Open Access Series Of Imaging Studies Research Articles

Performance Enhancement of Alzheimer's Disease Diagnosis Using Generative Adversarial Network

Insufficient medical images have always been a challenge for deep learning-based Alzheimer's disease classification and detection tasks. The availability of Magnetic Resonance Imaging (MRI) data is limited due to patients' privacy issues. Access to individual medical records is strongly protected by the law, and appropriate consent is needed to utilize them for research purposes. Besides that, publicly available databases often experience imbalanced classes, further contributing to the issue of insufficient data. Thus, the performance of deep learning models used to diagnose Alzheimer's disease is often hindered by this issue. Basic data augmentation methods such as geometrical augmentation techniques also had limited applications to medical data. Hence, this study proposes a deep learning technique of Generative Adversarial Network (GAN) to expand the MRI dataset and improve the classification model performance. MRI images from the Open Access Series of Imaging Studies (OASIS) database are used in this study to perform experiments and validate hypotheses. After applying GAN to expand the dataset, a pre-trained Convolutional Neural Network (CNN) model is used to classify the data into multiple classes of Alzheimer's and the model's performance is measured. As a result, an improvement in accuracy for the classification task can be observed, indicating that the GAN is a solution for overcoming the challenge of insufficient data for Alzheimer's diagnosis.

A LeViT–EfficientNet-Based Feature Fusion Technique for Alzheimer’s Disease Diagnosis

Alzheimer’s disease (AD) is a progressive neurodegenerative condition. It causes cognitive impairment and memory loss in individuals. Healthcare professionals face challenges in detecting AD in its initial stages. In this study, the author proposed a novel integrated approach, combining LeViT, EfficientNet B7, and Dartbooster XGBoost (DXB) models to detect AD using magnetic resonance imaging (MRI). The proposed model leverages the strength of improved LeViT and EfficientNet B7 models in extracting high-level features capturing complex patterns associated with AD. A feature fusion technique was employed to select crucial features. The author fine-tuned the DXB using the Bayesian optimization hyperband (BOHB) algorithm to predict AD using the extracted features. Two public datasets were used in this study. The proposed model was trained using the Open Access Series of Imaging Studies (OASIS) Alzheimer’s dataset containing 86,390 MRI images. The Alzheimer’s dataset was used to evaluate the generalization capability of the proposed model. The proposed model obtained an average generalization accuracy of 99.8% with limited computational power. The findings highlighted the exceptional performance of the proposed model in predicting the multiple types of AD. The recommended integrated feature extraction approach has supported the proposed model to outperform the state-of-the-art AD detection models. The proposed model can assist healthcare professionals in offering customized treatment for individuals with AD. The effectiveness of the proposed model can be improved by generalizing it to diverse datasets.

Integrating Demographics and Imaging Features for Various Stages of Dementia Classification: Feed Forward Neural Network Multi-Class Approach.

MRI magnetization-prepared rapid acquisition (MPRAGE) is an easily available imaging modality for dementia diagnosis. Previous studies suggested that volumetric analysis plays a crucial role in various stages of dementia classification. In this study, volumetry, radiomics and demographics were integrated as inputs to develop an artificial intelligence model for various stages, including Alzheimer's disease (AD), mild cognitive decline (MCI) and cognitive normal (CN) dementia classifications. The Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset was separated into training and testing groups, and the Open Access Series of Imaging Studies (OASIS) dataset was used as the second testing group. The MRI MPRAGE image was reoriented via statistical parametric mapping (SPM12). Freesurfer was employed for brain segmentation, and 45 regional brain volumes were retrieved. The 3D Slicer software was employed for 107 radiomics feature extractions from within the whole brain. Data on patient demographics were collected from the datasets. The feed-forward neural network (FFNN) and the other most common artificial intelligence algorithms, including support vector machine (SVM), ensemble classifier (EC) and decision tree (DT), were used to build the models using various features. The integration of brain regional volumes, radiomics and patient demographics attained the highest overall accuracy at 76.57% and 73.14% in ADNI and OASIS testing, respectively. The subclass accuracies in MCI, AD and CN were 78.29%, 89.71% and 85.14%, respectively, in ADNI testing, as well as 74.86%, 88% and 83.43% in OASIS testing. Balanced sensitivity and specificity were obtained for all subclass classifications in MCI, AD and CN. The FFNN yielded good overall accuracy for MCI, AD and CN categorization, with balanced subclass accuracy, sensitivity and specificity. The proposed FFNN model is simple, and it may support the triage of patients for further confirmation of the diagnosis.

