Interobserver Agreement on Intracranial Hemorrhage on Magnetic Resonance Imaging in Patients With Ischemic Stroke.

BACKGROUND: The Heidelberg Bleeding Classification, developed for computed tomography, is also frequently used to classify intracranial hemorrhage (ICH) on magnetic resonance imaging. Additionally, the presence of any ICH is frequently used as (safety) outcome measure in clinical stroke trials that evaluate acute interventions. We assessed the interobserver agreement on the presence of any ICH and the type of ICH according to the Heidelberg Bleeding Classification on magnetic resonance imaging in patients treated with reperfusion therapy. METHODS: We used 300 magnetic resonance imaging scans including susceptibility-weighted imaging or T2*-weighted gradient echo imaging of ischemic stroke patients within 1 week after reperfusion therapy. Six observers, blinded to clinical characteristics except for suspected location of the infarction, independently rated ICH according to the Heidelberg Bleeding Classification in random pairs. Percent agreement and Cohen's kappa (κ) were estimated for the presence of any ICH (yes/no), and for agreement on the Heidelberg Bleeding Classification class 1 and 2. For the Heidelberg Bleeding Classification class 1 and 2, weighted κ was estimated to take the degree of disagreement into account. RESULTS: In 297 of 300 scans, the quality of scans was sufficient to score ICH. Observers agreed on the presence or absence of any ICH in 264 of 297 scans (88.9%; κ 0.78 [95% CI, 0.71-0.85]). There was agreement on the Heidelberg Bleeding Classification class 1 and 2 and no ICH in class 1 and 2 in 226 of 297 scans (76.1%; κ 0.63 [95% CI, 0.56-0.69]; weighted κ 0.90 [95% CI, 0.87-0.93]). CONCLUSIONS: The presence of any ICH can be reliably scored on magnetic resonance imaging and can, therefore, be used as (safety) outcome measure in clinical stroke trials that evaluate acute interventions. Agreement of ICH types according to the Heidelberg Bleeding Classification is substantial and disagreements are small.

Comparison of diffusion weighted imaging b0 with T2*-weighted gradient echo or susceptibility weighted imaging for intracranial hemorrhage detection after reperfusion therapy for ischemic stroke.

PURPOSE: Diffusion-weighted imaging (DWI) b0 may be able to substitute T2*-weighted gradient echo (GRE) or susceptibility-weighted imaging (SWI) in case of comparable detection of intracranial hemorrhage (ICH), thereby reducing MRI examination time. We evaluated the diagnostic accuracy of DWI b0 compared to T2*GRE or SWI for detection of ICH after reperfusion therapy for ischemic stroke. METHODS: We pooled 300 follow-up MRI scans acquired within 1 week after reperfusion therapy. Six neuroradiologists each rated DWI images (b0 and b1000; b0 as index test) of 100 patients and, after a minimum of 4 weeks, T2*GRE or SWI images (reference standard) paired with DWI images of the same patients. Readers assessed the presence of ICH (yes/no) and type of ICH according to the Heidelberg Bleeding Classification. We determined the sensitivity and specificity of DWI b0 for detection of any ICH, and the sensitivity for detection of hemorrhagic infarction (HI1 & HI2) and parenchymal hematoma (PH1 & PH2). RESULTS: We analyzed 277 scans of ischemic stroke patients with complete image series and sufficient image quality (median age 65 years [interquartile range, 54-75], 158 [57%] men). For detection of any ICH on DWI b0, the sensitivity was 62% (95% CI: 50-76) and specificity 96% (95% CI: 93-99). The sensitivity of DWI b0 was 52% (95% CI: 28-68) for detection of hemorrhagic infarction and 84% (95% CI: 70-92) for parenchymal hematoma. CONCLUSION: DWI b0 is inferior for detection of ICH compared to T2*GRE/SWI, especially for smaller and more subtle hemorrhages. Follow-up MRI protocols should include T2*GRE/SWI for detection of ICH after reperfusion therapy.

Comprehensive routine diagnostic screening to identify predictive mutations, gene amplifications, and microsatellite instability in FFPE tumor material.

