Feature and decision-level fusion for schizophrenia detection based on resting-state fMRI data

Autism spectrum disorder (ASD) is a neurodevelopmental disease with unknown etiology but high incidence. The objective biomarkers of ASD are urgently awaited to be developed using neuroimaging method including resting-state fMRI (R-fMRI). However, the majority of current R-fMRI studies only examined the static features of brain activity in ASD patients, but neglected the dynamic aspects especially for regional metrics. Furthermore, the concordance of the dynamic regional indices was reported imbedded in human intrinsic brain activity, while its abnormality in ASD is largely unknown. In order to shed light on the abnormity of ASD from dynamic perspective, we analyzed R-fMRI data of 480 ASD male patients and 539 healthy male controls (HC) gathered from ASD public database (ABIDE I/ABIDE II). We used sliding window method to calculate the dynamics of mainstream regional indices of R-fMRI (amplitude of low frequency fluctuations (ALFF), fractional ALFF (fALFF), regional homogeneity (ReHo), voxel-mirrored homotopic connectivity (VMHC), degree centrality (DC) and the correlation with global signal (GSCorr)) and generated the SD statistic maps of these six dynamic regional indices. We performed z-standardization and smoothing on the SD statistic maps. After that, two-sample t -test between the SD statistic maps of ASD group and HC group was performed. We also calculated the concordance of dynamic regional indices for each time point, which is the Kendall’s coefficient of the ALFF, ReHo, DC, GSCorr and VMHC maps across voxels. Two-sample t -test between the SD and mean of concordance time series of ASD group and HC group was performed. We found a significant increase in the dynamics of ALFF and DC in the lateral frontal cortices in ASD patients as compared to HCs. Dorsal lateral frontal cortex (dlPFC) is a critical brain area for cognitive control and execution network. The abnormal activities in dlPFC indicate the disruption of control execution system and the impairment of relevant cognitive function. In the visual related brain areas, the dynamics of ALFF, DC and ReHo showed a decrease in fusiform gyrus, calcarine and lingual gyrus in ASD patients. Recent studies have indicated that the abnormal face processing in children with autism may be related with the impairment in social cognition of them. The deficits in face information processing of ASD patients may stem from the inflexible intrinsic brain activity in visual processing brain area (especially in fusiform gyrus). After further examining the concordance among these dynamic indices, the mean and SD of concordance of patients with ASD was found to be significantly lower than that of the HCs, demonstrating that the ASD patients’ inferior integration ability for different aspects of brain functions. These findings suggest that there exists abnormality in dynamics of spontaneous brain activity and its integration in ASD patients. Dynamic R-fMRI regional indices and the concordance of them could be efficient neuroimaging biomarkers for ASD.