Dementia detection using parameter optimization for multimodal datasets

Dementia, a neurodegenerative disorder, is more prominent among elderly people. This disease is one of the primary contributors amongst other diseases having a high social impact in continents of Europe and America. Treatment of the neurological disorders of dementia patients have become possible due to the Advances in medical diagnosis as in the use of Magnetic Resonance Imaging (MRI). Artificial Intelligence (AI) and Machine Learning (ML) techniques have provided solutions that enable fast, accurate and autonomous detection of diseases at their early stage. This in turn has improvised the entire health care system. This study proposes a diagnostic method, based on ML, for detecting dementia disease. The Open Access Series of Imaging Studies (OASIS) database and Alzheimer’s dataset (4 class of images) have been used for testing and training of various ML models. This involves the classification of the dependent variable into demented and non-demented patient. ML models as in Support Vector Machine (SVM), Logistic Regression, Naïve Bayes, k-nearest neighbor (KNN), Random Forest, Adaptive Boosting (ADA boost), Gradient Boosting, XG Boost, were trained and tested using OASIS dataset. Models were trained with 70% of data and tested on 30% of data. Hyper tuning of parameters of these models was also carried out to check for improvement in the results. Analysis showed that Naïve Bayes was the best amongst all giving 95% accuracy, 98% precision, 93% recall and 95% F1-score.

Adaptive 3DCNN-Based Interpretable Ensemble Model for Early Diagnosis of Alzheimer’s Disease

An adaptive interpretable ensemble model based on a 3-D convolutional neural network (3DCNN) and genetic algorithm (GA), i.e., 3DCNN <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$+$</tex-math> </inline-formula> EL <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$+$</tex-math> </inline-formula> GA, was proposed to differentiate the subjects with Alzheimer’s disease (AD) or mild cognitive impairment (MCI) and also identify the discriminative brain regions significantly contributing to the classifications in a data-driven way. The testing results on the datasets from both the AD Neuroimaging Initiative (ADNI) and the Open Access Series of Imaging Studies (OASIS) indicated that 3DCNN <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$+$</tex-math> </inline-formula> EL <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$+$</tex-math> </inline-formula> GA outperformed other state-of-the-art deep learning algorithms. More importantly, in these identified brain regions, the discriminative brain subregions at a voxel level were further located with a gradient-based attribution method designed for CNN and illustrated intuitively. Besides these, the behavioral domains corresponding to every identified discriminative brain region (e.g., the rostral hippocampus) were analyzed. It was shown that the resultant behavioral domains were consistent with those brain functions (e.g., emotion) impaired early in the AD process. Further research is needed to examine the generalizability of the proposed ideas and methods in identifying discriminative brain regions and subregions for the diagnosis of other brain disorders (especially little-known ones), such as Parkinson’s disease, epilepsy, severe depression, autism, Huntington’s disease, multiple sclerosis, and amyotrophic lateral sclerosis, using neuroimaging.

Systematic comparison of 3D Deep learning and classical machine learning explanations for Alzheimer’s Disease detection

Black-box deep learning (DL) models trained for the early detection of Alzheimer’s Disease (AD) often lack systematic model interpretation. This work computes the activated brain regions during DL and compares those with classical Machine Learning (ML) explanations. The architectures used for DL were 3D DenseNets, EfficientNets, and Squeeze-and-Excitation (SE) networks. The classical models include Random Forests (RFs), Support Vector Machines (SVMs), eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting (LightGBM), Decision Trees (DTs), and Logistic Regression (LR). For explanations, SHapley Additive exPlanations (SHAP) values, Local Interpretable Model-agnostic Explanations (LIME), Gradient-weighted Class Activation Mapping (GradCAM), GradCAM++ and permutation-based feature importance were implemented. During interpretation, correlated features were consolidated into aspects. All models were trained on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset. The validation includes internal and external validation on the Australian Imaging and Lifestyle flagship study of Ageing (AIBL) and the Open Access Series of Imaging Studies (OASIS).DL and ML models reached similar classification performances. Regarding the brain regions, both types focus on different regions. The ML models focus on the inferior and middle temporal gyri, and the hippocampus, and amygdala regions previously associated with AD. The DL models focus on a wider range of regions including the optical chiasm, the entorhinal cortices, the left and right vessels, and the 4th ventricle which were partially associated with AD. One explanation for the differences is the input features (textures vs. volumes). Both types show reasonable similarity to a ground truth Voxel-Based Morphometry (VBM) analysis. Slightly higher similarities were measured for ML models.

