Frequency-Specific Changes of Resting Brain Activity in Parkinson’s Disease: A Machine Learning Approach

Temporal dynamics of offline transcranial ultrasound stimulation

Transcranial ultrasound stimulation (TUS) is a promising non-invasive neuromodulation modality, characterized by deep-brain accuracy and the capability to induce longer-lasting effects. However, most TUS datasets are underpowered, hampering efforts to identify TUS longevity and temporal dynamics. This primate case was studied awake with over 50 fMRI datasets, with and without left anterior hippocampus TUS. We therefore amassed the highest-powered TUS dataset to date required to reveal TUS longevity and dynamics. Most of the effects were found in the TUS region itself and alongside the default mode and sensorimotor networks. Seed-based functional connectivity exhibited a time-constrained alteration which dissipated ∼60 min post-TUS. Intrinsic activity measure and regional homogeneity displayed extended diffusivity and longer durations. This high-powered dataset allowed predicting TUS using pre-stimulation features that can now extend to modeling of individuals scanned less extensively. This case report reveals the diversity of TUS temporal dynamics to help to advance long-lasting human applications.

Dark brain energy: Toward an integrative model of spontaneous slow oscillations

Neural oscillations facilitate the functioning of the human brain in spatial and temporal dimensions at various frequencies. These oscillations feature a universal frequency architecture that is governed by brain anatomy, ensuring frequency specificity remains invariant across different measurement techniques. Initial magnetic resonance imaging (MRI) methodology constrained functional MRI (fMRI) investigations to a singular frequency range, thereby neglecting the frequency characteristics inherent in blood oxygen level-dependent oscillations. With advancements in MRI technology, it has become feasible to decode intricate brain activities via multi-band frequency analysis (MBFA). During the past decade, the utilization of MBFA in fMRI studies has surged, unveiling frequency-dependent characteristics of spontaneous slow oscillations (SSOs) believed to base dark energy in the brain. There remains a dearth of conclusive insights and hypotheses pertaining to the properties and functionalities of SSOs in distinct bands. We surveyed the SSO MBFA studies during the past 15 years to delineate the attributes of SSOs and enlighten their correlated functions. We further proposed a model to elucidate the hierarchical organization of multi-band SSOs by integrating their function, aimed at bridging theoretical gaps and guiding future MBFA research endeavors.

Machine Learning Approaches to Identify Affected Brain Regions in Movement Disorders Using MRI Data: A Systematic Review and Diagnostic Meta-analysis

BACKGROUND

Movement disorders such as Parkinson's disease are associated with structural and functional changes in specific brain regions. Advanced magnetic resonance imaging (MRI) techniques combined with machine learning (ML) are promising tools for identifying imaging biomarkers and patterns associated with these disorders.

PURPOSE/HYPOTHESIS

We aimed to systematically identify the brain regions most commonly affected in movement disorders using ML approaches applied to structural and functional MRI data. We searched the PubMed and Scopus databases using relevant keywords up to June 2023 for studies that used ML approaches to detect brain regions associated with movement disorders using MRI data.

STUDY TYPE

A systematic review and diagnostic meta-analysis.

POPULATION/SUBJECTS

Sixty-seven studies with 6,285 patients were included.

FIELD STRENGTH/SEQUENCE

Studies utilizing 1.5T or 3T MR scanners and the acquisition of diffusion tensor imaging (DTI), structural MRI (sMRI), functional MRI (fMRI), or a combination of these were included.

ASSESSMENT

The authors independently assessed the study quality using the CLAIM and QUADAS-2 criteria and extracted data on diagnostic accuracy measures.

STATISTICAL TESTS

Sensitivity, specificity, accuracy, and area under the curve were pooled using random-effects models. Q statistics and the I2 index were used to evaluate heterogeneity, and Begg's funnel plot was used to identify publication bias.

