Longitudinal MRI analysis using a hybrid DenseNet-BiLSTM method for Alzheimer's disease prediction

Alzheimer's disease is a progressive neurological disorder characterized by brain atrophy and cell death, leading to cognitive decline and impaired functioning. Previous research has primarily focused on using cross-sectional data for Alzheimer's disease identification, but analyzing longitudinal sequential MR images is crucial for improved diagnostic accuracy and understanding disease progression. However, existing deep learning models face challenges in learning spatial and temporal features from such data. To address these challenges, this study presents a novel hybrid DenseNet-BiLSTM method for Alzheimer's disease prediction using longitudinal MRI analysis. The proposed framework combines Convolutional DenseNet for spatial information extraction and joined BiLSTM layers for capturing temporal characteristics and relationships between longitudinal images at different time points. This approach overcomes issues like overfitting, vanishing gradients, and incomplete patient data. We evaluated the model on 684 longitudinal MRI images from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database, including normal controls, individuals with mild cognitive impairment, and Alzheimer's disease patients. The results demonstrate high classification accuracy, with 95.28% for AD/CN, 88.19% for NC/MCI, 83.51% for sMCI/pMCI, and 92.14% for MCI/AD. These findings highlight the substantial improvement in Alzheimer's disease diagnosis achieved through the utilization of longitudinal MRI images. The contributions of this study lie in both the deep learning and medical domains. In the deep learning domain, our hybrid framework effectively learns spatial and temporal features from longitudinal data, addressing the challenges associated with multi-dimensional and sequential time series data. In the medical domain, our study emphasizes the importance of analyzing baseline and longitudinal MR images for accurate diagnosis and understanding disease progression.

Machine Learning-Derived MRI-Based Neurodegeneration Biomarker for Alzheimer's Disease: A Multi-Database Validation Study

BACKGROUND

Pilot study showed that Alzheimer's disease resemblance atrophy index (AD-RAI), a machine learning-derived MRI-based neurodegeneration biomarker of AD, achieved excellent diagnostic performance in diagnosing AD with moderate to severe dementia.

OBJECTIVE

The primary objective was to validate and compare the performance of AD-RAI with conventional volumetric hippocampal measures in diagnosing AD with mild dementia. The secondary objectives were 1) to investigate the association between imaging biomarkers with age and gender among cognitively unimpaired (CU) participants; 2) to analyze whether the performance of differentiating AD with mild dementia from CU will improve after adjustment for age/gender.

METHODS

AD with mild dementia (n = 218) and CU (n = 1,060) participants from 4 databases were included. We investigated the area under curve (AUC), sensitivity, specificity, and balanced accuracy of AD-RAI, hippocampal volume (HV), and hippocampal fraction (HF) in differentiating between AD and CU participants. Among amyloid-negative CU participants, we further analyzed correlation between the biomarkers with age/gender. We also investigated whether adjustment for age/gender will affect performance.

RESULTS

The AUC of AD-RAI (0.93) was significantly higher than that of HV (0.89) and HF (0.89). Subgroup analysis among A + AD and A- CU showed that AUC of AD-RAI (0.97) was also higher than HV (0.94) and HF (0.93). Diagnostic performance of AD-RAI and HF was not affected by age/gender while that of HV improved after age adjustment.

CONCLUSIONS

AD-RAI achieves excellent clinical validity and outperforms conventional volumetric hippocampal measures in aiding the diagnosis of AD mild dementia without the need for age adjustment.

The Value of First-Order Features Based on the Apparent Diffusion Coefficient Map in Evaluating the Therapeutic Effect of Low-Intensity Pulsed Ultrasound for Acute Traumatic Brain Injury With a Rat Model

Purpose

In order to evaluate the neuroprotective effect of low-intensity pulsed ultrasound (LIPUS) for acute traumatic brain injury (TBI), we studied the potential of apparent diffusion coefficient (ADC) values and ADC-derived first-order features regarding this problem.

Methods

Forty-five male Sprague Dawley rats (sham group: 15, TBI group: 15, LIPUS treated: 15) were enrolled and underwent magnetic resonance imaging. Scanning layers were acquired using a multi-shot readout segmentation of long variable echo trains (RESOLVE) to decrease distortion. The ultrasound transducer was applied to the designated region in the injured cortical areas using a conical collimator and was filled with an ultrasound coupling gel. Regions of interest were manually delineated in the center of the damaged cortex on the diffusion weighted images (b = 800 s/mm²) layer by layer for the TBI and LIPUS treated groups using the open-source software ITK-SNAP. Before analysis and modeling, the features were normalized using a z-score method, and a logistic regression model with a backward filtering method was employed to perform the modeling. The entire process was completed using the R language.

