Automated LVO detection and collateral scoring on CTA using a 3D self-configuring object detection network: a multi-center study.

The use of deep learning (DL) techniques for automated diagnosis of large vessel occlusion (LVO) and collateral scoring on computed tomography angiography (CTA) is gaining attention. In this study, a state-of-the-art self-configuring object detection network called nnDetection was used to detect LVO and assess collateralization on CTA scans using a multi-task 3D object detection approach. The model was trained on single-phase CTA scans of 2425 patients at five centers, and its performance was evaluated on an external test set of 345 patients from another center. Ground-truth labels for the presence of LVO and collateral scores were provided by three radiologists. The nnDetection model achieved a diagnostic accuracy of 98.26% (95% CI 96.25-99.36%) in identifying LVO, correctly classifying 339 out of 345 CTA scans in the external test set. The DL-based collateral scores had a kappa of 0.80, indicating good agreement with the consensus of the radiologists. These results demonstrate that the self-configuring 3D nnDetection model can accurately detect LVO on single-phase CTA scans and provide semi-quantitative collateral scores, offering a comprehensive approach for automated stroke diagnostics in patients with LVO.

Investigation of the need for computed tomography pulmonary angiography in the decision to discontinue treatment for pulmonary thromboembolism.

BACKGROUND: Acute pulmonary thromboembolism (PTE) is an important cause of morbidity and mortality that can reduce quality of life due to long-term complications during and after treatment discontinuation. OBJECTIVES: The aim of this study was to evaluate patients for these complications before discontinuing treatment and determine the necessity of computed tomography pulmonary angiography (CTPA) imaging. METHODS: This retrospective study included 116 patients over the age of 18 who received anticoagulant treatment for at least 3 months and presented for treatment discontinuation to the Atatürk University Research Hospital Chest Diseases Outpatient Clinic between January 2015 and September 2019. RESULTS: CTPA performed at treatment discontinuation showed complete thrombus resolution with treatment in 73 patients (62.9%). High pulmonary artery obstruction index (PAOI) at diagnosis was statistically associated with findings of residual or chronic thrombus on CTPA at treatment discontinuation (p = 0.001). In the differentiation of patients with residual/chronic thrombus and those with thrombus resolution, D-dimer at a cut-off value of 474 µg/L had 60% sensitivity and 70% specificity. At a cut-off value of 35.5 mmHg, mean pulmonary artery pressure on echocardiography had sensitivity and specificity of 72% and 77%, respectively. At a cut-off of 23.75, PAOI had sensitivity and specificity of 93% and 69%, respectively. CONCLUSION: In addition to physical examination findings, D-dimer and echocardiography were guiding parameters in the evaluation of treatment discontinuation and thrombus resolution in patients presenting to the outpatient clinic for discontinuation of treatment for acute PTE. PAOI at diagnosis may be another important guiding parameter in addition to these examinations.

Multiple Unusual Vascular Anomalies Accompanying Aortic Coarctation / Múltiples anomalías vasculares infrecuentes en la coartación aórtica

No disponible