Multimodal and Multiscale Deep Neural Networks for the Early Diagnosis of Alzheimer's Disease using structural MR and FDG-PET images

MACFNet: Detection of Alzheimer's disease via multiscale attention and cross-enhancement fusion network

BACKGROUND AND OBJECTIVE

Alzheimer's disease (AD) is a dreaded degenerative disease that results in a profound decline in human cognition and memory. Due to its intricate pathogenesis and the lack of effective therapeutic interventions, early diagnosis plays a paramount role in AD. Recent research based on neuroimaging has shown that the application of deep learning methods by multimodal neural images can effectively detect AD. However, these methods only concatenate and fuse the high-level features extracted from different modalities, ignoring the fusion and interaction of low-level features across modalities. It consequently leads to unsatisfactory classification performance.

METHOD

In this paper, we propose a novel multi-scale attention and cross-enhanced fusion network, MACFNet, which enables the interaction of multi-stage low-level features between inputs to learn shared feature representations. We first construct a novel Cross-Enhanced Fusion Module (CEFM), which fuses low-level features from different modalities through a multi-stage cross-structure. In addition, an Efficient Spatial Channel Attention (ECSA) module is proposed, which is able to focus on important AD-related features in images more efficiently and achieve feature enhancement from different modalities through two-stage residual concatenation. Finally, we also propose a multiscale attention guiding block (MSAG) based on dilated convolution, which can obtain rich receptive fields without increasing model parameters and computation, and effectively improve the efficiency of multiscale feature extraction.

RESULTS

Experiments on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset demonstrate that our MACFNet has better classification performance than existing multimodal methods, with classification accuracies of 99.59 %, 98.85 %, 99.61 %, and 98.23 % for AD vs. CN, AD vs. MCI, CN vs. MCI and AD vs. CN vs. MCI, respectively, and specificity of 98.92 %, 97.07 %, 99.58 % and 99.04 %, and sensitivity of 99.91 %, 99.89 %, 99.63 % and 97.75 %, respectively.

CONCLUSIONS

The proposed MACFNet is a high-accuracy multimodal AD diagnostic framework. Through the cross mechanism and efficient attention, MACFNet can make full use of the low-level features of different modal medical images and effectively pay attention to the local and global information of the images. This work provides a valuable reference for multi-mode AD diagnosis.

A minimalistic approach to classifying Alzheimer's disease using simple and extremely small convolutional neural networks

BACKGROUND

There is a broad interest in deploying deep learning-based classification algorithms to identify individuals with Alzheimer's disease (AD) from healthy controls (HC) based on neuroimaging data, such as T1-weighted Magnetic Resonance Imaging (MRI). The goal of the current study is to investigate whether modern, flexible architectures such as EfficientNet provide any performance boost over more standard architectures.

METHODS

MRI data was sourced from the Alzheimer's Disease Neuroimaging Initiative (ADNI) and processed with a minimal preprocessing pipeline. Among the various architectures tested, the minimal 3D convolutional neural network SFCN stood out, composed solely of 3x3x3 convolution, batch normalization, ReLU, and max-pooling. We also examined the influence of scale on performance, testing SFCN versions with trainable parameters ranging from 720 up to 2.9 million.

RESULTS

SFCN achieves a test ROC AUC of 96.0% while EfficientNet got an ROC AUC of 94.9 %. SFCN retained high performance down to 720 trainable parameters, achieving an ROC AUC of 91.4%.

COMPARISON WITH EXISTING METHODS

The SFCN is compared to DenseNet and EfficientNet as well as the results of other publications in the field.

CONCLUSIONS

The results indicate that using the minimal 3D convolutional neural network SFCN with a minimal preprocessing pipeline can achieve competitive performance in AD classification, challenging the necessity of employing more complex architectures with a larger number of parameters. This finding supports the efficiency of simpler deep learning models for neuroimaging-based AD diagnosis, potentially aiding in better understanding and diagnosing Alzheimer's disease.

Machine and deep learning algorithms for classifying different types of dementia: A literature review

The cognitive impairment known as dementia affects millions of individuals throughout the globe. The use of machine learning (ML) and deep learning (DL) algorithms has shown great promise as a means of early identification and treatment of dementia. Dementias such as Alzheimer's Dementia, frontotemporal dementia, Lewy body dementia, and vascular dementia are all discussed in this article, along with a literature review on using ML algorithms in their diagnosis. Different ML algorithms, such as support vector machines, artificial neural networks, decision trees, and random forests, are compared and contrasted, along with their benefits and drawbacks. As discussed in this article, accurate ML models may be achieved by carefully considering feature selection and data preparation. We also discuss how ML algorithms can predict disease progression and patient responses to therapy. However, overreliance on ML and DL technologies should be avoided without further proof. It's important to note that these technologies are meant to assist in diagnosis but should not be used as the sole criteria for a final diagnosis. The research implies that ML algorithms may help increase the precision with which dementia is diagnosed, especially in its early stages. The efficacy of ML and DL algorithms in clinical contexts must be verified, and ethical issues around the use of personal data must be addressed, but this requires more study.

Exceptional performance with minimal data using a generative adversarial network for alzheimer's disease classification

The classification of Alzheimer's disease (AD) using deep learning models is hindered by the limited availability of data. Medical image datasets are scarce due to stringent regulations on patient privacy, preventing their widespread use in research. Moreover, although open-access databases such as the Open Access Series of Imaging Studies (OASIS) are available publicly for providing medical image data for research, they often suffer from imbalanced classes. Thus, to address the issue of insufficient data, this study proposes the integration of a generative adversarial network (GAN) that can achieve comparable accuracy with a reduced data requirement. GANs are unsupervised deep learning networks commonly used for data augmentation that generate high-quality synthetic data to overcome data scarcity. Experimental data from the OASIS database are used in this research to train the GAN model in generating synthetic MRI data before being included in a pretrained convolutional neural network (CNN) model for multistage AD classification. As a result, this study has demonstrated that a multistage AD classification accuracy above 80% can be achieved even with a reduced dataset. The exceptional performance of GANs positions them as a solution for overcoming the challenge of insufficient data in AD classification.

A review of deep learning-based information fusion techniques for multimodal medical image classification

Multimodal medical imaging plays a pivotal role in clinical diagnosis and research, as it combines information from various imaging modalities to provide a more comprehensive understanding of the underlying pathology. Recently, deep learning-based multimodal fusion techniques have emerged as powerful tools for improving medical image classification. This review offers a thorough analysis of the developments in deep learning-based multimodal fusion for medical classification tasks. We explore the complementary relationships among prevalent clinical modalities and outline three main fusion schemes for multimodal classification networks: input fusion, intermediate fusion (encompassing single-level fusion, hierarchical fusion, and attention-based fusion), and output fusion. By evaluating the performance of these fusion techniques, we provide insight into the suitability of different network architectures for various multimodal fusion scenarios and application domains. Furthermore, we delve into challenges related to network architecture selection, handling incomplete multimodal data management, and the potential limitations of multimodal fusion. Finally, we spotlight the promising future of Transformer-based multimodal fusion techniques and give recommendations for future research in this rapidly evolving field.

Enhancing Alzheimer's disease diagnosis and staging: a multistage CNN framework using MRI

This study addresses the pervasive and debilitating impact of Alzheimer's disease (AD) on individuals and society, emphasizing the crucial need for timely diagnosis. We present a multistage convolutional neural network (CNN)-based framework for AD detection and sub-classification using brain magnetic resonance imaging (MRI). After preprocessing, a 26-layer CNN model was designed to differentiate between healthy individuals and patients with dementia. After detecting dementia, the 26-layer CNN model was reutilized using the concept of transfer learning to further subclassify dementia into mild, moderate, and severe dementia. Leveraging the frozen weights of the developed CNN on correlated medical images facilitated the transfer learning process for sub-classifying dementia classes. An online AD dataset is used to verify the performance of the proposed multistage CNN-based framework. The proposed approach yielded a noteworthy accuracy of 98.24% in identifying dementia classes, whereas it achieved 99.70% accuracy in dementia subclassification. Another dataset was used to further validate the proposed framework, resulting in 100% performance. Comparative evaluations against pre-trained models and the current literature were also conducted, highlighting the usefulness and superiority of the proposed framework and presenting it as a robust and effective AD detection and subclassification method.