Introduction We recently showed that people with obstructive sleep apnea (OSA) have higher breathing rate (BR) variability (BRV) in population (Pal et al. 2021)1. Simultaneously, Lynch et al. 20202 had assessed impaired breathing in the resting state healthy Human Connectome Dataset, and identified 21 people in each of the three groups of breathing patterns: eupnea (clean), sighs (deep breath) and suspected apnea breathing pattern (burst). During resting state functional MRI recordings, increased amplitude of low frequency fluctuations (ALFF) were found within areas related to hyperarousal such as the midbrain and bilateral extra-nucleus, whereas decreased ALFF were found within areas associated with memory and attention involving the parietal and occipital lobule and others; furthermore, the altered ALFF was associated with sleep efficiency (Ran et al. 20173). Could altered breathing pattern reflect an altered spontaneous neuronal activity state measured by fractional ALFF (fALFF) and associated psycho-physiological markers of sleep quality? Our goal was to characterize BRV and fALFF from the resting state HCP data in the three breathing pattern groups identified in Lynch et al. 2020 along with their psychophysiological states including sleep quality measured by Pittsburg Sleep Quality Index (PSQI). Methods In the three groups (n=21 X 3), clean group (6 males) age (mean±std. dev) 29±4 years, deep breath group (5 males) 29±4 years, burst group (14 males) 30±4 years - we calculated BR, absolute BRV (Interquartile range of BR) and relative BRV% from 15 minutes of resting state respiration belt data; and, fALFF from the minimally preprocessed resting state fMRI data filtered at 0.1-0.08 Hz and smoothed. We correlated fALFF with BR, BRV. Additionally, in the three groups, we report the mean±stdev of PSQI, BMI, systolic and diastolic blood pressure (BP), self-reported anxiety, attention problem, aggression scores along with their correlations with the absolute BRV. Results Absolute BRV was lower in deep breath group 3±3 breaths per minute (bpm) compared to clean (4±2 bpm) and burst (4±3 bpm) groups. BR was also lower in deep breath 14±7 bpm and correlated with BRV at Pearson R = 0.57 (p<0.05), compared to 18±2 bpm, R = -0.51 (p<0.05) in clean group and 18±3 bpm, R = 0.2 in burst group. In the deep breath group, the relative change in BRV 24±14%, correlated less with absolute BRV R = 0.78 (p<0.05) compared to the clean 24±13%, R = 0.98 (p<0.05) and burst groups 24±18%, R = 0.97 (p<0.05) indicating some voluntary sighs in the deep breath group as also validated by visual data inspection. The sleep quality (lower PSQI better sleep quality) was best in the clean 4±2 points, compared to both deep breath 5±3 and burst groups 5±3. Improved psychophysiological state in the clean and deep breath group compared to burst group was indicated by the systolic BP (121±12, 121±13 and 128±14 mmHg), BMI (25±5, 26±5, 28±6 kg/m2), anxiety (5±5, 5±5, 7±7)/attention problems (5±3, 5±4, 7±4)/aggression (3±2, 3±3, 5±2) scores in clean, deep breath and burst groups respectively. Only in the burst group, higher BRV correlated with higher BMI (R = 0.5, p<0.05). fALFF correlated with BRV (p<0.05, FWE corrected), not BR in all three groups at the cerebrospinal fluid (CSF) ventricles. With BRV as co-variate, burst group showed higher fALFF activity (p<0.001, uncorrected) compared to both clean and deep breath groups at the visual and somatosensory regions. Additionally, fALFF at the central executive network (CEN) was higher (p<0.001, uncorrected) for both clean and deep breath groups compared to burst. Interestingly, the clean group as well as the burst group had higher right somatosensory fALFF activity compared to deep breath group, that corresponded to the lower BRV in deep breath group. Conclusion Higher fALFF activity of burst compared to clean and deep breath groups in the visual and somatosensory regions were associated with sleep deprivation states (Dai et al., 20124; Wang et al., 20165 , Ran et al. 20173). Higher CEN fALFF activity indicating better sleep and physiological states (Zeighami et al., 20216, Ran et al. 20173) were found in the clean and deep breath groups compared to burst. Higher right somatosensory fALFF activity in the clean and burst groups compared to deep breath indicating higher breathing related movements in the groups having higher BR and BRV (clean and burst) compared to the deep breath group. The fALFF results are consistent with the indication of breathing coupled hemodynamic and CSF low-frequency oscillations that indicate sleep/wakefulness states during resting state (Fultz 20197). Overall, our study supports that BRV could be a potential indicator of psychophysiology, and taking sighs or deep breaths could potentially improve some psycho-neuro-physiological states but not necessarily sleep quality. As indicated earlier by Lynch et al. 20202, males report more burst breathing pattern while females report more deep breathing pattern indicating the ability to take deep breaths may counteract potential sleep disordered breathing problems. Support (If Any) HL135562

