Classification of nasal polyps and inverted papillomas using CT-based radiomics.

OBJECTIVES: Nasal polyp (NP) and inverted papilloma (IP) are two common types of nasal masses. And their differentiation is essential for determining optimal surgical strategies and predicting outcomes. Thus, we aimed to develop several radiomic models to differentiate them based on computed tomography (CT)-extracted radiomic features. METHODS: A total of 296 patients with nasal polyps or papillomas were enrolled in our study. Radiomics features were extracted from non-contrast CT images. For feature selection, three methods including Boruta, random forest, and correlation coefficient were used. We choose three models, namely SVM, naive Bayes, and XGBoost, to perform binary classification on the selected features. And the data was validated with tenfold cross-validation. Then, the performance was assessed by receiver operator characteristic (ROC) curve and related parameters. RESULTS: In this study, the performance ability of the models was in the following order: XGBoost > SVM > Naive Bayes. And the XGBoost model showed excellent AUC performance at 0.922, 0.9078, 0.9184, and 0.9141 under four conditions (no feature selection, Boruta, random forest, and correlation coefficient). CONCLUSIONS: We demonstrated that CT-based radiomics plays a crucial role in distinguishing IP from NP. It can provide added diagnostic value by distinguishing benign nasal lesions and reducing the need for invasive diagnostic procedures and may play a vital role in guiding personalized treatment strategies and developing optimal therapies. CRITICAL RELEVANCE STATEMENT: Based on the extraction of radiomic features of tumor regions from non-contrast CT, optimized by radiomics to achieve non-invasive classification of IP and NP which provide support for respective therapy of IP and NP. KEY POINTS: • CT images are commonly used to diagnose IP and NP. • Radiomics excels in feature extraction and analysis. • CT-based radiomics can be applied to distinguish IP from NP. • Use multiple feature selection methods and classifier models. • Derived from real clinical cases with abundant data.

Brain disorder prediction with dynamic multivariate spatio-temporal features: Application to Alzheimer's disease and autism spectrum disorder.

The dynamic functional connectivity (dFC) in functional magnetic resonance imaging (fMRI) is beneficial for the analysis and diagnosis of neurological brain diseases. The dFCs between regions of interest (ROIs) are generally delineated by a specific template and clustered into multiple different states. However, these models inevitably fell into the model-driven self-contained system which ignored the diversity at spatial level and the dynamics at time level of the data. In this study, we proposed a spatial and time domain feature extraction approach for Alzheimer's disease (AD) and autism spectrum disorder (ASD)-assisted diagnosis which exploited the dynamic connectivity among independent functional sub networks in brain. Briefly, independent sub networks were obtained by applying spatial independent component analysis (SICA) to the preprocessed fMRI data. Then, a sliding window approach was used to segment the time series of the spatial components. After that, the functional connections within the window were obtained sequentially. Finally, a temporal signal-sensitive long short-term memory (LSTM) network was used for classification. The experimental results on Alzheimer's Disease Neuroimaging Initiative (ADNI) and Autism Brain Imaging Data Exchange (ABIDE) datasets showed that the proposed method effectively predicted the disease at the early stage and outperformed the existing algorithms. The dFCs between the different components of the brain could be used as biomarkers for the diagnosis of diseases such as AD and ASD, providing a reliable basis for the study of brain connectomics.

A novel radiomics-platelet nomogram for the prediction of gastroesophageal varices needing treatment in cirrhotic patients.

BACKGROUND AND AIMS: Highly accurate noninvasive methods for predicting gastroesophageal varices needing treatment (VNT) are desired. Radiomics is a newly emerging technology of image analysis. This study aims to develop and validate a novel noninvasive method based on radiomics for predicting VNT in cirrhosis. METHODS: In this retrospective-prospective study, a total of 245 cirrhotic patients were divided as the training set, internal validation set and external validation set. Radiomics features were extracted from portal-phase computed tomography (CT) images of each patient. A radiomics signature (Rad score) was constructed with the least absolute shrinkage and selection operator algorithm and tenfold cross-validation in the training set. Combined with independent risk factors, a radiomics nomogram was built with a multivariate logistic regression model. RESULTS: The Rad score, consisting of 14 features from the gastroesophageal region and 5 from the splenic hilum region, was effective for VNT classification. The diagnostic performance was further improved by combining the Rad score with platelet counts, achieving an AUC of 0.987 (95% CI 0.969-1.00), 0.973 (95% CI 0.939-1.00) and 0.947 (95% CI 0.876-1.00) in the training set, internal validation set and external validation set, respectively. In efficacy and safety assessment, the radiomics nomogram could spare more than 40% of endoscopic examinations with a low risk of missing VNT (< 5%), and no more than 8.3% of unnecessary endoscopic examinations still be performed. CONCLUSIONS: In this study, we developed and validated a novel, diagnostic radiomics-based nomogram which is a reliable and noninvasive method to predict VNT in cirrhotic patients. CLINICAL TRIALS REGISTRATION: NCT04210297.