HAMMF: Hierarchical attention-based multi-task and multi-modal fusion model for computer-aided diagnosis of Alzheimer's disease

Alzheimer's disease (AD) is a progressive neurodegenerative condition, and early intervention can help slow its progression. However, integrating multi-dimensional information and deep convolutional networks increases the model parameters, affecting diagnosis accuracy and efficiency and hindering clinical diagnostic model deployment. Multi-modal neuroimaging can offer more precise diagnostic results, while multi-task modeling of classification and regression tasks can enhance the performance and stability of AD diagnosis. This study proposes a Hierarchical Attention-based Multi-task Multi-modal Fusion model (HAMMF) that leverages multi-modal neuroimaging data to concurrently learn AD classification tasks, cognitive score regression, and age regression tasks using attention-based techniques. Firstly, we preprocess MRI and PET image data to obtain two modal data, each containing distinct information. Next, we incorporate a novel Contextual Hierarchical Attention Module (CHAM) to aggregate multi-modal features. This module employs channel and spatial attention to extract fine-grained pathological features from unimodal image data across various dimensions. Using these attention mechanisms, the Transformer can effectively capture correlated features of multi-modal inputs. Lastly, we adopt multi-task learning in our model to investigate the influence of different variables on diagnosis, with a primary classification task and a secondary regression task for optimal multi-task prediction performance. Our experiments utilized MRI and PET images from 720 subjects in the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. The results show that our proposed model achieves an overall accuracy of 93.15% for AD/NC recognition, and the visualization results demonstrate its strong pathological feature recognition performance.

Machine learning with multimodal neuroimaging data to classify stages of Alzheimer's disease: a systematic review and meta-analysis

In recent years, Alzheimer's disease (AD) has been a serious threat to human health. Researchers and clinicians alike encounter a significant obstacle when trying to accurately identify and classify AD stages. Several studies have shown that multimodal neuroimaging input can assist in providing valuable insights into the structural and functional changes in the brain related to AD. Machine learning (ML) algorithms can accurately categorize AD phases by identifying patterns and linkages in multimodal neuroimaging data using powerful computational methods. This study aims to assess the contribution of ML methods to the accurate classification of the stages of AD using multimodal neuroimaging data. A systematic search is carried out in IEEE Xplore, Science Direct/Elsevier, ACM DigitalLibrary, and PubMed databases with forward snowballing performed on Google Scholar. The quantitative analysis used 47 studies. The explainable analysis was performed on the classification algorithm and fusion methods used in the selected studies. The pooled sensitivity and specificity, including diagnostic efficiency, were evaluated by conducting a meta-analysis based on a bivariate model with the hierarchical summary receiver operating characteristics (ROC) curve of multimodal neuroimaging data and ML methods in the classification of AD stages. Wilcoxon signed-rank test is further used to statistically compare the accuracy scores of the existing models. With a 95% confidence interval of 78.87-87.71%, the combined sensitivity for separating participants with mild cognitive impairment (MCI) from healthy control (NC) participants was 83.77%; for separating participants with AD from NC, it was 94.60% (90.76%, 96.89%); for separating participants with progressive MCI (pMCI) from stable MCI (sMCI), it was 80.41% (74.73%, 85.06%). With a 95% confidence interval (78.87%, 87.71%), the Pooled sensitivity for distinguishing mild cognitive impairment (MCI) from healthy control (NC) participants was 83.77%, with a 95% confidence interval (90.76%, 96.89%), the Pooled sensitivity for distinguishing AD from NC was 94.60%, likewise (MCI) from healthy control (NC) participants was 83.77% progressive MCI (pMCI) from stable MCI (sMCI) was 80.41% (74.73%, 85.06%), and early MCI (EMCI) from NC was 86.63% (82.43%, 89.95%). Pooled specificity for differentiating MCI from NC was 79.16% (70.97%, 87.71%), AD from NC was 93.49% (91.60%, 94.90%), pMCI from sMCI was 81.44% (76.32%, 85.66%), and EMCI from NC was 85.68% (81.62%, 88.96%). The Wilcoxon signed rank test showed a low P-value across all the classification tasks. Multimodal neuroimaging data with ML is a promising future in classifying the stages of AD but more research is required to increase the validity of its application in clinical practice.

Intelligent prediction of Alzheimer's disease via improved multifeature squeeze-and-excitation-dilated residual network

This study aimed to address the issue of larger prediction errors existing in intelligent predictive tasks related to Alzheimer's disease (AD). A cohort of 487 enrolled participants was categorized into three groups: normal control (138 individuals), mild cognitive impairment (238 patients), and AD (111 patients) in this study. An improved multifeature squeeze-and-excitation-dilated residual network (MFSE-DRN) was proposed for two important AD predictions: clinical scores and conversion probability. The model was characterized as three modules: squeeze-and-excitation-dilated residual block (SE-DRB), multifusion pooling (MF-Pool), and multimodal feature fusion. To assess its performance, the proposed model was compared with two other novel models: ranking convolutional neural network (RCNN) and 3D vision geometrical group network (3D-VGGNet). Our method showed the best performance in the two AD predicted tasks. For the clinical scores prediction, the root-mean-square errors (RMSEs) and mean absolute errors (MAEs) of mini-mental state examination (MMSE) and AD assessment scale-cognitive 11-item (ADAS-11) were 1.97, 1.46 and 4.20, 3.19 within 6 months; 2.48, 1.69 and 4.81, 3.44 within 12 months; 2.67, 1.86 and 5.81, 3.83 within 24 months; 3.02, 2.03 and 5.09, 3.43 within 36 months, respectively. At the AD conversion probability prediction, the prediction accuracies within 12, 24, and 36 months reached to 88.0, 85.5, and 88.4%, respectively. The AD predication would play a great role in clinical applications.

Brain structural indicators of β-amyloid neuropathology

Recent efforts demonstrated the efficacy of identifying early-stage neuropathology of Alzheimer's disease (AD) through lumbar puncture cerebrospinal fluid assessment and positron emission tomography (PET) radiotracer imaging. These methods are effective yet are invasive, expensive, and not widely accessible. We extend and improve the multiscale structural mapping (MSSM) procedure to develop structural indicators of β-amyloid neuropathology in preclinical AD, by capturing both macrostructural and microstructural properties throughout the cerebral cortex using a structural MRI. We find that the MSSM signal is regionally altered in clear positive and negative cases of preclinical amyloid pathology (N = 220) when cortical thickness alone or hippocampal volume is not. It exhibits widespread effects of amyloid positivity across the posterior temporal, parietal, and medial prefrontal cortex, surprisingly consistent with the typical pattern of amyloid deposition. The MSSM signal is significantly correlated with amyloid PET in almost half of the cortex, much of which overlaps with regions where beta-amyloid accumulates, suggesting it could provide a regional brain 'map' that is not available from systemic markers such as plasma markers.

Predicting long-term progression of Alzheimer's disease using a multimodal deep learning model incorporating interaction effects

BACKGROUND

Identifying individuals with mild cognitive impairment (MCI) at risk of progressing to Alzheimer's disease (AD) provides a unique opportunity for early interventions. Therefore, accurate and long-term prediction of the conversion from MCI to AD is desired but, to date, remains challenging. Here, we developed an interpretable deep learning model featuring a novel design that incorporates interaction effects and multimodality to improve the prediction accuracy and horizon for MCI-to-AD progression.

