RESUMEN
Background: Pulmonary segments are valuable because they can provide more precise localization and intricate details of lung cancer than lung lobes. With advances in precision therapy, there is an increasing demand for the identification and visualization of pulmonary segments in computed tomography (CT) images to aid in the precise treatment of lung cancer. This study aimed to integrate multiple deep-learning models to accurately segment pulmonary segments in CT images using a bronchial tree (BT)-based approach. Methods: The proposed segmentation method for pulmonary segments using the BT-based approach comprised the following five essential steps: (I) segmentation of the lung using a U-Net (R231) (public access) model; (II) segmentation of the lobes using a V-Net (self-developed) model; (III) segmentation of the airway using a combination of a differential geometric approach method and a BronchiNet (public access) model; (IV) labeling of the BT branches based on anatomical position; and (V) segmentation of the pulmonary segments based on the distance of each voxel to the labeled BT branches. This five-step process was applied to 14 high-resolution breath-hold CT images and compared against manual segmentations for evaluation. Results: For the lung segmentation, the lung mask had a mean dice similarity coefficient (DSC) of 0.98±0.03. For the lobe segmentation, the V-Net model had a mean DSC of 0.94±0.06. For the airway segmentation, the average total length of the segmented airway trees per image scan was 1,902.8±502.1 mm, and the average number of the maximum airway tree generations was 8.5±1.3. For the segmentation of the pulmonary segments, the proposed method had a DSC of 0.73±0.11 and a mean surface distance of 6.1±2.9 mm. Conclusions: This study demonstrated the feasibility of combining multiple deep-learning models for the auxiliary segmentation of pulmonary segments on CT images using a BT-based approach. The results highlighted the potential of the BT-based method for the semi-automatic segmentation of the pulmonary segment.
RESUMEN
BACKGROUND: This study was performed to determine the clinical correlates and long-term prognostic implications of microbleed burden and location in Chinese patients with ischemic stroke. METHODS AND RESULTS: We recruited 1003 predominantly Chinese patients with ischemic stroke who received magnetic resonance imaging at the University of Hong Kong. We determined the clinical correlates of microbleeds and the long-term risks (3126 patient-years of follow-up) of recurrent ischemic stroke and intracerebral hemorrhage (ICH) by microbleed burden (0 versus 1, 2-4, and ≥5) and location, adjusting for age, sex, and vascular risk factors and stratified by antithrombotic use. Microbleeds were present in 450 of 1003 of the study population (119/450 had ≥5, 187/450 had mixed location). Having ≥5 microbleeds was independently associated with prior antiplatelet and anticoagulant use, whereas microbleeds of mixed location were independently associated with hypertension and prior anticoagulant use (all P<0.05). Microbleed burden was associated with an increased risk of ICH (microbleed burden versus no microbleeds: 1 microbleed: multivariate hazard ratio: 0.59 [95% confidence interval, 0.07-5.05]; 2-4 microbleeds: multivariate hazard ratio: 2.14 [95% confidence interval, 0.50-9.12]; ≥5 microbleeds: multivariate hazard ratio: 9.51 [95% confidence interval, 3.25-27.81]; Ptrend<0.0001), but the relationship of microbleed burden and risk of recurrent ischemic stroke was not significant (Ptrend=0.054). Similar findings were noted in the 862 of 1003 patients treated with antiplatelet agents only (ICH: Ptrend<0.0001; ischemic stroke Ptrend=0.096). Multivariate analysis revealed that, independent of vascular risk factors, antithrombotic use, and other neuroimaging markers of small vessel disease, having ≥5 microbleeds (multivariate hazard ratio: 6.08 [95% confidence interval, 1.11-33.21]; P=0.037) was identified as an independent predictor of subsequent ICH, but neither microbleed burden nor location was predictive of recurrent ischemic stroke risk. CONCLUSIONS: In Chinese patients with ischemic stroke, a high burden of cerebral microbleeds was significantly associated with an increased risk of ICH; however, neither microbleed location nor burden was associated with recurrent ischemic stroke risk.