Matthias Anthony Mutke

BACKGROUND: Magnetic resonance imaging (MRI) is critical for acute stroke triage, but it is time-consuming and often requires contrast injection for perfusion imaging. This study aimed to synthesize T-map perfusion maps from routinely available, noncontrast diffusion-weighted imaging and fluid-attenuated inversion recovery using deep generative models. We hypothesized that relevant perfusion information could be inferred from these modalities to streamline imaging and reduce reliance on dynamic susceptibility contrast perfusion. METHODS: Acute magnetic resonance imaging data from 355 patients with anterior circulation stroke, including dynamic susceptibility contrast perfusion, were retrospectively collected from 2 European centers (Heidelberg: 2010–2018; Bordeaux: 2021–2022). Six versions of a denoising diffusion probabilistic model and a generative adversarial network architecture were trained to generate synthetic time-to-maximum (T-max) perfusion maps from diffusion-weighted imaging, fluid-attenuated inversion recovery, and infarct core mask as inputs. Performance was assessed by comparing synthetic and ground-truth T-max maps using image similarity metrics. Regions with T-max >6 s were compared using Dice coefficients, and mismatch volume distributions were analyzed. An ablation study quantified the contribution of each input. RESULTS: The best performance was achieved by a denoising diffusion probabilistic model with a 2.5D architecture using diffusion-weighted imaging, fluid-attenuated inversion recovery, infarct core mask, and a perfusion-weighted loss function. It produced synthetic perfusion T-max maps with high similarity to ground truth under 110 s. The model showed strong spatial overlap for T-max> 6 s regions in internal validation (average Dice, 0.82; SD, 0.08) and external validation (average Dice, 0.59; SD, 0.13), respectively. Synthetic maps closely matched ground truth mismatch distributions, capturing key perfusion patterns. The infarct core mask played a critical role in model performance, alongside diffusion-weighted imaging and fluid-attenuated inversion recovery inputs. CONCLUSIONS: We propose a noninvasive, scalable framework to generate synthetic T-max perfusion maps from noncontrast magnetic resonance imaging. This approach could expand access to perfusion data in acute stroke, shorten imaging protocols, and accelerate treatment decisions by eliminating the need for contrast-enhanced acquisition.

Purpose In idiopathic normal pressure hydrocephalus (iNPH), longitudinal monitoring of ventricular size is important for diagnosis and treatment follow-up. This study aimed to validate a fully automated AI model for CT ventricular volumetry with subcompartments and to compare AI-derived volume changes with routine radiology assessments. Methods This retrospective, single-center study included 88 patients with iNPH and 456 non-contrast-enhanced head CT examinations. The model was trained on 38 manually labeled CT scans with 12 ventricular subcompartments. Outcomes included segmentation accuracy, correspondence between AI-derived longitudinal ventricular volume changes and radiology report categories (decreased, unchanged, increased), radiologist detection thresholds for ventricular change, and paired pre- and postoperative volume changes in 22 patients with ventriculoperitoneal shunt. Results Mean segmentation accuracy was high (Dice, 0.83). 91% of 100 segmentations were rated as excellent by an expert neuroradiologist. AI-derived ventricular volume changes corresponded well to radiology report categories (median total ventricular volume changes of -17% in cases reported as decreased, 0% in unchanged cases, and +22% in increased cases; all p < 0.001). Radiologists reported ventricular volume change in 50% of cases at an AI-measured relative volume change of +/-6%, and in 90% of cases at +21% for enlargement and -18% for decrease. After shunt placement, ventricular volume decreased by -8% (median), with the largest relative reductions observed in the right temporal and occipital horns. Conclusions Automated AI-based ventricular segmentation on CT enables accurate and reproducible assessment of ventricular volume changes in iNPH and complements routine radiological evaluation for longitudinal and postoperative monitoring.

