COVID 19 Diagnosis Analysis using Transfer Learning

• URL: http://arxiv.org/abs/2503.12642v2
• Date: Sun, 23 Mar 2025 17:38:40 GMT
• Title: COVID 19 Diagnosis Analysis using Transfer Learning
• Authors: Anjali Dharmik,
• Abstract summary: This study explores the use of deep learning for a rapid and accurate diagnosis of COVID-19.<n>We propose an automated detection system leveraging state-of-the-art convolutional neural networks (CNNs), including updated versions of VGG16, VGG19, and ResNet50.<n>Our results demonstrate that the optimized ResNet50 model achieves the highest classification performance, with 97.77% accuracy, 100% sensitivity, 93.33% specificity, and a 98.0% F1-score.
• Score: 0.0
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Coronaviruses, including SARS-CoV-2, are responsible for COVID-19, a highly transmissible disease that emerged in December 2019 in Wuhan, China. During the past five years, significant advancements have been made in understanding and mitigating the virus. Although the initial outbreak led to global health crises, improved vaccination strategies, antiviral treatments, and AI-driven diagnostic tools have contributed to better disease management. However, COVID-19 continues to pose risks, particularly for immuno-compromised individuals and those with pre-existing conditions. This study explores the use of deep learning for a rapid and accurate diagnosis of COVID-19, addressing ongoing challenges in healthcare infrastructure and testing accessibility. We propose an enhanced automated detection system leveraging state-of-the-art convolutional neural networks (CNNs), including updated versions of VGG16, VGG19, and ResNet50, to classify COVID-19 infections from chest radiographs and computerized tomography (CT) scans. Our results, based on an expanded dataset of over 6000 medical images, demonstrate that the optimized ResNet50 model achieves the highest classification performance, with 97.77% accuracy, 100% sensitivity, 93.33% specificity, and a 98.0% F1-score. These findings reinforce the potential of AI-assisted diagnostic tools in improving early detection and pandemic preparedness.

Related papers

• Evaluating Convolutional Neural Networks for COVID-19 classification in chest X-ray images [0.31457219084519006]
  The effective screening of infected patients is a critical step to struggle with COVID-19.<n>Recent researches using chest X-ray images suggest they include relevant information about the COVID-19 virus.<n>This paper presents a method for automatic COVID-19 detection using chest Xray images through four convolutional neural networks.
  arXiv  Detail & Related papers  (2024-12-26T22:05:30Z)
• COVID-19 Probability Prediction Using Machine Learning: An Infectious Approach [0.0]
  This study delves into the application of advanced machine learning (ML) techniques for predicting COVID-19 infection probability. We conducted a rigorous investigation into the efficacy of various ML models, including XGBoost, LGBM, AdaBoost, Logistic Regression, Decision Tree, RandomForest, CatBoost, KNN, and Deep Neural Networks (DNN) Our findings reveal that Deep Neural Networks (DNN) emerge as the top-performing model, exhibiting superior accuracy and recall metrics.
  arXiv  Detail & Related papers  (2024-08-23T05:15:24Z)
• COVID-Net USPro: An Open-Source Explainable Few-Shot Deep Prototypical Network to Monitor and Detect COVID-19 Infection from Point-of-Care Ultrasound Images [66.63200823918429]
  COVID-Net USPro monitors and detects COVID-19 positive cases with high precision and recall from minimal ultrasound images. The network achieves 99.65% overall accuracy, 99.7% recall and 99.67% precision for COVID-19 positive cases when trained with only 5 shots.
  arXiv  Detail & Related papers  (2023-01-04T16:05:51Z)
• COVID-19 Disease Identification on Chest-CT images using CNN and VGG16 [0.0]
  COVID-19 is an infectious disease caused by a virus originating in Wuhan, China, in December 2019. In the earlier stage, medical organizations were dazzled because there were no proper health aids or medicine to detect a COVID-19. This study presents a Convolutional Neural Network (CNN) and VGG16-based model for automated COVID-19 identification on chest CT images.
  arXiv  Detail & Related papers  (2022-07-09T07:20:15Z)
• Comparative Analysis of State-of-the-Art Deep Learning Models for Detecting COVID-19 Lung Infection from Chest X-Ray Images [3.829821362301428]
  This paper evaluates the applicability of the recent top ten state-of-the-art Deep Convolutional Neural Networks (CNNs) for automatically detecting COVID-19 infection using chest X-ray images. Our trained models MobileNet, EfficentNet, and InceptionV3 achieved a classification average accuracy of 95%, 95%, and 94%, respectively.
