Differentiating Alzheimer's Disease from Dementia with Lewy Bodies Using a Deep Learning Technique Based on Structural Brain Connectivity

Automated Video Analysis of Audio-Visual Approaches to Predict and Detect Mild Cognitive Impairment and Dementia in Older Adults

BACKGROUND

Early identification of different stages of cognitive impairment is important to provide available intervention and timely care for the elderly.

OBJECTIVE

This study aimed to examine the ability of the artificial intelligence (AI) technology to distinguish participants with mild cognitive impairment (MCI) from those with mild to moderate dementia based on automated video analysis.

METHODS

A total of 95 participants were recruited (MCI, 41; mild to moderate dementia, 54). The videos were captured during the Short Portable Mental Status Questionnaire process; the visual and aural features were extracted using these videos. Deep learning models were subsequently constructed for the binary differentiation of MCI and mild to moderate dementia. Correlation analysis of the predicted Mini-Mental State Examination, Cognitive Abilities Screening Instrument scores, and ground truth was also performed.

RESULTS

Deep learning models combining both the visual and aural features discriminated MCI from mild to moderate dementia with an area under the curve (AUC) of 77.0% and accuracy of 76.0% . The AUC and accuracy increased to 93.0% and 88.0%, respectively, when depression and anxiety were excluded. Significant moderate correlations were observed between the predicted cognitive function and ground truth, and the correlation was strong excluding depression and anxiety. Interestingly, female, but not male, exhibited a correlation.

CONCLUSION

The study showed that video-based deep learning models can differentiate participants with MCI from those with mild to moderate dementia and can predict cognitive function. This approach may offer a cost-effective and easily applicable method for early detection of cognitive impairment.

Multimodal deep learning for Alzheimer's disease dementia assessment

Worldwide, there are nearly 10 million new cases of dementia annually, of which Alzheimer's disease (AD) is the most common. New measures are needed to improve the diagnosis of individuals with cognitive impairment due to various etiologies. Here, we report a deep learning framework that accomplishes multiple diagnostic steps in successive fashion to identify persons with normal cognition (NC), mild cognitive impairment (MCI), AD, and non-AD dementias (nADD). We demonstrate a range of models capable of accepting flexible combinations of routinely collected clinical information, including demographics, medical history, neuropsychological testing, neuroimaging, and functional assessments. We then show that these frameworks compare favorably with the diagnostic accuracy of practicing neurologists and neuroradiologists. Lastly, we apply interpretability methods in computer vision to show that disease-specific patterns detected by our models track distinct patterns of degenerative changes throughout the brain and correspond closely with the presence of neuropathological lesions on autopsy. Our work demonstrates methodologies for validating computational predictions with established standards of medical diagnosis.

Interhemispheric Cortical Network Connectivity Reorganization Predicts Vision Impairment in Stroke

Stroke is one of the main causes of disability in human beings, and when the occipital lobe is affected, this leads to partial vision loss (homonymous hemianopia). To understand brain mechanisms of vision loss and recovery, graph theory-based brain functional connectivity network (FCN) analysis was recently introduced. However, few brain network studies exist that have studied if the strength of the damaged FCN can predict the extent of functional impairment. We now characterized the brain FCN using deep neural network analysis to describe multiscale brain networks and explore their corresponding physiological patterns. In a group of 24 patients and 24 controls, Bi-directional long short-term memory (Bi-LSTM) was evaluated to reveal the cortical network pattern learning efficiency compared with other traditional algorithms. Bi-LSTM achieved the best balanced-overall accuracy of 73% with sensitivity of 70% and specificity and 75% in the low alpha band. This demonstrates that bi-directional learning can capture the brain network feature representation of both hemispheres. It shows that brain damage leads to reorganized FCN patterns with a greater number of functional connections of intermediate density in the high alpha band. Future studies should explore how this understanding of brain FCN can be used for clinical diagnostics and rehabilitation.

Decision Tree Application to Classification Problems with Boosting Algorithm

A personal credit evaluation algorithm is proposed by the design of a decision tree with a boosting algorithm, and the classification is carried out. By comparison with the conventional decision tree algorithm, it is shown that the boosting algorithm acts to speed up the processing time. The Classification and Regression Tree (CART) algorithm with the boosting algorithm showed 90.95% accuracy, slightly higher than without boosting, 90.31%. To avoid overfitting of the model on the training set due to unreasonable data set division, we consider cross-validation and illustrate the results with simulation; hypermeters of the model have been applied and the model fitting effect is verified. The proposed decision tree model is fitted optimally with the help of a confusion matrix. In this paper, relevant evaluation indicators are also introduced to evaluate the performance of the proposed model. For the comparison with the conventional methods, accuracy rate, error rate, precision, recall, etc. are also illustrated; we comprehensively evaluate the model performance based on the model accuracy after the 10-fold cross-validation. The results show that the boosting algorithm improves the performance of the model in accuracy and precision when CART is applied, but the model fitting time takes much longer, around 2 min. With the obtained result, it is verified that the performance of the decision tree model is improved under the boosting algorithm. At the same time, we test the performance of the proposed verification model with model fitting, and it could be applied to the prediction model for customers’ decisions on subscription to the fixed deposit business.

