Search

Background: The extended Thrombolysis in Cerebral Infarction (eTICI) score is used in digital subtraction angiography (DSA) to quantify reperfusion grade in patients with an ischemic stroke who undergo endovascular thrombectomy (EVT). A previously developed automatic TICI score (autoTICI), which quantifies the ratio of reperfused pixels after EVT, demonstrates good correlation with eTICI., Objective: To evaluate the autoTICI model in a large multicenter registry of patients with an ischemic stroke, investigate the association with visual eTICI, and compare prediction of functional outcome between autoTICI and eTICI., Methods: Patients in the MR CLEAN Registry with an internal carotid artery, M1, and M2 occlusion were selected if both anteroposterior and lateral views were present in pre- and post-EVT DSA scans. The autoTICI score was compared with eTICI in predicting favorable functional outcome (modified Rankin Scale score 0-2), using area under the receiver operating characteristics curve (AUC) with a multivariable logistic regression model including known prognostic characteristics., Results: In total 421 of 3637 patients were included. AutoTICI was significantly associated with eTICI non-linearly (below 70% cOR=2.3 (95% CI 2.1 to 2.5), above 70% cOR=1.6 (95% CI 1.6 to 1.7) per 10% increment). The AUC of the model predicting favorable functional outcome was similar for autoTICI and eTICI (0.86, 95% CI 0.82 to 0.92 vs 0.86, 95% CI 0.83 to 0.90, P=0.73) and was higher than for a model with prognostic patient characteristics alone (0.86 vs 0.84, P=0.01)., Conclusion: Automatic quantitative assessment of reperfusion after EVT is associated with eTICI, and prediction of functional outcome is similar to that with visual eTICI. Therefore, autoTICI could be used as an alternative or additional review for visual reperfusion assessment to facilitate reproducible and uniform reporting., Competing Interests: Competing interests: Erasmus MC received funds from Stryker® by DD, AvdL, and Bracco Imaging® by DD. Amsterdam UMC received funds from Stryker® for consultations by CM, YR and OB. MUMC received funds from Stryker® and Codman® for consultations by WZ., (© Author(s) (or their employer(s)) 2024. No commercial re-use. See rights and permissions. Published by BMJ.)

Background: Digital subtraction angiography (DSA) devices are commonly used in numerous interventional procedures across various parts of the body, necessitating multiple scans per procedure, which results in significant radiation exposure for both doctors and patients. Inspired by generative artificial intelligence techniques, this study proposes GenDSA, a large-scale pretrained multi-frame generative model-based real-time and low-dose DSA imaging system., Methods: GenDSA was developed to generate 1-, 2-, and 3-frame sequences following each real frame. A large-scale dataset comprising ∼3 million DSA images from 27,117 patients across 10 hospitals was constructed to pretrain, fine-tune, and validate GenDSA. Two other datasets from 25 hospitals were used for evaluation. Objective evaluations included SSIM and PSNR. Five interventional radiologists independently assessed the quality of the generated frames using the Likert scale and visual Turing test. Scoring consistency among the radiologists was measured using the Kendall coefficient of concordance (W). The Fleiss' kappa values were used for inter-rater agreement analysis for visual Turing tests., Findings: Using only one-third of the clinical radiation dose, videos generated by GenDSA were perfectly consistent with real videos. Objective evaluations demonstrated that GenDSA's performance (PSNR = 36.83, SSIM = 0.911, generation time = 0.07 s/frame) surpassed state-of-the-art algorithms. Subjective ratings and statistical results from five doctors indicated no significant difference between real and generated videos. Furthermore, the generated videos were comparable to real videos in overall quality (4.905 vs. 4.935) and lesion assessment (4.825 vs. 4.860)., Conclusions: With clear clinical and translational values, the developed GenDSA can significantly reduce radiation damage to both doctors and patients during DSA-guided procedures., Funding: This study was supported by the National Key R&D Program and the National Natural Science Foundation of China., Competing Interests: Declaration of interests The authors declare no competing interests., (Copyright © 2024 Elsevier Inc. All rights reserved.)

Deep convolutional neural networks for image segmentation do not learn the label structure explicitly and may produce segmentations with an incorrect structure, e.g., with disconnected cylindrical structures in the segmentation of tree-like structures such as airways or blood vessels. In this paper, we propose a novel label refinement method to correct such errors from an initial segmentation, implicitly incorporating information about label structure. This method features two novel parts: (1) a model that generates synthetic structural errors, and (2) a label appearance simulation network that produces segmentations with synthetic errors that are similar in appearance to the real initial segmentations. Using these segmentations with synthetic errors and the original images, the label refinement network is trained to correct errors and improve the initial segmentations. The proposed method is validated on two segmentation tasks: airway segmentation from chest computed tomography (CT) scans and brain vessel segmentation from 3D CT angiography (CTA) images of the brain. In both applications, our method significantly outperformed a standard 3D U-Net, four previous label refinement methods, and a U-Net trained with a loss tailored for tubular structures. Improvements are even larger when additional unlabeled data is used for model training. In an ablation study, we demonstrate the value of the different components of the proposed method., Competing Interests: Declaration of competing interest The authors declare the following financial interests/personal relationships which may be considered as potential competing interests: Shuai Chen reports financial support was provided by Chinese Scholarship Council. Shuai Chen reports a relationship with Erasmus Medical Center that includes: employment. Antonio Garcia-Uceda reports a relationship with Erasmus Medical Center that includes: employment. Jiahang Su reports a relationship with Erasmus Medical Center that includes: employment. Gijs van Tulder reports a relationship with Radboud University that includes: employment. Lennard Wolf reports a relationship with Erasmus Medical Center that includes: employment. Theo van Walsum reports a relationship with Erasmus Medical Center that includes: employment. Marleen de Bruijne reports a relationship with Erasmus Medical Center that includes: employment., (Copyright © 2024 The Authors. Published by Elsevier B.V. All rights reserved.)