eprintid: 18999 rev_number: 2 eprint_status: archive userid: 1 dir: disk0/00/01/89/99 datestamp: 2024-06-04 14:11:27 lastmod: 2024-06-04 14:11:27 status_changed: 2024-06-04 14:04:36 type: conference_item metadata_visibility: show creators_name: Saleh, B.J. creators_name: Omar, Z. creators_name: Bhateja, V. creators_name: Izhar, L.I. title: Auto-Lesion Segmentation with a Novel Intensity Dark Channel Prior for COVID-19 Detection ispublished: pub keywords: Computerized tomography; Deep neural networks; Diagnosis; Medical imaging; Multilayer neural networks; Network layers; Viruses, Auto segmentation; Classification models; Computed tomography scan; Dark channel priors; Lesion segmentations; Medical imaging techniques; Neural-networks; Novel processing; Processing method; Tomography imaging, COVID-19 note: cited By 0; Conference of 1st International Conference on Electronic and Computer Engineering, ECE 2023 ; Conference Date: 4 July 2023 Through 5 July 2023; Conference Code:196016 abstract: During the COVID-19 pandemic, medical imaging techniques like computed tomography (CT) scans have demonstrated effectiveness in combating the rapid spread of the virus. Therefore, it is crucial to conduct research on computerized models for the detection of COVID-19 using CT imaging. A novel processing method has been developed, utilizing radiomic features, to assist in the CT-based diagnosis of COVID-19. Given the lower specificity of traditional features in distinguishing between different causes of pulmonary diseases, the objective of this study is to develop a CT-based radiomics framework for the differentiation of COVID-19 from other lung diseases. The model is designed to focus on outlining COVID-19 lesions, as traditional features often lack specificity in this aspect. The model categorizes images into three classes: COVID-19, non-COVID-19, or normal. It employs enhancement auto-segmentation principles using intensity dark channel prior (IDCP) and deep neural networks (ALS-IDCP-DNN) within a defined range of analysis thresholds. A publicly available dataset comprising COVID-19, normal, and non-COVID-19 classes was utilized to validate the proposed model's effectiveness. The best performing classification model, Residual Neural Network with 50 layers (Resnet-50), attained an average accuracy, precision, recall, and F1-score of 98.8, 99, 98, and 98 respectively. These results demonstrate the capability of our model to accurately classify COVID-19 images, which could aid radiologists in diagnosing suspected COVID-19 patients. Furthermore, our model's performance surpasses that of more than 10 current state-of-the-art studies conducted on the same dataset. © 2023 Institute of Physics Publishing. All rights reserved. date: 2023 publisher: Institute of Physics official_url: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85182282415&doi=10.1088%2f1742-6596%2f2622%2f1%2f012002&partnerID=40&md5=14c3dacbb86cc92b644ff715f5fc8e59 id_number: 10.1088/1742-6596/2622/1/012002 full_text_status: none publication: Journal of Physics: Conference Series volume: 2622 number: 1 refereed: TRUE issn: 17426588 citation: Saleh, B.J. and Omar, Z. and Bhateja, V. and Izhar, L.I. (2023) Auto-Lesion Segmentation with a Novel Intensity Dark Channel Prior for COVID-19 Detection. In: UNSPECIFIED.