tetrakis (4-carboxyphenyl) porphyrin (ZnTCPP) by amidation reaction to enhance the utilization of visible light and reduce the recombination of electron-hole pairs. The composite (ZP/CN) is used to treat bacterial infection under visible light irradiation with a high efficacy of 99.99% within 10 min due to the enhanced photocatalytic activity. Ultraviolet photoelectron spectroscopy and density flooding theory calculations indicate the excellent electrical conductivity between the interface of ZnTCPP and g-C3N4. The formed built-in electric field is responsible for the high visible photocatalytic performance of ZP/CN. In vitro and in vivo tests have demonstrated that ZP/CN not only possesses excellent antibacterial activity upon visible light irradiation, but also facilitates the angiogenesis. In addition, ZP/CN also suppresses the inflammatory response. Therefore, this inorganic-organic material can serve as a promising platform for effective healing of bacteria-infected wounds.

Dynamic network biomarker to determine the critical point of breast cancer stage progression.

BACKGROUND: The discovery of early warning signs and biomarkers in patients with early breast cancer is crucial for the prevention and treatment of breast cancer. Dynamic Network Biomarker (DNB) is an approach based on nonlinear dynamics theory, which we exploited to identify a set of DNB members and their key genes as early warning signals during breast cancer staging progression. METHODS: First, based on the gene expression profile of breast cancer in the TCGA database, the DNB algorithm was used to calculate the composite index (CI) of each gene cluster in the process of breast cancer anatomical staging. Then we calculated gene modules associated with the clinical phenotype stage based on weighted gene co-expression network analysis (WGCNA), combined with DNB membership to identify key genes in the network. RESULTS: We identified a set of gene clusters with the highest CI in Stage II as DNBs, whose roles in related pathways indicate the emergence of a tipping point and impact on breast cancer development. In addition, analysis of the key gene GPRIN1 showed that high expression of GPRIN1 predicts poor prognosis, and related immune analysis showed that GPRIN1 is involved in the development of breast cancer through immune aspects. CONCLUSION: The discovery of DNBs and the key gene GPRIN1 can provide potential biomarkers and therapeutic targets for breast cancer.

Transcranial ultrasound stimulation modulates the interhemispheric balance of excitability in human motor cortex.

Background. Low-intensity transcranial ultrasound stimulation (TUS) could induce both immediate and long-lasting neuromodulatory effects in human brains. Interhemispheric imbalance at prefrontal or motor cortices generally associates with various cognitive decline in aging and mental disorders. However, whether TUS could modulate the interhemispheric balance of excitability in human brain remains unknown.Objective. This study aims to explore whether repetitive TUS (rTUS) intervention can modulate the interhemispheric balance of excitability between bilateral motor cortex (M1) in healthy subjects.Approach. Motor evoked potentials (MEPs) at bilateral M1 were measured at 15 min and 0 min before a 15 min active or sham rTUS intervention on left M1 and at 0 min, 15 min and 30 min after the intervention, and the Chinese version of brief neurocognitive test battery (C-BCT) was conducted before and after the intervention respectively. Cortical excitability was quantified by MEPs, and the long-lasting changes of MEP amplitude was used as an index of plasticity.Results. In the active rTUS group (n= 20), the ipsilateral MEP amplitude increased significantly compared with baselines and lasted for up to 30 min after intervention, while the contralateral MEP amplitude decreased lasting for 15 min, yielding increased laterality between bilateral MEPs. Furthermore, rTUS intervention induced changes in some C-BCT scores, and the changes of scores correlated with the changes of MEP amplitudes induced by rTUS intervention. The sham rTUS group (n= 20) showed no significant changes in MEPs and C-BCT scores. In addition, no participants reported any adverse effects during and after the rTUS intervention, and no obvious temperature increase appeared in skull or brain tissues in simulation.Significance. rTUS intervention modulated the plasticity of ipsilateral M1 and the interhemispheric balance of M1 excitability in human brain, and improved cognitive performance, suggesting a considerable potential of rTUS in clinical interventions.

Comparison of Traditional Radiomics, Deep Learning Radiomics and Fusion Methods for Axillary Lymph Node Metastasis Prediction in Breast Cancer.

RATIONALE AND OBJECTIVES: Accurate identification of axillary lymph node (ALN) status in breast cancer patients is important for determining treatment options and avoiding axillary overtreatments. Our study aims to comprehensively compare the performance of the traditional radiomics model, deep learning radiomics model, and the fusion models in evaluating breast cancer ALN status based on dynamic contrast-enhanced-magnetic resonance imaging (DCE-MRI) images. MATERIALS AND METHODS: The handcrafted radiomics features and deep features were extracted from 3062 DCE-MRI images. The feature selection was performed by applying mutual information and feature recursive elimination algorithms. The traditional radiomics model and deep learning radiomics model were built using the optimal features and machine learning classifiers, respectively. The fusion models for distinguishing axillary lymph node status were constructed using two fusion strategies. The performance of the models with MRI-reported lymphadenopathy or suspicious nodes to evaluate axillary lymph node status was also compared. RESULTS: The decision fusion model, with the integration of the radiomics features and deep learning features at the decision level, achieved an area under the curve (AUC) of 0.91 (95% confidence interval (CI): 0.879-0.937), which was higher than that of the traditional radiomics model and deep learning radiomics model. The results of the decision fusion model with clinical characteristic yielded an AUC of 0.93 (95% CI: 0.899-0.951), which was also superior to other models incorporating clinical characteristic. CONCLUSION: This study demonstrates the effectiveness of the fusion models for predicting axillary lymph node metastasis in breast cancer.

