Background Frontotemporal dementia (FTD) is caused by frontotemporal lobar degeneration (FTLD), characterized mainly by inclusions of Tau (FTLD-Tau) or TAR DNA binding43 (FTLD-TDP) proteins. Plasma... Show moreBackground Frontotemporal dementia (FTD) is caused by frontotemporal lobar degeneration (FTLD), characterized mainly by inclusions of Tau (FTLD-Tau) or TAR DNA binding43 (FTLD-TDP) proteins. Plasma biomarkers are strongly needed for specific diagnosis and potential treatment monitoring of FTD. We aimed to identify specific FTD plasma biomarker profiles discriminating FTD from AD and controls, and between FTD pathological subtypes. In addition, we compared plasma results with results in post-mortem frontal cortex of FTD cases to understand the underlying process. Methods Plasma proteins (n = 1303) from pathologically and/or genetically confirmed FTD patients (n = 56; FTLD-Tau n = 16; age = 58.2 +/- 6.2; 44% female, FTLD-TDP n = 40; age = 59.8 +/- 7.9; 45% female), AD patients (n = 57; age = 65.5 +/- 8.0; 39% female), and non-demented controls (n = 148; 61.3 +/- 7.9; 41% female) were measured using an aptamer-based proteomic technology (SomaScan). In addition, exploratory analysis in post-mortem frontal brain cortex of FTD (n = 10; FTLD-Tau n = 5; age = 56.2 +/- 6.9, 60% female, and FTLD-TDP n = 5; age = 64.0 +/- 7.7, 60% female) and non-demented controls (n = 4; age = 61.3 +/- 8.1; 75% female) were also performed. Differentially regulated plasma and tissue proteins were identified by global testing adjusting for demographic variables and multiple testing. Logistic lasso regression was used to identify plasma protein panels discriminating FTD from non-demented controls and AD, or FTLD-Tau from FTLD-TDP. Performance of the discriminatory plasma protein panels was based on predictions obtained from bootstrapping with 1000 resampled analysis. Results Overall plasma protein expression profiles differed between FTD, AD and controls (6 proteins; p = 0.005), but none of the plasma proteins was specifically associated to FTD. The overall tissue protein expression profile differed between FTD and controls (7-proteins; p = 0.003). There was no difference in overall plasma or tissue expression profile between FTD subtypes. Regression analysis revealed a panel of 12-plasma proteins discriminating FTD from AD with high accuracy (AUC: 0.99). No plasma protein panels discriminating FTD from controls or FTD pathological subtypes were identified. Conclusions We identified a promising plasma protein panel as a minimally-invasive tool to aid in the differential diagnosis of FTD from AD, which was primarily associated to AD pathophysiology. The lack of plasma profiles specifically associated to FTD or its pathological subtypes might be explained by FTD heterogeneity, calling for FTD studies using large and well-characterize cohorts. Show less
Bron, E.E.; Klein, S.; Papma, J.M.; Jiskoot, L.C.; Venkatraghavan, V.; Linders, J.; ... ; Lugt, A. van der 2021
This work validates the generalizability of MRI-based classification of Alzheimer's disease (AD) patients and controls (CN) to an external data set and to the task of prediction of conversion to AD... Show moreThis work validates the generalizability of MRI-based classification of Alzheimer's disease (AD) patients and controls (CN) to an external data set and to the task of prediction of conversion to AD in individuals with mild cognitive impairment (MCI). We used a conventional support vector machine (SVM) and a deep convolutional neural network (CNN) approach based on structural MRI scans that underwent either minimal pre-processing or more extensive preprocessing into modulated gray matter (GM) maps. Classifiers were optimized and evaluated using cross validation in the Alzheimer's Disease Neuroimaging Initiative (ADNI; 334 AD, 520 CN). Trained classifiers were subsequently applied to predict conversion to AD in ADNI MCI patients (231 converters, 628 non converters) and in the independent Health-RI Parelsnoer Neurodegenerative Diseases Biobank data set. From this multi-center study representing a tertiary memory clinic population, we included 199 AD patients, 139 participants with subjective cognitive decline, 48 MCI patients converting to dementia, and 91 MCI patients who did not convert to dementia. AD-CN classification based on modulated GM maps resulted in a similar area-under-the-curve (AUC) for SVM (0.940; 95%CI: 0.924-0.955) and CNN (0.933; 95%CI: 0.918-0.948). Application to conversion prediction in MCI yielded significantly higher performance for SVM (AUC = 0.756; 95%CI: 0.720-0.788) than for CNN (AUC = 0.742; 95%CI: 0.709-0.776) (p < 0.01 for McNemar's test). In external validation, performance was slightly decreased. For AD-CN, it again gave similar AUCs for SVM (0.896; 95%CI: 0.855-0.932) and CNN (0.876; 95%CI: 0.836-0.913). For prediction in MCI, performances decreased for both SVM (AUC = 0.665; 95%CI: 0.576-0.760) and CNN (AUC = 0.702; 95%CI: 0.624-0.786). Both with SVM and CNN, classification based on modulated GM maps significantly outperformed classification based on minimally processed images (p = 0.01). Deep and conventional classifiers performed equally well for AD classification and their performance decreased only slightly when applied to the external cohort. We expect that this work on external validation contributes towards translation of machine learning to clinical practice. Show less
Several anatomical MRI markers for Alzheimer's disease (AD) have been identified. Hippocampal volume, cortical thickness, and grey matter density have been used successfully to discriminate AD... Show moreSeveral anatomical MRI markers for Alzheimer's disease (AD) have been identified. Hippocampal volume, cortical thickness, and grey matter density have been used successfully to discriminate AD patients from controls. These anatomical MRI measures have so far mainly been used separately. The full potential of anatomical MRI scans for AD diagnosis might thus not yet have been used optimally. In this study, we therefore combined multiple anatomical MRI measures to improve diagnostic classification of AD. For 21 clinically diagnosed AD patients and 21 cognitively normal controls, we calculated (i) cortical thickness, (ii) cortical area, (iii) cortical curvature, (iv) grey matter density, (v) subcortical volumes, and (vi) hippocampal shape. These six measures were used separately and combined as predictors in an elastic net logistic regression. We made receiver operating curve plots and calculated the area under the curve (AUC) to determine classification performance. AUC values for the single measures ranged from 0.67 (cortical thickness) to 0.94 (grey matter density). The combination of all six measures resulted in an AUC of 0.98. Our results demonstrate that the different anatomical MRI measures contain complementary information. A combination of these measures may therefore improve accuracy of AD diagnosis in clinical practice. Hum Brain Mapp 37:1920-1929, 2016. (c) 2016 Wiley Periodicals, Inc. Show less