Identifying COVID-19-Infected Segments in Lung CT Scan Through Two Innovative Artificial Intelligence-Based Transformer Models.
Introduction: Automatic systems based on Artificial intelligence (AI) algorithms have made significant advancements across various domains, most notably in the field of medicine. This study introduces a novel approach for identifying COVID-19-infected regions in lung computed tomography (CT) scan th...
| Publicado en: | Archives of Academic Emergency Medicine Vol. 13; no. 1; pp. 1 - 11 |
|---|---|
| Autores principales: | , |
| Formato: | algorithm diagnostic images research tables/charts Journal Article |
| Publicado: |
Shahid Beheshti University of Medical Sciences
2025
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=190500675&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 190500675 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 26454904 MFMK jtl: Archives of Academic Emergency Medicine issn: 26454904 maglogo: N pubinfo: dt: 2025 vid: 13 iid: 1 pid: 87963 pub: Shahid Beheshti University of Medical Sciences artinfo: ui: 190500675 190500675 190500675 10.22037/aaemj.v13i1.2515 190500675 ppf: 1 ppct: 10 formats: fmt: @attributes: type: P tig: atl: Identifying COVID-19-Infected Segments in Lung CT Scan Through Two Innovative Artificial Intelligence-Based Transformer Models. aug: au: Momeni Pour, Zeinab Beheshti Shirazi, Ali Asghar affil: Department of Electrical Engineering, Iran University of Science and Technology, Tehran, Iran. sug: subj: COVID-19 Diagnosis Lung Radiography Tomography, X-Ray Computed Radiography, Thoracic Image Interpretation, Computer Assisted Image Processing, Computer Assisted Automation Deep Learning Sensitivity and Specificity Evaluation Human Comparative Studies Descriptive Statistics Data Analysis Software Convolutional Neural Networks False Negative Results False Positive Results Artificial Intelligence COVID-19 Testing Prediction Models Sample Size Determination COVID-19 Radiography Diagnosis, Computer Assisted Early Diagnosis Prediction Algorithms ab: Introduction: Automatic systems based on Artificial intelligence (AI) algorithms have made significant advancements across various domains, most notably in the field of medicine. This study introduces a novel approach for identifying COVID-19-infected regions in lung computed tomography (CT) scan through the development of two innovative models. Methods: In this study we used the Squeeze and Excitation based UNet TRansformers (SE-UNETR) and the Squeeze and Excitation based High-Quality Resolution Swin Transformer Network (SE-HQRSTNet), to develop two three-dimensional segmentation networks for identifying COVID-19-infected regions in lung CT scan. The SE-UNETR model is structured as a 3D UNet architecture with an encoder component built on Vision Transformers (ViTs). This model processes 3D patches directly as input and learns sequential representations of the volumetric data. The encoder connects to the decoder using skip connections, ultimately producing the final semantic segmentation output. Conversely, the SE-HQRSTNet model incorporates High-Resolution Networks (HRNet), Swin Transformer modules, and Squeeze and Excitation (SE) blocks. This architecture is designed to generate features at multiple resolutions, utilizing Multi-Resolution Feature Fusion (MRFF) blocks to effectively integrate semantic features across various scales. The proposed networks were evaluated using a 5-fold cross-validation methodology, along with data augmentation techniques, applied to the COVID-19-CT-Seg and MosMed datasets. Results: Our experimental results demonstrate that the Dice value for the infection masks within the COVID-19-CT-Seg dataset improved by 3.81% and 4.84% with the SEUNETR and SE-HQRSTNet models, respectively, compared to previously reported work. Furthermore, the Dice value for the MosMed dataset increased from 66.8% to 69.35% and 70.89% for the SE-UNETR and SE-HQRSTNet models, respectively. Conclusion: These improvements indicate that the proposed models exhibit superior efficiency and performance relative to existing methodologies. pubtype: Academic Journal doctype: algorithm diagnostic images research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|