History: A 36-year-old man with known history of relapsing multiple sclerosis (RMS) of 13-year duration who was undergoing continuous treatment with subcutaneous interferon-β (INF-β) (44 µg three times per week) presented to the emergency department of our hospital with blurry vision of 1-week duration. Routine MRI performed 1 month earlier had revealed five new fluid-attenuated inversion recovery (FLAIR) T2-hyperintense cerebellar lesions without contrast enhancement, suggesting active RMS, albeit without corresponding neurologic deficits. The patient denied any other symptoms, apart from known yet intensified intermittent tension-type headaches. His history was unremarkable for drug use, recent infections, or travel. There was no routine use of other medication. Apart from a markedly elevated blood pressure (214/122 mm Hg), vital signs were within normal ranges (heart rate, 72 beats per minute; temperature, 97.9 °F [36.6 °C]; respiratory rate, 19 breaths per minute; oxygen saturation, 100%). Physical examination findings were unremarkable. Findings of a neurologic examination were normal, except for known saccadic gaze, with an Expanded Disability Status Scale (or EDSS) of 1. Acute ophthalmologic evaluation with fundoscopy showed bilateral hypertensive retinopathy, without signs of optic neuritis. Laboratory analysis revealed known increased liver enzyme levels due to INF-β treatment (aspartate aminotransferase level, 123 U/L [2.05 µkat/L]; normal range, 11–34 U/L [0.18–0.57 µkat/L]; alanine aminotransferase level, 179 U/L [2.99 µkat/L]; normal range, 9–59 U/L [0.15–0.99 µkat/L]; γ-glutamyl transferase level, 154 U/L [2.57 µkat/L]; normal range, 12–68 U/L [0.20–1.14 µkat/L]). The patient was admitted for further diagnostic evaluation, including new brain and spinal (not shown) MRI studies. Antihypertensive treatment with perindopril and amlodipine was initiated. Further laboratory examinations revealed microalbuminuria (albumin-to-creatinine ratio in urine, 59.21 mg/mmol; reference range, <3.00 mg/mmol) and hyperlipidemia (low-density lipoprotein cholesterol level, 3.84 mmol/L; reference range, 1.60–3.40 mmol/L). Blood serologic examination and cerebrospinal fluid (CSF) laboratory analysis were unremarkable, except for positive oligoclonal bands, with a polymerase chain reaction panel that was negative for common meningitis and/or encephalitis pathogens and a polymerase chain reaction test that was negative for human polyomavirus 2 (or JC virus) DNA in the CSF. The clinical course supported a wait-and-see approach without the use of steroids or antimicrobial therapy. Follow-up contrast-enhanced brain MRI was performed 1 week after presentation.

Purpose: In outpatient settings, extensive patient records must frequently be reviewed under time constraints, making efficient extraction and summarization of key clinical information essential. Large language models (LLMs) are potentially useful for this task but require validation for clinical reliability. This study assesses OpenAI’s GPT-4o for generating structured summaries to assist in neurovascular consultation preparation, aiming to increase efficiency by automating critical data extraction. Methods: A prospective study was conducted from May to August 2024 at a tertiary care hospital, involving a total of 70 patients. Structured summaries were generated by GPT-4o using a predefined template. Extracted data were categorized into aneurysm-specific details, imaging summaries, and patient-specific clinical factors. Accuracy and completeness were assessed by clinicians, with performance measured using precision, recall, specificity, and accuracy. Results: High accuracy (≥ 0.96) was measured across most categories. In aneurysm-and patient-specific data, extraction performance varied based on stability over time. Aneurysm location and other stable details were extracted consistently, while changes in aneurysm size and medication lists showed variations. In rare cases, aneurysm details were misattributed to a different aneurysm within the same patient. Imaging summaries were generally concise and clinically useful, though their effectiveness declined when summarizing multiple prior studies. Conclusion: Neurovascular patient data was effectively structured by GPT-4o, demonstrating high accuracy with minimal errors. While occasional misattributions like outdated information were observed, reliable citation of sources facilitated easy verification. These findings support integrating LLM-generated summaries into neurovascular consultations, with further optimization needed for temporal data tracking and on-premise implementation to address privacy concerns.

The aim of this study was to develop an open-source nnU-Net-based AI model for combined detection and segmentation of unruptured intracranial aneurysms (UICA) in 3D TOF-MRI and compare models trained on datasets with aneurysm-like differential diagnoses. This retrospective study (2020–2023) included 385 anonymized 3D TOF-MRI images from 345 patients (mean age 59 years, 60% female) at multiple centers plus 113 subjects from the ADAM challenge. Images featured untreated or possible UICA and differential diagnoses. Four distinct training datasets were created, and the nnU-Net framework was used for model development. Performance was assessed on a separate test set using sensitivity and false positive (FP)/case rate for detection and DICE score and NSD (normalized surface distance, 0.5 mm threshold) for segmentation. Segmentation performance on the test set was also compared to a second human reader. The four models achieved overall sensitivity between 82 and 85% and an FP/case rate of 0.20 to 0.31, with no significant differences ( p = 0.90 and p = 0.16) between them. The primary model showed 85% sensitivity and 0.23 FP/case rate, outperforming the ADAM-challenge winner (61%) and a nnU-Net trained on ADAM data (51%) in sensitivity ( p < 0.05). Mean DICE (0.73) and NSD (0.84 for 0.5 mm threshold) for correctly detected UICA did not significantly differ from human reader performance. Our open-source, nnU-Net-based AI model (available at https://zenodo.org/records/13386859 ) demonstrates high sensitivity, low FP rates, and consistent segmentation accuracy for UICA detection and segmentation in 3D TOF-MRI, suggesting its potential to improve clinical diagnosis and monitoring of UICA.