This study is aimed at investigating the characteristics of the spontaneous brain activity in patients with myotonic dystrophy type 1 (DM1). A total of 18 patients with DM1 and 18 healthy controls (HCs) were examined by resting-state functional MRI. Combined methods include amplitude of low-frequency fluctuations (ALFFs), the fractional amplitude of low-frequency fluctuations (fALFFs), and Wavelet transform-based ALFFs (Wavelet-ALFFs) with standardization, percent amplitude of fluctuation (PerAF) with/without standardization were applied to evaluate the spontaneous brain activity of patients with DM1. Compared with HCs, patients with DM1 showed decreased ALFFs and Wavelet-ALFFs in the bilateral precuneus (PCUN), angular gyrus (ANG), inferior parietal, but supramarginal and angular gyri (IPL), posterior cingulate gyrus (PCG), superior frontal gyrus, medial (SFGmed), middle occipital gyrus (MOG), which were mainly distributed in the brain regions of default mode network (DMN). Decreased ALFFs and Wavelet-ALFFs were also seen in bilateral middle frontal gyrus (MFG), inferior frontal gyrus, opercular part (IFGoperc), which were the main components of the executive control network (ECN). Patients with DM1 also showed decreased fALFFs in SFGmed.R, the right anterior cingulate and paracingulate gyri (ACGR), bilateral MFG. Reduced PerAF in bilateral PCUN, ANG, PCG, MOG, and IPLL as well as decreased PerAF without standardization in PCUNR and bilateral PCG also existed in patients with DM1. In conclusion, patients with DM1 had decreased activity in DMN and ECN with increased fluctuations in the temporal cortex and cerebellum. Decreased brain activity in DMN was the most repeatable and reliable with PCUN and PCG being the most specific imaging biomarker of brain dysfunction in patients with DM1.

To explore the spatial patterns of the amplitude of low-frequency fluctuation (ALFF) in patients with hepatic encephalopathy (HE) of varying severity and to correlate these fluctuations with clinical markers of HE. This study was approved by the local ethics committee, and written informed consent was obtained from all participants. Twenty-nine patients with HE (15 with overt and 14 with minimal HE) and 17 healthy control subjects underwent resting-state functional magnetic resonance (MR) imaging. The ALFF, an index reflecting the amplitudes of spontaneous brain activity, was compared among patients with overt HE, patients with minimal HE, and control subjects with analysis of variance tests and t tests between each pair. Pearson correlation analysis was performed between the ALFF and the venous blood ammonia level and Child-Pugh score of all patients with HE. Compared with control subjects, patients with overt and minimal HE showed decreased ALFF mainly in regions within the default-mode network (DMN) and increased ALFF in the cerebellum and middle temporal gyrus. Compared with patients with minimal HE, those with overt HE showed decreased ALFF in DMN regions and increased ALFF in the posterior insular cortex (P<.05, corrected for multiple comparisons). Both the venous blood ammonia levels and Child-Pugh scores of individual patients with HE showed negative correlation with ALFF within some DMN regions, whereas they showed positive correlation with ALFF in the posterior insular cortex (P<.05, corrected for multiple comparisons). Patients with HE have diffuse abnormalities in intrinsic brain activity. The levels of decreased ALFF in the DMN and increased ALFF in the posterior insular cortex are dependent on the severity of HE, suggesting continuous impairment of the DMN and a compensatory role of the insula during the progression of HE. Resting-state functional MR imaging with ALFF analysis may be a noninvasive modality with which to detect the progression of HE.

