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.

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.

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.

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.

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.

autoTICI: Automatic Brain Tissue Reperfusion Scoring on 2D DSA Images of Acute Ischemic Stroke Patients.

The Thrombolysis in Cerebral Infarction (TICI) score is an important metric for reperfusion therapy assessment in acute ischemic stroke. It is commonly used as a technical outcome measure after endovascular treatment (EVT). Existing TICI scores are defined in coarse ordinal grades based on visual inspection, leading to inter- and intra-observer variation. In this work, we present autoTICI, an automatic and quantitative TICI scoring method. First, each digital subtraction angiography (DSA) acquisition is separated into four phases (non-contrast, arterial, parenchymal and venous phase) using a multi-path convolutional neural network (CNN), which exploits spatio-temporal features. The network also incorporates sequence level label dependencies in the form of a state-transition matrix. Next, a minimum intensity map (MINIP) is computed using the motion corrected arterial and parenchymal frames. On the MINIP image, vessel, perfusion and background pixels are segmented. Finally, we quantify the autoTICI score as the ratio of reperfused pixels after EVT. On a routinely acquired multi-center dataset, the proposed autoTICI shows good correlation with the extended TICI (eTICI) reference with an average area under the curve (AUC) score of 0.81. The AUC score is 0.90 with respect to the dichotomized eTICI. In terms of clinical outcome prediction, we demonstrate that autoTICI is overall comparable to eTICI.

Long-term outcome of popliteal artery aneurysms after ligation and bypass.

OBJECTIVES: After exclusion of popliteal artery aneurysms (PAAs) through bypass surgery, there is a risk of persistent flow through collaterals and growth of the excluded aneurysmal sac. This study was conducted to evaluate this risk at long-term follow-up. METHODS: Sixty-five PAAs treated by proximal and distal ligation and bypass grafting with reversed autologous vein in 52 patients (1998-2010) were retrospectively reviewed. RESULTS: Mean follow-up was 41 months (range, 1-144 months). Five aneurysms showed residual flow (8%). One of these aneurysms had increased in size, 36 months postoperatively. This aneurysm underwent an embolization procedure after which no flow or further enlargement was demonstrated. CONCLUSION: In this study, the risk of persistent flow in a PAA excluded by proximal and distal ligation and bypass is low. Still, considering this risk and its possible complications, follow-up by duplex ultrasound in all patients until up to more than 10 years postoperatively is recommended.

Focal fatty areas in the myocardium of patients with tuberous sclerosis complex: a unique finding.

With this collection of computed tomography and magnetic resonance images, we illustrate a recently described novel finding in the myocardium of patients with tuberous sclerosis complex.

Detection of occult endoleaks after endovascular treatment of abdominal aortic aneurysm using magnetic resonance imaging with a blood pool contrast agent: preliminary observations.

OBJECTIVE: To determine whether blood pool contrast agent-enhanced magnetic resonance imaging (MRI) can visualize endoleaks that are occult on computed tomography (CT) in patients with nonshrinking aneurysms after endovascular aneurysm repair. MATERIALS AND METHODS: Written informed consent was obtained for this prospective institutional review board approved study. Twelve patients with nonshrinking aneurysms but no evidence of endoleak on CT angiography and delayed CT underwent MRI with a blood pool contrast agent (Gadofosveset trisodium, Bayer Schering Pharma, Berlin, Germany). Patients could participate once in the study. T1-weighted images were acquired before injection, 3 minutes and 30 minutes after injection. Two blinded readers independently scored the images into "endoleak," "possible endoleak," or "no endoleak" by comparing postcontrast MR images with precontrast images. Weighted kappas with linear weighting scheme were calculated for interobserver agreement. RESULTS: One MRI examination was nondiagnostic because of patient motion. In the successful 11 MRI exams, MRI 3 minutes after injection demonstrated endoleak in 2/11 MRI exams (18%) and possible endoleak in 2/11 MRI exams (18%). After 30 minutes, MRI demonstrated endoleak in 6/11 scans (55%) and possible endoleak in 1/11 scans (9%). Weighted kappa was 0.78 and 0.89 for early and late postcontrast images. CONCLUSION: Endoleaks that are occult on CT can be detected by MRI with blood pool contrast agents. Late phase MRI 30 minutes after injection revealed additional endoleaks not seen 3 minutes after injection.