History: A 36-year-old man with known history of relapsing multiple sclerosis of 13-year duration who was undergoing continuous treatment with subcutaneous interferon-β (44 µg three times per week) presented to the emergency department of our hospital with blurry vision of 1-week duration. Routine MRI performed 1 month earlier had revealed five new fluid-attenuated inversion recovery (or FLAIR) T2-hyperintense cerebellar lesions without contrast enhancement, suggesting active relapsing multiple sclerosis ( Fig 1 ), albeit without corresponding neurologic deficits. The patient denied any other symptoms, apart from known yet intensified intermittent tension-type headaches. His history was unremarkable for drug use, recent infections, or travel. There was no routine use of other medication. Apart from a markedly elevated blood pressure (214/122 mm Hg), vital signs were within normal ranges (heart rate, 72 beats per minute; temperature, 97.9 °F [36.6 °C]; respiratory rate, 19 breaths per minute; oxygen saturation, 100%). Physical examination findings were unremarkable. Findings of a neurologic examination were normal, except for known saccadic gaze, with an Expanded Disability Status Scale (or EDSS) of 1. Acute ophthalmologic evaluation with fundoscopy showed bilateral hypertensive retinopathy, without signs of optic neuritis. Laboratory analysis revealed known increased liver enzyme levels due to interferon-β treatment (aspartate aminotransferase level, 123 U/L [2.05 µkat/L]; normal range, 11–34 U/L [0.18–0.57 µkat/L]; alanine aminotransferase level, 179 U/L [2.99 µkat/L]; normal range, 9–59 U/L [0.15–0.99 µkat/L]; γ-glutamyl transferase level, 154 U/L [2.57 µkat/L]; normal range, 12–68 U/L [0.20–1.14 µkat/L]). The patient was admitted for further diagnostic evaluation, including new brain ( Figs 2 , 3 ) and spinal (not shown) MRI studies. Antihypertensive treatment with perindopril and amlodipine was initiated. Further laboratory examinations revealed microalbuminuria (albumin-to-creatinine ratio in urine, 59.21 mg/mmol; reference range, <3.00 mg/mmol) and hyperlipidemia (low-density lipoprotein cholesterol level, 3.84 mmol/L; reference range, 1.60–3.40 mmol/L). Blood serologic examination and cerebrospinal fluid laboratory analysis were unremarkable, except for positive oligoclonal bands, with a polymerase chain reaction panel that was negative for common meningitis and/or encephalitis pathogens and a polymerase chain reaction test that was negative for human polyomavirus 2 (or JC virus) DNA in the cerebrospinal fluid. The clinical course supported a wait-and-see approach without the use of steroids or antimicrobial therapy. Follow-up contrast-enhanced brain MRI was performed 1 week after presentation ( Fig 4 ).

BACKGROUND AND PURPOSE: Patterns of the cerebral microcirculatory response with changes in the blood brain barrier and perfusion in patients with stroke and a large vessel occlusion are still unclear. We combined dynamic contrast enhancement (DCE) permeability and DSC perfusion MRI to detect such patterns beyond the borders of the diffusion-restricted infarct core after successful recanalization. MATERIALS AND METHODS: Combined DCE permeability and DSC perfusion MRI were performed prospectively in patients within 24h after successful mechanical recanalization of acute middle cerebral artery occlusion. Perfusion alterations were visually assessed on CBF and CBV maps, blood-brain-barrier disruptions (BBBD) on ktrans-maps and quantitatively evaluated with an ipsi-to contralateral ratio. Additionally, logistic regression analysis was performed for favorable early clinical outcome (NIHSS ≤2 at discharge). RESULTS: N=38 patients were included in the study. Subtle hyperperfusion beyond the DWI-lesion was present in 13/38 patients (34%) on CBF-maps and elevated CBV in 15/38 patients (39%). In these patients, the ratios between ipsi-and contralateral white matter CBF (p=0.01) and CBV (p<0.01) were elevated compared to patients with normal readings. Subtle, but visually and quantitatively elevated ktrans-values outside the DWI-lesion were observed in 7/38 patients (18%). None of these perfusion alterations were related to clinical outcome. CONCLUSIONS: Combined DCE-permeability and DSC-perfusion imaging is feasible in patients 24 hours after successful thrombectomy and reveals subtle hyperperfusion and BBBD occuring frequently beyond the diffusion restricted infarct core. ABBREVIATIONS: DCE = Dynamic Contrast Enhancement, BBBD = blood brain barrier disruption, MT = Mechanical thrombectomy.

Background: Established randomized trial-based parameters for acute ischemic stroke group patients into generic treatment groups, leading to attempts using various artificial intelligence (AI) methods to directly correlate patient characteristics to outcomes and thereby provide decision support to stroke clinicians. We review AI-based clinical decision support systems in the development stage, specifically regarding methodological robustness and constraints for clinical implementation. Methods: Our systematic review included full-text English language publications proposing a clinical decision support system using AI techniques for direct decision support in acute ischemic stroke cases in adult patients. We (1) describe data and outcomes used in those systems, (2) estimate the systems’ benefits compared with traditional stroke diagnosis and treatment, and (3) reported concordance with reporting standards for AI in healthcare. Results: One hundred twenty-one studies met our inclusion criteria. Sixty-five were included for full extraction. In our sample, utilized data sources, methods, and reporting practices were highly heterogeneous. Conclusions: Our results suggest significant validity threats, dissonance in reporting practices, and challenges to clinical translation. We outline practical recommendations for the successful implementation of AI research in acute ischemic stroke treatment and diagnosis.