PurposeWe aimed to evaluate the spontaneous neuronal activity and functional connectivity pattern variations using resting-state functional magnetic resonance imaging (rs-fMRI) measures, such as amplitude of low-frequency fluctuation (ALFF), fractional amplitude of low-frequency fluctuation (fALFF), and functional connectivity (FC), in patients with thyroid-associated ophthalmopathy (TAO).MethodA total of 24 active TAO patients, 26 inactive TAO patients, and 27 matched healthy controls (HCs) were included. First, ALFF and fALFF were used to detect local neural activity changes, the MRI data were analyzed, and regions with group differences were taken as seeds. Second, FC analysis was performed to explore the altered connection between seeds and other brain regions. A correlation analysis was performed to assess the relationship between functional brain activity and clinical indices and neuropsychiatric behaviors.ResultsCompared to HCs, both active and inactive TAO patients exhibited significantly lower ALFF values in the right calcarine (Calcarine_R) and left postcentral gyrus (Postcentral_L). Active TAO patients also showed significantly higher ALFF values in the left caudate nucleus (Caudate_L) and increased fALFF values in the superior lobe of the right cerebellum (Cerebelum_Crus1_R). Moreover, both active and inactive TAO patients demonstrated decreased FC within the left postcentral gyrus (Postcentral_L) compared to HCs. Additionally, active TAO patients exhibited lower FC compared to inactive TAO patients. The ALFF values in the Calcarine_R of active TAO patients positively correlated with disease duration (r = 0.5892, p = 0.0049) and the Hamilton Anxiety Rating Scale (HARS; r = 0.5377, p = 0.0119). Furthermore, the ALFF value in the Calcarine_R of inactive TAO patients negatively correlated with visual functioning (r = −0.5449, p = 0.0072), while the ALFF values in the Caudate_L of active TAO patients positively correlated with visual functioning (r = 0.6496, p = 0.0014).ConclusionWe found that the Caudate_L and Cerebelum_Crus1_R related to motor control and coordination in active TAO patients exhibit significant compensatory mechanisms; whereas, the Calcarine_R and Postcentral_L related to visual and somatosensory cortices show varying degrees of impairment. Our findings complement the functional neural mechanism of TAO.

Suicidality is commonly observed in patients with depressive episodes, and electroconvulsive therapy (ECT) has been found to be effective in treating these patients. However, the role of ECT in suicidality remains unclear. This study used resting-state functional magnetic resonance imaging (rs-fMRI) to explore the changes in brain function before and after ECT in depressed patients with suicidality. In total, 26 depressed patients with suicidality underwent rs-fMRI at baseline and after 8-12 sessions of ECT. In addition, 32 healthy controls (HCs) matched for age, gender, and educational level underwent rs-fMRI once. The amplitude of low-frequency fluctuations (ALFF), the fractional amplitude of low-frequency fluctuations (fALFF), and regional homogeneity (ReHo) were measured to evaluate whole brain function. Differences between the groups and time points (before and after ECT) were compared. Clinical symptoms were assessed using the 17-item Hamilton Depression Scale (HAMD-17) and Beck Scale for Suicide Ideation (BSSI). At baseline, patients exhibited decreased ALFF in the right postcentral and precentral gyrus and decreased fALFF in the right supramarginal and postcentral gyrus, left superior frontal gyrus (SFG), as well as the superior and middle temporal gyrus compared to HCs. Patients also had lower ReHo in the left amygdala, anterior cingulate, and postcentral gyrus, and in the right thalamus, insula, and postcentral gyrus. They also exhibited higher ALFF in the bilateral temporal gyrus and insula as well as higher fALFF in the cerebellum. Following ECT, fALFF in the left SFG and orbital frontal cortex (OFC) significantly increased and was inversely correlated with the reduction of BSSI scores (r = -0.416, p = 0.048), whereas no correlation was found with changes in HAMD-17scores. Our findings suggest that the left SFG and OFC may play a key role in the mechanism of ECT for suicidality. The decrease of fALFF in the left SFG and OFC may represent a potential mechanism through which ECT effectively treats suicidality in depressed patients.