BACKGROUND: Sensitive and reliable molecular diagnostics is needed to guide therapeutic decisions for cancer patients. Although less material becomes available for testing, genetic markers are rapidly expanding. Simultaneous detection of predictive markers, including mutations, gene amplifications and MSI, will save valuable material, time and costs. METHODS: Using a single-molecule molecular inversion probe (smMIP)-based targeted next-generation sequencing (NGS) approach, we developed an NGS panel allowing detection of predictive mutations in 33 genes, gene amplifications of 13 genes and microsatellite instability (MSI) by the evaluation of 55 microsatellite markers. The panel was designed to target all clinically relevant single and multiple nucleotide mutations in routinely available lung cancer, colorectal cancer, melanoma, and gastro-intestinal stromal tumor samples, but is useful for a broader set of tumor types. RESULTS: The smMIP-based NGS panel was successfully validated and cut-off values were established for reliable gene amplification analysis (i.e. relative coverage ≥3) and MSI detection (≥30% unstable loci). After validation, 728 routine diagnostic tumor samples including a broad range of tumor types were sequenced with sufficient sensitivity (2.4% drop-out), including samples with low DNA input (< 10 ng; 88% successful), low tumor purity (5-10%; 77% successful), and cytological material (90% successful). 75% of these tumor samples showed ≥1 (likely) pathogenic mutation, including targetable mutations (e.g. EGFR, BRAF, MET, ERBB2, KIT, PDGFRA). Amplifications were observed in 5.5% of the samples, comprising clinically relevant amplifications (e.g. MET, ERBB2, FGFR1). 1.5% of the tumor samples were classified as MSI-high, including both MSI-prone and non-MSI-prone tumors. CONCLUSIONS: We developed a comprehensive workflow for predictive analysis of diagnostic tumor samples. The smMIP-based NGS analysis was shown suitable for limited amounts of histological and cytological material. As smMIP technology allows easy adaptation of panels, this approach can comply with the rapidly expanding molecular markers.

Multicenter, retrospective analysis of endovascular treatment for acute ischemic stroke in nonagenarians.

BACKGROUND: With the increasing age of acute stroke patients being admitted to hospitals, more data are needed on indications, complications and outcome of endovascular treatment (EVT) in the very elderly. METHODS: Retrospective observational study with data collection from Belgian, Swiss, Canadian comprehensive stroke centers and Swedish EVT National database. All patients with acute ischemic stroke were eligible if aged older than or ≥90 years and treated with EVT ± pretreatment with intravenous thrombolysis (IVT). Safety assessment comprised presence of periprocedural complications, hemorrhagic transformation or other adverse events (<7days). Efficacy and outcome measures were successful recanalization (modified Treatment In Cerebral Infarction (mTICI) score ≥2b), favorable clinical outcome (modified Rankin Score (mRS) 0-2) and 3-months mortality. RESULTS: Inclusion of 112 nonagenarians (mean age 93.3 ± 2.5 years; 76.8% women; pre-mRS ≤2 in 69.4%). Pretreatment with IVT was performed in 54.7%. In 74.6% successful recanalization (mTICI ≥2b) was achieved. Favorable outcome (mRS ≤2) was seen in 16.4% and 3-months mortality was 62.3%. Multivariate logistic regression analysis showed younger age (odds ratio [OR] 2.99; 1.29-6.95; P = .011) and lower prestroke mRS (OR 13.46; 2.32-78.30; P = .004) as significant predictors for good clinical outcome at 90 days. CONCLUSIONS: Our observational study on EVT in nonagenarians demonstrates the need for careful patient selection. A substantial proportion of nonagenarians shows an unfavorable clinical outcome and high mortality, despite acceptable recanalization rates. A high prestroke disability (mRS) and advancing age predict an unfavorable outcome. Treatment decisions should be made on case-by-case evaluation, keeping in mind limited chances of favorable outcome and high risk of mortality.

A comprehensive report of long-term outcomes after catheter-directed thrombolysis for occluded infrainguinal bypass grafts.

