Deep Transfer Learning Based Parkinson’s Disease Detection Using Optimized Feature Selection

Abdullah, Sura Mahmood; Abbas, Thekra; Bashir, Munzir Hubiba; Khaja, Ishfaq Ahmad; Ahmad, Musheer; Soliman, Naglaa F.; El‐Shafai, Walid

doi:10.1109/access.2023.3233969

Cited by 24 publications

(6 citation statements)

References 27 publications

(23 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Abdullah et al [6]. proposed the combinations of transfer learning and genetic algorithms for feature selection and Ml models for final classification.…”

Section: Related Workmentioning

confidence: 99%

“…Biomedical biomarkers such as protein biomarkers, dopamine metabolites, and micro RNA are used for PD detection as well. [6] Due to the recent development in the fields of artificial intelligence, especially Machine learning (ML) and Deep Learning (DL), using these algorithms in the healthcare fields has increased [7]. Using pictures and electronic healthcare datasets for identifying neurodegenerative diseases like PD is one of these applications.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Late fused multi-modal neural network with votingclassifier for Parkinson’s Disease detection

aljohani

2024

Preprint

View full text Add to dashboard Cite

Parkinson’s Disease (PD) is categorized as a neurodegenerative progressivedisease caused by the destruction of the cells in the midbrain posterior.Detecting PD in its early stages will help physicians alleviate the complications of the disease. Artificial Intelligence (AI) is considered as the groupof trained models that can be used for classification and regression. Differentmodalities such as text, speech, and picture, can be used for detecting PD.This research proposes a multi-modal deep learning recognition technique forPD classification. To improve the quality of PD detection in the early stages,the proposed method is composed of three main sections. These sections are:feature extracting, merging, and classifying. As feature extractors a combination of Convolutional Neural Network (CNN) and attention mechanisms isdeveloped. To extract features from related motion signals a combination ofCNN and Long-Short Term Memory (LSTM) model is used. Finally, Random Forest (RF), Logistic Regression (LR), Support Vector Machine (SVM),Extreme Boot Classifier (XGB), and voting classifier are used to distinguishbetween healthy and PD subjects. The experimental result indicates 99.95%accuracy, 99.99% precision, 99.98% sensitivity, and 99.95% F1-score usingthe proposed CNN with attention and voting classifier on PD handwritingand corresponding motion datasets. The achieved results show the proposedmethod of extracting features from both handwriting pictures and correlatedmotor symptoms followed by fusing the features and finally using voting asthe classifier can achieve perfect performance for PD classification

show abstract

“…Abdullah et al [6]. proposed the combinations of transfer learning and genetic algorithms for feature selection and Ml models for final classification.…”

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Late fused multi-modal neural network with votingclassifier for Parkinson’s Disease detection

aljohani

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…A novel methodology for the precise identification of Parkinson's disease using handwritten records from a standard NewHandPD dataset was proposed by Sura Mahmood Abdullah et al [20]. To lessen the strain of training time, the suggested framework is built on transfer learning models like ResNet, VGG19, and In-ceptionV3.…”

Section: Aşuroğlu and Hasanmentioning

confidence: 99%

Data-driven Gait based Severity Classification for Parkinson's Disease using Duo Spatiotemporal Convoluted Kernel Boosted ResNet model

Victor Paul M,

Sankar

2024

Int. j. electr. comput. eng. syst. (Online)

View full text Add to dashboard Cite

Parkinson’s disease (PD) is one of the reformed brain syndromes that results in unintended stiffness and difficulty with balance and dexterity. To detect PD in medical scenery, physicians commonly use experimental indicators like motorized and non-motor symptoms and the severity rating depends on the unified PD Rating Scale (UPDRS). However, these medical assessments highly rely on expertized clinicians and lead to inter-variability discrepancies. Nowadays, gait sensor data assists doctors in diagnosing PD and estimates the severity level of gait abnormalities in patients. However, the gait sensor data increases the dimensionality issues and is subjected to high non-linear complexity. Hence, this study suggests an innovative deep learning (DL) technique for accurate PD analysis using gait patterns. Initially, the gait sensor data is preprocessed by performing data cleaning, and decimal scaling normalization (DS- Norm) to enhance the data quality. The Hoehn and Yahr (H&Y) scale is a commonly used rating scale for measuring the progression of Parkinson's disease symptoms. It's typically used to assess motor symptoms like tremors, rigidity, and bradykinesia. The scale ranges from 0 to 5, with higher numbers indicating more severe symptoms and disability. The preprocessed data are then fed into the proposed Duo spatiotemporal convoluted kernel boosted ResNet (DSCK-RNet) model for classifying the PD severity rating by learning the gait spatiotemporal features. The developed method is processed and scrutinized via the Python platform and a publicly available Physio- Net dataset is utilized for the simulation process. Various assessment measures like accuracy, precision, sensitivity, specificity, PPV, FPR, and MCC are examined and compared with traditional studies. In the experimental section, the developed DSCK-RNet model achieved an accuracy of 100%, 99.6%, 99%, and 99.64% for different classes like healthy, severity-2, severity-2.5, and severity-3 respectively. Compared to the conventional techniques, our suggested approach performs better. The experimental findings demonstrate the clinical significance of the suggested approach for the impartial evaluation of gait motor impairment in PD patients.

show abstract

“…Deep transfer learning techniques have been widely employed to: (i) address medical image analysis issues, particularly in detecting and diagnosing diseases that affect the heart, kidney, breast, lungs, brain, and other organs [3]. As such, this naturally has led to more and more researchers in recent times to continue seeking opportunities for (ii) optimization of the classifiers to achieve better performance.…”

Section: B Medical Imaging Modalitiesmentioning

confidence: 99%

Deep Transfer Learning Optimization Techniques for Medical Image Classifcation - A Survey

Kariuki¹,

Gikunda²,

Wandeto³

2023

Preprint

View full text Add to dashboard Cite

<p>Medical image classification is not only a complex task but also a challenging one due to the heterogeneous nature of medical data. Deep transfer learning has proven to be a viable technique for medical image classification throughout the years, mostly because it is able to leverage knowledge from pre-trained models learned from large-scale datasets, improved performance, minimal training and overcoming the disadvantage of small data sets. This paper offers a succinct review of the cutting-edge deep transfer learning optimization approaches for medical image classification. The paper begins with an overview of convolutional neural networks (CNN) and transfer learning techniques, such as relation-based, feature, parameter and instance-based transfer learning. Then, the study examines classical classifiers, such as Resnet, VGG, Alexnet, Googlenet, and Inception, and compare their performance on medical image classification tasks. The study also presents optimization techniques, including batch normalization, regularization, and weight initialization, data augmentation and the kernel mathematical formulations. Finally, the study unearths various challenges that arise when using deep transfer learning for medical image classification as well as potential future approaches for this field.</p>

show abstract

Deep Transfer Learning Based Parkinson’s Disease Detection Using Optimized Feature Selection

Cited by 24 publications

References 27 publications

Late fused multi-modal neural network with votingclassifier for Parkinson’s Disease detection

Late fused multi-modal neural network with votingclassifier for Parkinson’s Disease detection

Data-driven Gait based Severity Classification for Parkinson's Disease using Duo Spatiotemporal Convoluted Kernel Boosted ResNet model

Deep Transfer Learning Optimization Techniques for Medical Image Classifcation - A Survey

Contact Info

Product

Resources

About