Tools
Tools
Anand, Abhijeet (2022) Automated CAD System for Classification of Chest X-Rays using Xception Model. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (1MB) | Preview |
Preview |
PDF (Configuration manual)
Download (1MB) | Preview |
Abstract
WHO declared the Novel Cornoavirus a pandemic, on 11th March 2020 and it has continued to take a toll on well-being and health of people worldwide. An important step towards combating Covid-19 is early diagnosis and treatment of the infected patients, analysing the radiological images being one of the primary approaches. The author of this paper has designed an Automated CAD system to classify the Chest X-ray in to multiple classes of Covid-19, Pneumonia and Normal using the Deep learning approach. The dataset is taken from the Kaggle has train and test folders with more than 6432 images in it. This paper proposes Xception model with transfer learning to detect the Covid-19 with an accuracy of (training accuracy 94% and validation accuracy 92%). It also gives a high precision of 90.6%, recall of 90.5% and the F-1 score of 89.9%. The best model was saved as .h5 file and deployed using the flask in back-end on web application. Thus, the model proposed in this paper can be used for efficient and quicker diagnosis and treatement of Covid-19 patients which in turn reduces the pressure on the healthcare system and also strengthen the medical infrastructure.
| Item Type: | Thesis (Masters) |
|---|---|
| Uncontrolled Keywords: | Covid-19; Convolutional Neural Network (CNN); Xception; Confusion Matrix |
| Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science R Medicine > Healthcare Industry Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning |
| Divisions: | School of Computing > Master of Science in Data Analytics |
| Depositing User: | Tamara Malone |
| Date Deposited: | 17 Jan 2023 16:28 |
| Last Modified: | 07 Mar 2023 11:26 |
| URI: | https://norma.ncirl.ie/id/eprint/6070 |
Actions (login required)
 |
View Item |