Early diagnosis of Alzheime`s disease based on VGG19 feature extractor and MRI analysis

Alzheimer’s Disease (AD) is the most prevalent cause of dementia, a neurodegenerative\ndisorder primarily affecting the brain. Mild cases of dementia gradually worsen, resulting in a\ndecline in cognitive abilities, including memory, thinking, reasoning, and behavior. Currently,\nthere is no cure for AD; however, early diagnosis of mild cases can help slow the disease\'s\nprogression, improve its management, and enhance overall quality of life. Existing models for\nearly AD diagnosis encounter challenges, such as low accuracy and precision, poor\ngeneralization and overfitting due to data imbalances in datasets. To address these limitations, we\npropose a novel Deep Learning (DL) based model for early AD diagnosis. Our model comprises\nthree main components: image processing and data augmentation, feature extraction based on\nVGG19 (Visual Geometry Group 19), and a Multi-Layer Perceptron (MLP) based classifier\ncategorizing input Magnetic Resonance Imaging (MRI) scans into four classes representing AD\'s\ndevelopmental stages: Very-Mild-Demented, Mild-Demented, Moderate-Demented, and NonDemented. We optimized our model using the ADAM Algorithm and applied it to images selected\nfrom the Open Access Series of Imaging Studies (OASIS) dataset. Our model yielded impressive\nresults, achieving an accuracy of 92.58%, an AUC of 99%, and precision, recall, and F-measure\nvalues of 0.907, 0.894, and 0.890, respectively. Furthermore, we conducted a comparative\nanalysis with several state-of-the-art models, consistently demonstrating that our proposed model\noutperforms them.

Contrastive Brain Network Learning via Hierarchical Signed Graph Pooling Model.

Recently, brain networks have been widely adopted to study brain dynamics, brain development, and brain diseases. Graph representation learning techniques on brain functional networks can facilitate the discovery of novel biomarkers for clinical phenotypes and neurodegenerative diseases. However, current graph learning techniques have several issues on brain network mining. First, most current graph learning models are designed for unsigned graph, which hinders the analysis of many signed network data (e.g., brain functional networks). Meanwhile, the insufficiency of brain network data limits the model performance on clinical phenotypes' predictions. Moreover, few of the current graph learning models are interpretable, which may not be capable of providing biological insights for model outcomes. Here, we propose an interpretable hierarchical signed graph representation learning (HSGPL) model to extract graph-level representations from brain functional networks, which can be used for different prediction tasks. To further improve the model performance, we also propose a new strategy to augment functional brain network data for contrastive learning. We evaluate this framework on different classification and regression tasks using data from human connectome project (HCP) and open access series of imaging studies (OASIS). Our results from extensive experiments demonstrate the superiority of the proposed model compared with several state-of-the-art techniques. In addition, we use graph saliency maps, derived from these prediction tasks, to demonstrate detection and interpretation of phenotypic biomarkers.

A brain‐wide risk score of Alzheimer’s disease based on multimodal neuroimaging predicts cognition in large N&gt;37000 population data