OBJECTIVE: The objective of this study was to assess the technical and short- and long-term clinical outcomes of catheter-directed thrombolysis (CDT) with urokinase for occluded infrainguinal bypass grafts. In addition, factors associated with technical success and amputation-free survival were assessed. METHODS: A retrospective analysis of a cohort of patients treated with catheter-directed urokinase-based thrombolysis for occluded infrainguinal bypass grafts was conducted between January 2000 and December 2015. Demographics, procedural data, and short- and long-term outcome data, including patency rates of the bypasses, limb salvage, and overall survival, were collected. Statistical models for clustered data were applied to assess predictive factors. RESULTS: In 177 patients, 251 CDTs were performed on 204 bypasses. In 209 procedures (83.3%), the occluded bypass was reopened; clinical disappearance of ischemic symptoms occurred after 157 procedures (62.6%). Premature cessation of thrombolysis occurred in 33 procedures (13.2%), and periprocedural and postprocedural complications were noted in 91 patients (36.3%). Factors associated with long-term limb salvage are fewer vascular interventions before CDT (P = .0003), higher number of patent outflow vessels before start of CDT (P < .0001), and higher number of patent outflow vessels after CDT (P < .0001). The 1- and 5-year patency rates of bypasses after successful CDT were 64.6% and 48.9%; amputation-free survival after 1 year, 5 years, and 7 years was 81.5%, 71.3%, and 70.5%, respectively. CONCLUSIONS: Clinical success after CDT was observed in 62% of procedures with an associated complication rate of 36%. Patent outflow vessels before and after CDT are factors associated with long-term limb salvage. Amputation-free survival after 5 years is 71.3%.

Alberta Stroke Program Early CT Score Versus Computed Tomographic Perfusion to Predict Functional Outcome After Successful Reperfusion in Acute Ischemic Stroke.

Background and Purpose- We aimed to compare the ability of conventional Alberta Stroke Program Early CT Score (ASPECTS), automated ASPECTS, and ischemic core volume on computed tomographic perfusion to predict clinical outcome in ischemic stroke because of large vessel occlusion ≤18 hours after symptom onset. Methods- We selected patients with acute ischemic stroke from the CRISP study (Computed Tomographic Perfusion to Predict Response to Recanalization in Ischemic Stroke Project) with successful reperfusion (modified treatment in cerebral ischemia score 2b or 3). We used e-ASPECTS software to calculate automated ASPECTS and RAPID software to estimate ischemic core volumes. We studied associations between these imaging characteristics and good outcome (modified Rankin Scale score, 0-2) or poor outcome (modified Rankin Scale score, 4-6) in univariable and multivariable analysis, after adjustment for relevant clinical confounders. Results- We included 156 patients. Conventional and automated ASPECTS was not associated with good or poor outcome in univariable analysis ( P=nonsignificant for all). Automated ASPECTS was associated with good outcome in multivariable analysis ( P=0.02) but not with poor outcome. Ischemic core volume was associated with good ( P<0.01) and poor outcome ( P=0.04) in univariable and multivariable analysis ( P=0.03 and P=0.02, respectively). Computed tomographic perfusion predicted good outcome with an area under the curve of 0.62 (95% CI, 0.53-0.71) and optimal cutoff core volume of 15 mL. Conclusions- Ischemic core volume assessed on computed tomographic perfusion is a predictor of clinical outcome among patients in whom endovascular reperfusion is achieved ≤18 hours after symptom onset. In this population, conventional or automated ASPECTS did not predict outcome.

Safety and Efficacy of Repeat Embolization for Recurrent Hemoptysis: A 16-Year Retrospective Study Including 223 Patients.

