3,722 Hits in 4.8 sec

Transfer Learning with intelligent training data selection for prediction of Alzheimer's Disease

Naimul Mefraz Khan, Nabila Abraham, Marcia Hon
2019 IEEE Access  
Detection of Alzheimer's disease (AD) from neuroimaging data such as MRI through machine learning has been a subject of intense research in recent years.  ...  We also provide a detailed analysis of the effect of the intelligent training data selection method, changing the training size, and changing the number of layers to be fine-tuned.  ...  We show that through intelligent training data selection and transfer learning, we can achieve state-of-the-art classification results for all three classification scenarios in Alzheimer's prediction,  ... 
doi:10.1109/access.2019.2920448 fatcat:w5i3mlggvfgkbmyg5dmxhi2z3m

Efficient Machine Learning Techniques to Diagnose and Predict Alzheimer's disease

2020 International Journal of Engineering and Advanced Technology  
Despite of the development of numerous machine learning models for early diagnosis of Alzheimer's disease, it is observed that there is a lot more scope of research.  ...  In this context, prediction and diagnosis of fatal neurodegenerative diseases that comes under the class of dementia from medical image data is considered as the challenging area of research for many researchers  ...  [39] directly came with an idea of a book multi-domain transfer learning model (MDTL). Deep transfer learning is used by Hon et al.  ... 
doi:10.35940/ijeat.c6508.029320 fatcat:wzyju5k4wrhgtdcc5h74bqjwve

Towards Alzheimer's Disease Classification through Transfer Learning [article]

Marcia Hon, Naimul Khan
2017 arXiv   pre-print
Detection of Alzheimer's Disease (AD) from neuroimaging data such as MRI through machine learning have been a subject of intense research in recent years.  ...  We employ image entropy to select the most informative slices for training.  ...  Most informative training data selection While transfer learning provides an opportunity to use smaller set of training data, choosing the best possible data for training is still critical to the success  ... 
arXiv:1711.11117v1 fatcat:lxhc2ymkqvgjvidhk3fh2dx5mu

Artificial Intelligence in Health in 2018: New Opportunities, Challenges, and Practical Implications

Gretchen Jackson, Jianying Hu, Section Editors for the IMIA Yearbook Section on Artificial Intelligence in Health
2019 IMIA Yearbook of Medical Informatics  
Innovative training heuristics and encryption techniques may support distributed learning with preservation of privacy.  ...  Objective: To summarize significant research contributions to the field of artificial intelligence (AI) in health in 2018.  ...  ., ensembling single institution models, single weight transfer, and cyclic weight transfer) for training deep learning models using distributed data and produced valuable insights through a set of very  ... 
doi:10.1055/s-0039-1677925 pmid:31419815 pmcid:PMC6697508 fatcat:qhflemhlp5euvp5xmc4njd5pxq

Alzheimer Disease Detection Techniques and Methods: A Review

Sitara Afzal, Muazzam Maqsood, Umair Khan, Irfan Mehmood, Hina Nawaz, Farhan Aadil, Oh-Young Song, Yunyoung Nam
2021 International Journal of Interactive Multimedia and Artificial Intelligence  
Brain pathological changes linked with Alzheimer's disease (AD) can be measured with Neuroimaging.  ...  The study revealed that the deep learning techniques and support vector machine give higher accuracies in the identification of Alzheimer's disease.  ...  In [86] N.M et al. proposed a transfer learning approach for the prediction of the binary class Alzheimer's Disease and Maqsood et al. [87] proposed a transfer learning approach by utilizing pre-trained  ... 
doi:10.9781/ijimai.2021.04.005 fatcat:yklogr5wefei7e247dmjdrosum

Using ProtoPNet for Interpretable Alzheimer's Disease Classification

Sanaz Mohammadjafari, Mucahit Cevik, Mathusan Thanabalasingam, Ayse Basar, Alzheimer's Disease Neuroimaging Initiative
2021 Proceedings of the Canadian Conference on Artificial Intelligence  
Early detection of Alzheimer's disease (AD) is significant for identifying of better treatment plans for the patients as the AD is not curable.  ...  We find that the ProtoPNet model with DenseNet121 architecture can reach 90 percent accuracy while providing explanatory illustrations of the model's reasonings for the generated predictions.  ...  Acknowledgements Data collection and sharing for this project was funded by the Alzheimer's Disease Neuroimaging Initiative (ADNI) (National Institutes of Health Grant U01 AG024904) and DOD ADNI (Department  ... 
doi:10.21428/594757db.fb59ce6c fatcat:6ppf4lpfcjb6xmssil366mpdsa

Classification of Neurodegenerative Disease Stages using Ensemble Machine Learning Classifiers

M. Rohini, D. Surendran
2019 Procedia Computer Science  
The proposed study intends to develop a learning algorithm for the prediction of Alzheimer's disease at an early stage.  ...  The proposed study intends to develop a learning algorithm for the prediction of Alzheimer's disease at an early stage.  ...  This can be implemented by training the proposed ensemble of classifiers with hypothesis for each class of disease to predict probability and to make prediction on new disease class by choosing the class  ... 
doi:10.1016/j.procs.2020.01.071 fatcat:u2hpn2beebadvb2upcsqxj4iau

A Review of Artificial Intelligence, Big Data, and Blockchain Technology Applications in Medicine and Global Health

Supriya M., Vijay Kumar Chattu
2021 Big Data and Cognitive Computing  
ML algorithms can also analyze large amounts of data called Big data through electronic health records for disease prevention and diagnosis.  ...  In the context of a newly published study, the potential benefits of sophisticated data analytics and machine learning are discussed in this review.  ...  learning algorithms used for disease prediction.  ... 
doi:10.3390/bdcc5030041 fatcat:x25hkk3fxnbtll7cofmikpys3i