AbstractBackgroundAlzheimer’s disease (AD) is the most frequent age‐related dementia impairing memory, thinking, and social skills. Much research has been conducted in recent years to investigate the genetic risk of AD, but little effort has been made to find a brain imaging‐based AD risk evaluation. Here, we proposed a multimodal neuroimaging‐based measure of AD risk, called brain‐wide risk score (BRS).MethodFunctional network connectivity (FNC) and voxelwise gray matter (GM) from the Open Access Series of Imaging Studies (OASIS)‐3 (N = 1302 samples) cohort was used as a reference dataset to define mild cognitive impairment (MCI) and control (CN)group to evaluate individuals in the UK Biobank (N = 37,784) dataset. We calculated the mean of FNC and GM of MCI and CN. Next, we removed the mean FNC and GM from each sample FNC and GM of the target dataset. Then, we calculated the distance between the target dataset and CN (i.e., dist_CN) and MCI (i.e., dist_MCI) of the reference dataset using Euclidian distance. Finally, we calculated Δdiff = dist_CN‐dist_MCI as a BRS of AD, where the positive values are associated with higher AD BRS. Using two BRSs estimated based on FNC and GM for target dataset, we identified four AD biotypes. Samples with two negative Δdist represent low AD risk (Biotype1), samples with two positive Δdist represent high AD risk (Biotype4), and samples with one negative and one positive Δdist represent moderate AD risk (Biotype2/3). Next, we compared cognitive scores including fluid intelligence (FI) and reaction time (RT) across four biotypes.ResultFig.1 shows the 2D histogram of two BRS estimated from FNC and GM. We identified 11704 participants as biotype1, 10910 as biotype2, 7804 as biotype3 and 7366 as biotype4. We also found that Biotype1, with lower AD BRS, significantly shows a higher FI score than Biotype3 and Biotype4 (Fig.2, FI panel). Additionally, Biotype 4, with the highest BRS, had the most increased RT among all four AD biotypes (Fig.2, RT panel).ConclusionWe develop a new multimodal neuroimaging‐based BRS based which we identified four AD biotypes. We found that BRS predict cognitive scores in the identified biotypes.

MRI deep learning demonstrates featured neuropathological deteriorations in the AD brain

AbstractBackgroundDeep learning (DL) of non‐invasive brain structural magnetic resonance imaging (sMRI) has shown superb performance in differentiating Alzheimer’s disease (AD) from cognitively healthy participants (HC). Attention is needed to tackle AD pathological progression on sMRI using interpretable DL methods. Here, we studied the feasibility of DL in identifying neurodegenerative progression patterns in AD.MethodData applied to the study were from the multi‐centre Alzheimer’s Disease Neuroimaging Initiative (ADNI) and Open Access Series of Imaging Studies (OASIS) with 2,369 T1‐weighted brain images of 1,005 subjects. An interpretable DL technique named the ensemble 3‐dimensional convolutional neural network (Ensemble 3DCNN) was used to detect the longitudinal trajectory of sMRI changes during AD progression. The model used multiple 3D convolutional neural networks and a meta‐classifier to assess the degree of brain changes through generating an index score, named P‐score. The score was derived as the outcome of training and verifying the Ensemble 3DCNN model for difference in the whole‐brain sMRI between AD and HC. The predictive P‐scores values were used to analyze the sMRI images for mining neurodegenerative brain regions. In addition, dementia stages, and the temporal and spatial connectivity patterns of neurodegeneration progression were also analyzed.ResultBrain regions showing high P‐scores (&gt; 0.73/1.00) included the amygdala, nucleus accumbens, agranular insular cortex, and the hippocampus, matching the isocortex, basal magnocellular complex, and transentorhinal regions identified in Braak staging. The P‐score increased over time in 82% of the degenerative brain regions. The impaired areas were often spatially connected, consistently across multiple time points in the progression of AD. The trajectory of regional brain changes displayed multiple patterns with complex individual variability.ConclusionThe interpretable 3D DL model demonstrated featured deteriorations on the AD sMRI images. The finding confirmed the neuropathological degeneration of AD and captured additional whole‐brain changes, especially, relating to the heterogeneity of AD expression.