METHODS

This multi-center, multi-cohort retrospective study collected structural magnetic resonance imaging (sMRI), clinical assessments, and genetic polymorphism data of 252 patients with MCI at baseline from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Our deep learning model was cross-validated on the ADNI-1 and ADNI-2/GO cohorts and further generalized in the ongoing ADNI-3 cohort. We evaluated the model performance using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, and F1 score.

RESULTS

On the cross-validation set, our model achieved superior results for predicting MCI conversion within 4 years (AUC, 0.962; accuracy, 92.92%; sensitivity, 88.89%; specificity, 95.33%) compared to all existing studies. In the independent test, our model exhibited consistent performance with an AUC of 0.939 and an accuracy of 92.86%. Integrating interaction effects and multimodal data into the model significantly increased prediction accuracy by 4.76% (P = 0.01) and 4.29% (P = 0.03), respectively. Furthermore, our model demonstrated robustness to inter-center and inter-scanner variability, while generating interpretable predictions by quantifying the contribution of multimodal biomarkers.

CONCLUSIONS

The proposed deep learning model presents a novel perspective by combining interaction effects and multimodality, leading to more accurate and longer-term predictions of AD progression, which promises to improve pre-dementia patient care.

Deep learning-based multimodality classification of chronic mild traumatic brain injury using resting-state functional MRI and PET imaging

Mild traumatic brain injury (mTBI) is a public health concern. The present study aimed to develop an automatic classifier to distinguish between patients with chronic mTBI (n = 83) and healthy controls (HCs) (n = 40). Resting-state functional MRI (rs-fMRI) and positron emission tomography (PET) imaging were acquired from the subjects. We proposed a novel deep-learning-based framework, including an autoencoder (AE), to extract high-level latent and rectified linear unit (ReLU) and sigmoid activation functions. Single and multimodality algorithms integrating multiple rs-fMRI metrics and PET data were developed. We hypothesized that combining different imaging modalities provides complementary information and improves classification performance. Additionally, a novel data interpretation approach was utilized to identify top-performing features learned by the AEs. Our method delivered a classification accuracy within the range of 79-91.67% for single neuroimaging modalities. However, the performance of classification improved to 95.83%, thereby employing the multimodality model. The models have identified several brain regions located in the default mode network, sensorimotor network, visual cortex, cerebellum, and limbic system as the most discriminative features. We suggest that this approach could be extended to the objective biomarkers predicting mTBI in clinical settings.

Diagnosis of disease affecting gait with a body acceleration-based model using reflected marker data for training and a wearable accelerometer for implementation

This paper demonstrates the value of a framework for processing data on body acceleration as a uniquely valuable tool for diagnosing diseases that affect gait early. As a case study, we used this model to identify individuals with peripheral artery disease (PAD) and distinguish them from those without PAD. The framework uses acceleration data extracted from anatomical reflective markers placed in different body locations to train the diagnostic models and a wearable accelerometer carried at the waist for validation. Reflective marker data have been used for decades in studies evaluating and monitoring human gait. They are widely available for many body parts but are obtained in specialized laboratories. On the other hand, wearable accelerometers enable diagnostics outside lab conditions. Models trained by raw marker data at the sacrum achieve an accuracy of 92% in distinguishing PAD patients from non-PAD controls. This accuracy drops to 28% when data from a wearable accelerometer at the waist validate the model. This model was enhanced by using features extracted from the acceleration rather than the raw acceleration, with the marker model accuracy only dropping from 86 to 60% when validated by the wearable accelerometer data.

Review of artificial intelligence clinical applications in Nuclear Medicine

This paper provides an in-depth analysis of the clinical applications of artificial intelligence (AI) in Nuclear Medicine, focusing on three key areas: neurology, cardiology, and oncology. Beginning with neurology, specifically Alzheimer's disease and Parkinson's disease, the paper examines reviews on diagnosis and treatment planning. The same pattern is followed in cardiology studies. In the final section on oncology, the paper explores the various AI applications in multiple cancer types, including lung, head and neck, lymphoma, and pancreatic cancer.

A Deep Learning-Based Ensemble Method for Early Diagnosis of Alzheimer's Disease using MRI Images

Recently, the early diagnosis of Alzheimer's disease has gained major attention due to the growing prevalence of the disease and the resulting costs imposed on individuals and society. The main objective of this study was to propose an ensemble method based on deep learning for the early diagnosis of AD using MRI images. The methodology of this study consisted of collecting the dataset, preprocessing, creating the individual and ensemble models, evaluating the models based on ADNI data, and validating the trained model based on the local dataset. The proposed method was an ensemble approach selected through a comparative analysis of various ensemble scenarios. Finally, the six best individual CNN-based classifiers were selected to combine and constitute the ensemble model. The evaluation showed an accuracy rate of 98.57, 96.37, 94.22, 99.83, 93.88, and 93.92 for NC/AD, NC/EMCI, EMCI/LMCI, LMCI/AD, four-way and three-way classification groups, respectively. The validation results on the local dataset revealed an accuracy of 88.46 for three-way classification. Our performance results were higher than most reviewed studies and comparable with others. Although comparative analysis showed superior results of ensemble methods against individual architectures, there were no significant differences among various ensemble approaches. The validation results revealed the low performance of individual models in practice. In contrast, the ensemble method showed promising results. However, further studies on various and larger datasets are required to validate the generalizability of the model.

Graph-Based Fusion of Imaging, Genetic and Clinical Data for Degenerative Disease Diagnosis

Graph learning methods have achieved noteworthy performance in disease diagnosis due to their ability to represent unstructured information such as inter-subject relationships. While it has been shown that imaging, genetic and clinical data are crucial for degenerative disease diagnosis, existing methods rarely consider how best to use their relationships. How best to utilize information from imaging, genetic and clinical data remains a challenging problem. This study proposes a novel graph-based fusion (GBF) approach to meet this challenge. To extract effective imaging-genetic features, we propose an imaging-genetic fusion module which uses an attention mechanism to obtain modality-specific and joint representations within and between imaging and genetic data. Then, considering the effectiveness of clinical information for diagnosing degenerative diseases, we propose a multi-graph fusion module to further fuse imaging-genetic and clinical features, which adopts a learnable graph construction strategy and a graph ensemble method. Experimental results on two benchmarks for degenerative disease diagnosis (Alzheimers Disease Neuroimaging Initiative and Parkinson's Progression Markers Initiative) demonstrate its effectiveness compared to state-of-the-art graph-based methods. Our findings should help guide further development of graph-based models for dealing with imaging, genetic and clinical data.

Clinically-Inspired Multi-Agent Transformers for Disease Trajectory Forecasting From Multimodal Data

Deep neural networks are often applied to medical images to automate the problem of medical diagnosis. However, a more clinically relevant question that practitioners usually face is how to predict the future trajectory of a disease. Current methods for prognosis or disease trajectory forecasting often require domain knowledge and are complicated to apply. In this paper, we formulate the prognosis prediction problem as a one-to-many prediction problem. Inspired by a clinical decision-making process with two agents-a radiologist and a general practitioner - we predict prognosis with two transformer-based components that share information with each other. The first transformer in this framework aims to analyze the imaging data, and the second one leverages its internal states as inputs, also fusing them with auxiliary clinical data. The temporal nature of the problem is modeled within the transformer states, allowing us to treat the forecasting problem as a multi-task classification, for which we propose a novel loss. We show the effectiveness of our approach in predicting the development of structural knee osteoarthritis changes and forecasting Alzheimer's disease clinical status directly from raw multi-modal data. The proposed method outperforms multiple state-of-the-art baselines with respect to performance and calibration, both of which are needed for real-world applications. An open-source implementation of our method is made publicly available at https://github.com/Oulu-IMEDS/CLIMATv2.