RESULTS

sMRI showed the highest sensitivity (93%) and mixed modalities had the highest specificity (90%) for detecting regional abnormalities. sMRI had a 94% sensitivity for identifying subcortical changes. The support vector machine (93%) and logistic regression (91%) models exhibited high diagnostic accuracies.

DATA CONCLUSION

The combination of advanced MR neuroimaging techniques and ML is a promising approach for identifying brain biomarkers and affected regions in movement disorders with subcortical structures frequently implicated. Structural MRI, in particular, showed strong performance.

LEVEL OF EVIDENCE

1 TECHNICAL EFFICACY: Stage 2.

Multimodal data fusion reveals functional and neurochemical correlates of Parkinson's disease

BACKGROUND

Neurotransmitter deficits and spatial associations among neurotransmitter distribution, brain activity, and clinical features in Parkinson's disease (PD) remain unclear. Better understanding of neurotransmitter impairments in PD may provide potential therapeutic targets. Therefore, we aimed to investigate the spatial relationship between PD-related patterns and neurotransmitter deficits.

METHODS

We included 59 patients with PD and 41 age- and sex-matched healthy controls (HCs). The voxel-wise mean amplitude of the low-frequency fluctuation (mALFF) was calculated and compared between the two groups. The JuSpace toolbox was used to test whether spatial patterns of mALFF alterations in patients with PD were associated with specific neurotransmitter receptor/transporter densities.

RESULTS

Compared to HCs, patients with PD showed reduced mALFF in the sensorimotor- and visual-related regions. In addition, mALFF alteration patterns were significantly associated with the spatial distribution of the serotonergic, dopaminergic, noradrenergic, glutamatergic, cannabinoid, and acetylcholinergic neurotransmitter systems (p < 0.05, false discovery rate-corrected).

CONCLUSIONS

Our results revealed abnormal brain activity patterns and specific neurotransmitter deficits in patients with PD, which may provide new insights into the mechanisms and potential targets for pharmacotherapy.

Dynamical and individualised approach of transcranial ultrasound neuromodulation effects in non-human primates

Low-frequency transcranial ultrasound stimulation (TUS) allows to alter brain functioning with a high spatial resolution and to reach deep targets. However, the time-course of TUS effects remains largely unknown. We applied TUS on three brain targets for three different monkeys: the anterior medial prefrontal cortex, the supplementary motor area and the perigenual anterior cingulate cortex. For each, one resting-state fMRI was acquired between 30 and 150 min after TUS as well as one without stimulation (control). We captured seed-based brain connectivity changes dynamically and on an individual basis. We also assessed between individuals and between targets homogeneity and brain features that predicted TUS changes. We found that TUS prompts heterogenous functional connectivity alterations yet retain certain consistent changes; we identified 6 time-courses of changes including transient and long duration alterations; with a notable degree of accuracy we found that brain alterations could partially be predicted. Altogether, our results highlight that TUS induces heterogeneous functional connectivity alterations. On a more technical point, we also emphasize the need to consider brain changes over-time rather than just observed during a snapshot; to consider inter-individual variability since changes could be highly different from one individual to another.

Altered dynamic amplitude of low-frequency fluctuation in individuals at high risk for Alzheimer's disease

The brain's dynamic spontaneous neural activity is significant in supporting cognition; however, how brain dynamics go awry in subjective cognitive decline (SCD) and mild cognitive impairment (MCI) remains unclear. Thus, the current study aimed to investigate the dynamic amplitude of low-frequency fluctuation (dALFF) alterations in patients at high risk for Alzheimer's disease and to explore its correlation with clinical cognitive assessment scales, to identify an early imaging sign for these special populations. A total of 152 participants, including 72 SCD patients, 44 MCI patients and 36 healthy controls (HCs), underwent a resting-state functional magnetic resonance imaging and were assessed with various neuropsychological tests. The dALFF was measured using sliding-window analysis. We employed canonical correlation analysis (CCA) to examine the bi-multivariate correlations between neuropsychological scales and altered dALFF among multiple regions in SCD and MCI patients. Compared to those in the HC group, both the MCI and SCD groups showed higher dALFF values in the right opercular inferior frontal gyrus (voxel P < .001, cluster P < .05, correction). Moreover, the CCA models revealed that behavioural tests relevant to inattention correlated with the dALFF of the right middle frontal gyrus and right opercular inferior frontal gyrus, which are involved in frontoparietal networks (R = .43, P = .024). In conclusion, the brain dynamics of neural activity in frontal areas provide insights into the shared neural basis underlying SCD and MCI.

