Abstract:PurposeEntropy analysis of resting-state functional magnetic resonance imaging (R-fMRI) has recently been adopted to characterize brain temporal dynamics in some neuropsychological or psychiatric diseases. Thalamus-related dysfunction might be a potential trait marker of major depressive disorder (MDD), but the abnormal changes in the thalamus based on R-fMRI are still unclear from the perspective of brain temporal dynamics. The aim of this study was to identify local entropy changes and subregional connectivi… Show more
“…Thus, this heterogeneity may explain the differences in the results across thalamic subregions. The findings of heterogeneity across thalamic subregions were indirectly supported by the results of our previous study [ 6 ], which, through functional imaging data, revealed that MDD patients exhibited distinct resting-state functional connectivity patterns across thalamic subregions.…”
Section: Discussionsupporting
confidence: 80%
“…Nor does it mean that other functional MRI data of the thalamus are not suitable to be chosen as features for individualized recognition of MDD patients. One of our previous studies showed sample entropy changes in the bilateral thalami in MDD patients [ 6 ], so we are considering using the sample entropy of the resting-state fMRI data as a feature for the classification and prediction of MDD in our future studies [ 4 ]. The whole brain volume was not controlled as a covariate in this study, which may have potential correlation with the volume of the thalamus, and could be considered in future studies.…”
Section: Discussionmentioning
confidence: 99%
“…The following procedures were included in the rs-fMRI data preprocessing: [ 1 ] removal of first 10 volumes [ 2 ]; slice timing correction [ 3 ]; head motion correction [ 4 ]; coregistration of T1 images to the averaged EPI image [ 5 ]; spatial normalization to standard Montreal Neurological Institute (MNI) space using “Dartel+segment” [ 6 ]; regression of head motion effects with the Friston-24 parameter model (all the subject’s head motions were lower than our criteria of 2 mm and 2°) and regression of head motion, white matter (WM) and cerebrospinal fluid (CSF); and [ 7 ] removal of linear trends.…”
Section: Methodsmentioning
confidence: 99%
“…In searching for biomarkers useful for objective diagnosis of MDD, many studies have contributed a lot to the identification of biological correlates of MDD patients in recent years [ 3 – 5 ]. From a special perspective, our recent study demonstrated abnormalities in thalamus in MDD patients [ 6 ]. Also, results from many other studies suggest that thalamic abnormalities might be important potential biomarkers of MDD [ 7 – 9 ].…”
Background
Magnetic resonance imaging (MRI) studies have found thalamic abnormalities in major depressive disorder (MDD). Although there are significant differences in the structure and function of the thalamus between MDD patients and healthy controls (HCs) at the group level, it is not clear whether the structural and functional features of the thalamus are suitable for use as diagnostic prediction aids at the individual level. Here, we were to test the predictive value of gray matter density (GMD), gray matter volume (GMV), amplitude of low-frequency fluctuations (ALFF), and fractional amplitude of low-frequency fluctuations (fALFF) in the thalamus using multivariate pattern analysis (MVPA).
Methods
Seventy-four MDD patients and 44 HC subjects were recruited. The Gaussian process classifier (GPC) was trained to separate MDD patients from HCs, Gaussian process regression (GPR) was trained to predict depression scores, and Multiple Kernel Learning (MKL) was applied to explore the contribution of each subregion of the thalamus.
Results
The primary findings were as follows: [1] The balanced accuracy of the GPC trained with thalamic GMD was 96.59% (P < 0.001). The accuracy of the GPC trained with thalamic GMV was 93.18% (P < 0.001). The correlation between Hamilton Depression Scale (HAMD) score targets and predictions in the GPR trained with GMD was 0.90 (P < 0.001, r2 = 0.82), and in the GPR trained with GMV, the correlation between HAMD score targets and predictions was 0.89 (P < 0.001, r2 = 0.79). [2] The models trained with ALFF and fALFF in the thalamus failed to discriminate MDD patients from HC participants. [3] The MKL model showed that the left lateral prefrontal thalamus, the right caudal temporal thalamus, and the right sensory thalamus contribute more to the diagnostic classification.
Conclusions
The results suggested that GMD and GMV, but not functional indicators of the thalamus, have good potential for the individualized diagnosis of MDD. Furthermore, the thalamus shows the heterogeneity in the structural features of thalamic subregions for predicting MDD. To our knowledge, this is the first study to focus on the thalamus for the prediction of MDD using machine learning methods at the individual level.