[Accuracy of Classification of Cerebral Blood Flow Reduction Patterns Using Statistical Analysis Images Generated with Simulated SPECT Datasets via Deep Learning]

PURPOSE

The aim of this study was to evaluate the classification accuracy of specific blood flow reduction patterns in clinical images by deep learning using simulation data.

METHODS

We obtained Z-score maps for 100 cases each of simulated Alzheimer's disease (AD), simulated dementia with Lewy bodies (DLB), and simulated normal cognition (NC) by performing statistical analysis of the simulation data that provided defects and healthy patient data. The clinical images were determined by reference to radiological reports, and Z-score maps of AD (n=33), DLB (n=20), and NC (n=28) were used. A network was constructed with reference to AlexNet, 4-fold cross-validation was performed using only simulation data, and classification accuracy was evaluated. We also trained the model using the simulation data and classified the clinical images.

RESULTS

The accuracy rate of classification between simulations was 96.2% and that of the clinical images was 84.2%.

CONCLUSION

Through deep learning using simulation data, clinical images may be classified with an accuracy of 84.2%.

A Robust and Accurate Deep-learning-based Method for the Segmentation of Subcortical Brain: Cross-dataset Evaluation of Generalization Performance

Purpose:

To analyze subcortical brain volume more reliably, we propose a deep learning segmentation method of subcortical brain based on magnetic resonance imaging (MRI) having high generalization performance, accuracy, and robustness.

Methods:

First, local images of three-dimensional (3D) bounding boxes were extracted for seven subcortical structures (thalamus, putamen, caudate, pallidum, hippocampus, amygdala, and accumbens) from a whole brain MR image as inputs to the neural network. Second, dilated convolution layers, which input information of variable scope, were introduced to the blocks that make up the neural network. These blocks were connected in parallel to simultaneously process global and local information obtained by the dilated convolution layers. To evaluate generalization performance, different datasets were used for training and testing sessions (cross-dataset evaluation) because subcortical brain segmentation in clinical analysis is assumed to be applied to unknown datasets.

Results:

The proposed method showed better generalization performance that can obtain stable accuracy for all structures, whereas the state-of-the-art deep learning method obtained extremely low accuracy for some structures. The proposed method performed segmentation for all samples without failing with significantly higher accuracy (P < 0.005) than conventional methods such as 3D U-Net, FreeSurfer, and Functional Magnetic Resonance Imaging of the Brain’s (FMRIB’s) Integrated Registration and Segmentation Tool in the FMRIB Software Library (FSL-FIRST). Moreover, when applying this proposed method to larger datasets, segmentation was robustly performed for all samples without producing segmentation results on the areas that were apparently different from anatomically relevant areas. On the other hand, FSL-FIRST produced segmentation results on the area that were apparently and largely different from the anatomically relevant area for about one-third to one-fourth of the datasets.

Conclusion:

The cross-dataset evaluation showed that the proposed method is superior to existing methods in terms of generalization performance, accuracy, and robustness.

Differentiation between multiple sclerosis and neuromyelitis optica spectrum disorders by multiparametric quantitative MRI using convolutional neural network

Multiple sclerosis and neuromyelitis optica spectrum disorders are both neuroinflammatory diseases and have overlapping clinical manifestations. We developed a convolutional neural network model that differentiates between the two based on magnetic resonance imaging data. Thirty-five patients with relapsing-remitting multiple sclerosis and eighteen age-, sex-, disease duration-, and Expanded Disease Status Scale-matched patients with anti-aquaporin-4 antibody-positive neuromyelitis optica spectrum disorders were included in this study. All patients were scanned on a 3-T scanner using a multi-dynamic multi-echo sequence that simultaneously measures R1 and R2 relaxation rates and proton density. R1, R2, and proton density maps were analyzed using our convolutional neural network model. To avoid overfitting on a small dataset, we aimed to separate features of images into those specific to an image and those common to the group, based on SqueezeNet. We used only common features for classification. Leave-one-out cross validation was performed to evaluate the performance of the model. The area under the receiver operating characteristic curve of the developed convolutional neural network model for differentiating between the two disorders was 0.859. The sensitivity to multiple sclerosis and neuromyelitis optica spectrum disorders, and accuracy were 80.0%, 83.3%, and 81.1%, respectively. In conclusion, we developed a convolutional neural network model that differentiates between multiple sclerosis and neuromyelitis optica spectrum disorders, and which is designed to avoid overfitting on small training datasets. Our proposed algorithm may facilitate a differential diagnosis of these diseases in clinical practice.