Analysis of Breast Cancer Differences between China and Western Countries Based on Radiogenomics.

Using radiogenomics methods, the differences between tumor imaging data and genetic data in Chinese and Western breast cancer (BC) patients were analyzed, and the correlation between phenotypic data and genetic data was explored. In this paper, we analyzed BC patients' image characteristics and transcriptome data separately, then correlated the magnetic resonance imaging (MRI) phenotype with the transcriptome data through a computational method to develop a radiogenomics feature. The data was fed into the designed random forest (RF) model, which used the area under the receiver operating curve (AUC) as the evaluation index. Next, we analyzed the hub genes in the differentially expressed genes (DEGs) and obtained seven hub genes, which may cause Chinese and Western BC patients to behave differently in the clinic. We demonstrated that combining relevant genetic data and imaging features could better classify Chinese and Western patients than using genes or imaging characteristics alone. The AUC values of 0.74, 0.81, and 0.95 were obtained separately using the image characteristics, DEGs, and radiogenomics features. We screened SYT4, GABRG2, CHGA, SLC6A17, NEUROG2, COL2A1, and MATN4 and found that these genes were positively or negatively correlated with certain imaging characteristics. In addition, we found that the SLC6A17, NEUROG2, CHGA, and MATN4 genes were associated with clinical features.

Orientation algorithm for PPI networks based on network propagation approach.

Biological signal transduction of protein-protein interaction (PPI) networks occupies an important position in life activities because it affects the regulation mechanisms of growth, development and metabolism. To further understand the realization of cellular biological functions, we need to predict the directionality of PPIs. This study combines protein semantic similarity and overlapping clustering algorithm to improve the network propagation method for orientating signal transduction networks. This orientation algorithm was applied to an integrin-mediated PPI network (containing 1166 PPIs). As a result, 484 unoriented PPIs (forming protein complexes) and 682 oriented PPIs (interactions involving signal transmission) were obtained. Finally, in order to evaluate the effectiveness of this method, it was compared with the original method based on network propagation, and acceptable results were obtained.

Ti3 C2 TX MXene Modified with ZnTCPP with Bacteria Capturing Capability and Enhanced Visible Light Photocatalytic Antibacterial Activity.

Light-assisted antibacterial therapy is a promising alternative to antibiotic therapy due to the high antibacterial efficacy without bacterial resistance. Recent research has mainly focused on the use of near-infrared light irradiation to kill bacteria by taking advantage of the synergistic effects rendered by hyperthermia and radical oxygen species. However, photocatalytic antibacterial therapy excited by visible light is more convenient and practical, especially for wounds. Herein, a visible light responsive organic-inorganic hybrid of ZnTCPP/Ti3 C2 TX is designed and fabricated to treat bacterial infection with antibacterial efficiency of 99.86% and 99.92% within 10 min against Staphylococcus aureus and Escherichia coli, respectively. The porphyrin-metal complex, ZnTCPP, is assembled on the surface of Ti3 C2 TX MXene to capture bacteria electrostatically and the Schottky junction formed between Ti3 C2 TX and ZnTCPP promotes visible light utilization, accelerates charge separation, and enhances the mobility of photogenerated charges, and finally increases the photocatalytic activity. As a result of the excellent bacteria capturing ability and photocatalytic antibacterial effects, ZnTCPP/Ti3 C2 TX exposed to visible light has excellent antibacterial properties in vitro and in vivo. Therefore, organic-inorganic materials that have been demonstrated to possess good biocompatibility and enhance wound healing have large potential in bio-photocatalysis, antibacterial therapy, as well as antibiotics-free treatment of wounds.

Test-retest reliability of mismatch negativity and gamma-band auditory steady-state response in patients with schizophrenia.