Artificial intelligence for diagnostic and prognostic neuroimaging in dementia: A systematic review

INTRODUCTION

Artificial intelligence (AI) and neuroimaging offer new opportunities for diagnosis and prognosis of dementia.

METHODS

We systematically reviewed studies reporting AI for neuroimaging in diagnosis and/or prognosis of cognitive neurodegenerative diseases.

RESULTS

A total of 255 studies were identified. Most studies relied on the Alzheimer's Disease Neuroimaging Initiative dataset. Algorithmic classifiers were the most commonly used AI method (48%) and discriminative models performed best for differentiating Alzheimer's disease from controls. The accuracy of algorithms varied with the patient cohort, imaging modalities, and stratifiers used. Few studies performed validation in an independent cohort.

DISCUSSION

The literature has several methodological limitations including lack of sufficient algorithm development descriptions and standard definitions. We make recommendations to improve model validation including addressing key clinical questions, providing sufficient description of AI methods and validating findings in independent datasets. Collaborative approaches between experts in AI and medicine will help achieve the promising potential of AI tools in practice.

HIGHLIGHTS

There has been a rapid expansion in the use of machine learning for diagnosis and prognosis in neurodegenerative disease Most studies (71%) relied on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset with no other individual dataset used more than five times There has been a recent rise in the use of more complex discriminative models (e.g., neural networks) that performed better than other classifiers for classification of AD vs healthy controls We make recommendations to address methodological considerations, addressing key clinical questions, and validation We also make recommendations for the field more broadly to standardize outcome measures, address gaps in the literature, and monitor sources of bias.

Early Stage Detection of Alzheimer's Disease With Microsoft Azure Based Deep Learning

The early detection and diagnosis of Alzheimer's disease (AD) represent a pivotal aspect of ensuring effective patient care and timely intervention. This research introduces an innovative approach that harnesses the capabilities of Microsoft Azure-based custom vision technology for AD classification. The study primarily centers around the analysis of magnetic resonance imaging (MRI) scans as the primary input data, categorizing these scans into two distinct categories: Cognitive Normal and Cognitive Impairment. To accomplish this, we employ transfer learning, leveraging a pre-trained Microsoft Azure Custom Vision model fine-tuned specifically for multi-class AD classification. The proposed work shows better results with the best validation average accuracy on the test data of AD. This test accuracy score is significantly higher in comparison with existing works. This proposed solution showcases the immense potential of convolutional neural networks and advanced deep learning techniques in the early detection of Alzheimer's disease, thereby paving the way for significantly improved patient care.

Improving Alzheimer Diagnoses With An Interpretable Deep Learning Framework: Including Neuropsychiatric Symptoms

Alzheimer's disease (AD) is a prevalent neurodegenerative disorder characterized by the progressive cognitive decline. Among the various clinical symptoms, neuropsychiatric symptoms (NPS) commonly occur during the course of AD. Previous researches have demonstrated a strong association between NPS and severity of AD, while the research methods are not sufficiently intuitive. Here, we report a hybrid deep learning framework for AD diagnosis using multimodal inputs such as structural MRI, behavioral scores, age, and gender information. The framework uses a 3D convolutional neural network to automatically extract features from MRI. The imaging features are passed to the Principal Component Analysis for dimensionality reduction, which fuse with non-imaging information to improve the diagnosis of AD. According to the experimental results, our model achieves an accuracy of 0.91 and an area under the curve of 0.97 in the task of classifying AD and cognitively normal individuals. SHapley Additive exPlanations are used to visually exhibit the contribution of specific NPS in the proposed model. Among all behavioral symptoms, apathy plays a particularly important role in the diagnosis of AD, which can be considered a valuable factor in further studies, as well as clinical trials.

Overcoming the Challenges in the Development and Implementation of Artificial Intelligence in Radiology: A Comprehensive Review of Solutions Beyond Supervised Learning

Artificial intelligence (AI) in radiology is a rapidly developing field with several prospective clinical studies demonstrating its benefits in clinical practice. In 2022, the Korean Society of Radiology held a forum to discuss the challenges and drawbacks in AI development and implementation. Various barriers hinder the successful application and widespread adoption of AI in radiology, such as limited annotated data, data privacy and security, data heterogeneity, imbalanced data, model interpretability, overfitting, and integration with clinical workflows. In this review, some of the various possible solutions to these challenges are presented and discussed; these include training with longitudinal and multimodal datasets, dense training with multitask learning and multimodal learning, self-supervised contrastive learning, various image modifications and syntheses using generative models, explainable AI, causal learning, federated learning with large data models, and digital twins.

An interpretable Alzheimer's disease oligogenic risk score informed by neuroimaging biomarkers improves risk prediction and stratification

Introduction

Stratification of Alzheimer's disease (AD) patients into risk subgroups using Polygenic Risk Scores (PRS) presents novel opportunities for the development of clinical trials and disease-modifying therapies. However, the heterogeneous nature of AD continues to pose significant challenges for the clinical broadscale use of PRS. PRS remains unfit in demonstrating sufficient accuracy in risk prediction, particularly for individuals with mild cognitive impairment (MCI), and in allowing feasible interpretation of specific genes or SNPs contributing to disease risk. We propose adORS, a novel oligogenic risk score for AD, to better predict risk of disease by using an optimized list of relevant genetic risk factors.

Methods

Using whole genome sequencing data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort (n  =  1,545), we selected 20 genes that exhibited the strongest correlations with FDG-PET and AV45-PET, recognized neuroimaging biomarkers that detect functional brain changes in AD. This subset of genes was incorporated into adORS to assess, in comparison to PRS, the prediction accuracy of CN vs. AD classification and MCI conversion prediction, risk stratification of the ADNI cohort, and interpretability of the genetic information included in the scores.

Results

adORS improved AUC scores over PRS in both CN vs. AD classification and MCI conversion prediction. The oligogenic model also refined risk-based stratification, even without the assistance of APOE, thus reflecting the true prevalence rate of the ADNI cohort compared to PRS. Interpretation analysis shows that genes included in adORS, such as ATF6, EFCAB11, ING5, SIK3, and CD46, have been observed in similar neurodegenerative disorders and/or are supported by AD-related literature.

Discussion

Compared to conventional PRS, adORS may prove to be a more appropriate choice of differentiating patients into high or low genetic risk of AD in clinical studies or settings. Additionally, the ability to interpret specific genetic information allows the focus to be shifted from general relative risk based on a given population to the information that adORS can provide for a single individual, thus permitting the possibility of personalized treatments for AD.

Deep learning combining FDG-PET and neurocognitive data accurately predicts MCI conversion to Alzheimer's dementia 3-year post MCI diagnosis

INTRODUCTION

This study reports a novel deep learning approach to predict mild cognitive impairment (MCI) conversion to Alzheimer's dementia (AD) within three years using whole-brain fluorodeoxyglucose (FDG) positron emission tomography (PET) and cognitive scores (CS).

METHODS

This analysis consisted of 150 normal controls (CN), 257 MCI, and 205  AD subjects from ADNI. FDG-PET and CS were obtained at MCI diagnosis to predict AD conversion within three years of MCI diagnosis using convolutional neural networks.

RESULTS

Neurocognitive scores predicted better than FDG-PET per se, but the best model was a combination of FDG-PET, age, and neurocognitive data, yielding an AUC of 0.785 ± 0.096 and a balanced accuracy of 0.733 ± 0.098. Saliency maps highlighted putamen, thalamus, inferior frontal gyrus, parietal operculum, precuneus cortices, calcarine cortices, temporal gyrus, and planum temporale to be important for prediction.

DISCUSSION

Deep learning accurately predicts MCI conversion to AD and provides neural correlates of brain regions associated with AD conversion.

