OBJECTIVES:Quantitative chemical exchange saturation transfer (CEST) breast imaging is limited by pronounced fat-induced artifacts. The strongest fat artifact, appearing between [-2, -4] ppm in the Z-spectrum, directly overlaps the signal of the exchange-relayed nuclear Overhauser effect (rNOE) at around -3.5 ppm, a key biomarker for protein content and cellularity, making accurate rNOE-CEST evaluation extremely challenging. The aim of this study is to evaluate rNOE-CEST contrast corrected for fat-related artifacts using a novel, fully software-based fat correction method in breast cancer patients. MATERIALS AND METHODS:FATLESS (Fat Attenuation Technique using Lipid signal Estimation and Simulated Saturations in postprocessing) was developed for correcting fat-related artifacts across the entire Z-spectrum in CEST MRI. The FATLESS method estimates fat signals from residual signals at the direct water saturation offset (0 ppm) while accounting for partial saturation of fat resonances. FATLESS was retrospectively applied to 7T CEST data from breast cancer patients (acquired September 2018 to May 2019). Resulting fat-corrected rNOE, amide, and guanidino MTR Rex contrast values were quantified from 2D snapshot GRE CEST with low saturation power (B 1 =0.6, 0.9 μT). Kruskal-Wallis tests and Pearson correlation analyses were used to compare MTR Rex values between tumor and normal-appearing fibroglandular tissue and assess correlations with Ki-67, a tumor proliferation marker. RESULTS:Nine biopsy-confirmed breast cancer patients [mean age, 50 y ± 10 (SD)] and 7 healthy controls [mean age, 25 y ± 4 (SD)] were included. Fat-corrected MTR Rex rNOE maps were validated in phantom and in vivo data, confirming independence from fat artifacts using the FATLESS method. Tumor regions showed significantly higher fat-corrected MTR Rex rNOE values than healthy tissue (+140% mean increase, P <0.001). A strong positive correlation was found between fat-corrected MTR Rex rNOE values and Ki-67 ( R ² = 0.71). CONCLUSIONS:The developed FATLESS fat correction method enables full utilization of all CEST MRI contrasts in the human breast. The observed significant rNOE contrast elevation and strong correlation with tumor proliferation highlight its potential as a non-invasive imaging biomarker for breast cancer characterization.

PURPOSE:Response assessment after radiotherapy (RT) of gliomas remains challenging due to radiation-induced reactions that mimic tumor growth (pseudoprogression, PsPD). Unlike standard anatomical MRI, Chemical Exchange Saturation Transfer (CEST) MRI offers molecular image contrasts that could differentiate tumor growth from PsPD. Our aim was to quantify the influence of radiation dose on CEST contrasts in both healthy-appearing brain tissues and tumor tissues. METHODS:This prospective study enrolled 33 glioma patients (26 glioblastoma, 7 IDH-mutant glioma). In total, 81 longitudinal CEST MRI scans were performed before RT until seven months thereafter. CEST MRI included asymmetry analysis of the amide proton transfer-weighted (APTw) signal, and a multipool Lorentzian fitting approach was used to quantify the amide signal, ssMT signal and rNOE signal. CEST contrast changes were analyzed in normal-appearing brain tissues and tumor by cumulative histograms and based on Bayesian linear multilevel models. RESULTS:Normal-appearing brain tissues did not exhibit significant changes in any CEST contrasts after high-dose radiation. Conversely, the CEST contrasts changed in the tumor region of glioma patients according to their response to treatment. Particularly the APTw-signal demonstrated moderate opposing trends for tumor growth versus PsPD as early as four weeks after RT (stable disease: -0.08/month [-0.15 to -0.01], progressive disease: +0.18/month [0.07 - 0.29], PsPD: -0.53/month [-0.65 to 0.42]). CONCLUSIONS:Our findings indicate that CEST contrasts reveal tumor-specific molecular changes in gliomas following RT. These early changes support the potential of CEST MRI to differentiate PsPD from tumor growth at later time points.