A 2.5D residual U‐Net for improved amyloid PET harmonization preserving spatial information

AbstractBackgroundMultiple amyloid tracers with varying characteristics pose a significant challenge to standardized interpretation and quantification of amyloid PET measurements. We previously demonstrated that a deep learning based 2D residual inception encoder‐decoder network (RIED‐Net) architecture improved harmonization of florbetapir (FBP) and PiB PET. However, 2D networks fail to capture spatial information among image slices and 3D networks with more parameters require larger datasets and powerful computation for training. Here, we investigate the performance of a 2.5D approach to further improve harmonization preserving spatial information.Method92 PiB‐FBP image pairs from Open Access Series of Imaging Studies (OASIS) were processed using established pipelines to extract regional standard uptake value ratios (SUVRs), mean cortical SUVRs (mcSUVRs), and SUVR images. A 2.5D U‐Net model with residual connections was implemented to learn the nonlinear mappings from the image pairs. Input to the network is a stack of 3 adjacent FBP slices along a particular view, providing extra spatial information about volumetric data. The output of network is a stack of corresponding 3 PiB slices. Multi‐slice output avoids averaging/blurry effects common in traditional 2.5D approaches. 10‐fold cross‐validation was implemented on axial, coronal and sagittal views separately to generate synthetic PiB SUVR imaging from FBP data. The average synthetic PiB image from axial, coronal and sagittal views was used for performance evaluation. Correlation was evaluated between the virtual PiB mcSUVR derived from imputed PiB vs. the real PiB mcSUVR and voxel‐wise between the imputed vs. real PiB SUVR images.ResultThe agreement of mcSUVR improved from r = 0.90 between PiB and FBP to r = 0.95 between synthetic and real PiB SUVR images (p&lt;0.0001) in cross‐validation dataset. Additionally, imputed PiB SUVR images were visually more similar to real PiB SUVR images than FBP. Voxel‐wise correlation improved from 0.88 to 0.93 (p&lt;0.0001).ConclusionOur proposed 2.5D Residual U‐Net for synthetic imaging was able to learn voxel‐wise nonlinear associations between FBP and PiB images. The model trained in 2.5D approach with additional spatial information, was able to significantly improve agreements of amyloid burden measurement from two tracers and generate PiB SUVR images that are visually more similar to real PiB SUVR images than FBP.

Optimized Convolutional Fusion for Multimodal Neuroimaging in Alzheimer's Disease Diagnosis: Enhancing Data Integration and Feature Extraction.

Multimodal neuroimaging has gained traction in Alzheimer's Disease (AD) diagnosis by integrating information from multiple imaging modalities to enhance classification accuracy. However, effectively handling heterogeneous data sources and overcoming the challenges posed by multiscale transform methods remains a significant hurdle. This article proposes a novel approach to address these challenges. To harness the power of diverse neuroimaging data, we employ a strategy that leverages optimized convolution techniques. These optimizations include varying kernel sizes and the incorporation of instance normalization, both of which play crucial roles in feature extraction from magnetic resonance imaging (MRI) and positron emission tomography (PET) images. Specifically, varying kernel sizes allow us to adapt the receptive field to different image characteristics, enhancing the model's ability to capture relevant information. Furthermore, we employ transposed convolution, which increases spatial resolution of feature maps, and it is optimized with varying kernel sizes and instance normalization. This heightened resolution facilitates the alignment and integration of data from disparate MRI and PET data. The use of larger kernels and strides in transposed convolution expands the receptive field, enabling the model to capture essential cross-modal relationships. Instance normalization, applied to each modality during the fusion process, mitigates potential biases stemming from differences in intensity, contrast, or scale between modalities. This enhancement contributes to improved model performance by reducing complexity and ensuring robust fusion. The performance of the proposed fusion method is assessed on three distinct neuroimaging datasets, which include: Alzheimer's Disease Neuroimaging Initiative (ADNI), consisting of 50 participants each at various stages of AD for both MRI and PET (Cognitive Normal, AD, and Early Mild Cognitive); Open Access Series of Imaging Studies (OASIS), consisting of 50 participants each at various stages of AD for both MRI and PET (Cognitive Normal, Mild Dementia, Very Mild Dementia); and whole-brain atlas neuroimaging (AANLIB) (consisting of 50 participants each at various stages of AD for both MRI and PET (Cognitive Normal, AD). To evaluate the quality of the fused images generated via our method, we employ a comprehensive set of evaluation metrics, including Structural Similarity Index Measurement (SSIM), which assesses the structural similarity between two images; Peak Signal-to-Noise Ratio (PSNR), which measures how closely the generated image resembles the ground truth; Entropy (E), which assesses the amount of information preserved or lost during fusion; the Feature Similarity Indexing Method (FSIM), which assesses the structural and feature similarities between two images; and Edge-Based Similarity (EBS), which measures the similarity of edges between the fused and ground truth images. The obtained fused image is further evaluated using a Mobile Vision Transformer. In the classification of AD vs. Cognitive Normal, the model achieved an accuracy of 99.00%, specificity of 99.00%, and sensitivity of 98.44% on the AANLIB dataset.

