Meta-Health: Learning-to-Learn (Meta-learning) as a Next Generation of Deep Learning Exploring Healthcare Challenges and Solutions for Rare Disorders: A Systematic Analysis

Archives of Computational Methods in Engineering, Год журнала: 2023, Номер 30(7), С. 4081 - 4112

Опубликована: Апрель 29, 2023

Язык: Английский

---

Handwritten devanagari manuscript characters recognition using capsnet

International Journal of Cognitive Computing in Engineering, Год журнала: 2023, Номер 4, С. 47 - 54

Опубликована: Фев. 11, 2023

Manuscripts serve as a wealth of knowledge for future generations and are useful source information locating material from the Middle Ages. Ancient manuscripts can be found in handwritten form, thus they must translated into digital form so that computing equipment access them additional indexing search operations performed with ease. Manuscript recognition is already possible using variety methods. Regional languages like Devanagari, Gurmukhi, Sanskrit, etc., however, have very few methods available. In this study, Devanagari characters recognised CapsNet-based method. 33 fundamental characters, 3 conjuncts, 12 modifiers make up alphabet. The complete dataset divided 399 classes basic, modifiers, conjunct characters. Due to spatial relationship, CapsNet used recognize proposed model was run 10:70, 20:80, 30:70 test: train ratio Also, number epochs varied better accuracy. authors observed best accuracy 94.6% achieved CapsNet.

Язык: Английский

---

ConvADD: Exploring a Novel CNN Architecture for Alzheimer's Disease Detection

International Journal of Advanced Computer Science and Applications, Год журнала: 2024, Номер 15(4)

Опубликована: Янв. 1, 2024

Alzheimer's disease (AD) poses a significant healthcare challenge, with an escalating prevalence and forecasted surge in affected individuals. The urgency for precise diagnostic tools to enable early interventions improved patient care is evident. Despite advancements, existing detection frameworks exhibit limitations accurately identifying AD, especially its stages. Model optimisation accuracy are other issues. This paper aims address this critical research gap by introducing ConvADD, advanced Convolutional Neural Network architecture tailored AD detection. By meticulously designing study endeavours surpass the of current methodologies enhance metrics, optimisation, reliability diagnosis. dataset was collected from Kaggle consists preprocessed 2D images extracted 3D images. Through rigorous experimentation, ConvADD demonstrates remarkable performance showcasing potential as robust effective. proposed model shows results tool 98.01%, precision 98%, recall F1-Score only 2.1 million parameters. However, despite promising results, several challenges remain, such generalizability across diverse populations need further validation studies. elucidating these gaps challenges, contributes ongoing discourse on improving lays groundwork future domain.

Язык: Английский

---

Alzheimer Disease Progression Forecasting: Empowering Models Through hybrid of CNN and LSTM with PSO Op-Timization

2021 International Conference on Emerging Smart Computing and Informatics (ESCI), Год журнала: 2024, Номер unknown, С. 1 - 5

Опубликована: Март 5, 2024

A common neurodegenerative disease, Alzheimer Disease (AD) affects society. Early intervention and personalized care require accurate condition prediction. hybrid model using Convolutional Neural Networks (CNN) Long Short-Term Memory networks (LSTM) Particle Swarm Optimization (PSO) is developed in this study to optimize performance. This research uses a large MRI dataset with important neuroimaging data. train validate our models, enabling data-centric approach AD progression. Forecasting involves predicting future events or outcomes available causes cognitive decline memory loss, making healthcare more complicated. Timely prognosis essential for prompt interventions patient care. Conventional forecasting models like CNN LSTM are good at disease excels capturing spatial dependencies datasets, while temporal sequences. We proposed novel take advantage of both architectures. paper (PSO), an effective optimization algorithm, fine-tune parameters. The goal improve accuracy. In study, the CNN-LSTM without PSO accurately predicted Our analysis includes accuracy, precision, recall, F1-Score, ROC AUC assess efficacy. advances predictive analytics offers new ways outcomes.