Patients with schizophrenia show widespread impairments in clinical, cognitive and psychosocial functioning. Mismatch negativity (MMN) and gamma-band auditory steady-state response (ASSR) are two neurophysiological biomarkers widely used to inform diagnosis, guide treatments and track response to interventions in schizophrenia. However, evidence for the test-retest reliability of these indices across multiple sessions in schizophrenia patients remains scarce. In the present study, we included 34 schizophrenia patients (17 females) and obtained duration MMN (dMMN), frequency MMN (fMMN) and 40-Hz ASSR data across three sessions with intervals of 2 days. Event-related spectrum perturbation (ERSP) and inter-trial coherence (ITC) were calculated following Morlet wavelet time-frequency decomposition of ASSR data. The intra-class correlation coefficient (ICC) was used to quantify the reliability of MMN and ASSR measures among the three sessions. We found fair to good reliability for dMMN amplitudes but poor reliability for fMMN amplitudes. For the ASSR measures, ERSP showed good to excellent test-retest reliability while ITC had poor to fair test-retest reliability. In addition, the average of dMMN amplitudes was significantly correlated with that of ERSP across the three sessions. In summary, we established for the first time the short-term test-retest reliability of MMN and ASSR measures in schizophrenia patients. These findings demonstrate that dMMN amplitudes and ERSP of ASSR are reliable indices which may be used in longitudinal observational studies.

Test-retest reliability of duration-related and frequency-related mismatch negativity.

OBJECTIVES: -Mismatch negativity (MMN) has been demonstrated as a potential biomarker for pre-attentive processing and prognosis in patients with psychosis. However, previous studies mainly evaluated the reliability of MMN across only two repeated sessions, which is inadequate to draw a convincing conclusion. The current study aimed to assess multi-session test-retest reliability in duration-related MMN (dMMN) and frequency-related MMN (fMMN). METHODS: -We recorded four repeated sessions of electroencephalography (EEG) from 16 healthy participants in an oddball task. MMNs were extracted and their reliability was evaluated by intra-class coefficient (ICC). We also analyzed the correlation between fMMN and dMMN. RESULTS: -Both dMMN and fMMN amplitudes exhibited good test-retest reliability, and fMMN had better reliability (average ICC = 0.7279) than dMMN (average ICC = 0.6974). Moreover, dMMN and fMMN showed more than moderate linear correlation in amplitudes (r = 0.598, CI: [0.100, 0.857]). CONCLUSION: -Both the duration- and frequency-related MMN amplitudes were highly reliable across four-session experiments. These results provide further evidence for the potential utility of MMNs as biomarkers in research into brain function, and prognosis in psychotic illness.

Spatial-Frequency dual-branch attention model for determining KRAS mutation status in colorectal cancer with T2-weighted MRI.

BACKGROUND AND OBJECTIVE: Identifying the KRAS mutation status accurately in medical images is very important for the diagnosis and treatment of colorectal cancer. Despite the substantial progress achieved by existing methods, it remains challenging due to limited annotated dataset, large intra-class variances, and a high degree of inter-class similarities. METHODS: To tackle these challenges, we propose a spatial-frequency dual-branch attention model (SF-DBAM) to determine the KRAS mutation status of colorectal cancer patients using a limited T2-weighted MRI dataset. The dataset contains 169 wild-type patients (2151 images) and 137 mutation-type patients (1666 images). The first branch utilizes part of the pre-trained Xception model to capture spatial-domain information and alleviate the small-scale dataset problem. The second branch builds frequency-domain information into cube columns using block-based discrete cosine transform and channel rearrangement. Then the cube columns are fed into convolutional long short-term memory (convLSTM) to explore the effective information between the reconstructed frequency-domain channels. Also, we design a channel enhanced attention module (CEAM) at the end of each branch to make them focus on the lesion areas. Finally, we concatenate the two branches and output the classified results through fully connected layers. RESULTS: The proposed method achieves 88.03% overall accuracy with AUC of 94.27% and specificity of 90.75% in 10-fold cross-validation, which is better than the current non-invasive methods for determining KRAS mutation status. CONCLUSIONS: We believe that the proposed method can assist physicians to diagnose the KRAS mutation status in patients with colorectal cancer, and other medical problems can benefit from the spatial and frequency domains information.

The lateralization and reliability of spatial mismatch negativity elicited by auditory deviants with virtual spatial location.

Mismatch negativity (MMN) is an intensively studied event-related potential component that reflects pre-attentive auditory processing. Existing spatial MMN (sMMN) studies usually use loud-speakers in different locations or deliver sound with binaural localization cues through earphones to elicit MMN, which either was practically complicated or sounded unnatural to the subjects. In the present study, we generated head related transfer function (HRTF)-based spatial sounds and verified that the HRTF-based sounds retained the left and the right spatial localization cues. We further used them as deviants to elicit sMMN with conventional oddball paradigm. Results showed that sMMN was successfully elicited by the HRTF-based deviants in 18 of 21 healthy subjects in two separate sessions. Furthermore, the left deviants elicited higher sMMN amplitudes in the right hemisphere compared to the left hemisphere, while the right deviants elicited sMMN with similar amplitudes in both hemispheres, which supports a combination of contralateral and right-hemispheric dominance in spatial auditory information processing. In addition, the sMMN in response to the right deviants showed good test-retest reliability, while the sMMN in response to the left deviants had weak test-retest reliability. These findings implicate that HRTF-based sMMN could be a robust paradigm to investigate spatial localization and discrimination abilities.