Major depressive disorder (MDD) is one of the most widespread mental disorders and can result in suicide. Suicidal ideation (SI) is strongly predictive of death by suicide, and electroconvulsive therapy (ECT) is effective for MDD, especially in patients with SI. In the present study, we aimed to determine differences in resting-state functional magnetic resonance imaging (rs-fMRI) in 14 adolescents aged 12–17 with MDD and SI at baseline and after ECT. All participants were administered the Hamilton Depression Scale (HAMD) and Beck Scale for Suicide Ideation (BSSI) and received rs-fMRI scans at baseline and after ECT. Following ECT, the amplitude of low frequency fluctuation (ALFF) and fractional ALFF (fALFF) significantly decreased in the right precentral gyrus, and the degree centrality (DC) decreased in the left triangular part of the inferior frontal gyrus and increased in the left hippocampus. There were significant negative correlations between the change of HAMD (ΔHAMD) and ALFF in the right precentral gyrus at baseline, and between the change of BSSI and the change of fALFF in the right precentral gyrus. The ΔHAMD was positively correlated with the DC value of the left hippocampus at baseline. We suggest that these brain regions may be indicators of response to ECT in adolescents with MDD and SI.

ObjectivePostherpetic neuralgia (PHN), a refractory neuropathic pain following herpes zoster reactivation, lacks clear central mechanisms for emerging therapies like short-term spinal cord stimulation (stSCS). This longitudinal study used multimodal neuroimaging to examine the effects of 14-day stSCS on brain function and white matter microstructure in PHN patients, and to identify neural correlates of clinical improvements.MethodsIn this longitudinal, single-arm, pre-post study, 17 PHN patients received 14 days of continuous stSCS. Clinical outcomes including pain intensity (Numeric Rating Scale, NRS), anxiety and depression (Hospital Anxiety and Depression Scale, HADS), and sleep quality (Pittsburgh Sleep Quality Index, PSQI), were assessed pre-stSCS and 3 days post-stSCS. Resting-state functional MRI (rs-fMRI) and Diffusion Tensor Imaging (DTI) data were acquired at both time points. Longitudinal changes in amplitude of low-frequency fluctuations (ALFF) and fractional ALFF (fALFF) were analyzed, alongside white matter integrity via TBSS and ROI analysis of key tracts.ResultsPost-stSCS, significant improvements occurred in all clinical outcomes (Wilcoxon signed-rank, all p < 0.001). Neuroimaging showed no DTI microstructural changes but significant fALFF increases in regions including the dorsal striatum. Notably, right medial orbitofrontal cortex (mOFC) fALFF increases correlated with NRS reductions (Spearman’s r = 0.71, FDR-corrected p = 0.036). Baseline cingulum integrity (lower FA, higher MD/RD) predicted greater striatal fALFF changes (r = ±0.75, FDR-corrected p < 0.02).ConclusionThese findings suggest that stSCS’s early clinical benefits in PHN are mediated by rapid functional reorganization rather than immediate microstructural changes. This reorganization appears prominent within fronto-striatal circuits: specifically, mOFC functional changes correlate with analgesia, while baseline cingulum integrity predicts subsequent striatal plasticity. This provides initial mechanistic insights into stSCS and suggest that baseline brain structure could be explored as a potential biomarker for treatment response, warranting validation in larger, controlled cohorts.

The amplitude of low-frequency fluctuations (ALFF) in the blood oxygenation level-dependent (BOLD) signal during resting-state fMRI reflects the magnitude of local low-frequency BOLD oscillations, rather than interregional connectivity. ALFF is of interest to studies of cognition because fluctuations in spontaneous intrinsic brain activity relate to, and possibly even constrain, task-evoked brain responses in healthy people. Lower ALFF has been reported in schizophrenia, but the cognitive correlates of these reductions remain unknown. Here, we assess relationships between ALFF and attention and working memory in order to establish the functional relevance of intrinsic BOLD oscillatory power alterations with respect to specific cognitive impairments in schizophrenia. As part of the multisite FBIRN study, resting-state fMRI data were collected from schizophrenia subjects (SZ; n=168) and healthy controls (HC; n=166). Voxelwise fractional ALFF (fALFF), a normalized ALFF measure, was regressed on neuropsychological measures of sustained attention and working memory in SZ and HC to identify regions showing either common slopes across groups or slope differences between groups (all findings p<0.01 height, p<0.05 family-wise error cluster corrected). Poorer sustained attention was associated with smaller fALFF in the left superior frontal cortex and bilateral temporoparietal junction in both groups, with additional relationships in bilateral posterior parietal, posterior cingulate, dorsal anterior cingulate (ACC), and right dorsolateral prefrontal cortex (DLPFC) evident only in SZ. Poorer working memory was associated with smaller fALFF in bilateral ACC/mPFC, DLPFC, and posterior parietal cortex in both groups. Our findings indicate that smaller amplitudes of low-frequency BOLD oscillations during rest, measured by fALFF, were significantly associated with poorer cognitive performance, sometimes similarly in both groups and sometimes only in SZ, in regions known to subserve sustained attention and working memory. Taken together, these data suggest that the magnitude of resting-state BOLD oscillations shows promise as a biomarker of cognitive function in health and disease.

