Diagnosis of Coronary Artery Disease from Myocardial Perfusion Imaging Using Convolutional Neural Networks DOI Open Access
Vincent Peter C. Magboo, Ma. Sheila A. Magboo

Procedia Computer Science, Journal Year: 2023, Volume and Issue: 218, P. 810 - 817

Published: Jan. 1, 2023

Cardiovascular disease is a highly prevalent health problem in both underdeveloped and developing countries worldwide. As such, it remains to be one of the top priorities many countries. In coronary artery (CAD), formation an atherosclerotic plaque evident lumen blood vessels leading derangement flow resulting diminished delivery oxygen myocardium. Single Photon Emission Computed Tomography – Myocardial Perfusion Imaging (SPECT-MPI) usually requested imaging modality evaluate for CAD. Visual evaluation MPI images performed by nuclear medicine doctor largely dependent on his experience showing significant inter-observer variability. The study aims assess performance convolutional neural networks (CNN) using transfer learning classify SPECT-MPI perfusion abnormalities anonymized publicly available dataset. pre-processing methods that were applied dataset following: (a) normalization images, (b) shuffling (c) train-test split, (d) geometric augmentation. pre-processed data was then entered popular pre-trained CNNs typically medical images: VGG16, DenseNet121, InceptionV3 ResNet50. best performing models obtained VGG16 with highest accuracy rate 84.38%. However, had higher recall F1-scores as compared while precision. Nonetheless, DenseNet121 similar metrics each other (recall:80-100%, precision: 80.65-100%, F1-scores: 88.89-90.91%) ResNet50 generated lowest metrics. Overall findings suggest any these 3 CNN (VGG16, InceptionV3, DenseNet121) can deployed physicians their clinical practice further augment decision skills interpretation tests. also adopted dependable trusted secondary assessment which guide junior doctors seeking consultation reliable diagnosis. These likewise serve teaching or materials less experienced particularly those still training career. This highlights utility cardiology. results research exhibited encouraging outcomes may possibly incorporated work. has potential enrich CAD discernment monitoring.

Language: Английский

A Survey of Deep Learning Techniques for the Analysis of COVID-19 and their usability for Detecting Omicron DOI
Asifullah Khan, Saddam Hussain Khan,

Mahrukh Saif

et al.

Journal of Experimental & Theoretical Artificial Intelligence, Journal Year: 2023, Volume and Issue: 36(8), P. 1779 - 1821

Published: Jan. 12, 2023

The Coronavirus (COVID-19) outbreak in December 2019 has drastically affected humans worldwide, creating a health crisis that infected millions of lives and devastated the global economy. COVID-19 is ongoing, with emergence many new strains. Deep learning (DL) techniques have proven helpful efficiently analysing delineating infectious regions radiological images. This survey paper draws taxonomy deep for detecting infection radiographic imaging modalities Chest X-Ray, Computer Tomography. DL are broadly categorised into classification, segmentation, multi-stage approaches diagnosis at image region-level analysis. These further classified as pre-trained custom-made Convolutional Neural Network architectures. Furthermore, discussion drawn on datasets, evaluation metrics, commercial platforms provided detection. In end, brief look paid to emerging ideas, gaps existing research, challenges developing diagnostic techniques. provides insight promising areas research likely guide community upcoming development COVID-19. will pave way accelerate designing customised DL-based tools effectively dealing variants challenges.

Language: Английский

Citations

45
Real-Time Implementation of AI-Based Face Mask Detection and Social Distancing Measuring System for COVID-19 Prevention DOI Open Access
Safa Teboulbi, Seifeddine Messaoud, Mohamed Ali Hajjaji

et al.

Scientific Programming, Journal Year: 2021, Volume and Issue: 2021, P. 1 - 21

Published: Sept. 27, 2021

Since the infectious coronavirus disease (COVID-19) was first reported in Wuhan, it has become a public health problem China and even around world. This pandemic is having devastating effects on societies economies The increase number of COVID-19 tests gives more information about epidemic spread, which may lead to possibility surrounding prevent further infections. However, wearing face mask that prevents transmission droplets air maintaining an appropriate physical distance between people, reducing close contact with each other can still be beneficial combating this pandemic. Therefore, research paper focuses implementing Face Mask Social Distancing Detection model as embedded vision system. pretrained models such MobileNet, ResNet Classifier, VGG are used our context. People violating social distancing or not masks were detected. After deploying models, selected one achieved confidence score 100%. also provides comparative study different detection classification models. system performance evaluated terms precision, recall, F1-score, support, sensitivity, specificity, accuracy demonstrate practical applicability. performs F1-score 99%, sensitivity specificity Hence, solution tracks people without real-time scenario ensures by generating alarm if there violation scene places. existing camera infrastructure enable these analytics applied various verticals, well office building at airport terminals/gates.

Language: Английский

Citations

70
Coronavirus disease (COVID-19) detection using X-ray images and enhanced DenseNet DOI Open Access
Saleh Albahli, Nasir Ayub, Muhammad Shiraz

et al.