  arXiv  Detail & Related papers  (2022-07-01T02:23:23Z)
• COVID-19 Detection using Transfer Learning with Convolutional Neural Network [0.0]
  COVID-19 is a fatal infectious disease, first recognized in December 2019 in Wuhan, Hubei, China. In this study, a Transfer learning strategy (CNN) for detecting COVID-19 infection from CT images has been proposed. In the proposed model, a multilayer Convolutional neural network (CNN) with Transfer learning model Inception V3 has been designed.
  arXiv  Detail & Related papers  (2022-06-17T05:30:14Z)
• The Report on China-Spain Joint Clinical Testing for Rapid COVID-19 Risk Screening by Eye-region Manifestations [59.48245489413308]
  We developed and tested a COVID-19 rapid prescreening model using the eye-region images captured in China and Spain with cellphone cameras. The performance was measured using area under receiver-operating-characteristic curve (AUC), sensitivity, specificity, accuracy, and F1.
  arXiv  Detail & Related papers  (2021-09-18T02:28:01Z)
• COVID-Net US: A Tailored, Highly Efficient, Self-Attention Deep Convolutional Neural Network Design for Detection of COVID-19 Patient Cases from Point-of-care Ultrasound Imaging [101.27276001592101]
  We introduce COVID-Net US, a highly efficient, self-attention deep convolutional neural network design tailored for COVID-19 screening from lung POCUS images. Experimental results show that the proposed COVID-Net US can achieve an AUC of over 0.98 while achieving 353X lower architectural complexity, 62X lower computational complexity, and 14.3X faster inference times on a Raspberry Pi. To advocate affordable healthcare and artificial intelligence for resource-constrained environments, we have made COVID-Net US open source and publicly available as part of the COVID-Net open source initiative.
  arXiv  Detail & Related papers  (2021-08-05T16:47:33Z)
• Dual-Attention Residual Network for Automatic Diagnosis of COVID-19 [6.941255691176647]
  We propose a novel residual network to automatically identify COVID-19 from other common pneumonia and normal people using CT images. Our method can differentiate COVID-19 from the other two classes with 94.7% accuracy, 93.73% sensitivity, 98.28% specificity, 95.26% F1-score, and an area under the receiver operating characteristic curve (AUC) of 0.99.
  arXiv  Detail & Related papers  (2021-05-14T11:59:47Z)
• COVID-19 Detection from Chest X-ray Images using Imprinted Weights Approach [67.05664774727208]
  Chest radiography is an alternative screening method for the COVID-19. Computer-aided diagnosis (CAD) has proven to be a viable solution at low cost and with fast speed. To address this challenge, we propose the use of a low-shot learning approach named imprinted weights.
  arXiv  Detail & Related papers  (2021-05-04T19:01:40Z)
• Dual-Consistency Semi-Supervised Learning with Uncertainty Quantification for COVID-19 Lesion Segmentation from CT Images [49.1861463923357]
  We propose an uncertainty-guided dual-consistency learning network (UDC-Net) for semi-supervised COVID-19 lesion segmentation from CT images. Our proposed UDC-Net improves the fully supervised method by 6.3% in Dice and outperforms other competitive semi-supervised approaches by significant margins.
  arXiv  Detail & Related papers  (2021-04-07T16:23:35Z)
• COVIDx-US -- An open-access benchmark dataset of ultrasound imaging data for AI-driven COVID-19 analytics [116.6248556979572]
  COVIDx-US is an open-access benchmark dataset of COVID-19 related ultrasound imaging data. It consists of 93 lung ultrasound videos and 10,774 processed images of patients infected with SARS-CoV-2 pneumonia, non-SARS-CoV-2 pneumonia, as well as healthy control cases.
  arXiv  Detail & Related papers  (2021-03-18T03:31:33Z)
• Deep Neural Networks for COVID-19 Detection and Diagnosis using Images and Acoustic-based Techniques: A Recent Review [0.36550217261503676]
  The new coronavirus disease (COVID-19) has been declared a pandemic since March 2020 by the World Health Organization. It consists of an emerging viral infection with respiratory tropism that could develop atypical pneumonia. Experts emphasize the importance of early detection of those who have the COVID-19 virus.
  arXiv  Detail & Related papers  (2020-12-10T19:52:12Z)
• Classification of COVID-19 in CT Scans using Multi-Source Transfer Learning [91.3755431537592]
  We propose the use of Multi-Source Transfer Learning to improve upon traditional Transfer Learning for the classification of COVID-19 from CT scans. With our multi-source fine-tuning approach, our models outperformed baseline models fine-tuned with ImageNet. Our best performing model was able to achieve an accuracy of 0.893 and a Recall score of 0.897, outperforming its baseline Recall score by 9.3%.