Efficient multimodel method based on transformers and CoAtNet for Alzheimer's diagnosis

Convolutional neural networks (CNNs) have been widely used in medical imaging applications, including brain diseases such as Alzheimer's disease (AD) classification based on neuroimaging data. Researchers extract the potential brain regions related to AD disease using CNN from various imaging modalities due to its architectural inductive bias. The major limitation of the current CNN-based model is that it doesn't capture long-range relationships and long-distance correlation within the image features. Vision transformers (ViT) have proven an astounding performance in encoding long-range relationships with strong modeling capacity and global feature extraction due to the self attention mechanism. However, ViT doesn't model the spatial information or the local features within the image and is hard to train. Researchers have demonstrated that combining CNN and a transformer yields outstanding results. In this study, two new methods are proposed for Alzheimer's disease diagnosis. The first method combines the Swin transformer with an enhanced EfficientNet with multi-head attention and a Depthwise Over-Parameterized Convolutional Layer (DO-Conv). The second method consists of modifying the CoAtNet network with ECA-Net and fused inverted residuals blocks. We evaluated the effectiveness of our proposed methods based on the Open Access Series of Imaging Studies (OASIS) and the Alzheimer's Disease Neuroimaging Initiative (ADNI). Further, we evaluated the proposed methods using the Gradient-based Localization (Grad-CAM) method. The first method achieved 93.23% accuracy of classification on the OASIS dataset. The second method achieved 97.33% accuracy of classification on the OASIS dataset. We applied different multimodal image fusion methods (MRI and PET, MRI and CT) using our proposed method. The experimental results demonstrate that the fusion method based on PET and MRI outperforms the fusion method based on MRI and CT achieving 99.42% accuracy. Our methods outperform some traditional CNN models and the recent methods that are based on transformer for AD classification.

Intelligent Interactive Deformable Image Registration for Online Adaptive Radiotherapy.

The goal of this study is to streamline the time-consuming contouring process in online adaptive radiotherapy (ART) by utilizing a deep learning-based interactive deformable image registration (DIR) algorithm. The objective is to minimize manual review and editing of automatically generated initial contours of organs-at-risk (OARs) and targets, thereby improving the efficiency and effectiveness of the treatment process. Our proposed method reforms the current DIR-based contour propagation method in clinical practice through the implementation of a deep learning-based interactive approach. The steps include: 1) generation of an initial deformable vector field (DVF) using a DL model, based on fixed and moving image pairs, resulting in the initial contours of OARs and targets; 2) clinician review/edit one the OAR/target contours as needed; 3) updated contour is sent to DL model to update the DVF and the remaining OARs/targets contours. Repeat this process until satisfactory contour qualities are achieved. We used the Open Access Series of Imaging Studies (OASIS) as the testbed, including 394 (train) and 20 (test) brain T1-weighted MRI scans, each containing 35 annotated organs. The U-Net architecture was employed to update the DVF from fixed/moving images, initial contours, and updated contours. We compared our approach to traditional manual editing without interaction and quantified the effort reduction using the added path length (APL) metric which is supposed to be proportional to the absolute time spent on the contour editing. We conducted paired t-test to show the significance. For comparison purpose, we assumed the clinicians edit the contours with the largest APL, i.e., the contours that require the most editing efforts. The editing effort, as measured by APL, was reduced by 18.5% to 25.4% with a mean of 23.3%, median of 23.6%, and standard deviation of 1.9%. The significance of the results was confirmed with a p-value of 1.47e-24. Our study demonstrates a significant reduction in editing effort, as measured by APL, compared to traditional manual contour editing. These results demonstrate the potential of our deep learning-based interactive approach to improve the efficiency and accuracy of the contouring process in clinical practice.