Deep learning analysis of UPLC-MS/MS-based metabolomics data to predict Alzheimer's disease

OBJECTIVE

Metabolic biomarkers can potentially inform disease progression in Alzheimer's disease (AD). The purpose of this study is to identify and describe a new set of diagnostic biomarkers for developing deep learning (DL) tools to predict AD using Ultra Performance Liquid Chromatography Mass Spectrometry (UPLC-MS/MS)-based metabolomics data.

METHODS

A total of 177 individuals, including 78 with AD and 99 with cognitive normal (CN), were selected from the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort along with 150 metabolomic biomarkers. We performed feature selection using the Least Absolute Shrinkage and Selection Operator (LASSO). The H2O DL function was used to build multilayer feedforward neural networks to predict AD.

RESULTS

The LASSO selected 21 metabolic biomarkers. To develop DL models, the 21 biomarkers identified by LASSO were imported into the H2O package. The data was split into 70% for training and 30% for validation. The best DL model with two layers and 18 neurons achieved an accuracy of 0.881, F1-score of 0.892, and AUC of 0.873. Several metabolomic biomarkers involved in glucose and lipid metabolism, in particular bile acid metabolites, were associated with APOE-ε4 allele and clinical biomarkers (Aβ42, tTau, pTau), cognitive assessments [the Alzheimer's Disease Assessment Scale-cognitive subscale 13 (ADAS13), the Mini-Mental State Examination (MMSE)], and hippocampus volume.

CONCLUSIONS

This study identified a new set of diagnostic metabolomic biomarkers for developing DL tools to predict AD. These biomarkers may help with early diagnosis, prognostic risk stratification, and/or early treatment interventions for patients at risk for AD.

Self-Supervised Contrastive Learning to Predict the Progression of Alzheimer's Disease with 3D Amyloid-PET

Early diagnosis of Alzheimer's disease (AD) is an important task that facilitates the development of treatment and prevention strategies, and may potentially improve patient outcomes. Neuroimaging has shown great promise, including the amyloid-PET, which measures the accumulation of amyloid plaques in the brain-a hallmark of AD. It is desirable to train end-to-end deep learning models to predict the progression of AD for individuals at early stages based on 3D amyloid-PET. However, commonly used models are trained in a fully supervised learning manner, and they are inevitably biased toward the given label information. To this end, we propose a selfsupervised contrastive learning method to accurately predict the conversion to AD for individuals with mild cognitive impairment (MCI) with 3D amyloid-PET. The proposed method, SMoCo, uses both labeled and unlabeled data to capture general semantic representations underlying the images. As the downstream task is given as classification of converters vs. non-converters, unlike the general self-supervised learning problem that aims to generate task-agnostic representations, SMoCo additionally utilizes the label information in the pre-training. To demonstrate the performance of our method, we conducted experiments on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. The results confirmed that the proposed method is capable of providing appropriate data representations, resulting in accurate classification. SMoCo showed the best classification performance over the existing methods, with AUROC = 85.17%, accuracy = 81.09%, sensitivity = 77.39%, and specificity = 82.17%. While SSL has demonstrated great success in other application domains of computer vision, this study provided the initial investigation of using a proposed self-supervised contrastive learning model, SMoCo, to effectively predict MCI conversion to AD based on 3D amyloid-PET.

Artificial intelligence in psychiatry research, diagnosis, and therapy

Psychiatric disorders are now responsible for the largest proportion of the global burden of disease, and even more challenges have been seen during the COVID-19 pandemic. Artificial intelligence (AI) is commonly used to facilitate the early detection of disease, understand disease progression, and discover new treatments in the fields of both physical and mental health. The present review provides a broad overview of AI methodology and its applications in data acquisition and processing, feature extraction and characterization, psychiatric disorder classification, potential biomarker detection, real-time monitoring, and interventions in psychiatric disorders. We also comprehensively summarize AI applications with regard to the early warning, diagnosis, prognosis, and treatment of specific psychiatric disorders, including depression, schizophrenia, autism spectrum disorder, attention-deficit/hyperactivity disorder, addiction, sleep disorders, and Alzheimer's disease. The advantages and disadvantages of AI in psychiatry are clarified. We foresee a new wave of research opportunities to facilitate and improve AI technology and its long-term implications in psychiatry during and after the COVID-19 era.

Machine learning in the positron emission tomography imaging of Alzheimer's disease

The utilization of machine learning techniques in medicine has exponentially increased over the last decades due to innovations in computer processing, algorithm development, and access to big data. Applications of machine learning techniques to neuroimaging specifically have unveiled various hidden interactions, structures, and mechanisms related to various neurological disorders. One application of interest is the imaging of Alzheimer's disease, the most common cause of progressive dementia. The diagnoses of Alzheimer's disease, mild cognitive impairment, and preclinical Alzheimer's disease have been difficult. Molecular imaging, particularly via PET scans, holds tremendous value in the imaging of Alzheimer's disease. To date, many novel algorithms have been developed with great success that leverage machine learning in the context of Alzheimer's disease. This review article provides an overview of the diverse applications of machine learning to PET imaging of Alzheimer's disease.

Detection of Alzheimer's Disease Based on Cloud-Based Deep Learning Paradigm

Deep learning is playing a major role in identifying complicated structure, and it outperforms in term of training and classification tasks in comparison to traditional algorithms. In this work, a local cloud-based solution is developed for classification of Alzheimer's disease (AD) as MRI scans as input modality. The multi-classification is used for AD variety and is classified into four stages. In order to leverage the capabilities of the pre-trained GoogLeNet model, transfer learning is employed. The GoogLeNet model, which is pre-trained for image classification tasks, is fine-tuned for the specific purpose of multi-class AD classification. Through this process, a better accuracy of 98% is achieved. As a result, a local cloud web application for Alzheimer's prediction is developed using the proposed architectures of GoogLeNet. This application enables doctors to remotely check for the presence of AD in patients.

A systematic review on machine learning and deep learning techniques in the effective diagnosis of Alzheimer's disease

Alzheimer's disease (AD) is a brain-related disease in which the condition of the patient gets worse with time. AD is not a curable disease by any medication. It is impossible to halt the death of brain cells, but with the help of medication, the effects of AD can be delayed. As not all MCI patients will suffer from AD, it is required to accurately diagnose whether a mild cognitive impaired (MCI) patient will convert to AD (namely MCI converter MCI-C) or not (namely MCI non-converter MCI-NC), during early diagnosis. There are two modalities, positron emission tomography (PET) and magnetic resonance image (MRI), used by a physician for the diagnosis of Alzheimer's disease. Machine learning and deep learning perform exceptionally well in the field of computer vision where there is a requirement to extract information from high-dimensional data. Researchers use deep learning models in the field of medicine for diagnosis, prognosis, and even to predict the future health of the patient under medication. This study is a systematic review of publications using machine learning and deep learning methods for early classification of normal cognitive (NC) and Alzheimer's disease (AD).This study is an effort to provide the details of the two most commonly used modalities PET and MRI for the identification of AD, and to evaluate the performance of both modalities while working with different classifiers.

Automated F18-FDG PET/CT image quality assessment using deep neural networks on a latest 6-ring digital detector system

To evaluate whether a machine learning classifier can evaluate image quality of maximum intensity projection (MIP) images from F18-FDG-PET scans. A total of 400 MIP images from F18-FDG-PET with simulated decreasing acquisition time (120 s, 90 s, 60 s, 30 s and 15 s per bed-position) using block sequential regularized expectation maximization (BSREM) with a beta-value of 450 and 600 were created. A machine learning classifier was fed with 283 images rated "sufficient image quality" and 117 images rated "insufficient image quality". The classification performance of the machine learning classifier was assessed by calculating sensitivity, specificity, and area under the receiver operating characteristics curve (AUC) using reader-based classification as the target. Classification performance of the machine learning classifier was AUC 0.978 for BSREM beta 450 and 0.967 for BSREM beta 600. The algorithm showed a sensitivity of 89% and 94% and a specificity of 94% and 94% for the reconstruction BSREM 450 and 600, respectively. Automated assessment of image quality from F18-FDG-PET images using a machine learning classifier provides equivalent performance to manual assessment by experienced radiologists.