Altered local spontaneous brain activity pattern in children with right-eye amblyopia of varying degrees: evidence from fMRI

PURPOSE

To investigate the abnormal changes of local brain activity in children with right-eye amblyopia of varying degrees.

METHODS

Data of resting-state functional magnetic resonance imaging were collected from 16 children with severe amblyopia, 17 children with mild to moderate amblyopia, and 15 children with normal binocular vision. Local brain activity was analyzed using the amplitude of low-frequency fluctuations (ALFF) and regional homogeneity (ReHo).

RESULTS

There were extensive ALFF differences among the three groups in 10 brain regions. There were extensive differences in ReHo among the three groups in 11 brain regions. The ALFF and ReHo of the right orbital part of the middle frontal gyrus displayed a significantly positive correlation with the best-corrected visual acuity of the right eye, respectively. The ALFF value and ReHo value of the right orbital part of the middle frontal gyrus followed the pattern of normal control < mild to moderate amblyopia < severe amblyopia.

CONCLUSION

This study demonstrated that there were changes in specific patterns of ALFF and ReHo in children with right-eye amblyopia of different degrees in brain regions performing visual sensorimotor and attentional control functions.

Using histogram analysis of the intrinsic brain activity mapping to identify essential tremor

Background

Essential tremor (ET) is one of the most common movement disorders. Histogram analysis based on brain intrinsic activity imaging is a promising way to identify ET patients from healthy controls (HCs) and further explore the spontaneous brain activity change mechanisms and build the potential diagnostic biomarker in ET patients.

Methods

The histogram features based on the Resting-state functional magnetic resonance imaging (Rs-fMRI) data were extracted from 133 ET patients and 135 well-matched HCs as the input features. Then, a two-sample t-test, the mutual information, and the least absolute shrinkage and selection operator methods were applied to reduce the feature dimensionality. Support vector machine (SVM), logistic regression (LR), random forest (RF), and k-nearest neighbor (KNN) were used to differentiate ET and HCs, and classification performance of the established models was evaluated by the mean area under the curve (AUC). Moreover, correlation analysis was carried out between the selected histogram features and clinical tremor characteristics.

Results

Each classifier achieved a good classification performance in training and testing sets. The mean accuracy and area under the curve (AUC) of SVM, LR, RF, and KNN in the testing set were 92.62%, 0.948; 92.01%, 0.942; 93.88%, 0.941; and 92.27%, 0.939, respectively. The most power-discriminative features were mainly located in the cerebello-thalamo-motor and non-motor cortical pathways. Correlation analysis showed that there were two histogram features negatively and one positively correlated with tremor severity.

Conclusion

Our findings demonstrated that the histogram analysis of the amplitude of low-frequency fluctuation (ALFF) images with multiple machine learning algorithms could identify ET patients from HCs and help to understand the spontaneous brain activity pathogenesis mechanisms in ET patients.

