Search

This study aimed to (1) replicate a deep-learning-based model for cerebral aneurysm segmentation in TOF-MRAs, (2) improve the approach by testing various fully automatic pre-processing pipelines, and (3) rigorously validate the model's transferability on independent, external test-datasets. A convolutional neural network was trained on 235 TOF-MRAs acquired on local scanners from a single vendor to segment intracranial aneurysms. Different pre-processing pipelines including bias field correction, resampling, cropping and intensity-normalization were compared regarding their effect on model performance. The models were tested on independent, external same-vendor and other-vendor test-datasets, each comprised of 70 TOF-MRAs, including patients with and without aneurysms. The best-performing model achieved excellent results on the external same-vendor test-dataset, surpassing the results of the previous publication with an improved sensitivity (0.97 vs. ~ 0.86), a higher Dice score coefficient (DSC, 0.60 ± 0.25 vs. 0.53 ± 0.31), and an improved false-positive rate (0.87 ± 1.35 vs. ~ 2.7 FPs/case). The model further showed excellent performance in the external other-vendor test-datasets (DSC 0.65 ± 0.26; sensitivity 0.92, 0.96 ± 2.38 FPs/case). Specificity was 0.38 and 0.53, respectively. Raising the voxel-size from 0.5 × 0.5×0.5 mm to 1 × 1×1 mm reduced the false-positive rate seven-fold. This study successfully replicated core principles of a previous approach for detecting and segmenting cerebral aneurysms in TOF-MRAs with a robust, fully automatable pre-processing pipeline. The model demonstrated robust transferability on two independent external datasets using TOF-MRAs from the same scanner vendor as the training dataset and from other vendors. These findings are very encouraging regarding the clinical application of such an approach., (© 2024. The Author(s).)

Currently, surgical revascularization procedures using intracranial-intracranial (IC-IC) or extracranial-intracranial (EC-IC) bypass and distal clipping or trapping are the valid and rescue treatment modality for extremely rare unilateral distal fusiform superior cerebellar artery (SCA) aneurysms. Yet, in case of bilateral fusiform SCA aneurysms, surgical therapy reaches its limit. Mini-flow diverter devices (FDDs) have only recently become available for treating fusiform aneurysms of such small vessels. We report the unique case of bilateral distal fusiform SCA aneurysms in a 43-year-old man with subarachnoid hemorrhage (Fisher grade IV and World Federation of Neurosurgical Societies [WFNS] grade II) treated with endovascular implantation of bilateral mini-FDDs with excellent outcome and no radiographic signs of infarction. Yet, occlusion of one of the FDDs was found in the follow-up, which again shows the eminent danger of occlusion in case of an implantation of FDDs in such small-caliber vessels, which leaves the discussion about the optimal therapy method open., Competing Interests: None declared., (Thieme. All rights reserved.)

Background: De novo aneurysm formation after completely occluded aneurysms via clipping or coiling has not been well studied. Although known to occur several years after initial aneurysm management, the natural history of de novo aneurysms is obscure. We investigated the formation of new aneurysms in patients who had previously undergone treatment of intracranial aneurysms., Methods: In a retrospective, single-institutional series, eligible patients who had undergone treatment of ruptured cerebral aneurysms from 2000 to 2011 were included. The primary outcome measure was the development of de novo aneurysms during long-term follow-up., Results: Overall, 130 patients (63% women) who had undergone microsurgical clipping (n = 63; 48.5%) or endovascular coiling (n = 67%; 51.5%) for ruptured aneurysms were included. The average follow-up time for our cohort was 10 ± 2.7 years. De novo aneurysms occurred in 10 of 130 patients (7.7%), with a mean time of 7.9 years for aneurysm detection. No association between the formation of de novo aneurysms and the location of the treated aneurysms, smoking status, hypertension, age, or gender was found. Follow-up imaging studies were performed every 2 years. De novo aneurysms had formed in 2 patients within 2-5 years, 7 patients after 5-10 years, and 1 patient after 10 years of follow-up. In 2 of 10 patients, the de novo aneurysm had ruptured and led to subarachnoid haemorrhage., Conclusion: The rate of de novo aneurysm occurrence was 7.6%, with a mean time to development of 7.9 years. This underscores the significance of long-term monitoring of patients with intracranial aneurysms. In our series, most new aneurysms had occurred after 5 years of follow-up., (Copyright © 2018 Elsevier Inc. All rights reserved.)