Deep learning application for the classification of Alzheimer's disease using 18F-flortaucipir (AV-1451) tau positron emission tomography

The positron emission tomography (PET) with 18F-flortaucipir can distinguish individuals with mild cognitive impairment (MCI) and Alzheimer's disease (AD) from cognitively unimpaired (CU) individuals. This study aimed to evaluate the utility of 18F-flortaucipir-PET images and multimodal data integration in the differentiation of CU from MCI or AD through DL. We used cross-sectional data (18F-flortaucipir-PET images, demographic and neuropsychological score) from the ADNI. All data for subjects (138 CU, 75 MCI, 63 AD) were acquired at baseline. The 2D convolutional neural network (CNN)-long short-term memory (LSTM) and 3D CNN were conducted. Multimodal learning was conducted by adding the clinical data with imaging data. Transfer learning was performed for classification between CU and MCI. The AUC for AD classification from CU was 0.964 and 0.947 in 2D CNN-LSTM and multimodal learning. The AUC of 3D CNN showed 0.947, and 0.976 in multimodal learning. The AUC for MCI classification from CU had 0.840 and 0.923 in 2D CNN-LSTM and multimodal learning. The AUC of 3D CNN showed 0.845, and 0.850 in multimodal learning. The 18F-flortaucipir PET is effective for the classification of AD stage. Furthermore, the effect of combination images with clinical data increased the performance of AD classification.

Automated Medical Diagnosis of Alzheimer´s Disease Using an Efficient Net Convolutional Neural Network

Alzheimer's disease (AD) poses an enormous challenge to modern healthcare. Since 2017, researchers have been using deep learning (DL) models for the early detection of AD using neuroimaging biomarkers. In this paper, we implement the EfficietNet-b0 convolutional neural network (CNN) with a novel approach-"fusion of end-to-end and transfer learning"-to classify different stages of AD. 245 T1W MRI scans of cognitively normal (CN) subjects, 229 scans of AD subjects, and 229 scans of subjects with stable mild cognitive impairment (sMCI) were employed. Each scan was preprocessed using a standard pipeline. The proposed models were trained and evaluated using preprocessed scans. For the sMCI vs. AD classification task we obtained 95.29% accuracy and 95.35% area under the curve (AUC) for model training and 93.10% accuracy and 93.00% AUC for model testing. For the multiclass AD vs. CN vs. sMCI classification task we obtained 85.66% accuracy and 86% AUC for model training and 87.38% accuracy and 88.00% AUC for model testing. Based on our experimental results, we conclude that CNN-based DL models can be used to analyze complicated MRI scan features in clinical settings.

Should artificial intelligence be used in conjunction with Neuroimaging in the diagnosis of Alzheimer's disease?

Alzheimer's disease (AD) is a progressive, neurodegenerative disorder that affects memory, thinking, behavior, and other cognitive functions. Although there is no cure, detecting AD early is important for the development of a therapeutic plan and a care plan that may preserve cognitive function and prevent irreversible damage. Neuroimaging, such as magnetic resonance imaging (MRI), computed tomography (CT), and positron emission tomography (PET), has served as a critical tool in establishing diagnostic indicators of AD during the preclinical stage. However, as neuroimaging technology quickly advances, there is a challenge in analyzing and interpreting vast amounts of brain imaging data. Given these limitations, there is great interest in using artificial Intelligence (AI) to assist in this process. AI introduces limitless possibilities in the future diagnosis of AD, yet there is still resistance from the healthcare community to incorporate AI in the clinical setting. The goal of this review is to answer the question of whether AI should be used in conjunction with neuroimaging in the diagnosis of AD. To answer the question, the possible benefits and disadvantages of AI are discussed. The main advantages of AI are its potential to improve diagnostic accuracy, improve the efficiency in analyzing radiographic data, reduce physician burnout, and advance precision medicine. The disadvantages include generalization and data shortage, lack of in vivo gold standard, skepticism in the medical community, potential for physician bias, and concerns over patient information, privacy, and safety. Although the challenges present fundamental concerns and must be addressed when the time comes, it would be unethical not to use AI if it can improve patient health and outcome.

A combination model of AD biomarkers revealed by machine learning precisely predicts Alzheimer's dementia: China Aging and Neurodegenerative Initiative (CANDI) study

INTRODUCTION

To test the utility of the "A/T/N" system in the Chinese population, we study core Alzheimer's disease (AD) biomarkers in a newly established Chinese cohort.

METHODS

A total of 411 participants were selected, including 96 cognitively normal individuals, 94 patients with mild cognitive impairment (MCI) patients, 173 patients with AD, and 48 patients with non-AD dementia. Fluid biomarkers were measured with single molecule array. Amyloid beta (Aβ) deposition was determined by 18F-Flobetapir positron emission tomography (PET), and brain atrophy was quantified using magnetic resonance imaging (MRI).

RESULTS

Aβ42/Aβ40 was decreased, whereas levels of phosphorylated tau (p-tau) were increased in cerebrospinal fluid (CSF) and plasma from patients with AD. CSF Aβ42/Aβ40, CSF p-tau, and plasma p-tau showed a high concordance in discriminating between AD and non-AD dementia or elderly controls. A combination of plasma p-tau, apolipoprotein E (APOE) genotype, and MRI measures accurately predicted amyloid PET status.

DISCUSSION

These results revealed a universal applicability of the "A/T/N" framework in a Chinese population and established an optimal diagnostic model consisting of cost-effective and non-invasive approaches for diagnosing AD.

Graph Fusion Network-Based Multimodal Learning for Freezing of Gait Detection

Freezing of gait (FoG) is identified as a sudden and brief episode of movement cessation despite the intention to continue walking. It is one of the most disabling symptoms of Parkinson's disease (PD) and often leads to falls and injuries. Many computer-aided FoG detection methods have been proposed to use data collected from unimodal sources, such as motion sensors, pressure sensors, and video cameras. However, there are limited efforts of multimodal-based methods to maximize the value of all the information collected from different modalities in clinical assessments and improve the FoG detection performance. Therefore, in this study, a novel end-to-end deep architecture, namely graph fusion neural network (GFN), is proposed for multimodal learning-based FoG detection by combining footstep pressure maps and video recordings. GFN constructs multimodal graphs by treating the encoded features of each modality as vertex-level inputs and measures their adjacency patterns to construct complementary FoG representations, thus reducing the representation redundancy among different modalities. In addition, since GFN is devised to process multimodal graphs of arbitrary structures, it is expected to achieve superior performance with inputs containing missing modalities, compared to the alternative unimodal methods. A multimodal FoG dataset was collected, which included clinical assessment videos and footstep pressure sequences of 340 trials from 20 PD patients. Our proposed GFN demonstrates a great promise of multimodal FoG detection with an area under the curve (AUC) of 0.882. To the best of our knowledge, this is one of the first studies to utilize multimodal learning for automated FoG detection, which offers significant opportunities for better patient assessments and clinical trials in the future.

Advanced Overview of Biomarkers and Techniques for Early Diagnosis of Alzheimer's Disease

The development of early non-invasive diagnosis methods and identification of novel biomarkers are necessary for managing Alzheimer's disease (AD) and facilitating effective prognosis and treatment. AD has multi-factorial nature and involves complex molecular mechanism, which causes neuronal degeneration. The primary challenges in early AD detection include patient heterogeneity and lack of precise diagnosis at the preclinical stage. Several cerebrospinal fluid (CSF) and blood biomarkers have been proposed to show excellent diagnosis ability by identifying tau pathology and cerebral amyloid beta (Aβ) for AD. Intense research endeavors are being made to develop ultrasensitive detection techniques and find potent biomarkers for early AD diagnosis. To mitigate AD worldwide, understanding various CSF biomarkers, blood biomarkers, and techniques that can be used for early diagnosis is imperative. This review attempts to provide information regarding AD pathophysiology, genetic and non-genetic factors associated with AD, several potential blood and CSF biomarkers, like neurofilament light, neurogranin, Aβ, and tau, along with biomarkers under development for AD detection. Besides, numerous techniques, such as neuroimaging, spectroscopic techniques, biosensors, and neuroproteomics, which are being explored to aid early AD detection, have been discussed. The insights thus gained would help in finding potential biomarkers and suitable techniques for the accurate diagnosis of early AD before cognitive dysfunction.