A schizophrenia study based on multi-frequency dynamic functional connectivity analysis of fMRI

At present, fMRI studies mainly focus on the entire low-frequency band (0. 01-0.08 Hz). However, the neuronal activity is dynamic, and different frequency bands may contain different information. Therefore, a novel multi-frequency-based dynamic functional connectivity (dFC) analysis method was proposed in this study, which was then applied to a schizophrenia study. First, three frequency bands (Conventional: 0.01-0.08 Hz, Slow-5: 0.0111-0.0302 Hz, and Slow-4: 0.0302-0.0820 Hz) were obtained using Fast Fourier Transform. Next, the fractional amplitude of low-frequency fluctuations was used to identify abnormal regions of interest (ROIs) of schizophrenia, and dFC among these abnormal ROIs was implemented by the sliding time window method at four window-widths. Finally, recursive feature elimination was employed to select features, and the support vector machine was applied for the classification of patients with schizophrenia and healthy controls. The experimental results showed that the proposed multi-frequency method (Combined: Slow-5 and Slow-4) had a better classification performance compared with the conventional method at shorter sliding window-widths. In conclusion, our results revealed that the dFCs among the abnormal ROIs varied at different frequency bands and the efficiency of combining multiple features from different frequency bands can improve classification performance. Therefore, it would be a promising approach for identifying brain alterations in schizophrenia.

Alterations in regional homogeneity and functional connectivity associated with cognitive impairment in patients with hypertension: a resting-state functional magnetic resonance imaging study

Our study aims to investigate the alterations and diagnostic efficiency of regional homogeneity (ReHo) and functional connectivity (FC) in hypertension patients with cognitive impairment. A total of 62 hypertension patients with cognitive impairment (HTN-CI), 59 hypertension patients with normal cognition (HTN-NC), and 58 healthy controls (HCs) with rs-fMRI data were enrolled in this study. Univariate analysis (based on whole-brain ReHo and seed-based FC maps) was performed to observe brain regions with significant differences among the three groups. Multiple voxel pattern analysis (MVPA) was applied to evaluate the diagnostic accuracy in classifying HTN-CI from HTN-NC and HCs. Compared with the HCs and HTN-NC, HTN-CI exhibited decreased ReHo in the right caudate, left postcentral gyrus, posterior cingulate gyrus, insula, while increased ReHo in the left superior occipital gyrus and superior parietal gyrus. HTN-CI showed increased FC between seed regions (left posterior cingulate gyrus, insula, postcentral gyrus) with many specific brain regions. MVPA analysis (based on whole-brain ReHo and seed-based FC maps) displayed high classification ability in distinguishing HTN-CI from HTN-NC and HCs. The ReHo values (right caudate) and the FC values (left postcentral gyrus seed to left posterior cingulate gyrus) were positively correlated with the MoCA scores in HTN-CI. HTN-CI was associated with decreased ReHo and increased FC mainly in the left posterior cingulate gyrus, postcentral gyrus, insula compared to HTN-NC and HC. Besides, MVPA analysis yields excellent diagnostic accuracy in classifying HTN-CI from HTN-NC and HCs. The findings may contribute to unveiling the underlying neuropathological mechanism of HTN-CI.

Amplitude of low-frequency fluctuation-based regional radiomics similarity network: Biomarker for Parkinson's disease

Parkinson's disease (PD) is a highly heterogeneous disorder that is difficult to diagnose. Therefore, reliable biomarkers are needed. We implemented a method constructing a regional radiomics similarity network (R2SN) based on the amplitude of low-frequency fluctuation (ALFF). We classified patients with PD and healthy individuals by using a machine learning approach in accordance with the R2SN connectome. The ALFF-based R2SN exhibited great reproducibility with different brain atlases and datasets. Great classification performances were achieved both in primary (AUC = 0.85 ± 0.02 and accuracy = 0.81 ± 0.03) and independent external validation (AUC = 0.77 and accuracy = 0.70) datasets. The discriminative R2SN edges correlated with the clinical evaluations of patients with PD. The nodes of discriminative R2SN edges were primarily located in the default mode, sensorimotor, executive control, visual and frontoparietal network, cerebellum and striatum. These findings demonstrate that ALFF-based R2SN is a robust potential neuroimaging biomarker for PD and could provide new insights into connectome reorganization in PD.