Objectives: The pathogenesis leading to poor functional outcome after aneurysmal subarachnoid haemorrhage (aSAH) is multifactorial and not fully understood. We evaluated a machine learning approach based on easily determinable clinical and CT perfusion (CTP) features in the course of patient admission to predict the functional outcome 6 months after ictus., Methods: Out of 630 consecutive subarachnoid haemorrhage patients (2008-2015), 147 (mean age 54.3, 66.7% women) were retrospectively included (Inclusion: aSAH, admission within 24 h of ictus, CTP within 24 h of admission, documented modified Rankin scale (mRS) grades after 6 months. Exclusion: occlusive therapy before first CTP, previous aSAH, CTP not evaluable). A random forests model with conditional inference trees was optimised and trained on sex, age, World Federation of Neurosurgical Societies (WFNS) and modified Fisher grades, aneurysm in anterior vs. posterior circulation, early external ventricular drainage (EVD), as well as MTT and T max maximum, mean, standard deviation (SD), range, 75th quartile and interquartile range to predict dichotomised mRS (≤ 2; > 2). Performance was assessed using the balanced accuracy over the training and validation folds using 20 repeats of 10-fold cross-validation., Results: In the final model, using 200 trees and the synthetic minority oversampling technique, median balanced accuracy was 84.4% (SD 0.7) over the training folds and 70.9% (SD 1.2) over the validation folds. The five most important features were the modified Fisher grade, age, MTT range, WFNS and early EVD., Conclusions: A random forests model trained on easily determinable features in the course of patient admission can predict the functional outcome 6 months after aSAH with considerable accuracy., Key Points: • Features determinable in the course of admission of a patient with aneurysmal subarachnoid haemorrhage (aSAH) can predict the functional outcome 6 months after the occurrence of aSAH. • The top five predictive features were the modified Fisher grade, age, the mean transit time (MTT) range from computed tomography perfusion (CTP), the WFNS grade and the early necessity for an external ventricular drainage (EVD). • The range between the minimum and the maximum MTT may prove to be a valuable biomarker for detrimental functional outcome.

Background: The invasiveness and risk of thromboembolic complications of catheter angiography underline the need for alternative imaging modalities in patients following intracranial aneurysm (IA) repair. However, the overall image quality of existing noninvasive imaging modalities, such as single-energy CT angiography (SE-CTA), compromises its value in this respect., Objective: We prospectively investigated the value of a novel dual-energy CTA (DE-CTA) scanner and algorithm for assessing the degree of occlusion and parent vessel patency in patients following IA repair., Methods: A prospective cohort of 17 patients underwent DE-CTA imaging following surgical or endovascular IA repair. This dataset was matched with an identical historical cohort of 17 patients, who underwent IA repair and SE-CTA imaging. Beam-hardening artifacts, as a measure for objective imaging quality were analyzed based on the volume of a prolate ellipsoid, whereas subjective imaging quality at the IA site and corresponding parent vessels was rated by 2 independent neuroradiologists on a scale from 4 (excellent, no artifacts) to 1 (poor, severe artifacts)., Results: Objective DE-CTA image quality was markedly higher, compared to SE-CTA in patients undergoing surgical (0.77 ± 0.23 vs. 10.91 ± 1.88 mL, respectively; p < 0.001) or endovascular (32.36 ± 10.62 vs. 107.63 ± 24.51 mL, respectively; p = 0.026) IA repair. Subjective image quality for DE-CTA was significantly improved compared to SE-CTA in the surgical group but not in the endovascular group. The calculated dose values for DE-CTA in our study remain markedly below the legally required radiation dose limits., Conclusion: The imaging quality of DE-CTA, especially for patients undergoing surgical IA repair, is distinctly superior, compared to SE-CTA imaging. Therefore, DE-CTA may serve as a noninvasive alternative for assessing the IA occlusion rate and parent vessel patency., (© 2017 S. Karger AG, Basel.)