PURPOSE: To assess safety, efficacy, and long-term outcome of repeat bronchial artery embolization (BAE) for recurrent hemoptysis. MATERIALS AND METHODS: This was a retrospective study of patients referred for repeat BAE to manage recurrent hemoptysis after initial successful embolization. BAE was performed in 223 patients; 36 (16.1%) of these patients underwent 59 repeat BAE procedures because of recurring symptoms. The most frequent underlying lung diseases were bronchiectasis (n = 8; 22%), cystic fibrosis (n = 7; 19%), and idiopathic hemoptysis (n = 7; 19%). RESULTS: Most patients (64%) underwent 2 embolization procedures owing to vessel recanalization (71%) as the most frequent pathophysiologic mechanism of recurrent hemoptysis. No serious adverse events requiring prolonged hospital stay were noted. Risk for relapse of hemoptysis was significantly lower for bronchiectasis compared with other chronic infections (P = .0022) and cystic fibrosis (P = .0004). Overall survival after 3-year and 5-year follow-up was 92% and 84%, respectively. CONCLUSIONS: Repeat BAE for recurrent hemoptysis after initial successful BAE is safe and efficacious, especially in patients with bronchiectasis as the underlying lung disease.

Multicenter, Randomized Trial of Conventional Balloon Angioplasty versus Paclitaxel-Coated Balloon Angioplasty for the Treatment of Dysfunctioning Autologous Dialysis Fistulae.

PURPOSE: To investigate the potential added value of paclitaxel-coated balloon (PCB) angioplasty to reduce fistula dysfunction related to recurrent stenoses in patients undergoing hemodialysis. MATERIALS AND METHODS: A prospective, randomized study was conducted in 3 dialysis referral centers. From January 2013 to October 2015, 64 patients (22 female, 42 male) with dysfunctional autologous dialysis fistulae were randomized to undergo conventional percutaneous balloon angioplasty (n = 31) or PCB angioplasty (n = 33). Procedural and postprocedural data were assessed. Primary patency of the fistula was evaluated at 3, 6, and 12 months following the procedure. Statistical analysis was based on the Fisher exact test and independent t test. RESULTS: There were no procedural or postprocedural complications. After 3, 6, and 12 months of follow-up, primary patency rates after PCB angioplasty and percutaneous transluminal angioplasty (PTA) were 88% and 80% (P = .43), 67% and 65% (P = .76), and 42% and 39% (P = .95), respectively. CONCLUSIONS: Although primary patency rates after PCB angioplasty in autologous dialysis fistulae at 3, 6, and 12 months of follow-up are slightly better than those after PTA, the difference is not statistically significant.

A new imaging technology to reduce the radiation dose during uterine fibroid embolization.

BACKGROUND: Uterine fibroid embolization (UFE) is a minimally invasive imaging-guided treatment using radiation exposure. PURPOSE: To compare the patients' radiation exposure during UFE before and after introduction of a new X-ray imaging platform. MATERIAL AND METHODS: Forty-one patients were enrolled in a prospective, comparative two-arm project before and after introduction of a new X-ray imaging platform with reduced dose settings, i.e. novel real-time image processing techniques (AlluraClarity). Demographic, pre-interventional imaging, and procedural data, including dose area product (DAP) and estimated organ dose on the ovaries and uterus, were recorded and angiographic quality of overall procedure was assessed. RESULTS: There were no significant differences in demographic characteristics and preoperative fibroid and uterine volumes in the two groups. The new imaging platform led to a significant reduction in mean total DAP (102 vs. 438 Gy.cm2; P < 0.001), mean fluoroscopy DAP (32 vs. 138 Gy.cm2; P < 0.001), mean acquisition DAP (70 vs. 300 Gy.cm2; P < 0.001), and acquisition DAP estimated organ dose in ovaries (42 vs. 118 mGy; P < 0.001) and uterus (40 vs. 118 mGy, P < 0.001), without impairment of the procedure and angiographic image quality. CONCLUSION: A substantial 77% reduction of DAP values and 64% and 66% reduction in organ dose on ovaries and uterus, respectively, was demonstrated with the new imaging platform, while maintaining optimal imaging quality and efficacy.

Safety and efficacy of doxorubicin-eluting superabsorbent polymer microspheres for the treatment of liver metastases from neuroendocrine tumours: preliminary results.