Advanced MRI techniques may provide non-invasive insight into the molecular heterogeneity of glioblastoma. Amide proton transfer-weighted (APTw) chemical exchange saturation transfer (CEST) MRI reflects endogenous protein and peptide content, but its clinical and molecular correlates in therapy-naive glioblastoma, IDH-wildtype, remain incompletely understood. This retrospective single-center study included 53 adult patients with therapy-naive glioblastoma, IDH-wildtype, who underwent preoperative APTw MRI. Median time between imaging and tissue sampling was two days. Median and 90th percentile (p90) APTw signal intensities were extracted from contrast-enhancing (T1-CE) tumor regions and FLAIR-hyperintense regions using automated deep learning-based segmentation with manual quality control. Histological and molecular analyses included MGMT promoter methylation, Ki-67 index, and DNA methylation-based subclassification. Associations were assessed using non-parametric tests, multivariable linear regression, and Cox regression analyses. APTw signal intensity was significantly higher in T1-CE tumor regions than in FLAIR-hyperintense regions (p < 0.0001). Within the T1-CE region, higher APTw signal intensity was modestly associated with younger age. Glioblastomas of the mesenchymal methylation subtype demonstrated significantly higher median and p90 APTw signal intensity compared with RTK1 and RTK2 subtypes, independent of MGMT status and Ki-67 index. APTw signal intensity was not independently associated with PFS or OS. APTw CEST MRI reflects molecular heterogeneity in therapy-naive IDH-wildtype glioblastoma, with potentially increased signal intensity in the mesenchymal subtype. These findings support its possible role as a complementary imaging biomarker for non-invasive molecular characterization.

Noninvasive magnetic resonance imaging (MRI) techniques are increasingly applied in the clinic with a fast-growing body of evidence regarding their value in diagnostic radiology. In contrast to biochemical or histological markers, the key advantages of imaging biomarkers are the noninvasive nature and the spatial and temporal resolution of these approaches. This chapter focuses on clinical applications of novel MR biomarkers in humans with a strong focus on oncologic diseases. These include both clinically established biomarkers (parts 1-4) and novel MRI techniques that recently demonstrated high potential for clinical utility (parts 5-7).

Abstract Background To assess the predictive value of different chemical exchange saturation transfer (CEST) contrasts, i.e. of the amide proton transfer (APT), relayed nuclear Overhauser effect (rNOE), and semi-solid magnetization transfer (ssMT), as well as of clinical routine perfusion- and diffusion-weighted MRI, in terms of treatment outcome in patients with glioma following surgery at baseline before radiotherapy at 3 T. Materials and methods From September 2018 to December 2022, 78 study participants (median age 62 years, 27/78 female) prospectively underwent CEST, diffusion, and perfusion imaging. CEST contrasts were reconstructed for the APT-weighted magnetization transfer ratio asymmetry (APTwasym), relaxation-compensated CEST metrics (MTRRexAPT, MTRRexNOE, MTRRexMT), and MTconst. Contrast-enhancing and whole tumor volumes were segmented on T2w-FLAIR and T1w images. Associations of mean contrast values with therapy response were tested using ROC analyses, while relationships with progression-free survival (PFS, median 6.04 months) and overall survival (OS, median 11.58 months), as well as added benefit compared to nCBV and ADC maps, were assessed using dichotomized Cox regression models. Results MTRRexAPT, MTRRexNOE, and MTRRexMT were associated with therapy response (AUC = 0.82, 0.81, 0.68; all p ≤ 0.03), PFS (HR = 2.92, 0.37, 3.40; all p ≤ 0.02), and OS (HR = 2.76, 0.63, 8.09; all p ≤ 0.05). MTconst was correlated with OS (HR = 5.52, p < 0.01), while APTwasym was linked to therapy response (AUC = 0.71, p = 0.02). MTRRexMT (χ² = 13.71, p < 0.01) and MTconst (χ² = 5.62, p = 0.018) provided each additional value to nCBV for OS prediction. Conclusion Relaxation-compensated CEST imaging of the APT, rNOE, and ssMT, as well as conventional APTwasym showed ability to predict treatment outcome, whilst ssMT-weighted imaging provided added benefit for OS prediction in patients with diffuse glioma following surgery at baseline before radiotherapy at 3 T.