Patterns of structure-function association in normal aging and in Alzheimer's disease: Screening for mild cognitive impairment and dementia with ML regression and classification models

Background

The combined analysis of imaging and functional modalities is supposed to improve diagnostics of neurodegenerative diseases with advanced data science techniques.

Objective

To get an insight into normal and accelerated brain aging by developing the machine learning models that predict individual performance in neuropsychological and cognitive tests from brain MRI. With these models we endeavor to look for patterns of brain structure-function association (SFA) indicative of mild cognitive impairment (MCI) and Alzheimer's dementia.

Materials and methods

We explored the age-related variability of cognitive and neuropsychological test scores in normal and accelerated aging and constructed regression models predicting functional performance in cognitive tests from brain radiomics data. The models were trained on the three study cohorts from ADNI dataset-cognitively normal individuals, patients with MCI or dementia-separately. We also looked for significant correlations between cortical parcellation volumes and test scores in the cohorts to investigate neuroanatomical differences in relation to cognitive status. Finally, we worked out an approach for the classification of the examinees according to the pattern of structure-function associations into the cohorts of the cognitively normal elderly and patients with MCI or dementia.

Results

In the healthy population, the global cognitive functioning slightly changes with age. It also remains stable across the disease course in the majority of cases. In healthy adults and patients with MCI or dementia, the trendlines of performance in digit symbol substitution test and trail making test converge at the approximated point of 100 years of age. According to the SFA pattern, we distinguish three cohorts: the cognitively normal elderly, patients with MCI, and dementia. The highest accuracy is achieved with the model trained to predict the mini-mental state examination score from voxel-based morphometry data. The application of the majority voting technique to models predicting results in cognitive tests improved the classification performance up to 91.95% true positive rate for healthy participants, 86.21%-for MCI and 80.18%-for dementia cases.

Conclusion

The machine learning model, when trained on the cases of this of that group, describes a disease-specific SFA pattern. The pattern serves as a "stamp" of the disease reflected by the model.

Longitudinal prediction of motor dysfunction after stroke: a disconnectome study

Motricity is the most commonly affected ability after a stroke. While many clinical studies attempt to predict motor symptoms at different chronic time points after a stroke, longitudinal acute-to-chronic studies remain scarce. Taking advantage of recent advances in mapping brain disconnections, we predict motor outcomes in 62 patients assessed longitudinally two weeks, three months, and one year after their stroke. Results indicate that brain disconnection patterns accurately predict motor impairments. However, disconnection patterns leading to impairment differ between the three-time points and between left and right motor impairments. These results were cross-validated using resampling techniques. In sum, we demonstrated that while some neuroplasticity mechanisms exist changing the structure-function relationship, disconnection patterns prevail when predicting motor impairment at different time points after stroke.

Triploid genetic algorithm for convolutional neural network-based diagnosis of mild cognitive impairment

The diagnosis of mild cognitive impairment (MCI), which is deemed a formative phase of dementia, may greatly assist clinicians in delaying its headway toward dementia. This article proposes a deep learning approach based on a triploid genetic algorithm, a proposed variant of genetic algorithms, for classifying MCI converts and non-converts using structural magnetic resonance imaging data. It also explores the effect of the choice of activation functions and that of the selection of hyper-parameters on the performance of the model. The proposed work is a step toward automated convolutional neural networks. The performance of the proposed method is measured in terms of accuracy and empirical studies exhibit the preeminence of our proposed method over the existing ones. The proposed model results in a maximum accuracy of 0.97961. Thus, it may contribute to the effective diagnosis of MCI and may prove important in clinical settings.

Deep learning-based diagnosis of Alzheimer's disease using brain magnetic resonance images: an empirical study

The limited accessibility of medical specialists for Alzheimer's disease (AD) can make obtaining an accurate diagnosis in a timely manner challenging and may influence prognosis. We investigated whether VUNO Med-DeepBrain AD (DBAD) using a deep learning algorithm can be employed as a decision support service for the diagnosis of AD. This study included 98 elderly participants aged 60 years or older who visited the Seoul Asan Medical Center and the Korea Veterans Health Service. We administered a standard diagnostic assessment for diagnosing AD. DBAD and three panels of medical experts (ME) diagnosed participants with normal cognition (NC) or AD using T1-weighted magnetic resonance imaging. The accuracy (87.1% for DBAD and 84.3% for ME), sensitivity (93.3% for DBAD and 80.0% for ME), and specificity (85.5% for DBAD and 85.5% for ME) of both DBAD and ME for diagnosing AD were comparable; however, DBAD showed a higher trend in every analysis than ME diagnosis. DBAD may support the clinical decisions of physicians who are not specialized in AD; this may enhance the accessibility of AD diagnosis and treatment.

Deep learning in neuroimaging data analysis: Applications, challenges, and solutions

Methods for the analysis of neuroimaging data have advanced significantly since the beginning of neuroscience as a scientific discipline. Today, sophisticated statistical procedures allow us to examine complex multivariate patterns, however most of them are still constrained by assuming inherent linearity of neural processes. Here, we discuss a group of machine learning methods, called deep learning, which have drawn much attention in and outside the field of neuroscience in recent years and hold the potential to surpass the mentioned limitations. Firstly, we describe and explain the essential concepts in deep learning: the structure and the computational operations that allow deep models to learn. After that, we move to the most common applications of deep learning in neuroimaging data analysis: prediction of outcome, interpretation of internal representations, generation of synthetic data and segmentation. In the next section we present issues that deep learning poses, which concerns multidimensionality and multimodality of data, overfitting and computational cost, and propose possible solutions. Lastly, we discuss the current reach of DL usage in all the common applications in neuroimaging data analysis, where we consider the promise of multimodality, capability of processing raw data, and advanced visualization strategies. We identify research gaps, such as focusing on a limited number of criterion variables and the lack of a well-defined strategy for choosing architecture and hyperparameters. Furthermore, we talk about the possibility of conducting research with constructs that have been ignored so far or/and moving toward frameworks, such as RDoC, the potential of transfer learning and generation of synthetic data.

Alzheimer’s Disease Prediction Algorithm Based on Group Convolution and a Joint Loss Function

Alzheimer's disease (AD) can effectively predict by 18F-fluorodeoxyglucose positron emission tomography (18F-FDG PET) of the brain, but current PET images still suffer from indistinct lesion features, low signal-to-noise ratios, and severe artefacts, resulting in poor prediction accuracy for patients with mild cognitive impairment (MCI) and unclear lesion features. In this paper, an AD prediction algorithm based on group convolution and a joint loss function is proposed. First, a group convolutional backbone network based on ResNet18 is designed to extract lesion features from multiple channels, which makes the expression ability of the network improved to a great extent. Then, a hybrid attention mechanism is presented, which enables the network to focus on target regions and learn feature weights, so as to enhance the network's learning ability of the lesion regions that are relevant to disease diagnosis. Finally, a joint loss function, that avoids the overfitting phenomenon, increases the generalization of the model, and improves prediction accuracy by adding a regularization loss function to the conventional cross-entropy function, is proposed. Experiments conducted on the public Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset show that the algorithm we proposed gives a prediction accuracy improvement of 2.4% over that of the current AD prediction algorithm, thus proving the effectiveness and availability of the new algorithm.

