Autor: |
Feretzakis G; School of Science and Technology, Hellenic Open University, Patras, Greece.; Department of Quality Control, Research and Continuing Education, Sismanogleio General Hospital, 15126 Marousi, Greece., Dalamarinis K; Department of Radiology, Sismanogleio General Hospital, 15126 Marousi, Greece., Kalles D; School of Science and Technology, Hellenic Open University, Patras, Greece., Kiourt C; Athena-Research and Innovation Center in Information, Communication and Knowledge Technologies, Xanthi, Greece., Pantos G; Department of Radiology, Sismanogleio General Hospital, 15126 Marousi, Greece., Papadopoulos I; Department of Radiology, Sismanogleio General Hospital, 15126 Marousi, Greece., Kouris S; Department of Radiology, Sismanogleio General Hospital, 15126 Marousi, Greece., Verykios VS; School of Science and Technology, Hellenic Open University, Patras, Greece., Ioannakis G; Athena-Research and Innovation Center in Information, Communication and Knowledge Technologies, Xanthi, Greece., Loupelis E; IT department, Sismanogleio General Hospital, 15126 Marousi, Greece., Sakagianni A; Intensive Care Unit, Sismanogleio General Hospital, 15126 Marousi, Greece. |
Abstrakt: |
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. |