Background Differentiating progressive disease (PD) from treatment-related effects (TRE) in glioblastoma remains challenging, particularly at single time point evaluations. TRE can occur at any disease stage, and its underlying biology is poorly understood. This study evaluates the clinical feasibility and diagnostic performance of amide proton transfer-weighted (APTw) MRI in this challenge. Methods Following the integration of APTw MRI into the routine clinical workflow for brain tumor imaging, we screened a total of 870 scans from 626 patients. APTw signal (voxel-based measurement) was automatically quantified in gadolinium-enhanced T1w and FLAIR regions of interest using a deep learning-based approach for 3D tumor segmentations. PD and TRE were compared using unpaired t-tests, and diagnostic accuracy was assessed via ROC- and logistic regression analysis. Results Among 256 MRI scans of 143 patients with glioblastoma, 65 scans showed PD (n = 42) or TRE (n = 23). The median APTw signal was higher in PD (2.23%) vs TRE (1.76%; P = .001). ROC analysis showed an area under the curve (AUC) of 0.82. In patients with early PD or TRE (<6 months post-radiotherapy), the AUC increased to 0.93. Anti-angiogenic therapy decreased APTw signal (P < .01). Combining APTw MRI with DWI and PWI improved diagnostic accuracy (AUC = 0.90). Conclusions APTw MRI is a non-invasive imaging tool that is feasible for clinical routine and aids in differentiation of early progression from pseudoprogression in glioblastoma. Its diagnostic accuracy decreases with application of anti-angiogenic treatment and at later follow-up time points. Highest diagnostic accuracy was found in a multimodal approach combining APTw MRI, PWI and DWI.

Radiology has evolved from the pioneering days of X-ray imaging to a field rich in advanced technologies on the cusp of a transformative future driven by artificial intelligence (AI). As imaging workloads grow in volume and complexity, and economic as well as environmental pressures intensify, visionary leadership is needed to navigate the unprecedented challenges and opportunities ahead. Leveraging its strengths in automation, accuracy and objectivity, AI will profoundly impact all aspects of radiology practice—from workflow management, to imaging, diagnostics, reporting and data-driven analytics—freeing radiologists to focus on value-driven tasks that improve patient care. However, successful AI integration requires strong leadership and robust governance structures to oversee algorithm evaluation, deployment, and ongoing maintenance, steering the transition from static to continuous learning systems. The vision of a “diagnostic cockpit” that integrates multidimensional data for quantitative precision diagnoses depends on visionary leadership that fosters innovation and interdisciplinary collaboration. Through administrative automation, precision medicine, and predictive analytics, AI can enhance operational efficiency, reduce administrative burden, and optimize resource allocation, leading to substantial cost reductions. Leaders need to understand not only the technical aspects but also the complex human, administrative, and organizational challenges of AI’s implementation. Establishing sound governance and organizational frameworks will be essential to ensure ethical compliance and appropriate oversight of AI algorithms. As radiology advances toward this AI-driven future, leaders must cultivate an environment where technology enhances rather than replaces human skills, upholding an unwavering commitment to human-centered care. Their vision will define radiology’s pioneering role in AI-enabled healthcare transformation. Question Artificial intelligence (AI) will transform radiology, improving workflow efficiency, reducing administrative burden, and optimizing resource allocation to meet imaging workloads’ increasing complexity and volume. Findings Strong leadership and governance ensure ethical deployment of AI, steering the transition from static to continuous learning systems while fostering interdisciplinary innovation and collaboration. Clinical relevance Visionary leaders must harness AI to enhance, rather than replace, the role of professionals in radiology, advancing human-centered care while pioneering healthcare transformation.

