AI based COVID-19 detection using Densenet in CT SCANS -Matlab


In thsi project AI based approach for covid 19 detection on CT Scans. Platform : Matlab Delivery : One Working Day Support : Online Demo ( 2 Hours)

100 in stock

SKU: AI based approach for covid 19 detection Categories: , ,



Artificial Intelligence and Data Science community has contributed to the global response against the new coronavirus, COVID-19. Significant attention has been given to detection and diagnosis tools with rapid diagnostic tools based on X-rays using deep learning being proposed. In this paper we present an evaluation of pretrained CNN model in a transfer learning setup for COVID-19 detection from chest X-ray images. To evaluate the model performance, we have collected 100 chest X-ray images of 70 patients confirmed with COVID-19 from the Github repository. To facilitate deep learning, more data are needed. Thus, we have also collected 1431 additional chest X-ray images confirmed as other pneumonia of 1008 patients from the public ChestX-ray14 dataset. Our initial experimental results show that the model developed here can reliably detect 96.00% COVID-19 cases (sensitivity being 96.00%) and 70.65% non-COVID-19 cases (specificity being 70.65%) when evaluated on 1531 Xray images with two splits of the dataset


COVID-19 is a highly infectious disease, which is caused by the SARS-CoV-2 virus. In March 2020 and after spreading to more than 100 countries and leading to several thousands of cases, the World Health Organization (WHO) officially declared the outbreak of the new coronavirus as a pandemic. Although COVID-19 affects the entire population, young people that have been affected by COVID-19 are in most cases either asymptomatic or present mild symptoms like cough, headache, fatigue and fever. For non-young ages and especially for elders and/or for patients with chronic conditions COVID-19 positive cases may progress to more serious symptoms like diarrhea, dyspnea, pneumonia and death. Young and middle-aged patients being diagnosed with COVID-19 are having significantly lower mortality rates comparing to elder patients with COVID-19 which are more likely to progress to severe disease. With COVID-19 being highly infectious it can easily be spread from asymptomatic to vulnerable population. To stop the spread of COVID-19 virus and to protect vulnerable people many countries worldwide have introduced isolation measures like social distancing and lockdown and in parallel they perform diagnostic tests to key staff and the general population to detect COVID-19 positive cases. The diagnosis of COVID-19 is performed by the reverse-transcription polymerase chain reaction (RT-PCR) test after collection of proper respiratory tract specimen, which is a laboratory-based test for detection and quantification of a targeted DNA molecule. The RT-PCR test can be done only in laboratories that are equipped with the needed infrastructure. Moreover, in some cases the COVID-19 test may need be repeated after one or two days while the cost of the equipment and the required PCR reagents is not low, thus making this diagnostic test expensive and sometimes time consuming, without counting the need for specialized microbiologists to do the tests analyses and the appropriate safety measures (personal protective equipment) that are required to keep laboratory staff safe. Due to these difficulties and restrictions many countries are restricting the performed diagnostic tests for COVID-19 to only suspicious cases and/or vulnerable groups of population as it is not possible to do massive testing of the general population. At the same time governments introduce isolation measures, which are causing socio economical problems, such as increase of the number of domestic abuse cases, reduction of the economic growth [8] and the global trade [9]. Based on the above-mentioned facts, the development of alternative, complementary and low-cost tools for detection of COVID19 positive cases and for decision making support is essential. The recent development of technology in deep learning and medical image processing in combination with big data repositories for COVID-19 could offer support in the global effort against the new coronavirus. Several studies have investigated the potential of using X-ray and/or CT images identify COVID-19. An automatic X-ray COVID-19 lung image classification system was presented in, which first increases the contrast of the image by applying a median filter on it and using threshold based segmentation and support vector machines (SVM) it classifies infected from non-infected lung images. A decompose, transfer and compose convolutional neural networks (CNNs) based method for classification of COVID-19 chest X-ray images was presented in , extracting deep local features of each image and a class-composition layer to refine the classification of the images. Pre-trained CNN models together with SVM classifier to detect the COVID-19 from chest X-ray images were reported in . In a deep convolutional neural network design was proposed tailored for detection of COVID-19 cases from chest X-ray images, named COVID-Net, using a human-machine collaborative design strategy to design it. In a 3D deep learning framework to detect COVID-19 cases from chest X-ray images called COVNet was presented, first extracting the lung region of interest using U-net. An automated CT image analysis tools for detection, quantification, and tracking of COVID-19 cases was presented in , with the method consisting of two sub systems and analysing the CT case at two distinct levels. A deep CNN based transfer learning approach for automatic detection of COVID-19 pneumonia was presented in, using four different popular CNN based deep learning algorithms. In this paper we present an evaluation of several pre-trained deep convolutional neural network (CNN) models on the detection of positive cases the new COVID-19 virus from chest X-ray images. Different experimental setups are tested using two X-ray datasets either separately to each other or by mixing them.


  • To design a CAD (Computer Aided Diagnostic) System for automatic screening and detection of Covid Patients.
  • In this paper we present an evaluation of pretrained CNN model in a transfer learning setup for COVID-19 detection from chest X-ray images.
  • System should be Self sustained without Doctor Intervention.
  • Should have More accuracy and Precision.




  • Detect in intial stage
  • High accuracy
  • Low complexity


  • Biomedical
  • Medical Image Testability


  • MATLAB 2021a


CT scans are promising in providing accurate, fast, and cheap screening and testing of COVID-19. In this paper, we build a publicly available COVID-CT dataset, containing 275 CT scans that are positive for COVID-19, to foster the research and development of deep learning methods which predict whether a person is affected with COVID-19 by analyzing his/her CTs. We train a deep convolutional neural network on this dataset and achieve an F1 of 0.85 which is a promising performance but yet to be further improved.

Additional information

Weight 0.000000 kg


There are no reviews yet.

Be the first to review “AI based COVID-19 detection using Densenet in CT SCANS -Matlab”

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.