Abnormal amygdala functional connectivity and deep learning classification in multifrequency bands in autism spectrum disorder: A multisite functional magnetic resonance imaging study

Previous studies have explored resting-state functional connectivity (rs-FC) of the amygdala in patients with autism spectrum disorder (ASD). However, it remains unclear whether there are frequency-specific FC alterations of the amygdala in ASD and whether FC in specific frequency bands can be used to distinguish patients with ASD from typical controls (TCs). Data from 306 patients with ASD and 314 age-matched and sex-matched TCs were collected from 28 sites in the Autism Brain Imaging Data Exchange database. The bilateral amygdala, defined as the seed regions, was used to perform seed-based FC analyses in the conventional, slow-5, and slow-4 frequency bands at each site. Image-based meta-analyses were used to obtain consistent brain regions across 28 sites in the three frequency bands. By combining generative adversarial networks and deep neural networks, a deep learning approach was applied to distinguish patients with ASD from TCs. The meta-analysis results showed frequency band specificity of FC in ASD, which was reflected in the slow-5 frequency band instead of the conventional and slow-4 frequency bands. The deep learning results showed that, compared with the conventional and slow-4 frequency bands, the slow-5 frequency band exhibited a higher accuracy of 74.73%, precision of 74.58%, recall of 75.05%, and area under the curve of 0.811 to distinguish patients with ASD from TCs. These findings may help us to understand the pathological mechanisms of ASD and provide preliminary guidance for the clinical diagnosis of ASD.

Neuroimaging biomarkers for detecting schizophrenia: A resting-state functional MRI-based radiomics analysis

Schizophrenia (SZ) is a common psychiatric disorder that is difficult to accurately diagnose in clinical practice. Quantifiable biomarkers are urgently required to explore the potential physiological mechanism of SZ and improve its diagnostic accuracy. Thus, this study aimed to identify biomarkers that classify SZ patients and healthy control subjects and investigate the potential neural mechanisms of SZ using degree centrality (DC)- and voxel-mirrored homotopic connectivity (VMHC)-based radiomics. Radiomics features were extracted from DC and VMHC metrics generated via resting-state functional magnetic resonance imaging, and significant features were selected and dimensionality was reduced using t-tests and least absolute shrinkage and selection operator. Subsequently, we built our model using a support vector machine classifier. We observed that our method obtained great classification performance (area under the curve, 0.808; accuracy, 74.02%), and it could be generalized to different brain atlases. The regions that we identified as discriminative features mainly included bilateral dorsal caudate and front-parietal, somatomotor, limbic, and default mode networks. Our findings showed that the radiomics-based machine learning method could facilitate us to understand the potential pathological mechanism of SZ more comprehensively and contribute to the accurate diagnosis of patients with SZ.

Classification of Parkinson's disease using a region-of-interest- and resting-state functional magnetic resonance imaging-based radiomics approach

To investigate the value of combining amplitude of low-frequency fluctuations-based radiomics and the support vector machine classifier method in distinguishing patients with Parkinson's disease from healthy controls. A total of 123 patients with Parkinson's disease and 90 healthy controls from three centers with functional and structural MRI images were included in this study. We extracted radiomics features using the Brainnetome 246 atlas from the mean amplitude of low-frequency fluctuations maps. Two-sample t-tests and recursive feature elimination combined with support vector machine method were applied for feature selection and dimensionality reduction. We used support vector machine classifier to construct model and identify the discriminative features. The automated anatomical labeling 90 atlas and fivefold cross-validation were used to evaluate the robustness and generalization of the classifier. We found our model obtained a high classification performance with an accuracy of 78.07%, and AUC, sensitivity, and specificity of 0.8597, 78.80%, and 76.08%, respectively. We detected 7 discriminative brain subregions. The fivefold cross-validation and automated anatomical labeling 90 atlas also got high classification accuracy, and we found Brainnetome 246 atlas achieved a higher classification performance than the automated anatomical labeling 90 atlas both with tenfold and fivefold cross-validation. Our findings may help the early diagnosis of Parkinson's disease and provide support for research on Parkinson's disease mechanisms and clinical evaluation.

