Purpose: Alzheimer's disease (AD) and dementia with Lewy bodies (DLB) are representative disorders of dementia of the elderly and the neuroimaging has contributed to early diagnosis by estimation of alterations of brain volume, blood flow and metabolism.A brain network analysis by MR imaging (MR connectome) is a recently developed technique and can estimate the dysfunction of the brain network in AD and DLB.A graph theory which is a major technique of network analysis is useful for a group study to extract the feature of disorders, but is not necessarily suitable for the disorder differentiation at the individual level.In this investigation, we propose a deep learning technique as an alternative method of the graph analysis for recognition and classification of AD and DLB at the individual subject level.Materials and Methods: Forty-eight brain structural connectivity data of 18 AD, 8 DLB and 22 healthy controls were applied to the machine learning consisting of a six-layer convolution neural network (CNN) model.Estimation of the deep learning model to classify AD, DLB and non-AD/DLB was performed using the 4-fold cross-validation method. Results:The accuracy, average precision and recall of our CNN model were 0.73, 0.78 and 0.73, and the specificity precision and recall were 0.68 and 0.79 in AD, 0.94 and 0.65 in DLB and 0.73 and 0.75 in non-AD/DLB.The triangular probability map of the MR connectome revealed the probability of AD, DLB and non-AD/DLB in each subject. Conclusion:Our preliminary investigation revealed the adaptation of deep learning to the MR connectome and proposed its utility in the differentiation of dementia disorders at the individual subject level.
It is widely held that long-term memory gradually develops in the temporal neocortex after initial memory encoding into the hippocampus. However, little is known as to whether and where long-term memory can be newly created in the human temporal neocortex. In this functional magnetic resonance imaging study, we detected brain activity in the temporal neocortex that was developed ∼8 weeks after study of unfamiliar pictorial paired associates. Two sets of paired Fourier figures were studied, one ∼8 weeks before test and the other immediately before test, keeping the correct performance during the tests balanced across the two sets of stimuli. Significant signal increase was observed in the right hippocampus during retrieval of newly studied pairs relative to initially studied pairs. In contrast, significant signal increase was observed in the anterior temporal cortex during retrieval of initially studied pairs relative to newly studied pairs. The greater activity during retrieval of older memory developed in the temporal neocortex provides direct evidence of formation of temporal neocortical representation for stable long-term memory.
Objective and background This study aimed to develop a deep convolutional neural network (DCNN) model capable of generating synthetic 4D magnetic resonance angiography (MRA) from 3D time-of-flight (TOF) images, allowing estimation of temporal changes in arterial flow. TOF MRA provides static information about arterial structures through maximum intensity projection (MIP) processing, but it does not capture the dynamic information of contrast agent circulation, which is lost during MIP processing. Considering the principles of TOF, it is hypothesized that dynamic information about arterial blood flow is latent within TOF signals. Although arterial spin labeling (ASL) can extract dynamic arterial information, ASL MRA has drawbacks, such as longer imaging times and lower spatial resolution than TOF MRA. This study's primary aim is to extend the utility of TOF MRA by training a machine-learning model on paired TOF and ASL data to extract latent dynamic information from TOF signals. Methods A DCNN combining a modified U-Net and a long-short-term memory (LSTM) network was trained on a dataset of 13 subjects (11 men and two women, aged 42-77 years) using paired 3D TOF MRA and 4D ASL MRA images. Subjects had no history of cerebral vessel occlusion or significant stenosis. The dataset was acquired using a 3T MRI system with a 32-channel head coil. Preprocessing involved resampling and intensity normalization of TOF and ASL images, followed by data augmentation and arterial mask generation. The model learned to extract flow information from TOF images and generate 8-phase 4D MRA images. The precision of flow estimation was evaluated using the coefficient of determination (R²) and Bland-Altman analysis. A board-certified neuroradiologist validated the quality of the images and the absence of significant stenosis in the major cerebral arteries. Results The generated 4D MRA images closely resembled the ground-truth ASL MRA data, with R² values of 0.92, 0.85, and 0.84 for the internal carotid artery (ICA), proximal middle cerebral artery (MCA), and distal MCA, respectively. Bland-Altman analysis revealed a systematic error of -0.06, with 95% agreement limits ranging from -0.18 to 0.12. Additionally, the model successfully identified flow abnormalities in a subject with left MCA stenosis, displaying a delayed peak and subsequent flattening distal to the stenosis, indicative of reduced blood flow. Visualization of the predicted arterial flow overlaid on the original TOF MRA images highlighted the spatial progression and dynamics of the flow. Conclusions The DCNN model effectively generated synthetic 4D MRA images from TOF images, demonstrating its potential to estimate temporal changes in arterial flow accurately. This non-invasive technique offers a promising alternative to conventional methods for visualizing and evaluating healthy and pathological flow dynamics. It has significant potential to improve the diagnosis and treatment of cerebrovascular diseases by providing detailed temporal flow information without the need for contrast agents or invasive procedures. The practical implementation of this model could enable the extraction of dynamic cerebral blood flow information from routine brain MRI examinations, contributing to the early diagnosis and management of cerebrovascular disorders.
Early-phase pathologies of Alzheimer's disease (AD) are attracting much attention after clinical trials of drugs designed to remove beta-amyloid (Aβ) aggregates failed to recover memory and cognitive function in symptomatic AD patients. Here, we show that phosphorylation of serine/arginine repetitive matrix 2 (SRRM2) at Ser1068, which is observed in the brains of early phase AD mouse models and postmortem end-stage AD patients, prevents its nuclear translocation by inhibiting interaction with T-complex protein subunit α. SRRM2 deficiency in neurons destabilized polyglutamine binding protein 1 (PQBP1), a causative gene for intellectual disability (ID), greatly affecting the splicing patterns of synapse-related genes, as demonstrated in a newly generated PQBP1-conditional knockout model. PQBP1 and SRRM2 were downregulated in cortical neurons of human AD patients and mouse AD models, and the AAV-PQBP1 vector recovered RNA splicing, the synapse phenotype, and the cognitive decline in the two mouse models. Finally, the kinases responsible for the phosphorylation of SRRM2 at Ser1068 were identified as ERK1/2 (MAPK3/1). These results collectively reveal a new aspect of AD pathology in which a phosphorylation signal affecting RNA splicing and synapse integrity precedes the formation of extracellular Aβ aggregates and may progress in parallel with tau phosphorylation.
Poster: ECR 2016 / C-0527 / Impact of axon undulation on the estimation of dMRI metrics: Monte-Carlo simulation study with conventional DTI and NODDI by: Kamiya, R. Irie, K. Kamagata, M. Hori, Y. Suzuki, H. Mori, A. Kunimatsu, S. Aoki, K. Ohtomo; Tokyo/JP