Functional and Structural Brain Alterations in Encephalitis With LGI1 Antibodies.

Objective: The purpose of this study was to examine the neural substrates and mechanisms that generate memory deficits, seizures and neuropsychiatric abnormalities in encephalitis with LGI1 antibodies using a data-driven, multimodal magnetic resonance imaging (MRI) approach. Methods: Functional MRI data were acquired from 14 anti-LGI1 encephalitis patients and 14 age and gender matched normal controls. Independent component analysis with hierarchical partner matching (HPM-ICA) was used to assess the whole-brain intrinsic functional connectivity. Granger causality (GC) was applied to investigate the effective connectivity among the brain regions that identified by HPM-ICA. Diffusion tensor imaging (DTI) was utilized to investigate white matter microstructural changes of the patients. Results: Participants with LGI1 antibodies encephalitis presented reduced functional connectivity in the brain areas associated with memory, cognition and motion circuits, while increased functional connectivity in putamen and caudate in comparison to the normal controls. Moreover, the effective connectivity in patients was decreased from the frontal cortex to supplementary motor area. Finally, patients had significant reductions in fractional anisotropy (FA) for the corpus callosum, internal capsule, corona radiata and superior longitudinal fasciculus, accompanied by increases in mean diffusivity (MD) for these regions as compared to controls. Conclusion: Our findings suggest that the neural disorder and behavioral deficits of anti-LGI1 encephalitis may be associated with extensive changes in brain connectivity and microstructure. These pathological alterations affect the basal ganglia and limbic system besides the temporal and frontal lobe.

Multivariate Deep Learning Classification of Alzheimer's Disease Based on Hierarchical Partner Matching Independent Component Analysis.

Machine learning and pattern recognition have been widely investigated in order to look for the biomarkers of Alzheimer's disease (AD). However, most existing methods extract features by seed-based correlation, which not only requires prior information but also ignores the relationship between resting state functional magnetic resonance imaging (rs-fMRI) voxels. In this study, we proposed a deep learning classification framework with multivariate data-driven based feature extraction for automatic diagnosis of AD. Specifically, a three-level hierarchical partner matching independent components analysis (3LHPM-ICA) approach was proposed first in order to address the issues in spatial individual ICA, including the uncertainty of the numbers of components, the randomness of initial values, and the correspondence of ICs of multiple subjects, resulting in stable and reliable ICs which were applied as the intrinsic brain functional connectivity (FC) features. Second, Granger causality (GC) was utilized to infer directional interaction between the ICs that were identified by the 3LHPM-ICA method and extract the effective connectivity features. Finally, a deep learning classification framework was developed to distinguish AD from controls by fusing the functional and effective connectivities. A resting state fMRI dataset containing 34 AD patients and 34 normal controls (NCs) was applied to the multivariate deep learning platform, leading to a classification accuracy of 95.59%, with a sensitivity of 97.06% and a specificity of 94.12% with leave-one-out cross validation (LOOCV). The experimental results demonstrated that the measures of neural connectivities of ICA and GC followed by deep learning classification represented the most powerful methods of distinguishing AD clinical data from NCs, and these aberrant brain connectivities might serve as robust brain biomarkers for AD. This approach also allows for expansion of the methodology to classify other psychiatric disorders.

Functional neural circuits that underlie developmental stuttering.