Novel insights into the role of circular RNAs in Parkinson disease: An emerging renaissance in the management of neurodegenerative diseases

Parkinson's disease (PD), as a debilitating neurodegenerative disease, particularly affects the elderly population, and is clinically identified by resting tremor, rigidity, and bradykinesia. Pathophysiologically, PD is characterized by an early loss of dopaminergic neurons in the Substantia nigra pars compacta, accompanied by the extensive aggregation of alpha-synuclein (α-Syn) in the form of Lewy bodies. The onset of PD has been reported to be influenced by multiple biological molecules. In this context, circular RNAs (circRNAs), as tissue-specific noncoding RNAs with closed structures, have been recently demonstrated to involve in a set of PD's pathogenic processes. These RNA molecules can either up- or downregulate the expression of α-Syn, as well as moderating its accumulation through different regulatory mechanisms, in which targeting microRNAs (miRNAs) is considered the most common pathway. Since circRNAs have prominent structural and biological characteristics, they could also be considered as promising candidates for PD diagnosis and treatment. Unfortunately, PD has become a global health concern, and a large number of its pathogenic processes are still unclear; thus, it is crucial to elucidate the ambiguous aspects of PD pathophysiology to improve the efficiency of diagnostic and therapeutic strategies. In line with this fact, the current review aims to highlight the interplay between circRNAs and PD pathogenesis, and then discusses the diagnostic and therapeutic potential of circRNAs in PD progression. This study will thus be the first of its kind reviewing the relationship between circRNAs and PD.

Frequency-specific coactivation patterns in resting-state and their alterations in schizophrenia: An fMRI study

The resting‐state human brain is a dynamic system that shows frequency‐dependent characteristics. Recent studies demonstrate that coactivation pattern (CAP) analysis can identify recurring brain states with similar coactivation configurations. However, it is unclear whether and how CAPs depend on the frequency bands. The current study investigated the spatial and temporal characteristics of CAPs in the four frequency sub‐bands from slow‐5 (0.01–0.027 Hz), slow‐4 (0.027–0.073 Hz), slow‐3 (0.073–0.198 Hz), to slow‐2 (0.198–0.25 Hz), in addition to the typical low‐frequency range (0.01–0.08 Hz). In the healthy subjects, six CAP states were obtained at each frequency band in line with our prior study. Similar spatial patterns with the typical range were observed in slow‐5, 4, and 3, but not in slow‐2. While the frequency increased, all CAP states displayed shorter persistence, which caused more between‐state transitions. Specifically, from slow‐5 to slow‐4, the coactivation not only changed significantly in distributed cortical networks, but also increased in the basal ganglia as well as the amygdala. Schizophrenia patients showed significant alteration in the persistence of CAPs of slow‐5. Using leave‐one‐pair‐out, hold‐out and resampling validations, the highest classification accuracy (84%) was achieved by slow‐4 among different frequency bands. In conclusion, our findings provide novel information about spatial and temporal characteristics of CAP states at different frequency bands, which contributes to a better understanding of the frequency aspect of biomarkers for schizophrenia and other disorders.

Functional Connectivity Changes in Multiple-Frequency Bands in Acute Basal Ganglia Ischemic Stroke Patients: A Machine Learning Approach

Purpose

Several functional magnetic resonance imaging (fMRI) studies have investigated the resting-state functional connectivity (rs-FC) changes in the primary motor cortex (M1) in patients with acute basal ganglia ischemic stroke (BGIS). However, the frequency-specific FC changes of M1 in acute BGIS patients are still unclear. Our study was aimed at exploring the altered FC of M1 in three frequency bands and the potential features as biomarkers for the identification by using a support vector machine (SVM).

Methods

We included 28 acute BGIS patients and 42 healthy controls (HCs). Seed-based FC of two regions of interest (ROI, bilateral M1s) were calculated in conventional, slow-5, and slow-4 frequency bands. The abnormal voxel-wise FC values were defined as the features for SVM in different frequency bands.