BACKGROUND AND PURPOSE:Intracranial hypotension (IH) results from cerebrospinal fluid (CSF) leakage from the dural sac, occurring spontaneously or iatrogenically (e.g., post-lumbar puncture), and may cause a wide range of symptoms with significant functional impairment. Accurate detection of the epidural CSF lamella is key to diagnosis. This study evaluated the diagnostic value of intravenous contrast-enhanced MRI using heavily T2-weighted FLAIR (HT2-FLAIR) spine imaging compared to nonenhanced MR myelography at 3 Tesla. METHODS:Ten consecutive patients with IH symptoms were prospectively examined using HT2-FLAIR imaging of the spine before and up to 3 h after gadolinium-based contrast agent administration, alongside noncontrast MR myelography. Two readers assessed the conspicuity of the CSF lamella on contrast-enhanced HT2-FLAIR (ceHT2-FLAIR) using a score from -2 to +2 and evaluated additional diagnostic benefit. RESULTS:A CSF lamella was seen in eight of 10 patients as a strongly enhancing band on ceHT2-FLAIR. In one case, the lamella was visible exclusively on ceHT2-FLAIR (conspicuity score [CS] = 2, n = 1) and was more conspicuous in three cases (CS = 1, n = 3). Six cases showed equal conspicuity (CS = 0, n = 6). In two cases each, ceHT2-FLAIR either enabled diagnosis or provided supporting information. In six cases, it confirmed diagnosis based on noncontrast imaging. Beyond improved conspicuity, ceHT2-FLAIR helped detect low-flow leaks, optimize axial slice positioning, and assess CSF lamella distribution. CONCLUSIONS:Intravenous ceHT2-FLAIR MRI may be considered as an additional tool in CSF leak evaluation, particularly when used for detecting indirect signs of IH.

IntroductionThe characterization of tumor microenvironment in vivo can be supported by 31P MRSI, a non-invasive technique that enables the determination of intracellular pH and magnesium ion concentration, among other parameters. However, it remains unclear from recent studies whether imaging biomarkers, like the intracellular pH value (as determined conventionally via the chemical shift separation between inorganic phosphate (Pi) and phosphocreatine), are correlated with different glioma subtypes. Therefore, this study aimed to explore the behavior of multiple chemical shifts, specifically those of Pi and adenosine triphosphate (ATP), to approach a more detailed characterization of glioma tissues.MethodsA retrospective analysis on 31P MRSI datasets from 11 patients with newly diagnosed glioma acquired at 7 T prior to any treatment was conducted. Mean values of the quantified chemical shifts of Pi, γ-, α- and β-ATP across different regions-of-interest were determined for each patient separately. The mean chemical shifts were compared for different tumor sub-compartments and for different IDH mutation status.ResultsIn high-grade gliomas, significant differences in chemical shifts were observed between tumor and healthy tissue. In low-grade glioma, smaller differences were found for the chemical shifts of Pi, γ- and α-ATP than in the high-grade glioma. The latter pattern was not observed for β-ATP resonances, where the mean chemical shift across the tumor was comparably high between low-grade and high-grade glioma. In patients with IDH-wildtype, slightly stronger shifts of Pi and γ-ATP peaks were observed than for patients with IDH-mutant. No differences between IDH-wildtype and IDH-mutant were observed for the chemical shifts of α- and β-ATP.DiscussionThese findings suggest a potential benefit of a joint evaluation of Pi and ATP chemical shifts for possible discrimination of different glioma subtypes. Using the complementary information of multiple 31P chemical shifts could improve the characterization of tumor tissue and provide new insights beyond current knowledge.