Objective To explore the changes of rest-state functional MRI (fMRI) features in patients with Parkinson's disease. Methods Twelve patients with Parkinson's disease, collected in our hospital from September 2013 to March 2014, and 12 volunteers (controls) were recruited. The fMRI based on blood oxygen level dependent (BOLD) was performed at resting state; the differences of amplitude of low frequency fluctuation (ALFF) and regional homogeneity (ReHo) were statistically analyzed; and the correlations of values of ALFF and ReHo with uniformed Parkinsonism rating scale (UPDRS) scores and Hoehn-Yahr (H-Y) grading were analyzed. Results PD patients exhibited increased ALFF values in the limbic lobe, the right parahippocampal gyrus and the right middle temporal pole, and reduced ALFF values in the left thalamus as compared with the controls. PD patients exhibited increased ReHo values in the superior medial frontal gyrus, the left middle frontal gyrus, brodmann area (BA) 9 and medial frontal gyrus, and reduced ReHo values in the left rolandic, the left superior temporal gyrus and insula lobe as compared with the controls. ALFF values were positively correlated with the UPDRS III scores in the right posterior cerebellum lobe and cerebellar tonsil. ALFF values and H-Y grading were negatively correlated on the left superior frontal gyrus. Negative correlation was noted between the ReHo values and UPDRS III scores in the right superior temporal gyrus and insular lobe. Positive correlation was noted between the ReHo values and H-Y grading in medial frontal gyrus, limbic lobe, anterior cingulate, medial orbitofrontal area, middle superior frontal gyrus, BA32, left superior frontal gyrus and BA10. Conclusion By resting-state fMRI, abnormal brain function in Parkinson's disease was noted; ReHo and ALFF showed abnormal changes in the connection of neuronal networks, and the compensatory response may lead to the increased brain function. Key words: Parkinson’s disease; Functional MR imaging; Regional homogeneity; Amplitude of low frequency fluctuation

The high comorbidity of alcohol use disorder and depressive disorder is associated with poor patient prognosis. The mechanisms underlying this comorbidity, however, are largely unknown. By applying the amplitude of low-frequency fluctuations parameter in resting-state functional magnetic resonance imaging, this study investigated changes in the brain functioning of alcohol-dependent patients with and without depression. Alcohol-dependent patients (n = 48) and healthy controls (n = 31) were recruited. The alcohol-dependent patients were divided into those with and without depression, according to Patients Health Questionnaire-9 scores. Amplitude of low-frequency fluctuations in resting-state brain images were compared among the alcohol-dependent patients with depression, alcohol-dependent patients without depression, and healthy controls groups. We further examined associations between amplitude of low-frequency fluctuations alterations, alcohol-dependence severity, and depressive levels (assessed with scales). Compared with the healthy controls group, both alcohol groups showed amplitude of low-frequency fluctuations enhancement in the right cerebellum and amplitude of low-frequency fluctuations abatement in the posterior central gyrus. The alcohol-dependent patients with depression group had higher amplitude of low-frequency fluctuations in the right cerebellum than the alcohol-dependent patients without depression group. Additionally, we observed a positive correlation between amplitude of low-frequency fluctuations value and Patients Health Questionnaire-9 score in the right superior temporal gyrus in the alcohol-dependent patients with depression group. Alcohol-dependent subjects showed abnormally increased spontaneous neural activity in the right cerebellum, which was more significant in alcohol-dependent patients with depression. These findings may support a targeted intervention in this brain location for alcohol and depressive disorder comorbidity.

