Salience network anatomical and molecular markers are linked with cognitive dysfunction in mild cognitive impairment

Abstract

Background and Purpose:Recent studies indicate disrupted functional mechanisms of salience network (SN) regions-right anterior insula, left anterior insula, and anterior cingulate cortex-in mild cognitive impairment (MCI). However, the underlying anatomical and molecular mechanisms in these regions are not clearly understood yet. It is also unknown whether integration of multimodal-anatomical and molecular-markers could predict cognitive impairment better in MCI.Methods: Herein we quantified anatomical volumetric markers via structural MRI and molecular amyloid markers via PET with Pittsburgh compound B in SN regions of MCI (n = 33) and healthy controls (n = 27). From these markers, we built support vector machine learning models aiming to estimate cognitive dysfunction in MCI. Results:We found that anatomical markers are significantly reduced and molecular markers are significantly elevated in SN nodes of MCI compared to healthy controls (p < .05).These altered markers in MCI patients were associated with their worse cognitive performance (p < .05). Our machine learning-based modeling further suggested that the integration of multimodal markers predicts cognitive impairment in MCI superiorly compared to using single modality-specific markers.Conclusions: These findings shed light on the underlying anatomical volumetric and molecular amyloid alterations in SN regions and show the significance of multimodal markers integration approach in better predicting cognitive impairment in MCI.

Amyloid-beta biomarkers in Braak stages and their predictive relationships with cognitive impairment: Support vector machine and deep learning approaches

“…45.45% and 55.56% of participants were females in MCI an in controls respectively.Average MMSE (standard deviation) was 26.70 (2.64) in subjects with MCI and 28.70 (1.64) in controls. Data were acquired from the OASIS as per our previous work [27]. Study participants were given an MCI diagnosis based on the widely used clinical dementia rating (CDR) scale [28, 29].…”

“…All participants got T1-weighted brain MRI using 3T Biograph MR or 1.5T Vision, Siemens 3T TrioTim. Multi-atlas region Segmentation utilizing Ensembles of registration algorithms and parameters and locally optimal atlas selection (MUSE) was used for individual T1-MRI segmentation [27, 32, 33]. We quantified dynamic PET scans as the Distribution Volume Ratio (DVR) outcome [34], the most suitable one compared to other statistic approaches.…”

“…Data acquisition and processing were performed as per our previous work [27]. In brief, bolus injection of [11]C-PiB, was followed by Dynamic PET 3D scans that were acquired for more than an hour, using ECATHR plus 962 PET scanner or Biograph 40 PET/CT scanner.…”

“…One challenge to the appropriate quantification of PET images is the partial volume effect [35] which was accounted for in our study by using a state-of-the-art parallel level set (PLS) regularization-based partial volume correction method [36]. To harmonize multi-scanner datasets, we relied on our previously used and validated approach [27,32] in which we used data from all study participants to compute the coefficients accounting for the effect of factors such as site, age and sex and apply them to each individual participant [37]. After correcting for the site, age, and sex covariates, we produced the harmonized DVR and used that in our analyses.…”

“…(response) variable. For our study, we employed two machine learning algorithms, especially support vector machine (SVM) consistent with our previous studies [27,38] and artificial neural network (ANN) to evaluate the predictions of MMSE. For the SVM model (Fig.…”