Applied Soft Computing, Journal Year: 2021, Volume and Issue: 110, P. 107645 - 107645

Published: June 25, 2021

Language: Английский

Citations

66
Screening of COVID-19 Suspected Subjects Using Multi-Crossover Genetic Algorithm Based Dense Convolutional Neural Network DOI Creative Commons
Dilbag Singh, Vijay Kumar,

Manjit Kaur

et al.

IEEE Access, Journal Year: 2021, Volume and Issue: 9, P. 142566 - 142580

Published: Jan. 1, 2021

Fast and accurate screening of novel coronavirus (COVID-19) suspected subjects plays a vital role in timely quarantine medical care. Deep transfer learning-based models on chest X-ray (CXR) are effective for countering the COVID-19 outbreak. However, an efficient is still huge task due to spatial complexity CXRs. In this paper, dense convolutional neural network (DCov-Net) based learning model proposed using CXR images. A modified multi-crossover genetic algorithm (MMCGA) then tune hyper-parameters DCov-Net. Majority existing diagnosis not interpretable as they do provide any transparency users. Therefore, concept heat-maps used achieve explainability interpretability. MMCGA DCov-Net implemented multiclass dataset that contains four different classes. Experimental results reveal achieves better performance than models. The can be utilized initial with accuracy 99.34 ± 0.51 %.

Language: Английский

Citations

56
Machine Learning-Based Research for COVID-19 Detection, Diagnosis, and Prediction: A Survey DOI Open Access
Yassine Meraihi, Asma Benmessaoud Gabis, Seyedali Mirjalili

et al.

SN Computer Science, Journal Year: 2022, Volume and Issue: 3(4)

Published: May 12, 2022

Language: Английский

Citations

51
COVLIAS 2.0-cXAI: Cloud-Based Explainable Deep Learning System for COVID-19 Lesion Localization in Computed Tomography Scans DOI Creative Commons
Jasjit S. Suri, Sushant Agarwal, Gian Luca Chabert

et al.

Diagnostics, Journal Year: 2022, Volume and Issue: 12(6), P. 1482 - 1482

Published: June 16, 2022

Background: The previous COVID-19 lung diagnosis system lacks both scientific validation and the role of explainable artificial intelligence (AI) for understanding lesion localization. This study presents a cloud-based AI, “COVLIAS 2.0-cXAI” using four kinds class activation maps (CAM) models. Methodology: Our cohort consisted ~6000 CT slices from two sources (Croatia, 80 patients Italy, 15 control patients). COVLIAS 2.0-cXAI design three stages: (i) automated segmentation hybrid deep learning ResNet-UNet model by automatic adjustment Hounsfield units, hyperparameter optimization, parallel distributed training, (ii) classification DenseNet (DN) models (DN-121, DN-169, DN-201), (iii) CAM visualization techniques: gradient-weighted mapping (Grad-CAM), Grad-CAM++, score-weighted (Score-CAM), FasterScore-CAM. was validated trained senior radiologists its stability reliability. Friedman test also performed on scores radiologists. Results: resulted in dice similarity 0.96, Jaccard index 0.93, correlation coefficient 0.99, with figure-of-merit 95.99%, while classifier accuracies DN nets DN-201) were 98%, 99% loss ~0.003, ~0.0025, ~0.002 50 epochs, respectively. mean AUC all 0.99 (p < 0.0001). showed 80% scans alignment (MAI) between heatmaps gold standard, score out five, establishing clinical settings. Conclusions: successfully AI localization scans.

Language: Английский

Citations

50
Deep Transfer Learning Approaches to Predict Glaucoma, Cataract, Choroidal Neovascularization, Diabetic Macular Edema, DRUSEN and Healthy Eyes: An Experimental Review DOI
Yogesh Kumar, Surbhi Gupta

Archives of Computational Methods in Engineering, Journal Year: 2022, Volume and Issue: 30(1), P. 521 - 541

Published: Sept. 4, 2022

Language: Английский

Citations

49
Supervised and weakly supervised deep learning models for COVID-19 CT diagnosis: A systematic review DOI
Haseeb Hassan,

Zhaoyu Ren,

Chengmin Zhou

et al.

Computer Methods and Programs in Biomedicine, Journal Year: 2022, Volume and Issue: 218, P. 106731 - 106731

Published: March 5, 2022

Language: Английский

Citations

40
Diagnosis of Coronavirus Disease From Chest X-Ray Images Using DenseNet-169 Architecture DOI Open Access
Pooja Pradeep Dalvi, Damodar Reddy Edla,

B. Purushothama

et al.

SN Computer Science, Journal Year: 2023, Volume and Issue: 4(3)

Published: Feb. 17, 2023

Language: Английский

Citations

23
Small size CNN (CAS-CNN), and modified MobileNetV2 (CAS-MODMOBNET) to identify cashew nut and fruit diseases DOI
Kamini G. Panchbhai, Madhusudan G. Lanjewar,

Vishant V. Malik

et al.

Multimedia Tools and Applications, Journal Year: 2024, Volume and Issue: unknown

Published: April 2, 2024

Language: Английский

Citations

13