Chemical exchange saturation transfer (CEST) MRI is a promising molecular imaging technique with established clinical relevance in neuro-oncology. While CEST contrast differences between gray matter (GM) and white matter (WM) are documented, brain region-specific contrast variations remain underexplored. This study investigates the regional variability of CEST contrasts in healthy brains to provide a baseline reference, which could enhance the detection of subtle pathological changes in clinical settings. Ten healthy volunteers (five female, mean age 25 ± 3.1 years) underwent 3D CEST imaging on a 3-T Siemens Prisma scanner. Using a custom segmentation tool, GM and WM regions of interest (ROIs) were automatically selected in the frontal, parietotemporal, and occipital regions and the calcarine sulcus to analyze regional contrast changes for the relaxation-compensated MTRRex and asymmetry-based APTw CEST contrasts. Individual and grouped analyses showed significant regional differences in GM and WM for all CEST contrasts. Globally, significant GM-WM differences were also detected for the APTw, MTRRex AMIDE, and MTRRex ssMT, which demonstrated higher GM contrast values for APTw and MTRRex AMIDE and lower GM contrast values for the MTRRex ssMT. Regionally, all contrasts showed reduced GM signals in the frontal lobe and increased signals in the calcarine sulcus when compared to the occipital and parietotemporal lobe; however, these differences were less pronounced for MTRRex rNOE and MTRRex ssMT. Relaxation-compensated CEST and APTw CEST contrast values exhibit significant regional variation in the healthy brain, highlighting the importance of consistent ROI placement in clinical studies. At the same time, low intersubject variability was observed, providing robust normative values for future comparisons. These regional reference values can aid in the detection of subtle pathological changes in CEST MRI by offering a reliable baseline for interpreting deviations in patient data.

BACKGROUND:7T MRI received FDA/CE clearance almost 7 years ago. However, until today, it has not yet been widely adopted in clinical routine. This is mainly due to field inhomogeneities that impede whole-brain coverage. Moreover, the long scan times often associated with high-resolution imaging are an additional limiting factor. PURPOSE:To combine calibration-free parallel transmit technology (pTx) using universal pulses (UP) with advanced imaging acceleration strategies to achieve homogenous multicontrast 7T MRI with whole-brain coverage and high spatial resolution in short scan time. MATERIALS AND METHODS:Ten healthy volunteers were scanned both with conventional vendor-provided sequences and with custom sequences for anatomical whole-brain imaging [-weighted, -weighted, FLAIR, and susceptibility-weighted]. The scan times for the 2 anatomical protocols were matched (25 minutes). In addition, a quantitative MRI protocol [multi-parametric mapping (MPM) and chemical exchange saturation transfer (CEST)] was scanned twice using custom sequences with conventional (circular polarized) and UPs, respectively, in a scan time of 2×25 minutes. Moreover, 4 patients with different neurological diseases were scanned, namely temporal lobe epilepsy, spinocerebellar ataxia, cerebral amyloid angiopathy, and glioblastoma. For the patients, only optimized custom sequences with UPs were acquired. RESULTS:Compared with conventional implementations, the custom sequences provide strongly improved image homogeneity and quality with significantly higher SNR and CNR across the whole brain, including cerebellum and brain stem. Moreover, UPs improve the repeatability of derived quantitative parameters. The suggested protocol has additionally been successfully demonstrated in 4 patients with different neurological pathologies. CONCLUSIONS:Homogeneous whole-brain 7T MRI with high spatial resolution and high image quality is possible in clinically feasible scan times. The developed protocol can be applied without any expert knowledge and is ready for clinical use. The approach could largely extend applicability of UHF MRI in neuroradiology paving the way for increased routine use of 7T MRI.

