Published: April 11, 2024
Language: Английский
Cogent Engineering, Journal Year: 2024, Volume and Issue: 11(1)
Published: Feb. 11, 2024
Alzheimer’s disease is a gradual neurodegenerative condition affecting the brain, causing decline in cognitive function by progressively damaging nerve cells over time. While cure for remains elusive, detection of (AD) through brain biomarkers crucial to impede its advancement. High-resolution structural MRI scans, particularly T1-weighted images, are commonly used detection. These images provide detailed information about brain’s structure, allowing researchers and clinicians identify abnormalities. Our study employs deep learning methodology using binary classification task—distinguishing between AD normal/healthy control (NC). The volumetric convolutional neural network model deployed on pre-processed validated MIRIAD datasets, achieving an impressive accuracy 97%, surpassing other models. Addressing challenge limited datasets models, we incorporated various augmentation techniques such as rotation rescaling, resulting outstanding effective discerning normal controls.
Language: Английский
Citations
8
Sensors, Journal Year: 2023, Volume and Issue: 23(19), P. 8272 - 8272
Published: Oct. 6, 2023
Alzheimer's disease (AD) is a progressive illness with slow start that lasts many years; the disease's consequences are devastating to patient and patient's family. If detected early, impact prognosis can be altered significantly. Blood biosamples often employed in simple medical testing since they cost-effective easy collect analyze. This research provides diagnostic model for based on federated learning (FL) hardware acceleration using blood biosamples. We used biosample datasets provided by ADNI website compare evaluate performance of our models. FL has been train shared without sharing local devices' raw data central server preserve privacy. developed approach building so we could speed up training procedures. The VHDL description language an Altera 10 GX FPGA utilized construct hardware-accelerator approach. results simulations reveal proposed methods achieve accuracy sensitivity early detection 89% 87%, respectively, while simultaneously requiring less time than other algorithms considered state-of-the-art. have power consumption ranging from 35 39 mW, which qualifies them use limited devices. Furthermore, result shows method lower inference latency (61 ms) existing fewer resources.
Language: Английский
Citations
14
Journal of Medical Physics, Journal Year: 2025, Volume and Issue: 50(1), P. 131 - 139
Published: Jan. 1, 2025
Abstract Purpose: This study proposes a novel approach combining mathematical modeling and machine learning (ML) to classify four Alzheimer’s disease (AD) stages from magnetic resonance imaging (MRI) scans. Methodology: We first mapped each MRI pixel value matrix 2 × matrix, using the techniques of forming moment inertia (MI) tensor, commonly used in physics measure mass distribution. Using properties obtained tensor their eigenvalues, along with ML techniques, we different AD. Results: In this study, have compared performance an intuitive model integrated across various models. Among them, Gaussian Naïve Bayes classifier achieves highest accuracy 95.45%. Conclusions: Beyond improved accuracy, our method offers potential for computational efficiency due dimensionality reduction provides physical insights into AD through analysis.
Language: Английский
Citations
0
PLoS ONE, Journal Year: 2025, Volume and Issue: 20(4), P. e0321697 - e0321697
Published: April 22, 2025
Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder leading to an inability socially communicate and in extreme cases individuals are completely dependent on caregivers. ASD detection at early ages crucial as can reduce the effect social impairment. Deep learning models have shown capability detect earlier compared traditional methods used by clinics experts. Ensemble models, renowned for their ability enhance predictive performance combining multiple emerged powerful tool machine learning. This study harnesses strength of ensemble address critical challenge diagnosis. proposed deep model leveraging strengths VGG16 Xception net trained Facial Images overcoming limitations existing datasets through extensive preprocessing. Proposed preprocessed training dataset facial images converting side posed into frontal face images, using Histogram Equalization (HE) colors, data augmentation techniques application, Hue Saturation Value (HSV) color model. By integrating feature extraction with fully connected layers, our has achieved notable 97% accuracy Kaggle Face Image Dataset. approach supports aligns Sustainable Development Goal 3, which focuses improving health well-being.
Language: Английский
Citations
0
Archives of Computational Methods in Engineering, Journal Year: 2024, Volume and Issue: unknown
Published: April 30, 2024
Language: Английский
Citations
2
Frontiers in Physiology, Journal Year: 2024, Volume and Issue: 15
Published: July 9, 2024
Introduction: Alzheimer’s Disease (AD) is a degenerative brain disorder characterized by cognitive and memory dysfunctions. The early detection of AD necessary to reduce the mortality rate through slowing down its progression. prevention emerging research topic for many researchers. structural Magnetic Resonance Imaging (sMRI) an extensively used imaging technique in AD, because it efficiently reflects variations. Methods: Machine learning deep models are widely applied on sMRI images accelerate diagnosis process assist clinicians timely treatment. In this article, effective automated framework implemented AD. At first, Region Interest (RoI) segmented from acquired employing Otsu thresholding method with Tunicate Swarm Algorithm (TSA). TSA finds optimal segmentation threshold value method. Then, vectors extracted RoI applying Local Binary Pattern (LBP) Directional variance (LDPv) descriptors. last, passed Deep Belief Networks (DBN) image classification. Results Discussion: proposed achieves supreme classification accuracy 99.80% 99.92% Neuroimaging Initiative (ADNI) Australian Imaging, Biomarker Lifestyle flagship work ageing (AIBL) datasets, which higher than conventional models.
Language: Английский
Citations
2
IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 109912 - 109929
Published: Jan. 1, 2024
Alzheimer's disease is a progressive for which researchers have yet to discover the main cause, but believe it probably involves combination of age-related changes in brain, genetic, environmental and lifestyle factors. an irreversible that still has no cure. Therefore, its early diagnosis very important prevent progression. Developing Machine Learning algorithms healthcare, especially brain disorders such as disease, provides new opportunities recognition biomarkers. This paper presents overview advanced studies based on techniques diagnosing different stages mild cognitive impairment magnetic resonance imaging (MRI) images last 10 years. Also, this comprehensively describes commonly efficient each stage processing used papers, can facilitate comparison with other provide insight into impact technique classification performance. review be valuable resource gain perspective various research methods recent disease.
Language: Английский
Citations
1
NeuroToxicology, Journal Year: 2024, Volume and Issue: 105, P. 196 - 207
Published: Oct. 11, 2024
Language: Английский
Citations
1
Advances in bioinformatics and biomedical engineering book series, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 26
Published: Nov. 1, 2024
Alzheimer's Disease (AD) is a relentless neurodegenerative disorder that profoundly affects cognitive abilities. Early detection and precise tracking of AD progression are pivotal for effective intervention management. In this study, we introduce NeuroTrackNet, an innovative machine learning (ML) algorithm seamlessly integrates spectrum biomarkers to enhance the monitoring Disease. By leveraging synergistic combination imaging, genetic, biochemical data, NeuroTrackNet significantly elevates diagnostic accuracy offers robust disease progression. Our comprehensive validation on dataset revealed NeuroTrackNet's impressive performance, achieving overall 92%, sensitivity 90%, specificity 94%.
Language: Английский
Citations
1
Bioengineering, Journal Year: 2024, Volume and Issue: 11(11), P. 1153 - 1153
Published: Nov. 15, 2024
Alzheimer's disease (AD) is a progressive and irreversible neurodegenerative condition that increasingly impairs cognitive functions daily activities. Given the incurable nature of AD its profound impact on elderly, early diagnosis (at mild impairment (MCI) stage) intervention are crucial, focusing delaying progression improving patients' quality life.
Language: Английский
Citations
1