BACKGROUND: The aim of the study was to retrospectively evaluate the symptom control, tumour response, and complication rate in patients with liver-predominant metastatic neuroendocrine tumours treated with transarterial chemoembolization using doxorubicin-eluting superabsorbent polymer (SAP) microspheres. PATIENTS AND METHODS: Patients with neuroendocrine liver metastases who underwent hepatic transarterial chemoembolization using doxorubicin-eluting SAP-microspheres (50-100 µm Hepasphere/Quadrasphere Microsphere® particles, Merit Medical, South Jordan, Utah, USA) were included in this study. Pre-and post-procedure imaging studies were evaluated to assess short and intermediate-term tumour response using modified RECIST criteria. Symptom relief and procedure-related complications were evaluated. RESULTS: A total of 27 embolization procedures were performed on 17 patients. Twelve of 17 patients (70%) were symptomatic, including carcinoid syndrome (n = 8) and severe, uncontrollable hypoglycemia (n = 4). Eight of 12 patients (67%) had complete symptom relief, and the remaining 4 (33%) had partial relief. One patient developed ischemic cholecystitis (6%). No other hepatobiliary complications occurred. Short-term and intermediate-term imaging follow-up was available for 15/17 patients (88%) and 12/14 patients (86%) respectively. At short-term follow-up (< 3 months), 14 patients (93%) showed partial response and the remaining patient had progressive disease (7%). At intermediate-term imaging follow-up (> 3 months), partial response, stable disease and progressive disease were found respectively in 7 (58%), 3 (25%) and 2 (17%) patients. CONCLUSIONS: Chemoembolization with doxorubicin-eluting SAP-microspheres is a safe and effective treatment option for neuroendocrine liver metastases and is associated with a low complication rate. In particular, no clinically evident liver necrosis or bile duct complications were encountered.

Somatic mutations in MLH1 and MSH2 are a frequent cause of mismatch-repair deficiency in Lynch syndrome-like tumors.

Lynch syndrome is caused by germline mutations in the mismatch repair (MMR) genes. Tumors are characterized by microsatellite instability (MSI). However, a considerable number of MSI-positive tumors have no known molecular mechanism of development. By using Sanger and ion semiconductor sequencing, 25 MSI-positive tumors were screened for somatic mutations and loss of heterozygosity in mutL homolog 1 (MLH1) and mutS homolog 2 (MSH2). In 13 of 25 tumors (8 MLH1-deficient and 5 MSH2-deficient tumors), we identified 2 somatic mutations in these genes. We conclude that 2 acquired events explain the MMR-deficiency in more than 50% of the MMR-deficient tumors without causal germline mutations or promoter methylation.

Automated image registration of cerebral digital subtraction angiography.

PURPOSE: Our aim is to automatically align digital subtraction angiography (DSA) series, recorded before and after endovascular thrombectomy. Such alignment may enable quantification of procedural success. METHODS: Firstly, we examine the inherent limitations for image registration, caused by the projective characteristics of DSA imaging, in a representative set of image pairs from thrombectomy procedures. Secondly, we develop and assess various image registration methods (SIFT, ORB). We assess these methods using manually annotated point correspondences for thrombectomy image pairs. RESULTS: Linear transformations that account for scale differences are effective in aligning DSA sequences. Two anatomical landmarks can be reliably identified for registration using a U-net. Point-based registration using SIFT and ORB proves to be most effective for DSA registration and are applicable to recordings for all patient sub-types. Image-based techniques are less effective and did not refine the results of the best point-based registration method. CONCLUSION: We developed and assessed an automated image registration approach for cerebral DSA sequences, recorded before and after endovascular thrombectomy. Accurate results were obtained for approximately 85% of our image pairs.

Assessment of automated TICI scoring during endovascular treatment in patients with an ischemic stroke.

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.

CAVE: Cerebral artery-vein segmentation in digital subtraction angiography.