  arXiv  Detail & Related papers  (2020-09-22T11:53:06Z)
• A New Screening Method for COVID-19 based on Ocular Feature Recognition by Machine Learning Tools [66.20818586629278]
  Coronavirus disease 2019 (COVID-19) has affected several million people. New screening method of analyzing the eye-region images, captured by common CCD and CMOS cameras, could reliably make a rapid risk screening of COVID-19.
  arXiv  Detail & Related papers  (2020-09-04T00:50:27Z)
• CovidDeep: SARS-CoV-2/COVID-19 Test Based on Wearable Medical Sensors and Efficient Neural Networks [51.589769497681175]
  The novel coronavirus (SARS-CoV-2) has led to a pandemic. The current testing regime based on Reverse Transcription-Polymerase Chain Reaction for SARS-CoV-2 has been unable to keep up with testing demands. We propose a framework called CovidDeep that combines efficient DNNs with commercially available WMSs for pervasive testing of the virus.
  arXiv  Detail & Related papers  (2020-07-20T21:47:28Z)
• Dual-Sampling Attention Network for Diagnosis of COVID-19 from Community Acquired Pneumonia [46.521323145636906]
  We develop a dual-sampling attention network to automatically diagnose COVID-19 from the community acquired pneumonia (CAP) in chest computed tomography (CT) In particular, we propose a novel online attention module with a 3D convolutional network (CNN) to focus on the infection regions in lungs when making decisions of diagnoses. Our algorithm can identify the COVID-19 images with the area under the receiver operating characteristic curve (AUC) value of 0.944, accuracy of 87.5%, sensitivity of 86.9%, specificity of 90.1%, and F1-score of 82.0%.
  arXiv  Detail & Related papers  (2020-05-06T09:56:51Z)
• Automatic Detection of Coronavirus Disease (COVID-19) in X-ray and CT Images: A Machine Learning-Based Approach [2.488407849738164]
  COVID-19 is highly transmittable and pathogenic with no clinically approved antiviral drug or vaccine available for treatment. Medical imaging is not currently recommended in Canada for primary diagnosis of COVID-19. In this study, we compare popular deep learning-based feature extraction frameworks for automatic COVID-19 classification.
  arXiv  Detail & Related papers  (2020-04-22T15:34:45Z)
• JCS: An Explainable COVID-19 Diagnosis System by Joint Classification and Segmentation [95.57532063232198]
  coronavirus disease 2019 (COVID-19) has caused a pandemic disease in over 200 countries. To control the infection, identifying and separating the infected people is the most crucial step. This paper develops a novel Joint Classification and (JCS) system to perform real-time and explainable COVID-19 chest CT diagnosis.
  arXiv  Detail & Related papers  (2020-04-15T12:30:40Z)
• COVID-CAPS: A Capsule Network-based Framework for Identification of COVID-19 cases from X-ray Images [34.93885932923011]
  Coronavirus disease (COVID-19) has abruptly and undoubtedly changed the world as we know it at the end of the 2nd decade of the 21st century. Early diagnosis of COVID-19 enables health care professionals and government authorities to break the chain of transition and flatten the epidemic curve. There has been an urgent surge of interest to develop Deep Neural Network (DNN)-based diagnosis solutions, mainly based on Convolutional Neural Networks (CNNs) The paper presents an alternative modeling framework based on Capsule Networks, referred to as the COVID-CAPS, being capable of handling small datasets.
  arXiv  Detail & Related papers  (2020-04-06T14:20:47Z)
• Mapping the Landscape of Artificial Intelligence Applications against COVID-19 [59.30734371401316]
  COVID-19, the disease caused by the SARS-CoV-2 virus, has been declared a pandemic by the World Health Organization. We present an overview of recent studies using Machine Learning and, more broadly, Artificial Intelligence to tackle many aspects of the COVID-19 crisis.
  arXiv  Detail & Related papers  (2020-03-25T12:30:33Z)
• Automatic Detection of Coronavirus Disease (COVID-19) Using X-ray Images and Deep Convolutional Neural Networks [0.0]
  coronavirus disease (COVID-19), with a starting point in China, has spread rapidly among people living in other countries. There are a limited number of COVID-19 test kits available in hospitals due to the increasing cases daily. Five pre-trained convolutional neural network based models have been proposed for the detection of coronavirus pneumonia infected patient using chest X-ray radiographs.
  arXiv  Detail & Related papers  (2020-03-24T13:50:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.