Язык: Английский

---

Classification of Alzheimer disease using DenseNet-201 based on deep transfer learning technique

PLoS ONE, Год журнала: 2024, Номер 19(9), С. e0304995 - e0304995

Опубликована: Сен. 6, 2024

Alzheimer's disease (AD) is a brain illness that causes gradual memory loss. AD has no treatment and cannot be cured, so early detection critical. Various diagnosis approaches are used in this regard, but Magnetic Resonance Imaging (MRI) provides the most helpful neuroimaging tool for detecting AD. In paper, we employ DenseNet-201 based transfer learning technique diagnosing different stages as Non-Demented (ND), Moderate Demented (MOD), Mild (MD), Very (VMD), Severe (SD). The suggested method dataset of MRI scans divided into five classes. Data augmentation methods were to expand size increase DenseNet-201's accuracy. It was found proposed strategy very high classification This practical reliable model delivers success rate 98.24%. findings experiments demonstrate deep approach more accurate performs well compared existing techniques state-of-the-art methods.

Язык: Английский

---

Neuropsychiatric Symptoms and Commonly Used Biomarkers of Alzheimer’s Disease: A Literature Review from a Machine Learning Perspective

Journal of Alzheimer s Disease, Год журнала: 2023, Номер 92(4), С. 1131 - 1146

Опубликована: Март 3, 2023

There is a growing interest in the application of machine learning (ML) Alzheimer’s disease (AD) research. However, neuropsychiatric symptoms (NPS), frequent subjects with AD, mild cognitive impairment (MCI), and other related dementias have not been analyzed sufficiently using ML methods. To portray landscape potential research AD NPS studies, we present comprehensive literature review existing approaches commonly studied biomarkers. We conducted PubMed searches keywords to NPS, biomarkers, learning, cognition. included total 38 articles this after excluding some irrelevant studies from search results including 6 based on snowball bibliography relevant studies. found limited number focused or without In contrast, multiple statistical deep methods used build predictive diagnostic models known These mainly imaging scores, various omics Deep that combine these biomarkers multi-modality datasets typically outperform single-modality datasets. conclude may be leveraged untangle complex relationships This potentially help predict progression MCI dementia develop more targeted early intervention NPS.

Язык: Английский

---

A deep learning-based early alzheimer’s disease detection using magnetic resonance images

Multimedia Tools and Applications, Год журнала: 2024, Номер unknown

Опубликована: Июнь 28, 2024

Язык: Английский

---

Diagnosis of Alzheimer’s Disease Using Convolutional Neural Network With Select Slices by Landmark on Hippocampus in MRI Images

IEEE Access, Год журнала: 2023, Номер 11, С. 61688 - 61697

Опубликована: Янв. 1, 2023

Alzheimer's disease (AD) is a major public health priority. Hippocampus one of the most affected areas brain and easily accessible as biomarker using MRI images in machine learning for diagnosing AD. In learning, entire image slices showed lower accuracy AD classification. We present select method by landmarks on hippocampus region images. This study aims to see which views have higher Then, get value three categories, we used multiclass classification with publicly available Disease Neuroimaging Initiative (ADNI) dataset Resnet50 LeNet. The models were total 4,500 categories. Our demonstrated that selecting performed better than improves coronal view accuracy. played significant role improving performance. results similar medical experts usually diagnose also found LeNet became potential model

Язык: Английский

---

Detection of Alzheimer's disease using deep learning models: A systematic literature review

Informatics in Medicine Unlocked, Год журнала: 2024, Номер 50, С. 101551 - 101551

Опубликована: Янв. 1, 2024

Alzheimer's disease (AD) is a progressive neurological considered the most common form of late-stage dementia. Usually, AD leads to reduction in brain volume, impacting various functions. This article comprehensively analyzes context fivefold main topics. Firstly, it reviews imaging techniques used diagnosing disease. Secondly, explores proposed deep learning (DL) algorithms for detecting Thirdly, investigates commonly datasets develop DL techniques. Fourthly, we conducted systematic review and selected 45 papers published highly ranked publishers (Science Direct, IEEE, Springer, MDPI). We analyzed them thoroughly by delving into stages diagnosis emphasizing role preprocessing Lastly, paper addresses remaining practical implications challenges context. Building on analysis, this survey contributes covering several aspects related that have not been studied thoroughly.

Язык: Английский

---

Using Deep Learning Techniques for Predictive Analysis of Alzheimer's Disease Early Diagnosis

Lecture notes in networks and systems, Год журнала: 2025, Номер unknown, С. 377 - 394

Опубликована: Янв. 1, 2025

Язык: Английский

---