Improved detection of small pulmonary embolism on unenhanced computed tomography using an artificial intelligence-based algorithm – a single centre retrospective study

• Published in: The international journal of cardiovascular imaging 2024-11, Vol.40 (11), p.2293-2304
• Main Authors: Hagen, Florian, Vorberg, Linda, Thamm, Florian, Ditt, Hendrik, Maier, Andreas, Brendel, Jan Michael, Ghibes, Patrick, Bongers, Malte Niklas, Krumm, Patrick, Nikolaou, Konstantin, Horger, Marius
• Format: Article
• Language: English
• Subjects: Adult; Aged; Aged, 80 and over; Algorithms; Angiography; Artificial intelligence; Boxes; Cardiac Imaging; Cardiology; Chest; Computed tomography; Computed Tomography Angiography; Deep Learning; Embolism; Embolisms; Feasibility Studies; Female; Hematocrit; Hemoglobin; Humans; Image contrast; Image enhancement; Imaging; Incidental Findings; Localization; Machine learning; Male; Medical imaging; Medicine; Medicine & Public Health; Middle Aged; Original Paper; Predictive Value of Tests; Pulmonary arteries; Pulmonary artery; Pulmonary Artery - diagnostic imaging; Pulmonary Embolism - diagnostic imaging; Pulmonary embolisms; Radiographic Image Interpretation, Computer-Assisted; Radiology; Reproducibility of Results; Retrospective Studies; Sensitivity analysis; Subgroups
• ISSN: 1875-8312; 1569-5794; 1875-8312; 1573-0743
• DOI: 10.1007/s10554-024-03222-8

To preliminarily verify the feasibility of a deep-learning (DL) artificial intelligence (AI) model to localize pulmonary embolism (PE) on unenhanced chest-CT by comparison with pulmonary artery (PA) CT angiography (CTA). In a monocentric study, we retrospectively reviewed 99 oncological patients (median age in years: 64 (range: 28–92 years); percentage of female: 39.4%) who received unenhanced and contrast-enhanced chest CT examinations in one session between January 2020 and October 2022 and who were diagnosed incidentally with PE. Findings in the unenhanced images were correlated with the contrast-enhanced images, which were considered the gold standard for central, segmental and subsegmental PE. The new algorithm was trained and tested based on the 99 unenhanced chest-CT image data sets. Based on them, candidate boxes, which were output by the model, were post-processed by evaluating whether the predicted box intersects with the patient’s lung segmentation at any position. The AI-based algorithm proved to have an overall sensitivity of 54.5% for central, of 81.9% for segmental and 80.0% for subsegmental PE if taking n  = 20 candidate boxes into account. Depending on the localization of the pulmonary embolism, the detection rate for only one box was: 18.1% central, 34.7% segmental and 0.0% subsegmental. The median volume of the clots differed significantly between the three subgroups and was 846.5 mm 3 (IQR:591.1-964.8) in central, 201.3 mm 3 (IQR:98.3-390.9) in segmental and 110.6 mm 3 (IQR:94.3–128.0) in subsegmental PA ( p