The aim of this study was to identify differences in functional and effective brain connectivity between persons who stutter (PWS) and typically developing (TD) fluent speakers, and to assess whether those differences can serve as biomarkers to distinguish PWS from TD controls. We acquired resting-state functional magnetic resonance imaging data in 44 PWS and 50 TD controls. We then used Independent Component Analysis (ICA) together with Hierarchical Partner Matching (HPM) to identify networks of robust, functionally connected brain regions that were highly reproducible across participants, and we assessed whether connectivity differed significantly across diagnostic groups. We then used Granger Causality (GC) to study the causal interactions (effective connectivity) between the regions that ICA and HPM identified. Finally, we used a kernel support vector machine to assess how well these measures of functional connectivity and granger causality discriminate PWS from TD controls. Functional connectivity was stronger in PWS compared with TD controls in the supplementary motor area (SMA) and primary motor cortices, but weaker in inferior frontal cortex (IFG, Broca's area), caudate, putamen, and thalamus. Additionally, causal influences were significantly weaker in PWS from the IFG to SMA, and from the basal ganglia to IFG through the thalamus, compared to TD controls. ICA and GC indices together yielded an accuracy of 92.7% in classifying PWS from TD controls. Our findings suggest the presence of dysfunctional circuits that support speech planning and timing cues for the initiation and execution of motor sequences in PWS. Our high accuracy of classification further suggests that these aberrant brain features may serve as robust biomarkers for PWS.

Aberrant Functional Network Connectivity as a Biomarker of Generalized Anxiety Disorder.

Neural disruptions during emotion regulation are common of generalized anxiety disorder (GAD). Identifying distinct functional and effective connectivity patterns in GAD may provide biomarkers for their diagnoses. This study aims to investigate the differences of features of brain network connectivity between GAD patients and healthy controls (HC), and to assess whether those differences can serve as biomarkers to distinguish GAD from controls. Independent component analysis (ICA) with hierarchical partner matching (HPM-ICA) was conducted on resting-state functional magnetic resonance imaging data collected from 20 GAD patients with medicine-free and 20 matched HC, identifying nine highly reproducible and significantly different functional brain connectivity patterns across diagnostic groups. We then utilized Granger causality (GC) to study the effective connectivity between the regions that identified by HPM-ICA. The linear discriminant analysis was finally used to distinguish GAD from controls with these measures of neural connectivity. The GAD patients showed stronger functional connectivity in amygdala, insula, putamen, thalamus, and posterior cingulate cortex, but weaker in frontal and temporal cortex compared with controls. Besides, the effective connectivity in GAD was decreased from the cortex to amygdala and basal ganglia. Applying the ICA and GC features to the classifier led to a classification accuracy of 87.5%, with a sensitivity of 90.0% and a specificity of 85.0%. These findings suggest that the presence of emotion dysregulation circuits may contribute to the pathophysiology of GAD, and these aberrant brain features may serve as robust brain biomarkers for GAD.

Fractal Dimension Analysis of Subcortical Gray Matter Structures in Schizophrenia.

A failure of adaptive inference-misinterpreting available sensory information for appropriate perception and action-is at the heart of clinical manifestations of schizophrenia, implicating key subcortical structures in the brain including the hippocampus. We used high-resolution, three-dimensional (3D) fractal geometry analysis to study subtle and potentially biologically relevant structural alterations (in the geometry of protrusions, gyri and indentations, sulci) in subcortical gray matter (GM) in patients with schizophrenia relative to healthy individuals. In particular, we focus on utilizing Fractal Dimension (FD), a compact shape descriptor that can be computed using inputs with irregular (i.e., not necessarily smooth) surfaces in order to quantify complexity (of geometrical properties and configurations of structures across spatial scales) of subcortical GM in this disorder. Probabilistic (entropy-based) information FD was computed based on the box-counting approach for each of the seven subcortical structures, bilaterally, as well as the brainstem from high-resolution magnetic resonance (MR) images in chronic patients with schizophrenia (n = 19) and age-matched healthy controls (n = 19) (age ranges: patients, 22.7-54.3 and healthy controls, 24.9-51.6 years old). We found a significant reduction of FD in the left hippocampus (median: 2.1460, range: 2.07-2.18 vs. median: 2.1730, range: 2.15-2.23, p<0.001; Cohen's effect size, U3 = 0.8158 (95% Confidence Intervals, CIs: 0.6316, 1.0)), the right hippocampus (median: 2.1430, range: 2.05-2.19 vs. median: 2.1760, range: 2.12-2.21, p = 0.004; U3 = 0.8421 (CIs: 0.5263, 1)), as well as left thalamus (median: 2.4230, range: 2.40-2.44, p = 0.005; U3 = 0.7895 (CIs: 0.5789, 0.9473)) in schizophrenia patients, relative to healthy individuals. Our findings provide in-vivo quantitative evidence for reduced surface complexity of hippocampus, with reduced FD indicating a less complex, less regular GM surface detected in schizophrenia.