Quantitative Assessment of Resting-State for Mild Cognitive Impairment Detection: A Functional Near-Infrared Spectroscopy and Deep Learning Approach

BACKGROUND

Mild cognitive impairment (MCI) is considered a prodromal stage of Alzheimer's disease. Early diagnosis of MCI can allow for treatment to improve cognitive function and reduce modifiable risk factors.

OBJECTIVE

This study aims to investigate the feasibility of individual MCI detection from healthy control (HC) using a minimum duration of resting-state functional near-infrared spectroscopy (fNIRS) signals.

METHODS

In this study, nine different measurement durations (i.e., 30, 60, 90, 120, 150, 180, 210, 240, and 270 s) were evaluated for MCI detection via the graph theory analysis and traditional machine learning approach, such as linear discriminant analysis, support vector machine, and K-nearest neighbor algorithms. Moreover, feature representation- and classification-based transfer learning (TL) methods were applied to identify MCI from HC through the input of connectivity maps with 30 and 90 s duration.

RESULTS

There was no significant difference among the nine various time windows in the machine learning and graph theory analysis. The feature representation-based TL showed improved accuracy in both 30 and 90 s cases (i.e., 30 s: 81.27% and 90 s: 76.73%). Notably, the classification-based TL method achieved the highest accuracy of 95.81% using the pre-trained convolutional neural network (CNN) model with the 30 s interval functional connectivity map input.

CONCLUSION

The results indicate that a 30 s measurement of the resting-state with fNIRS could be used to detect MCI. Moreover, the combination of neuroimaging (e.g., functional connectivity maps) and deep learning methods (e.g., CNN and TL) can be considered as novel biomarkers for clinical computer-assisted MCI diagnosis.

Deep learning for brain disorders: from data processing to disease treatment

In order to reach precision medicine and improve patients' quality of life, machine learning is increasingly used in medicine. Brain disorders are often complex and heterogeneous, and several modalities such as demographic, clinical, imaging, genetics and environmental data have been studied to improve their understanding. Deep learning, a subpart of machine learning, provides complex algorithms that can learn from such various data. It has become state of the art in numerous fields, including computer vision and natural language processing, and is also growingly applied in medicine. In this article, we review the use of deep learning for brain disorders. More specifically, we identify the main applications, the concerned disorders and the types of architectures and data used. Finally, we provide guidelines to bridge the gap between research studies and clinical routine.

Artificial intelligence for brain diseases: A systematic review

Artificial intelligence (AI) is a major branch of computer science that is fruitfully used for analyzing complex medical data and extracting meaningful relationships in datasets, for several clinical aims. Specifically, in the brain care domain, several innovative approaches have achieved remarkable results and open new perspectives in terms of diagnosis, planning, and outcome prediction. In this work, we present an overview of different artificial intelligent techniques used in the brain care domain, along with a review of important clinical applications. A systematic and careful literature search in major databases such as Pubmed, Scopus, and Web of Science was carried out using "artificial intelligence" and "brain" as main keywords. Further references were integrated by cross-referencing from key articles. 155 studies out of 2696 were identified, which actually made use of AI algorithms for different purposes (diagnosis, surgical treatment, intra-operative assistance, and postoperative assessment). Artificial neural networks have risen to prominent positions among the most widely used analytical tools. Classic machine learning approaches such as support vector machine and random forest are still widely used. Task-specific algorithms are designed for solving specific problems. Brain images are one of the most used data types. AI has the possibility to improve clinicians' decision-making ability in neuroscience applications. However, major issues still need to be addressed for a better practical use of AI in the brain. To this aim, it is important to both gather comprehensive data and build explainable AI algorithms.

Deep Feature Selection and Causal Analysis of Alzheimer's Disease

Deep convolutional neural networks (DCNNs) have achieved great success for image classification in medical research. Deep learning with brain imaging is the imaging method of choice for the diagnosis and prediction of Alzheimer’s disease (AD). However, it is also well known that DCNNs are “black boxes” owing to their low interpretability to humans. The lack of transparency of deep learning compromises its application to the prediction and mechanism investigation in AD. To overcome this limitation, we develop a novel general framework that integrates deep leaning, feature selection, causal inference, and genetic-imaging data analysis for predicting and understanding AD. The proposed algorithm not only improves the prediction accuracy but also identifies the brain regions underlying the development of AD and causal paths from genetic variants to AD via image mediation. The proposed algorithm is applied to the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset with diffusion tensor imaging (DTI) in 151 subjects (51 AD and 100 non-AD) who were measured at four time points of baseline, 6 months, 12 months, and 24 months. The algorithm identified brain regions underlying AD consisting of the temporal lobes (including the hippocampus) and the ventricular system.