Alzheimer’s Disease (AD) is a progressive neurodegenerative disease where biomarkers for disease based on pathophysiology may be able to provide objective measures for disease diagnosis and staging. Neuroimaging scans acquired from MRI and metabolism images obtained by FDG-PET provide in-vivo measurements of structure and function (glucose metabolism) in a living brain. It is hypothesized that combining multiple different image modalities providing complementary information could help improve early diagnosis of AD. In this paper, we propose a novel deep-learning-based framework to discriminate individuals with AD utilizing a multimodal and multiscale deep neural network. Our method delivers 82.4% accuracy in identifying the individuals with mild cognitive impairment (MCI) who will convert to AD at 3 years prior to conversion (86.4% combined accuracy for conversion within 1–3 years), a 94.23% sensitivity in classifying individuals with clinical diagnosis of probable AD, and a 86.3% specificity in classifying non-demented controls improving upon results in published literature.
To evaluate the performance of a federated learning framework for deep neural network-based retinal microvasculature segmentation and referable diabetic retinopathy (RDR) classification using OCT and OCT angiography (OCTA). Retrospective analysis of clinical OCT and OCTA scans of control participants and patients with diabetes. The 153 OCTA en face images used for microvasculature segmentation were acquired from 4 OCT instruments with fields of view ranging from 2 × 2-mm to 6 × 6-mm. The 700 eyes used for RDR classification consisted of OCTA en face images and structural OCT projections acquired from 2 commercial OCT systems. OCT angiography images used for microvasculature segmentation were delineated manually and verified by retina experts. Diabetic retinopathy (DR) severity was evaluated by retinal specialists and was condensed into 2 classes: non-RDR and RDR. The federated learning configuration was demonstrated via simulation using 4 clients for microvasculature segmentation and was compared with other collaborative training methods. Subsequently, federated learning was applied over multiple institutions for RDR classification and was compared with models trained and tested on data from the same institution (internal models) and different institutions (external models). For microvasculature segmentation, we measured the accuracy and Dice similarity coefficient (DSC). For severity classification, we measured accuracy, area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve, balanced accuracy, F1 score, sensitivity, and specificity. For both applications, federated learning achieved similar performance as internal models. Specifically, for microvasculature segmentation, the federated learning model achieved similar performance (mean DSC across all test sets, 0.793) as models trained on a fully centralized dataset (mean DSC, 0.807). For RDR classification, federated learning achieved a mean AUROC of 0.954 and 0.960; the internal models attained a mean AUROC of 0.956 and 0.973. Similar results are reflected in the other calculated evaluation metrics. Federated learning showed similar results to traditional deep learning in both applications of segmentation and classification, while maintaining data privacy. Evaluation metrics highlight the potential of collaborative learning for increasing domain diversity and the generalizability of models used for the classification of OCT data.
Like many neurodegenerative diseases, the clinical symptoms of Parkinson’s disease (PD) do not manifest until significant progression of the disease has already taken place, motivating the need for sensitive biomarkers of the disease. While structural imaging is a potentially attractive method due to its widespread availability and non-invasive nature, global morphometric measures (e.g. volume) have proven insensitive to subtle disease change. Here we use individual surface displacements from deformations of an average surface model to capture disease related changes in shape of the subcortical structures in Parkinson’s disease. Data were obtained from both the University of British Columbia (UBC) (n=54 healthy controls (HC) & n=55 Parkinson’s disease (PD) patients) and the publicly available Parkinson’s Progression Marker’s Initiative (PPMI)(n=137(HC) & n=189 (PD)) database. A high dimensional non-rigid registration algorithm was used to register target segmentation labels (caudate, putamen, pallidum and thalamus) to a set of segmentation labels defined on the average-template. The vertex-wise surface displacements were significantly different between PD and HC in thalamic and caudate structures. However overall displacements did not correlate with disease severity, as assessed by the Unified Parkinson's Disease Rating Scale (UPDRS). The results from this study suggest disease-relevant shape abnormalities can be robustly detected in subcortical structures in Parkinson’s disease. Future studies will be required to determine if shape changes in subcortical structures are seen in the prodromal phases of the disease.
18F‐fluorodeoxyglucose positron emission tomography (FDG‐PET) enables in‐vivo capture of the topographic metabolism patterns in the brain. These images have shown great promise in revealing the altered metabolism patterns in Alzheimer's disease (AD). The AD pathology is progressive, and leads to structural and functional alterations that lie on a continuum. There is a need to quantify the altered metabolism patterns that exist on a continuum into a simple measure. This work proposes a 3D convolutional neural network with residual connections that generates a probability score useful for interpreting the FDG‐PET images along the continuum of AD. This network is trained and tested on images of stable normal control and stable Dementia of the Alzheimer's type (sDAT) subjects, achieving an AUC of 0.976 via repeated fivefold cross‐validation. An independent test set consisting of images in between the two extreme ends of the DAT spectrum is used to further test the generalization performance of the network. Classification performance of 0.811 AUC is achieved in the task of predicting conversion of mild cognitive impairment to DAT for conversion time of 0–3 years. The saliency and class activation maps, which highlight the regions of the brain that are most important to the classification task, implicate many known regions affected by DAT including the posterior cingulate cortex, precuneus, and hippocampus.