Alzheimer's Disease: A Survey

Harshitha, Gowthami Chamarajan, Charishma Y
2021 International Journal of Artificial Intelligence  
In recent years, Neuroimaging combined with machine learning techniques have been used for detection of Alzheimer's disease.  ...  There are many such methods which can be used for detection of Alzheimer's Disease.  ...  The conclusion says that TI-weighted brain images are widely available and best for prediction of Alzheimer's Disease.  ... 
doi:10.36079/lamintang.ijai-0801.220 fatcat:s5375uw5j5hxlci3yj4tz6icfu


Shereen A. El-Aal, Neveen I. Ghali
2021 Journal of Southwest Jiaotong University  
Alzheimer's disease (AD) is an advanced and incurable neurodegenerative disease that causes progressive impairment of memory and cognitive functions due to the deterioration of brain cells.  ...  Experimental results showed that the most efficient accuracies were obtained by PBPSO selected features which reached 87.3% and 94.8% accuracy with less time of 46.7 sec, 32.7 sec for features based ResNet  ...  RECOGNITION SYSTEM FOR ALZHEIMER'S DISEASE BASED ON TRANSFER LEARNING AND OPTIMIZATION ALGORITHMS In this section, the dataset used for training and testing is described briefly.  ... 
doi:10.35741/issn.0258-2724.56.5.22 fatcat:ajqk4yqkvbdmtcwke4p5425gky

Prediction of Cognitive Decline in Temporal Lobe Epilepsy and Mild Cognitive Impairment by EEG, MRI, and Neuropsychology

Yvonne Höller, Kevin H. G. Butz, Aljoscha C. Thomschewski, Elisabeth V. Schmid, Christoph D. Hofer, Andreas Uhl, Arne C. Bathke, Wolfgang Staffen, Raffaele Nardone, Fabian Schwimmbeck, Markus Leitinger, Giorgi Kuchukhidze (+3 others)
2020 Computational Intelligence and Neuroscience  
On the background of a unifying hypothesis for cognitive decline, we merged knowledge from dementia and epilepsy research in order to identify biomarkers with a high predictive value for cognitive decline  ...  subset selection and 5-fold cross validation.  ...  Based on the large database of Alzheimer's Disease Neuroimaging Initiative, conversion from mild cognitive impairment to Alzheimer's disease was predictable with an accuracy of 0.7-0.79 [25] .  ... 
doi:10.1155/2020/8915961 pmid:32549888 pmcid:PMC7256687 fatcat:lmdh4ptwefg35lw7dkvyvwaada

Machine Learning on Biomedical Images: Interactive Learning, Transfer Learning, Class Imbalance, and Beyond [article]

Naimul Mefraz Khan, Nabila Abraham, Ling Guan
2019 arXiv   pre-print
can drastically improve exploration time and quality of direct volume rendering. 2) transfer learning: we show how transfer learning along with intelligent pre-processing can result in better Alzheimer's  ...  diagnosis using a much smaller training set 3) data imbalance: we show how our novel focal Tversky loss function can provide better segmentation results taking into account the imbalanced nature of segmentation  ...  To combat the issue of dependence on large training sets for deep learning architectures, we employ Transfer Learning (TL) in combination with an intelligent training data selection method based on image  ... 
arXiv:1902.05908v1 fatcat:65k2olw3tndlhnbhs5yjgvo2ni

A Review of Artificial Intelligence Technologies for Early Prediction of Alzheimer's Disease [article]

Kuo Yang, Emad A. Mohammed
2020 arXiv   pre-print
, Graph CNN (GCN), Ensemble Learning, and Transfer Learning.  ...  Alzheimer's Disease (AD) is a severe brain disorder, destroying memories and brain functions. AD causes chronically, progressively, and irreversibly cognitive declination and brain damages.  ...  Mohammed A Review of Artificial Intelligence Technologies for Early Prediction of Alzheimer's Disease extraction and representation of the image or text data, as shown in Table I.  ... 
arXiv:2101.01781v1 fatcat:lqtovw4jlbdcjhh5rvresp2gmq

A Comparison of Transfer Learning Performance versus Health Experts in Disease Diagnosis from Medical Imaging

Hassaan Malik, Muhammad Shoaib Farooq, Adel Khelifi, Adnan Abid, Junaid Nasir Qureshi, Muzammil Hussain
2020 IEEE Access  
Deep learning methods have huge success in task specific feature representation. Transfer learning algorithms are very much effective when large training data is scarce.  ...  This article presents a systematic literature review (SLR) by conducting a comparison of a variety of transfer learning approaches with healthcare experts in diagnosing diseases from medical imaging.  ...  Moreover, the methods of neural network mostly require large amount of data for training process, which feasible to apply on pre-trained models for rare diseases [65] .  ... 
doi:10.1109/access.2020.3004766 fatcat:ynlcahzrxndv3pe4uzwbsywoje

Longitudinal Speech Biomarkers for Automated Alzheimer's Detection

Jordi Laguarta, Brian Subirana
2021 Frontiers in Computer Science  
Transfer Learning is subsequently used to incorporate features from this model into various other biomarker-based OVBM architectures.  ...  Inspired by research conducted at the MIT Center for Brain Minds and Machines (CBMM), OVBM combines biomarker implementations of the four modules of intelligence: The brain OS chunks and overlaps audio  ...  COVID-19 deaths are more likely with Alzheimer's than with Parkinson's disease (Yu et al., 2020) .  ... 
doi:10.3389/fcomp.2021.624694 fatcat:m3kdwrsmbvgtlcdmjuccctkmrq
« Previous Showing results 1 — 15 out of 3,722 results