Prediction of dementia using machine learning model and performance improvement with cuckoo algorithm

Dementia is a brain disease that stays in the seventh position of death rate as per the report of the World Health Organization (WHO). Among the various types of dementia, Alzheimer’s disease has more than 70% of cases of dementia. The objective is to predict dementia disease from the open access series of imaging studies (OASIS) dataset using machine learning techniques. Also, the performance of the machine learning model is analyzed to improve the performance of the model using the cuckoo algorithm. In this paper, feature engineering has been focused and the prediction of dementia has been done using the OASIS dataset with the help of data mining techniques. Feature engineering is followed by prediction using the machine learning model Gaussian naïve Bayes (NB), support vector machine, and linear regression. Also, the best prediction model has been selected and done the validation. The evaluation metrics considered for validating the models are accuracy, precision, recall, and F1-Score and the highest values are 95%, 97%, 95%, and 95%. The Gaussian NB has been given these best results. The accuracy of the machine learning models has been increased by eliminating the factors which affect the performance of the models using the cuckoo algorithm.

Transfer learning based deep encoder decoder network for amyloid PET harmonization with small datasets

AbstractBackgroundThe existence of multiple amyloid tracers with varied characteristics poses a significant challenge to standardized interpretation and quantification of amyloid PET data. We previously demonstrated that a deep learning model using a residual inception encoder‐decoder network (RIED‐Net) architecture improved harmonization of florbetapir (FBP) and PiB PET. However, scarcity of head‐to‐head comparison datasets of other amyloid PET tracer may limit the ability to generalize this approach to the other amyloid PET tracers. In this research, we investigate the performance of RIED‐Net model trained on smaller datasets and explore transfer learning (TL) approaches which can leverage multiple different datasets and address the data scarcity issue.MethodWe previously trained our RIED‐Net model using PiB‐FBP data from Open Access Series of Imaging Studies (OASIS) (N = 92) and tested the performance in the independent Global Alzheimer’s Association Interactive Network (GAAIN) (N = 46) dataset. We now use the same procedure to train the RIED‐Net model using the smaller GAAIN dataset and evaluate the model performance. We then examine the feasibility of a TL approach by comparing the model performance between RIED‐Net model directly trained on the PiB‐florbetaben (FBB) from GAAIN (N = 35) and the TL approach in which we started with the optimal RIED‐Net model for PiB‐FBP data and fine‐tuned the network parameters using the GAAIN PiB‐FBB data. A cross‐validation (CV) approach was used to evaluate model performance based on difference before and after harmonization in terms of correlation between mean cortical SUVR (mcSUVR) measurements from different tracers.ResultRIED‐Net model trained using the smaller GAAIN PiB‐FBP data improved the agreement of mcSUVR measurements as measured by Pearson correlation from r = 0.93 to r = 0.96 (p&lt;0.01) on test‐set. For PiB‐FBB harmonization, the TL approach provided numerically better agreement in mcSUVR from r = 0.96 (direct train) to r = 0.97 (with TL), demonstrating the potential benefits of applying TL based technique to address the issue of smaller sample size.ConclusionWe demonstrate our RIED‐Net model can achieve improved harmonization even when trained on a relatively small training set. We also demonstrate the potential of transferring knowledge learned from one tracer pairs to improve the harmonization model of other related tracer pairs.

Using Machine Learning to Forecast Progression from Cognitively Normal to Alzheimer's Disease

Alzheimer's Disease (AD) affects approximately 50 million individuals worldwide and is estimated to rise to 152 million by 2050. There is currently no treatment for AD that halts the progression from cognitively normal (CN) and/or mild cognitive impairment (MCI) to AD. The ability to predict disease progression will allow for early treatment. While Machine Learning (ML) has been successful in diagnosing the cognitive state, further improvement is necessary for predicting progression. In this study, Random Forest and Bagging Decision Tree Recursive Feature Elimination (RFE) was utilized to ascertain the cognitive state and forecast progression. Clinical diagnoses, demographics, and post-processed PET and MRI scans used in this study were obtained from the Open Access Series of Imaging Studies (OASIS). The findings suggest that aging and lower levels of education are associated with higher risk. The study found that ML using post-processed MRI and PET scans, particularly RFE ML, is effective in diagnosing cognitive states with 90% accuracy. It can predict progression from CN to MCI or AD with 85% accuracy, which is significantly higher than the average reported in literature. Patients with progression from CN to AD were distinguished by elevated amyloid deposition, hippocampus and amygdala atrophy, left accumbens atrophy, thinning of the left hemisphere temporal, and enlarged inferior lateral ventricles. The study demonstrated that RFE ML is effective in diagnosing and predicting the progression of AD. Future studies will concentrate on identifying the specific regions of amyloid plaque that have the most significant impact on cognitive state and progression.&#x0D;

A Novel Approach Utilizing Machine Learning for the Early Diagnosis of Alzheimer's Disease.