Cerebral X-ray digital subtraction angiography (DSA) is a widely used imaging technique in patients with neurovascular disease, allowing for vessel and flow visualization with high spatio-temporal resolution. Automatic artery-vein segmentation in DSA plays a fundamental role in vascular analysis with quantitative biomarker extraction, facilitating a wide range of clinical applications. The widely adopted U-Net applied on static DSA frames often struggles with disentangling vessels from subtraction artifacts. Further, it falls short in effectively separating arteries and veins as it disregards the temporal perspectives inherent in DSA. To address these limitations, we propose to simultaneously leverage spatial vasculature and temporal cerebral flow characteristics to segment arteries and veins in DSA. The proposed network, coined CAVE, encodes a 2D+time DSA series using spatial modules, aggregates all the features using temporal modules, and decodes it into 2D segmentation maps. On a large multi-center clinical dataset, CAVE achieves a vessel segmentation Dice of 0.84 (±0.04) and an artery-vein segmentation Dice of 0.79 (±0.06). CAVE surpasses traditional Frangi-based k-means clustering (P < 0.001) and U-Net (P < 0.001) by a significant margin, demonstrating the advantages of harvesting spatio-temporal features. This study represents the first investigation into automatic artery-vein segmentation in DSA using deep learning. The code is publicly available at https://github.com/RuishengSu/CAVE_DSA.

Spontaneous Iliac Vein Ruptures: A Systematic Review.

INTRODUCTION: Spontaneous iliac vein rupture is a rare, but frequently lethal condition. It is important to timely recognize its clinical features and immediately start adequate treatment. We aimed to increase awareness to clinical features, specific diagnostics, and treatment strategies of spontaneous iliac vein rupture by evaluating the current literature. METHODS: A systematic search was conducted in EMBASE, Ovid MEDLINE, Cochrane, Web of Science, and Google Scholar from inception until January 23, 2023, without any restrictions. Two reviewers independently screened for eligibility and selected studies describing a spontaneous iliac vein rupture. Patient characteristics, clinical features, diagnostics, treatment strategies, and survival outcomes were collected from included studies. RESULTS: We included 76 cases (64 studies) from the literature, mostly presenting with left-sided spontaneous iliac vein rupture (96.1%). Patients were predominantly female (84.2%), had a mean age of 61 years, and frequently presented with a concomitant deep vein thrombosis (DVT) (84.2%). After various follow-up times, 77.6% of the patients survived, either after conservative, endovascular, or open treatment. Endovenous or hybrid procedures were frequently performed if the diagnose was made before treatment, and almost all survived. Open treatment was common if the venous rupture was missed, for some cases leading to death. CONCLUSION: Spontaneous iliac vein rupture is rare and easily missed. The diagnose should at least be considered for middle-aged and elderly females presenting with hemorrhagic shock and concomitant left-sided DVT. There are various treatment strategies for spontaneous iliac vein rupture. An early diagnose brings options for endovenous treatment, which seems to have good survival outcomes based on previously described cases.

Lack of thrombus organization in nonshrinking aneurysms years after endovascular abdominal aortic aneurysm repair.

OBJECTIVE: During endovascular abdominal aortic aneurysm repair (EVAR), blood is trapped in the aneurysm sac at the moment the endograft is deployed. It is generally assumed that this blood will coagulate and evolve into an organized thrombus. It is unknown whether this process always occurs, what its time span is, and how it influences aneurysm shrinkage. With magnetic resonance imaging (MRI), quantitative analysis of the aneurysm sac is possible in terms of endoleak volume as well as unorganized thrombus volume and organized thrombus volume. We investigated the presence of unorganized thrombus in nonshrinking aneurysms years after EVAR. METHODS: Fourteen patients with a nonshrinking aneurysm without endoleak on computed tomography/computed tomography angiography underwent MRI with a blood pool agent (gadofosveset trisodium). Precontrast T1-, precontrast T2-, and postcontrast T1-weighted images (3 and 30 minutes after injection) were acquired and evaluated for the presence of endoleak. The aneurysm sac was segmented into endoleak, unorganized thrombus, and organized thrombus by interactively thresholding the differently weighted images. The classification was visualized in real-time as a color overlay on the MR images. The volumes of endoleak, unorganized thrombus, and organized thrombus were calculated. RESULTS: Median time after EVAR was 2 years (range, 1-8.2 years). The average aneurysm sac volume of the patients was 167 ± 107 mL (mean ± standard deviation). Nine patients had an endoleak on the postcontrast T1-w images 30 minutes after injection. On average, the aneurysm sac contained 78 ± 61 mL unorganized thrombus, which corresponded to 51 ± 21 volume-percentage, irrespective of the presence of an endoleak on the blood pool agent enhanced MRI images (independent t-test, P = .8). CONCLUSIONS: In our study group, half of the nonshrinking aneurysm sac contents consisted of unorganized thrombus years after EVAR.

