The 2D segmentation U-Net model detected pulmonary embolism on CTPA scans with a sensitivity of 0.80, specificity of 0.74, and an AUROC of 0.85 at the scan level.
Observational (n=251)
No
Does a deep learning U-Net model accurately detect pulmonary embolism on computed tomographic pulmonary angiography compared to expert radiologists?
A deep learning U-Net model demonstrated high sensitivity and accuracy for the automated detection of pulmonary embolism on CTPA, potentially aiding radiologists in rapid triage and reducing missed findings.
BACKGROUND: Computed tomographic pulmonary angiography (CTPA) is the diagnostic standard for confirming pulmonary embolism (PE). Since PE is a life-threatening condition, early diagnosis and treatment are critical to avoid PE-associated morbidity and mortality. However, PE remains subject to misdiagnosis. METHODS: We retrospectively identified 251 CTPAs performed at a tertiary care hospital between January 2018 to January 2021. The scans were classified as positive (n = 55) and negative (n = 196) for PE based on the annotations made by board-certified radiologists. A fully anonymized CT slice served as input for the detection of PE by the 2D segmentation model comprising U-Net architecture with Xception encoder. The diagnostic performance of the model was calculated at both the scan and the slice levels. RESULTS: The model correctly identified 44 out of 55 scans as positive for PE and 146 out of 196 scans as negative for PE with a sensitivity of 0.80 95% CI 0.68, 0.89, a specificity of 0.74 95% CI 0.68, 0.80, and an accuracy of 0.76 95% CI 0.70, 0.81. On slice level, 4817 out of 5183 slices were marked as positive for the presence of emboli with a specificity of 0.89 95% CI 0.88, 0.89, a sensitivity of 0.93 95% CI 0.92, 0.94, and an accuracy of 0.89 95% CI 0.887, 0.890. The model also achieved an AUROC of 0.85 0.78, 0.90 and 0.94 0.936, 0.941 at scan level and slice level, respectively for the detection of PE. CONCLUSION: The development of an AI model and its use for the identification of pulmonary embolism will support healthcare workers by reducing the rate of missed findings and minimizing the time required to screen the scans.
Ajmera et al. (Fri,) conducted a observational in Pulmonary embolism (n=251). 2D segmentation U-Net model (DxPE AI Screen) vs. Board-certified radiologists' annotations was evaluated on Scan-level sensitivity for pulmonary embolism detection (95% CI 0.68-0.89). The 2D segmentation U-Net model detected pulmonary embolism on CTPA scans with a sensitivity of 0.80, specificity of 0.74, and an AUROC of 0.85 at the scan level.