Selective Amygdala Hypoactivity to Fear in Boys With Persistent Conduct Problems After Parent Training

BACKGROUND

Parenting interventions reduce antisocial behavior (ASB) in some children with conduct problems (CPs), but not others. Understanding the neural basis for this disparity is important because persistent ASB is associated with lifelong morbidity and places a huge burden on our health and criminal justice systems. One of the most highly replicated neural correlates of ASB is amygdala hypoactivity to another person's fear. We aimed to assess whether amygdala hypoactivity to fear in children with CPs is remediated following reduction in ASB after successful treatment and/or if it is a marker for persistent ASB.

METHODS

We conducted a prospective, case-control study of boys with CPs and typically developing (TD) boys. Both groups (ages 5-10 years) completed 2 magnetic resonance imaging sessions (18 ± 5.8 weeks apart) with ASB assessed at each visit. Participants included boys with CPs following referral to a parenting intervention group and TD boys recruited from the same schools and geographical regions. Final functional magnetic resonance imaging data were available for 36 TD boys and 57 boys with CPs. Boys with CPs were divided into those whose ASB improved (n = 27) or persisted (n = 30) following the intervention. Functional magnetic resonance imaging data assessing fear reactivity were then analyzed using a longitudinal group (TD/improving CPs/persistent CPs) × time point (pre/post) design.

RESULTS

Amygdala hypoactivity to fear was observed only in boys with CPs who had persistent ASB and was absent in those whose ASB improved following intervention.

CONCLUSIONS

Our findings suggest that amygdala hypoactivity to fear is a marker for ASB that is resistant to change following a parenting intervention and a putative target for future treatments.

Development of a deep learning network for Alzheimer’s disease classification with evaluation of imaging modality and longitudinal data

Objective. Neuroimaging uncovers important information about disease in the brain. Yet in Alzheimer’s disease (AD), there remains a clear clinical need for reliable tools to extract diagnoses from neuroimages. Significant work has been done to develop deep learning (DL) networks using neuroimaging for AD diagnosis. However, no particular model has emerged as optimal. Due to a lack of direct comparisons and evaluations on independent data, there is no consensus on which modality is best for diagnostic models or whether longitudinal information enhances performance. The purpose of this work was (1) to develop a generalizable DL model to distinguish neuroimaging scans of AD patients from controls and (2) to evaluate the influence of imaging modality and longitudinal data on performance. Approach. We trained a 2-class convolutional neural network (CNN) with and without a cascaded recurrent neural network (RNN). We used datasets of 772 (N AD = 364, N control = 408) 3D 18F-FDG PET scans and 780 (N AD = 280, N control = 500) T1-weighted volumetric-3D MR images (containing 131 and 144 patients with multiple timepoints) from the Alzheimer’s Disease Neuroimaging Initiative, plus an independent set of 104 (N AD = 63, N NC = 41) 18F-FDG PET scans (one per patient) for validation. Main Results. ROC analysis showed that PET-trained models outperformed MRI-trained, achieving maximum AUC with the CNN + RNN model of 0.93 ± 0.08, with accuracy 82.5 ± 8.9%. Adding longitudinal information offered significant improvement to performance on 18F-FDG PET, but not on T1-MRI. CNN model validation with an independent 18F-FDG PET dataset achieved AUC of 0.99. Layer-wise relevance propagation heatmaps added CNN interpretability. Significance. The development of a high-performing tool for AD diagnosis, with the direct evaluation of key influences, reveals the advantage of using 18F-FDG PET and longitudinal data over MRI and single timepoint analysis. This has significant implications for the potential of neuroimaging for future research on AD diagnosis and clinical management of suspected AD patients.

A Review on Multiscale-Deep-Learning Applications

In general, most of the existing convolutional neural network (CNN)-based deep-learning models suffer from spatial-information loss and inadequate feature-representation issues. This is due to their inability to capture multiscale-context information and the exclusion of semantic information throughout the pooling operations. In the early layers of a CNN, the network encodes simple semantic representations, such as edges and corners, while, in the latter part of the CNN, the network encodes more complex semantic features, such as complex geometric shapes. Theoretically, it is better for a CNN to extract features from different levels of semantic representation because tasks such as classification and segmentation work better when both simple and complex feature maps are utilized. Hence, it is also crucial to embed multiscale capability throughout the network so that the various scales of the features can be optimally captured to represent the intended task. Multiscale representation enables the network to fuse low-level and high-level features from a restricted receptive field to enhance the deep-model performance. The main novelty of this review is the comprehensive novel taxonomy of multiscale-deep-learning methods, which includes details of several architectures and their strengths that have been implemented in the existing works. Predominantly, multiscale approaches in deep-learning networks can be classed into two categories: multiscale feature learning and multiscale feature fusion. Multiscale feature learning refers to the method of deriving feature maps by examining kernels over several sizes to collect a larger range of relevant features and predict the input images' spatial mapping. Multiscale feature fusion uses features with different resolutions to find patterns over short and long distances, without a deep network. Additionally, several examples of the techniques are also discussed according to their applications in satellite imagery, medical imaging, agriculture, and industrial and manufacturing systems.

Deep Learning Techniques for the Effective Prediction of Alzheimer’s Disease: A Comprehensive Review

“Alzheimer’s disease” (AD) is a neurodegenerative disorder in which the memory shrinks and neurons die. “Dementia” is described as a gradual decline in mental, psychological, and interpersonal qualities that hinders a person’s ability to function autonomously. AD is the most common degenerative brain disease. Among the first signs of AD are missing recent incidents or conversations. “Deep learning” (DL) is a type of “machine learning” (ML) that allows computers to learn by doing, much like people do. DL techniques can attain cutting-edge precision, beating individuals in certain cases. A large quantity of tagged information with multi-layered “neural network” architectures is used to perform analysis. Because significant advancements in computed tomography have resulted in sizable heterogeneous brain signals, the use of DL for the timely identification as well as automatic classification of AD has piqued attention lately. With these considerations in mind, this paper provides an in-depth examination of the various DL approaches and their implementations for the identification and diagnosis of AD. Diverse research challenges are also explored, as well as current methods in the field.

A deep learning framework for diagnosing periprosthetic joint infections using X-ray images: a discovery and validation study

BACKGROUND

X-ray examination is the first-line imaging test for periprosthetic joint infections (PJIs). Deep learning has the potential to improve the diagnostic performance of X-ray examination for PJIs.

METHODS

A deep learning framework was developed for PJI diagnosis based on 1,062 X-ray images of the index prosthesis from patients who had PJI or aseptic failure. The classification network was constructed based on an ensemble of four deep learning models in a two-channel format for dual-view X-ray images. The interpret network was developed based on gradient weighted class to generate disease probability maps of individual PJI risk. The discrimination performance and disease probability maps were estimated in the validation set.

RESULTS

This PJI deep learning technique achieved an area under the curve (AUC) of 0.913 (95% confidence interval [CI]: 0.840-0.948), sensitivity of 0.844 (95% CI: 0.768-0.861), and specificity of 0.882 (95% CI: 0.851-0.934) for PJI recognition in hip prostheses. The PJI deep learning technique achieved an AUC of 0.931 (95% CI: 0.893-0.978), sensitivity of 0.905 (95% CI: 0.806-0.942), and specificity of 0.889 (95% CI: 0.747-0.944) for PJI recognition in knee prostheses. The high-risk prosthetic regions predicted by PJI deep learning were closely tracked with intraoperative clinical and pathological findings.

CONCLUSIONS

Deep learning provided a clinically applicable strategy for diagnosing PJI with high accuracy and robustness using routinely available X-ray images. However, the finding should be considered preliminary, the diagnosis performance might be partially attributed to prosthesis loosening, and the deep learning method is only helpful in patients already deemed suitable for revision.