Objectives Double-dose contrast-enhanced brain imaging improves tumor delineation and detection of occult metastases but is limited by concerns about gadolinium-based contrast agents' effects on patients and the environment. The purpose of this study was to test the benefit of a deep learning–based contrast signal amplification in true single-dose T1-weighted (T-SD) images creating artificial double-dose (A-DD) images for metastasis detection in brain magnetic resonance imaging. Materials and Methods In this prospective, multicenter study, a deep learning–based method originally trained on noncontrast, low-dose, and T-SD brain images was applied to T-SD images of 30 participants (mean age ± SD, 58.5 ± 11.8 years; 23 women) acquired externally between November 2022 and June 2023. Four readers with different levels of experience independently reviewed T-SD and A-DD images for metastases with 4 weeks between readings. A reference reader reviewed additionally acquired true double-dose images to determine any metastases present. Performances were compared using Mid-p McNemar tests for sensitivity and Wilcoxon signed rank tests for false-positive findings. Results All readers found more metastases using A-DD images. The 2 experienced neuroradiologists achieved the same level of sensitivity using T-SD images (62 of 91 metastases, 68.1%). While the increase in sensitivity using A-DD images was only descriptive for 1 of them (A-DD: 65 of 91 metastases, +3.3%, P = 0.424), the second neuroradiologist benefited significantly with a sensitivity increase of 12.1% (73 of 91 metastases, P = 0.008). The 2 less experienced readers (1 resident and 1 fellow) both found significantly more metastases on A-DD images (resident, T-SD: 61.5%, A-DD: 68.1%, P = 0.039; fellow, T-SD: 58.2%, A-DD: 70.3%, P = 0.008). They were therefore able to use A-DD images to increase their sensitivity to the neuroradiologists' initial level on regular T-SD images. False-positive findings did not differ significantly between sequences. However, readers showed descriptively more false-positive findings on A-DD images. The benefit in sensitivity particularly applied to metastases ≤5 mm (5.7%–17.3% increase in sensitivity). Conclusions A-DD images can improve the detectability of brain metastases without a significant loss of precision and could therefore represent a potentially valuable addition to regular single-dose brain imaging.

Abstract Background The discovery of cellular tumor networks in glioblastoma, with routes of malignant communication extending far beyond the detectable tumor margins, has highlighted the potential of supramarginal resection strategies. Retrospective data suggest that these approaches may improve long-term disease control. However, their application is limited by the proximity of critical brain regions and vasculature, posing challenges for validation in randomized trials. Anterior temporal lobectomy (ATL) is a standardized surgical procedure commonly performed in patients with pharmacoresistant temporal lobe epilepsy. Translating the ATL approach from epilepsy surgery to the neuro-oncological field may provide a model for investigating supramarginal resection in glioblastomas located in the anterior temporal lobe. Methods The ATLAS/NOA-29 trial is a prospective, multicenter, multinational, phase III randomized controlled trial designed to compare ATL with standard gross-total resection (GTR) in patients with newly-diagnosed anterior temporal lobe glioblastoma. The primary endpoint is overall survival (OS), with superiority defined by significant improvements in OS and non-inferiority in the co-primary endpoint, quality of life (QoL; “global health” domain of the European organization for research and treatment of cancer (EORTC) QLQ-C30 questionnaire). Secondary endpoints include progression-free survival (PFS), seizure outcomes, neurocognitive performance, and the longitudinal assessment of six selected domains from the EORTC QLQ-C30 and BN20 questionnaires. Randomization will be performed intraoperatively upon receipt of the fresh frozen section result. A total of 178 patients will be randomized in a 1:1 ratio over a 3-year recruitment period and followed-up for a minimum of 3 years. The trial will be supervised by a Data Safety Monitoring Board, with an interim safety analysis planned after the recruitment of the 57th patient to assess potential differences in modified Rankin Scale (mRS) scores between the treatment arms 6 months after resection. Assuming a median improvement in OS from 17 to 27.5 months, the trial is powered at > 80% to detect OS differences with a two-sided log-rank test at a 5% significance level. Discussion The ATLAS/NOA-29 trial aims to determine whether ATL provides superior outcomes at equal patients’ Qol compared to GTR in anterior temporal lobe glioblastoma, potentially establishing ATL as the surgical approach of choice for isolated temporal glioblastoma and redefining the standard of care for this patient population. Trial registration German Clinical Trials Register (DRKS00035314), registered on October 18, 2024.