Objective To investigate the characteristic of regional amplitude of low frequency fluctuation (ALFF) in the brain of adolescents with online game addiction during the resting state. Methods The ALFF method was employed to explore the local features of spontaneous brain activity in adolescents with online game addiction (n=26) and healthy controls (n=23) during resting-state by Resting-State fMRI Data Analysis Toolkit. Results Compared with healthy controls, adolescents with online game addiction showed increased ALFF values in the anterior cingulate cortex (ACC), left middle cingulate cortex (MCC), bilateral caudate, right pallidum, bilateral parahippocampal gyrus, and right insula. It was noteworthy that the ALFF values of the right caudate (r=0.4437, P=0.0232) and right parahippocampal gyrus (r=0.5227, P=0.0062) were positively correlated with the duration of online game addiction. Conclusion The abnormal spontaneous neuronal activity properties during the resting state were revealed in the brain regions of adolescents with online game addiction. And the abnormalities may become more significant as the disease progresses. Key words: Online game addiction; Resting state; Amplitude of low frequency fluctuation

Amplitude of low-frequency oscillations in schizophrenia: A resting state fMRI study

Objective: To investigate the alterations of the cerebral resting-state spontaneous neural activity in colorectal cancer patients with depressive symptoms. Methods: Thirty-three colorectal cancer patients (patient group) with depression and 43 healthy subjects (control group) underwent the resting state functional magnetic resonance imaging (rs-fMRI). The amplitude of low-frequency fluctuations (ALFF) and fractional ALFF (fALFF) were calculated. Two independent samples t test were used to compare the ALFF and fALFF values between two groups by DPABI software, and then correlation analysis was performed between ALFF and fALFF with statistical significance and Patient Health Questionnaire (PHQ-9) scores and Generalized Anxiety Disorder (GAD-7) scores. Results: Compared with the control group, the patient group showed significantly lower ALFF and fALFF values in the bilateral precuneus, calcarine gyrus, lingual gyrus, left cuneus, superior, middle, inferior occipital gyrus and right fusiform gyrus (t=-5.730, P<0.05; t=-4.872, P<0.05). There were no significant correlations between the ALFF and fALFF values in these regions and PHQ-9 or GAD-7 scores (P>0.05). Conclusion: Spontaneous decrease of neural activity in occipital and parietal lobes exists in colorectal cancer patients with depression at resting-sate, which may be a potential neurobiological marker.

The resting-state functional magnetic resonance imaging (rs-fMRI) is a non-invasive neuroimaging modality to measure brain activity and helps in the diagnosis of various brain-related disorders. Given the 1/f power spectrum characteristic of brain dynamics, where the energy value is higher at a low frequency than high frequency, it is established that low-frequency oscillations (LFO) provide a better representation of the spontaneous neuronal activity of the brain. In this research, a combination of the amplitude of low-frequency fluctuation (ALFF) and fractional ALFF (fALFF) from the resting-state blood oxygen level-dependent (BOLD) signal in the classic band i.e., 0.01-0.1 Hz is used for the classification of Alzheimer's disease (AD) from normal controls (NC). A total of 60 subjects participated in this study consisting of 30 AD patients and 30 NC from Alzheimer's disease neuroimaging initiative (ADNI). The feature selection is performed using minimum-redundancy maximum-relevance (mRMR) and ReliefF algorithm due to the large dimension of rs-fMRI data to be fed to the machine learning (ML) classifier. The proposed AD classification method employing the fusion of ALFF and fALFF obtained the highest classification accuracy of 96.36%, indicating the good potential of the proposed method for the diagnosis of AD, as well as other neurological conditions.