Results

During the observation time, the ADC values ipsilateral to the trauma in the TBI and LIPUS groups increased rapidly up to 24 h. After statistical analysis, the 10th percentile, 90th percentile, mean, skewness, and uniformity demonstrated a significant difference among three groups. The receiver operating characteristic curve (ROC) analysis shows that the combined LR model exhibited the highest area under the curve value (AUC: 0.96).

Conclusion

The combined LR model of first-order features based on the ADC map can acquire a higher diagnostic performance than each feature only in evaluating the neuroprotective effect of LIPUS for TBI. Models based on first-order features may have potential value in predicting the therapeutic effect of LIPUS in clinical practice in the future.

Treatment Enhances Betweenness Centrality of Fronto-Parietal Network in Parkinson’s Patients

Previous studies have demonstrated a close relationship between early Parkinson’s disease and functional network abnormalities. However, the pattern of brain changes in the early stages of Parkinson’s disease has not been confirmed, which has important implications for the study of clinical indicators of Parkinson’s disease. Therefore, we investigated the functional connectivity before and after treatment in patients with early Parkinson’s disease, and further investigated the relationship between some topological properties and clinicopathological indicators. We included resting state-fMRI (rs-fMRI) data from 27 patients with early Parkinson’s disease aged 50–75 years from the Parkinson’s Disease Progression Markers Initiative (PPMI). The results showed that the functional connectivity of 6 networks, cerebellum network (CBN), cingulo_opercular network (CON), default network (DMN), fronto-parietal network (FPN), occipital network (OCC), and sensorimotor network (SMN), was significantly changed. Compared to before treatment, the main functional connections were concentrated in the CBN after treatment. In addition, the coefficients of these nodes have also changed. For betweenness centrality (BC), the FPN showed a significant improvement in treatment (p < 0.001). In conclusion, the alteration of functional networks in early Parkinson’s patients is critical for clarifying the mechanisms of early diagnosis of the disease.

The Task Pre-Configuration Is Associated With Cognitive Performance Evidence From the Brain Synchrony

Although many resting state and task state characteristics have been studied, it is still unclear how the brain network switches from the resting state during tasks. The current theory shows that the brain is a complex dynamic system and synchrony is defined to measure brain activity. The study compared the changes of synchrony between the resting state and different task states in healthy young participants (N = 954). It also examined the ability to switch from the resting state to the task-general architecture of synchrony. We found that the synchrony increased significantly during the tasks. And the results showed that the brain has a task-general architecture of synchrony during different tasks. The main feature of task-based reasoning is that the increase in synchrony of high-order cognitive networks is significant, while the increase in synchrony of sensorimotor networks is relatively low. In addition, the high synchrony of high-order cognitive networks in the resting state can promote task switching effectively and the pre-configured participants have better cognitive performance, which shows that spontaneous brain activity and cognitive ability are closely related. These results revealed changes in the brain network configuration for switching between the resting state and task state, highlighting the consistent changes in the brain network between different tasks. Also, there was an important relationship between the switching ability and the cognitive performance.

Abnormal Dynamic Functional Networks in Subjective Cognitive Decline and Alzheimer's Disease

Subjective cognitive decline (SCD) is considered to be the preclinical stage of Alzheimer's disease (AD) and has the potential for the early diagnosis and intervention of AD. It was implicated that CSF-tau, which increases very early in the disease process in AD, has a high sensitivity and specificity to differentiate AD from normal aging, and the highly connected brain regions behaved more tau burden in patients with AD. Thus, a highly connected state measured by dynamic functional connectivity may serve as the early changes of AD. In this study, forty-five normal controls (NC), thirty-six individuals with SCD, and thirty-five patients with AD were enrolled to obtain the resting-state functional magnetic resonance imaging scanning. Sliding windows, Pearson correlation, and clustering analysis were combined to investigate the different levels of information transformation states. Three states, namely, the low state, the middle state, and the high state, were characterized based on the strength of functional connectivity between each pair of brain regions. For the global dynamic functional connectivity analysis, statistically significant differences were found among groups in the three states, and the functional connectivity in the middle state was positively correlated with cognitive scales. Furthermore, the whole brain was parcellated into four networks, namely, default mode network (DMN), cognitive control network (CCN), sensorimotor network (SMN), and occipital-cerebellum network (OCN). For the local network analysis, statistically significant differences in CCN for low state and SMN for middle state and high state were found in normal controls and patients with AD. Meanwhile, the differences were also found in normal controls and individuals with SCD. In addition, the functional connectivity in SMN for high state was positively correlated with cognitive scales. Converging results showed the changes in dynamic functional states in individuals with SCD and patients with AD. In addition, the changes were mainly in the high strength of the functional connectivity state.