Many neurological diseases are characterized by the accumulation of toxic proteins in the brain. This accumulation has been associated with improper clearance from the parenchyma. Recent discoveries highlighted perivascular spaces, which are cerebrospinal fluid (CSF)-filled spaces, as the channels of brain clearance. The forces driving CSF mobility within perivascular spaces are still debated. Here we present a noninvasive, CSF-specific magnetic resonance imaging technique (CSF-Selective T2-prepared REadout with Acceleration and Mobility-encoding) that enables detailed in vivo measurement of CSF mobility in humans, down to the level of perivascular spaces located around penetrating vessels, which is close to protein production sites. We find region-specific drivers of CSF mobility and demonstrate that CSF mobility can be increased by entraining vasomotion. Furthermore, we find region-specific CSF mobility alterations in patients with cerebral amyloid angiopathy, a brain disorder associated with clearance impairment. The availability of this technique opens up avenues to investigate the impact of CSF-mediated clearance in neurodegeneration and sleep.

Objectives Small lesions are the limiting factor for reducing gadolinium-based contrast agents in brain magnetic resonance imaging (MRI). The purpose of this study was to compare the sensitivity and precision in metastasis detection on true contrast-enhanced T1-weighted (T1w) images and artificial images synthesized by a deep learning method using low-dose images. Materials and Methods In this prospective, multicenter study (5 centers, 12 scanners), 917 participants underwent brain MRI between October 2021 and March 2023 including T1w low-dose (0.033 mmol/kg) and full-dose (0.1 mmol/kg) images. Forty participants with metastases or unremarkable brain findings were evaluated in a reading (mean age ± SD, 54.3 ± 15.1 years; 24 men). True and artificial T1w images were assessed for metastases in random order with 4 weeks between readings by 2 neuroradiologists. A reference reader reviewed all data to confirm metastases. Performances were compared using mid-P McNemar tests for sensitivity and Wilcoxon signed rank tests for false-positive findings. Results The reference reader identified 97 metastases. The sensitivity of reader 1 did not differ significantly between sequences (sensitivity [precision]: true, 66.0% [98.5%]; artificial, 61.9% [98.4%]; P = 0.38). With a lower precision than reader 1, reader 2 found significantly more metastases using true images (sensitivity [precision]: true, 78.4% [87.4%]; artificial, 60.8% [80.8%]; P < 0.001). There was no significant difference in sensitivity for metastases ≥5 mm. The number of false-positive findings did not differ significantly between sequences. Conclusions One reader showed a significantly higher overall sensitivity using true images. The similar detection performance for metastases ≥5 mm is promising for applying low-dose imaging in less challenging diagnostic tasks than metastasis detection.

Pseudovestibular syndrome refers to central pathologies that mimic acute unilateral peripheral vestibulopathy, often posing a diagnostic challenge, particularly when key symptoms indicating a central origin are absent. The most common etiology is brain ischemia resulting from posterior inferior cerebellar artery occlusion. This article presents a rare case of a left paramedian cerebellar hemorrhage initially misdiagnosed as right-sided vestibular neuritis. Cerebellar hemorrhage can induce pseudovestibular syndrome by disrupting the connective fibers from the flocculus to the ipsilateral vestibular nucleus in the pons. Additionally, central pathologies affecting the vestibular system may occasionally manifest a pathological vestibulo-ocular reflex. This case report underscores the importance of considering potentially severe central-origin conditions in the differential diagnosis of seemingly benign unilateral peripheral vestibulopathy.