Alzheimer's disease (AD) is one of the leading causes of dementia among older people. In addition, a considerable portion of the world's population suffers from metabolic problems, such as Alzheimer's disease and diabetes. Alzheimer's disease affects the brain in a degenerative manner. As the elderly population grows, this illness can cause more people to become inactive by impairing their memory and physical functionality. This might impact their family members and the financial, economic, and social spheres. Researchers have recently investigated different machine learning and deep learning approaches to detect such diseases at an earlier stage. Early diagnosis and treatment of AD help patients to recover from it successfully and with the least harm. This paper proposes a machine learning model that comprises GaussianNB, Decision Tree, Random Forest, XGBoost, Voting Classifier, and GradientBoost to predict Alzheimer's disease. The model is trained using the open access series of imaging studies (OASIS) dataset to evaluate the performance in terms of accuracy, precision, recall, and F1 score. Our findings showed that the voting classifier attained the highest validation accuracy of 96% for the AD dataset. Therefore, ML algorithms have the potential to drastically lower Alzheimer's disease annual mortality rates through accurate detection.

Dementia Classification Using Deep Reinforcement Learning for Early Diagnosis

Neurodegeneration and impaired neuronal transmission in the brain are at the root of Alzheimer’s disease (AD) and dementia. As of yet, no successful treatments for dementia or Alzheimer’s disease have indeed been found. Therefore, preventative measures such as early diagnosis are essential. This research aimed to evaluate the accuracy of the Open Access Series of Imaging Studies (OASIS) database for the purpose of identifying biomarkers of dementia using effective machine learning methods. In most parts of the world, AD is responsible for dementia. When the challenge level is high, it is nearly impossible to get anything done without assistance. This is increasing due to population growth and the diagnostic period. Two current approaches are the medical history and testing. The main challenge for dementia research is the imbalance of datasets and their impact on accuracy. A proposed system based on reinforcement learning and neural networks could generate and segment imbalanced classes. Making a precise diagnosis and taking into account dementia in all four stages will result in high-resolution sickness probability maps. It employs deep reinforcement learning to generate accurate and understandable representations of a person’s dementia sickness risk. To avoid an imbalance, classes should be evenly represented in the samples. There is a significant class imbalance in the MRI image. The Deep Reinforcement System improved trial accuracy by 6%, precision by 9%, recall by 13%, and F-score by 9–10%. The diagnosis efficiency has improved as well.

Dementia Prediction Using Machine Learning

Dementia is a chronic and degenerative condition, which has become a major health concern among the elderly. With ever-continuing cases of dementia, it has become a very challenging task in the 21st century to provide care for patients with dementia. This paper proposes a framework for the prediction of dementia using the data collected from the OASIS (Open Access Series of Imaging Studies) project which was made available by the Washington University Alzheimer's Disease Research Centre. Different techniques have been implemented for data imputation, pre-processing and data transformation to create suitable data for training the model. Machine learning approaches like Adaboost (AB), Decision Tree (DT), Extra Tree (ET), Gradient Boost (GB), K-Nearest Neighbour (KNN), Logistic Regression (LR), Naïve Bayes (NB), Random Forest (RF), and SVM (Support Vector Machine) has been used for a combination of features. These techniques have been applied to the full set of features and features selected from Least Absolute Shrinkage and Selection Operator (LASSO) techniques. A comparison between the accuracy, precision, and other metrics based on the results of the classification algorithms has been provided. The experimental results show that the highest accuracy of 96.77% was obtained by Support Vector Machine (SVM) with full features. The proposed methodology is promising and if developed and deployed can be helpful for the rapid assessment of Alzheimer's Disease (AD).