Enhancing Pulmonary Embolism Detection in COVID-19 Patients Through Advanced Deep Learning Techniques
Studies in Health Technology and Informatics · 22.08.2024
DOI: 10.3233/shti240622 ↗Kurz gefasst
Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, erschienen am 22.08.2024. Verfasst von Georgios Feretzakis und 10 weiteren Autor:innen. Beteiligte Einrichtung: School of Science and Technology, Hellenic Open University, Patras, Greece. Hauptthemen laut MEDLINE: Pulmonary Embolism, COVID-19, Deep Learning, Computed Tomography Angiography. Die Arbeit wurde bisher 6-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
The intersection of COVID-19 and pulmonary embolism (PE) has posed unprecedented challenges in medical diagnostics. The critical nature of PE and its increased incidence during the pandemic underline the need for improved detection methods. This study evaluates the effectiveness of advanced deep learning techniques in enhancing PE detection in post-COVID-19 patients through Computed Tomography Pulmonary Angiography (CTPA) scans. Using a dataset of 746 anonymized CTPA images from 25 patients, we fine-tuned the state-of-the-art Ultralytics YOLOv8 object detection model, which was trained on 676 images with 1,517 annotated bounding boxes and validated on 70 images with 108 bounding boxes. After 200 epochs of training, which lasted approximately 1.021 hours, the YOLOv8 model demonstrated significant diagnostic proficiency, achieving a mean Average Precision (mAP) of 0.683 at an IoU threshold of 0.50 and a mAP of 0.246 at the IoU range of 0.50:0.95 in the validation dataset. Notably, the model reached a maximum precision of 0.85949 and a maximum recall of 0.81481, though these metrics were observed in separate epochs. These findings emphasize the model’s potential for high diagnostic accuracy and offer a promising direction for deploying AI tools in clinical settings, significantly contributing to healthcare innovation and patient care post-pandemic.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Science and Technology, Hellenic Open University, Patras, Greece.
- Department of Quality Control, Research and Continuing Education, Sismanogleio General Hospital, 15126 Marousi, Greece.
- Department of Radiology, Sismanogleio General Hospital, 15126 Marousi, Greece.
- Athena-Research and Innovation Center in Information, Communication and Knowledge Technologies, Xanthi, Greece.
- IT department, Sismanogleio General Hospital, 15126 Marousi, Greece.
- Intensive Care Unit, Sismanogleio General Hospital, 15126 Marousi, Greece.
Zitieren
APA
Feretzakis, G., Dalamarinis, K., Kalles, D., Kiourt, C., Pantos, G., Papadopoulos, I., Kouris, S., Verykios, V. S., Ioannakis, G., Loupelis, E., & Sakagianni, A. (2024). Enhancing Pulmonary Embolism Detection in COVID-19 Patients Through Advanced Deep Learning Techniques. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti240622
Vancouver
Feretzakis G, Dalamarinis K, Kalles D, Kiourt C, Pantos G, Papadopoulos I, et al. Enhancing Pulmonary Embolism Detection in COVID-19 Patients Through Advanced Deep Learning Techniques. Studies in Health Technology and Informatics. 2024. doi:10.3233/shti240622
BibTeX
@article{Feretzakis2024,
author = {Feretzakis, Georgios and Dalamarinis, Konstantinos and Kalles, Dimitris and Kiourt, Chairi and Pantos, Georgios and Papadopoulos, Ioannis and Kouris, Spyros and Verykios, Vassilios S and Ioannakis, George and Loupelis, Evangelos and Sakagianni, Aikaterini},
title = {Enhancing Pulmonary Embolism Detection in COVID-19 Patients Through Advanced Deep Learning Techniques},
journal = {Studies in Health Technology and Informatics},
year = {2024},
doi = {10.3233/shti240622}
}
EUVIMED