“…Thus, this heterogeneity may explain the differences in the results across thalamic subregions. The findings of heterogeneity across thalamic subregions were indirectly supported by the results of our previous study [ 6 ], which, through functional imaging data, revealed that MDD patients exhibited distinct resting-state functional connectivity patterns across thalamic subregions.…”
Section: Discussionsupporting
confidence: 80%
“…Nor does it mean that other functional MRI data of the thalamus are not suitable to be chosen as features for individualized recognition of MDD patients. One of our previous studies showed sample entropy changes in the bilateral thalami in MDD patients [ 6 ], so we are considering using the sample entropy of the resting-state fMRI data as a feature for the classification and prediction of MDD in our future studies [ 4 ]. The whole brain volume was not controlled as a covariate in this study, which may have potential correlation with the volume of the thalamus, and could be considered in future studies.…”
Section: Discussionmentioning
confidence: 99%
“…The following procedures were included in the rs-fMRI data preprocessing: [ 1 ] removal of first 10 volumes [ 2 ]; slice timing correction [ 3 ]; head motion correction [ 4 ]; coregistration of T1 images to the averaged EPI image [ 5 ]; spatial normalization to standard Montreal Neurological Institute (MNI) space using “Dartel+segment” [ 6 ]; regression of head motion effects with the Friston-24 parameter model (all the subject’s head motions were lower than our criteria of 2 mm and 2°) and regression of head motion, white matter (WM) and cerebrospinal fluid (CSF); and [ 7 ] removal of linear trends.…”
Section: Methodsmentioning
confidence: 99%
“…In searching for biomarkers useful for objective diagnosis of MDD, many studies have contributed a lot to the identification of biological correlates of MDD patients in recent years [ 3 – 5 ]. From a special perspective, our recent study demonstrated abnormalities in thalamus in MDD patients [ 6 ]. Also, results from many other studies suggest that thalamic abnormalities might be important potential biomarkers of MDD [ 7 – 9 ].…”
Background
Magnetic resonance imaging (MRI) studies have found thalamic abnormalities in major depressive disorder (MDD). Although there are significant differences in the structure and function of the thalamus between MDD patients and healthy controls (HCs) at the group level, it is not clear whether the structural and functional features of the thalamus are suitable for use as diagnostic prediction aids at the individual level. Here, we were to test the predictive value of gray matter density (GMD), gray matter volume (GMV), amplitude of low-frequency fluctuations (ALFF), and fractional amplitude of low-frequency fluctuations (fALFF) in the thalamus using multivariate pattern analysis (MVPA).
Methods
Seventy-four MDD patients and 44 HC subjects were recruited. The Gaussian process classifier (GPC) was trained to separate MDD patients from HCs, Gaussian process regression (GPR) was trained to predict depression scores, and Multiple Kernel Learning (MKL) was applied to explore the contribution of each subregion of the thalamus.
Results
The primary findings were as follows: [1] The balanced accuracy of the GPC trained with thalamic GMD was 96.59% (P < 0.001). The accuracy of the GPC trained with thalamic GMV was 93.18% (P < 0.001). The correlation between Hamilton Depression Scale (HAMD) score targets and predictions in the GPR trained with GMD was 0.90 (P < 0.001, r2 = 0.82), and in the GPR trained with GMV, the correlation between HAMD score targets and predictions was 0.89 (P < 0.001, r2 = 0.79). [2] The models trained with ALFF and fALFF in the thalamus failed to discriminate MDD patients from HC participants. [3] The MKL model showed that the left lateral prefrontal thalamus, the right caudal temporal thalamus, and the right sensory thalamus contribute more to the diagnostic classification.
Conclusions
The results suggested that GMD and GMV, but not functional indicators of the thalamus, have good potential for the individualized diagnosis of MDD. Furthermore, the thalamus shows the heterogeneity in the structural features of thalamic subregions for predicting MDD. To our knowledge, this is the first study to focus on the thalamus for the prediction of MDD using machine learning methods at the individual level.
“…The amygdala [26,36] (part of the subcallosal region), regions in the inferior temporal [56], the medial frontal lobe [56], posterior cingulate cortex [63] and supplementary motor area [64] have been implicated in MDD. In [61], disruption between the connections between regions in the thalamus and the transverse temporal gyrus were reported, which our consistent with our results.…”
Section: Identified Salient Features Are Clinically Relevantsupporting
Neuroscientific knowledge points to the presence of redundancy in the correlations of brain's functional activity. These redundancies can be removed to mitigate the problem of overfitting when deep neural network (DNN) models are used to classify neuroimaging datasets. We propose an algorithm that removes insignificant nodes of DNNs in a layerwise manner and then adds a subset of correlated features in a single shot. When performing experiments with functional MRI datasets for classifying patients from healthy controls, we were able to obtain simpler and more generalizable DNNs. The obtained DNNs maintained a similar performance as the full network with only around 2% of the initial trainable parameters. Further, we used the trained network to identify salient brain regions and connections from functional connectome for multiple brain disorders. The identified biomarkers were found to closely correspond to previously known disease biomarkers. The proposed methods have cross-modal applications in obtaining leaner DNNs that seem to fit the data better. The corresponding code is available at https: //github.com/SCSE-Biomedical-Computing-Group/LEAN_CLIP. Keywords: Alzheimer's disease, attention deficit hyperactivity disorder, brain decoding, deep neural networks, feature selection, major depressive disorder, mild cognitive impairment 1 These authors contributed equally. 2 Data used in preparation of this article were obtained from the ADNI database (adni. loni.usc.edu). As such, the investigators within the ADNI contributed to the design and implementation of ADNI and/or provided data but did not participate in analysis or writing of this report. A complete list of the ADNI investigators can be found at
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.