An MRI-based deep learning approach for accurate detection of Alzheimer’s disease

EL-Geneedy, Marwa; Moustafa, Hossam El-Din; Khalifa, Fahmi; Khater, Hatem A.; AbdElhalim, Eman

doi:10.1016/j.aej.2022.07.062

Cited by 102 publications

(14 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed methods were compared with the traditional homogeneous ensemble deep learning in the next experiment. The CNN architectures that were compared with the proposed methods included EfficientNetV2B3, EfficientNetV2M, ConvNeXtSmall, DenseNet201 ( 69 ), NASNetMobile ( 61 ), and EfficientNetB7 ( 59 ). All methods were executed for two hundred epochs using batch sizes of 2, 3, 5, 12, 10, and 8 for EfficientNetV2B3, EfficientNetV2M, ConvNeXtSmall, DenseNet201, NASNetMobile, and EfficientNetB7, respectively.…”

Section: Computational Results and Frameworkmentioning

confidence: 99%

Computer-aided diagnosis using embedded ensemble deep learning for multiclass drug-resistant tuberculosis classification

et al. 2023

View full text Add to dashboard Cite

IntroductionThis study aims to develop a web application, TB-DRD-CXR, for the categorization of tuberculosis (TB) patients into subgroups based on their level of drug resistance. The application utilizes an ensemble deep learning model that classifies TB strains into five subtypes: drug sensitive tuberculosis (DS-TB), drug resistant TB (DR-TB), multidrug-resistant TB (MDR-TB), pre-extensively drug-resistant TB (pre-XDR-TB), and extensively drug-resistant TB (XDR-TB).MethodsThe ensemble deep learning model employed in the TB-DRD-CXR web application incorporates novel fusion techniques, image segmentation, data augmentation, and various learning rate strategies. The performance of the proposed model is compared with state-of-the-art techniques and standard homogeneous CNN architectures documented in the literature.ResultsComputational results indicate that the suggested method outperforms existing methods reported in the literature, providing a 4.0%-33.9% increase in accuracy. Moreover, the proposed model demonstrates superior performance compared to standard CNN models, including DenseNet201, NASNetMobile, EfficientNetB7, EfficientNetV2B3, EfficientNetV2M, and ConvNeXtSmall, with accuracy improvements of 28.8%, 93.4%, 2.99%, 48.0%, 4.4%, and 7.6% respectively.ConclusionThe TB-DRD-CXR web application was developed and tested with 33 medical staff. The computational results showed a high accuracy rate of 96.7%, time-based efficiency (ET) of 4.16 goals/minutes, and an overall relative efficiency (ORE) of 100%. The system usability scale (SUS) score of the proposed application is 96.7%, indicating user satisfaction and a likelihood of recommending the TB-DRD-CXR application to others based on previous literature.

show abstract

Section: Computational Results and Frameworkmentioning

confidence: 99%

Computer-aided diagnosis using embedded ensemble deep learning for multiclass drug-resistant tuberculosis classification

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Mouse GO-Regulators that used by [17] are obtained from the Gene Ontology [20] based on the knowledge from EBI [21] and both are mapped (as the expression profiles) to XM gene to the regulators. Regulators with less than 100 genes among the expressed genes are not included in our investigation because the statistical tests do not apply to them.…”

Section: Table 2 : Sample Of Ged After Modification 62 Gene Regulator...mentioning

confidence: 99%

Gat2Get: A Novel Approach to Infer Gene Regulatory Network from Gene Activity using Dynamic Bayesian Network learning

Saleh

Alnsari²,

Ead³

et al. 2023

Port-Said Engineering Research Journal

View full text Add to dashboard Cite

Discovering Gene Regulatory Network (GRN) gives some idea about gene pathways and helps many potential applications in medicine. The essential source of data for this task is the gene expression data. High complexity and poor quality of gene expression data acquired by high throughput methods like microarray provide many difficulties in the context of the current issue. A promising method for evaluating gene expression noisy data to characterize processes made up of locally interacting components is Bayesian Network. In fact, because of the intricacy of the inputs and results of the cellular mechanism, inferring GRN from expression data presents numerous difficulties. This work proposes a new approach for inferring GRNs from time series gene expression data. The present work extends the existing Bayesian Network methods to include the regulation properties of genes to improve the process of capturing natural classes during inferring the relations between genes. The proposed approach is evaluated in comparing to the corresponding techniques of the related works, and the results show the ability of the present approach is efficient to some level to deal with such high dimensional data even without dimension reduction, but in the presence of regulatory information.

show abstract

“…Moreover, CNN techniques have exhibited success in various research domains, encompassing tasks like ocean noise detection [10], COVID-19 detection via X-ray images [11]- [13], mammography image segmentation and classification [14], classification of environmental sounds [15], Alzheimer's disease detection [16], skin cancer diagnosis [17], identification of cartilage lesions [18], fatigue diagnosis based www.ijacsa.thesai.org on heart sounds [19], diagnosis of joint disorders [20], premature retinopathy assessment [21], and even the diagnosis of idiopathic Parkinson's disease [22].…”

Section: Introductionmentioning

confidence: 99%

Use of ANN, LSTM and CNN Classifiers for the New MSCC and BSCC Methods in the Detection of Parkinson's Disease by Voice Analysis

Mounia,

Nouhaila,

Benayad

et al. 2023

IJACSA

View full text Add to dashboard Cite

Parkinson's disease (PD) is a neurodegenerative condition that impacts a significant global population. The timely and precise identification of PD plays a pivotal role in facilitating early intervention and the efficient management of the condition. Recently, speech analysis has emerged as a promising noninvasive technique for the detection of PD due to its accessibility and ability to reveal subtle vocal biomarkers associated with the disease. This research introduces an innovative approach utilizing Short-Time Fourier Transform (STFT) to generate spectrograms, specifically Bark Spectrogram Cepstral Coefficients (BSCC) and Mel Spectrogram Cepstral Coefficients (MSCC). These coefficients are compared with traditional and well-known coefficients, namely Mel-Frequency Cepstral Coefficients (MFCC) and Bark Frequency Cepstral Coefficients (BFCC). To extract the most effective coefficients for Parkinson's disease detection, three robust classification techniques-Long Short-Term Memory neural networks (LSTM), Convolutional Neural Networks (CNN), and Artificial Neural Networks (ANN)-are employed. As a result, the BSCC and MSCC algorithms achieve a maximum accuracy rate of 90%, surpassing the accuracy of the traditional MFCC and BFCC coefficients. Therefore, these newly proposed coefficients prove to be more precise in diagnosing Parkinson's disease compared to the conventional MFCC and BFCC coefficients.

show abstract

An MRI-based deep learning approach for accurate detection of Alzheimer’s disease

Cited by 102 publications

References 10 publications

Computer-aided diagnosis using embedded ensemble deep learning for multiclass drug-resistant tuberculosis classification

Computer-aided diagnosis using embedded ensemble deep learning for multiclass drug-resistant tuberculosis classification

Gat2Get: A Novel Approach to Infer Gene Regulatory Network from Gene Activity using Dynamic Bayesian Network learning

Use of ANN, LSTM and CNN Classifiers for the New MSCC and BSCC Methods in the Detection of Parkinson's Disease by Voice Analysis

Contact Info

Product

Resources

About