Results

In the ipsilesional M1, the acute BGIS patients exhibited decreased FC with the right lingual gyrus in the conventional and slow-4 frequency band. Besides, the acute BGIS patients showed increased FC with the right medial superior frontal gyrus (SFGmed) in the conventional and slow-5 frequency band and decreased FC with the left lingual gyrus in the slow-5 frequency band. In the contralesional M1, the BGIS patients showed lower FC with the right SFGmed in the conventional frequency band. The higher FC values with the right lingual gyrus and left SFGmed were detected in the slow-4 frequency band. In the slow-5 frequency band, the BGIS patients showed decreased FC with the left calcarine sulcus. SVM results showed that the combined features (slow-4+slow-5) had the highest accuracy in classification prediction of acute BGIS patients, with an area under curve (AUC) of 0.86.

Conclusion

Acute BGIS patients had frequency-specific alterations in FC; SVM is a promising method for exploring these frequency-dependent FC alterations. The abnormal brain regions might be potential targets for future researchers in the rehabilitation and treatment of stroke patients.

Machine Learning for Detecting Parkinson's Disease by Resting-State Functional Magnetic Resonance Imaging: A Multicenter Radiomics Analysis

Parkinson's disease (PD) is one of the most common progressive degenerative diseases, and its diagnosis is challenging on clinical grounds. Clinically, effective and quantifiable biomarkers to detect PD are urgently needed. In our study, we analyzed data from two centers, the primary set was used to train the model, and the independent external validation set was used to validate our model. We applied amplitude of low-frequency fluctuation (ALFF)-based radiomics method to extract radiomics features (including first- and high-order features). Subsequently, t-test and least absolute shrinkage and selection operator (LASSO) were harnessed for feature selection and data dimensionality reduction, and grid search method and nested 10-fold cross-validation were applied to determine the optimal hyper-parameter λ of LASSO and evaluate the performance of the model, in which a support vector machine was used to construct the classification model to classify patients with PD and healthy controls (HCs). We found that our model achieved good performance [accuracy = 81.45% and area under the curve (AUC) = 0.850] in the primary set and good generalization in the external validation set (accuracy = 67.44% and AUC = 0.667). Most of the discriminative features were high-order radiomics features, and the identified brain regions were mainly located in the sensorimotor network and lateral parietal cortex. Our study indicated that our proposed method can effectively classify patients with PD and HCs, ALFF-based radiomics features that might be potential biomarkers of PD, and provided further support for the pathological mechanism of PD, that is, PD may be related to abnormal brain activity in the sensorimotor network and lateral parietal cortex.

Abnormal Neural Activity in Different Frequency Bands in Parkinson's Disease With Mild Cognitive Impairment

Background: Abnormal spontaneous neural activity is often found in patients with Parkinson's disease with mild cognitive impairment (PD-MCI). However, the frequency dependence of neuronal interaction activities, especially the fractional amplitude of low-frequency fluctuation (fALFF) and degree centrality (DC), in PD-MCI is still unclear. Thus, this study aimed to explore the frequency dependence of PD-MCI based on fALFF and DC maps. Methods: Twenty-four patients with PD-MCI, 42 PD patients with normal cognition (PD-NC), and 33 healthy controls (HCs) were enrolled. Neuropsychological assessments and resting-state functional MRI (rs-fMRI) were performed. The fALFF and DC values in the conventional, slow4 and slow5 frequency bands were compared among the groups. Results: In the conventional frequency band, the DC value in the left precentral area was decreased in PD-MCI patients, while that in the right fusiform area was increased in PD-NC patients compared with HCs. Regarding fALFFs, both the PD-MCI and PD-NC patients had decreased values in the right precentral area compared with those of the HCs. The fALFFs did not differ between PD-MCI and PD-NC patients. The fALFF results in the slow4 subfrequency band were consistent with those in the conventional frequency band. In the slow5 band, the DC value in the left middle temporal lobe was higher in PD-MCI patients than in PD-NC patients and was positively correlated with the performance of the PD-MCI patients on the Montreal Cognitive Assessment (MoCA). Additionally, both PD-MCI and PD-NC patients showed lower fALFF values in the bilateral putamen than the HCs, and the fALFF in the bilateral putamen was negatively correlated with the Hoehn and Yahr stages of PD-MCI. The fALFF in the left putamen was negatively correlated with the scores of PD-MCI patients on the Movement Disorder Society-Unified Parkinson Disease Rating Scale Part III (MDS-UPRDS-III). Conclusion: Our results suggested that abnormal neuronal activities, such as fALFF and DC, are dependent on frequency in PD-MCI. Some subfrequency bands could distinguish PD-MCI from PD. Our findings may be helpful for further revealing the frequency-dependent resting functional disruption in PD-MCI.