Sex-specific neural activity when resolving cognitive interference in individuals with or without prior internalizing disorders.

The processing of cognitive interference is a self-regulatory capacity that is impaired in persons with internalizing disorders. This investigation was to assess sex differences in the neural correlates of cognitive interference in individuals with and without an illness history of an internalizing disorder. We compared functional magnetic resonance imaging blood-oxygenation-level-dependent responses in both males (n=63) and females (n=80) with and without this illness history during performance of the Simon task. Females deactivated superior frontal gyrus, inferior parietal lobe, and posterior cingulate cortex to a greater extent than males. Females with a prior history of internalizing disorder also deactivated these regions more compared to males with that history, and they additionally demonstrated greater activation of right inferior frontal gyrus. These group differences were represented in a significant sex-by-illness interaction in these regions. These deactivated regions compose a task-negative or default mode network, whereas the inferior frontal gyrus usually activates when performing an attention-demanding task and is a key component of a task-positive network. Our findings suggest that a prior history of internalizing disorders disproportionately influences functioning of the default mode network and is associated with an accompanying activation of the task-positive network in females during the resolution of cognitive interference.

Brain activity classifies adolescents with and without a familial history of substance use disorders.

We aimed to uncover differences in brain circuits of adolescents with parental positive or negative histories of substance use disorders (SUD), when performing a task that elicits emotional conflict, testing whether the brain circuits could serve as endophenotype markers to distinguish these adolescents. We acquired functional magnetic resonance imaging data from 11 adolescents with a positive familial history of SUD (FH+ group) and seven adolescents with a negative familial history of SUD (FH- group) when performing an emotional stroop task. We extracted brain features from the conflict-related contrast images in group level analyses and granger causality indices (GCIs) that measure the causal interactions among regions. Support vector machine (SVM) was applied to classify the FH+ and FH- adolescents. Adolescents with FH+ showed greater activity and weaker connectivity related to emotional conflict, decision making and reward system including anterior cingulate cortex (ACC), prefrontal cortex (PFC), and ventral tegmental area (VTA). High classification accuracies were achieved with leave-one-out cross validation (89.75% for the maximum conflict, 96.71% when combining maximum conflict and general conflict contrast, 97.28% when combining activity of the two contrasts and GCIs). Individual contributions of the brain features to the classification were further investigated, indicating that activation in PFC, ACC, VTA and effective connectivity from PFC to ACC play the most important roles. We concluded that fundamental differences of neural substrates underlying cognitive behaviors of adolescents with parental positive or negative histories of SUD provide new insight into potential neurobiological mechanisms contributing to the elevated risk of FH+ individuals for developing SUD.

Normalization of Intrinsic Neural Circuits Governing Tourette's Syndrome Using Cranial Electrotherapy Stimulation.

GOAL: The aim of this study was to investigate the normalization of the intrinsic functional activity and connectivity of TS adolescents before and after the cranial electrotherapy stimulation (CES) with alpha stim device. METHODS: We performed resting-state functional magnetic resonance imaging on eight adolescents before and after CES with mean age of about nine-years old who had Tourette's syndrome with moderate to severe tics symptom. Independent component analysis (ICA) with hierarchical partner matching method was used to examine the functional connectivity between regions within cortico-striato-thalamo-cortical (CSTC) circuit. Granger causality was used to investigate effective connectivity among these regions detected by ICA. We then performed pattern classification on independent components with significant group differences that served as endophenotype markers to distinguish the adolescents between TS and the normalized ones after CES. RESULTS: Results showed that TS adolescents after CES treatment had stronger functional activity and connectivity in anterior cingulate cortex (ACC), caudate and posterior cingulate cortex while had weaker activity in supplementary motor area within the motor pathway compared with TS before CES. CONCLUSION: The results suggest that the functional activity and connectivity in motor pathway was suppressed while activities in the control portions within CSTC loop including ACC and caudate were increased in TS adolescents after CES compared with adolescents before CES. SIGNIFICANCE: The normalization of the balance between motor and control portions of the CSTC circuit may result in the recovery of TS adolescents.