Treatment of ruptured subclavian steal flow-related vertebrobasilar junction aneurysms: Case report on surgical and endovascular considerations from two cases.

INTRODUCTION: Subclavian steal phenomenon causes retrograde flow through the vertebral artery, ipsilateral to the affected subclavian artery, which rarely leads to flow-related vertebrobasilar junction (VBJ) aneurysms. CASE DESCRIPTIONS: We describe two cases of subarachnoid hemorrhage from such ruptured aneurysms in which the retrograde flow direction in the vertebral artery complicated surgical and endovascular treatment. DISCUSSION: Reversed flow in the vertebral artery, ipsilateral to the stenotic subclavian artery leads to a lack of proximal control in surgical clipping of these VBJ aneurysms and jeopardizes stability of coil and stent placement in endovascular aneurysm treatments in this setting. CONCLUSION: From these 2 experiences over 7 years, treatment considerations emerged for future cases.

Spatio-temporal deep learning for automatic detection of intracranial vessel perforation in digital subtraction angiography during endovascular thrombectomy.

Intracranial vessel perforation is a peri-procedural complication during endovascular therapy (EVT). Prompt recognition is important as its occurrence is strongly associated with unfavorable treatment outcomes. However, perforations can be hard to detect because they are rare, can be subtle, and the interventionalist is working under time pressure and focused on treatment of vessel occlusions. Automatic detection holds potential to improve rapid identification of intracranial vessel perforation. In this work, we present the first study on automated perforation detection and localization on X-ray digital subtraction angiography (DSA) image series. We adapt several state-of-the-art single-frame detectors and further propose temporal modules to learn the progressive dynamics of contrast extravasation. Application-tailored loss function and post-processing techniques are designed. We train and validate various automated methods using two national multi-center datasets (i.e., MR CLEAN Registry and MR CLEAN-NoIV Trial), and one international multi-trial dataset (i.e., the HERMES collaboration). With ten-fold cross-validation, the proposed methods achieve an area under the curve (AUC) of the receiver operating characteristic of 0.93 in terms of series level perforation classification. Perforation localization precision and recall reach 0.83 and 0.70 respectively. Furthermore, we demonstrate that the proposed automatic solutions perform at similar level as an expert radiologist.

Deep-Learning-Based Thrombus Localization and Segmentation in Patients with Posterior Circulation Stroke.

Thrombus volume in posterior circulation stroke (PCS) has been associated with outcome, through recanalization. Manual thrombus segmentation is impractical for large scale analysis of image characteristics. Hence, in this study we develop the first automatic method for thrombus localization and segmentation on CT in patients with PCS. In this multi-center retrospective study, 187 patients with PCS from the MR CLEAN Registry were included. We developed a convolutional neural network (CNN) that segments thrombi and restricts the volume-of-interest (VOI) to the brainstem (Polar-UNet). Furthermore, we reduced false positive localization by removing small-volume objects, referred to as volume-based removal (VBR). Polar-UNet is benchmarked against a CNN that does not restrict the VOI (BL-UNet). Performance metrics included the intra-class correlation coefficient (ICC) between automated and manually segmented thrombus volumes, the thrombus localization precision and recall, and the Dice coefficient. The majority of the thrombi were localized. Without VBR, Polar-UNet achieved a thrombus localization recall of 0.82, versus 0.78 achieved by BL-UNet. This high recall was accompanied by a low precision of 0.14 and 0.09. VBR improved precision to 0.65 and 0.56 for Polar-UNet and BL-UNet, respectively, with a small reduction in recall to 0.75 and 0.69. The Dice coefficient achieved by Polar-UNet was 0.44, versus 0.38 achieved by BL-UNet with VBR. Both methods achieved ICCs of 0.41 (95% CI: 0.27-0.54). Restricting the VOI to the brainstem improved the thrombus localization precision, recall, and segmentation overlap compared to the benchmark. VBR improved thrombus localization precision but lowered recall.