Use of machine learning method on automatic classification of motor subtype of Parkinson's disease based on multilevel indices of rs-fMRI

OBJECTIVE

This study aimed to develop an automatic classifier to distinguish different motor subtypes of Parkinson's disease (PD) based on multilevel indices of resting-state functional magnetic resonance imaging (rs-fMRI).

METHODS

Ninety-six PD patients, which included thirty-nine postural instability and gait difficulty (PIGD) subtype and fifty-seven tremor-dominant (TD) subtype, were enrolled and allocated to training and validation datasets with a ratio of 7:3. A total of five types of index, consisting of mean regional homogeneity (mReHo), mean amplitude of low-frequency fluctuation (mALFF), degree of centrality (DC), voxel-mirrored homotopic connectivity (VMHC), and functional connectivity (FC), were extracted. The features were then selected using a two-sample t-test, the least absolute shrinkage and selection operator (LASSO), and Spearman's rank correlation coefficient. Finally, support vector machine (SVM) models based on the separate index and multilevel indices were built, and the performance of models was assessed via the area under the receiver operating characteristic curve (AUC). Feature importance was evaluated using Shapley additive explanation (SHAP) values.

RESULTS

The optimal SVM model was obtained based on multilevel rs-fMRI indices, with an AUC of 0.934 in the training dataset and an AUC of 0.917 in the validation dataset. The AUCs of the models based on the separate index were ranged from 0.783 to 0.858 for the training dataset and from 0.713 to 0.792 for the validation dataset. SHAP analysis revealed that functional activity and connectivity in frontal lobe and cerebellum were important features for differentiating PD subtypes.

CONCLUSIONS

Our findings demonstrated multilevel rs-fMRI indices could provide more comprehensive information on brain functionalteration. Furthermore, the machine learning method based on multilevel rs-fMRI indices might be served as an alternative approach for automatically classifying clinical subtypes in PD at the individual level.

Frequency specific co-activation pattern analysis via sparse nonnegative tensor decomposition

BACKGROUND

Traditionally, the diagnosis of Parkinson's disease (PD) has been made based on symptoms. Extensive studies have demonstrated that PD may lead to variation of brain activity in different frequency bands. However, frequency specific dynamic alterations of PD have not yet been explored.

NEW METHOD

In order to address this gap, a novel sparse nonnegative tensor decomposition (SNTD) method was used to estimate frequency specific co-activation patterns (CAP). The difference between PD and healthy controls (HC) are investigated with the proposed framework.

RESULT

The difference between PD and HC mainly exists at frequency band 0.04-0.1 Hz in basal ganglia. We also found that the average intensity of PD in this frequency band is significantly correlated with the Hoehn and Yahr scale.

COMPARISON WITH EXISTING METHODS

Compared with conventional CAP approach, SNTD estimates frequency specific CAPs that show alterations in PD patients.

CONCLUSION

SNTD provides an alternative to K-means clustering used in conventional CAP analysis. With the proposed framework, frequency specific CAPs are extracted, and alterations in PD patients are also successfully discovered.