OBJECTIVES:The aim of this study was to determine whether ChatGPT-4 can correctly suggest MRI protocols and additional MRI sequences based on real-world Radiology Request Forms (RRFs) as well as to investigate the ability of ChatGPT-4 to suggest time saving protocols. MATERIAL & METHODS:Retrospectively, 1,001 RRFs of our Department of Neuroradiology (in-house dataset), 200 RRFs of an independent Department of General Radiology (independent dataset) and 300 RRFs from an external, foreign Department of Neuroradiology (external dataset) were included. Patients' age, sex, and clinical information were extracted from the RRFs and used to prompt ChatGPT- 4 to choose an adequate MRI protocol from predefined institutional lists. Four independent raters then assessed its performance. Additionally, ChatGPT-4 was tasked with creating case-specific protocols aimed at saving time. RESULTS:Two and 7 of 1,001 protocol suggestions of ChatGPT-4 were rated "unacceptable" in the in-house dataset for reader 1 and 2, respectively. No protocol suggestions were rated "unacceptable" in both the independent and external dataset. When assessing the inter-reader agreement, Coheńs weighted ĸ ranged from 0.88 to 0.98 (each p < 0.001). ChatGPT-4's freely composed protocols were approved in 766/1,001 (76.5 %) and 140/300 (46.67 %) cases of the in-house and external dataset with mean time savings (standard deviation) of 3:51 (minutes:seconds) (±2:40) minutes and 2:59 (±3:42) minutes per adopted in-house and external MRI protocol. CONCLUSION:ChatGPT-4 demonstrated a very high agreement with board-certified (neuro-)radiologists in selecting MRI protocols and was able to suggest approved time saving protocols from the set of available sequences.

Background The optimal salvage therapy for recurrent MGMT-methylated glioblastoma (GBM), IDH wildtype, remains undefined. While lomustine is often used in clinical trials and considered standard-of-care, cumulative toxicity precludes its use in patients previously treated with lomustine/temozolomide. The role of temozolomide rechallenge in this setting is unclear. Methods This monocentric retrospective study included 70 patients with MGMT-methylated GBM, IDH wildtype, who received lomustine/temozolomide as first-line therapy. Descriptive data on second-line therapies were collected, and therapy responses were assessed. Survival outcomes were evaluated using Kaplan-Meier analysis. Results Of 55 patients with documented tumor progression, 40 patients received second-line therapy. The most frequently used systemic therapy was temozolomide (n = 33, 79% of patients with second-line therapy), with a median number of 6 cycles and hematotoxicity grade 3 or 4 observed in <20% of patients. Among patients receiving temozolomide only, stable disease or partial response was achieved in 53.3%, with a progression-free survival rate at 6 months after first recurrence of 50% and a 1-year OS rate of 45%. Conclusions Temozolomide rechallenge is a common, safe, and effective second-line option for patients with MGMT-methylated, IDH wildtype GBM following first-line lomustine/temozolomide therapy. These findings support its consideration as a salvage therapy in appropriate clinical scenarios.

BACKGROUND:Perfusion magnetic resonance imaging (MRI)s plays a central role in the diagnosis and monitoring of neurovascular or neurooncological disease. However, conventional processing techniques are limited in their ability to capture relevant characteristics of the perfusion dynamics and suffer from a lack of standardization. PURPOSE:We propose a physics-informed deep learning framework which is capable of analyzing dynamic susceptibility contrast perfusion MRI data and recovering the dynamic tissue response with high accuracy. METHODS:The framework uses physics-informed neural networks (PINNs) to learn the voxel-wise TRF, which represents the dynamic response of the local vascular network to the contrast agent bolus. The network output is stabilized by total variation and elastic net regularization. Parameter maps of normalized cerebral blood flow (nCBF) and volume (nCBV) are then calculated from the predicted residue functions. The results are validated using extensive comparisons to values derived by conventional Tikhonov-regularized singular value decomposition (TiSVD), in silico simulations and an in vivo dataset of perfusion MRI exams of patients with high-grade gliomas. RESULTS:The simulation results demonstrate that PINN-derived residue functions show a high concordance with the true functions and that the calculated values of nCBF and nCBV converge towards the true values for higher contrast-to-noise ratios. In the in vivo dataset, we find high correlations between conventionally derived and PINN-predicted perfusion parameters (Pearson's rho for nCBF: 0.84 ± 0.03 $0.84 \pm 0.03$ and nCBV: 0.92 ± 0.03 $0.92 \pm 0.03$ ) and very high indices of image similarity (structural similarity index for nCBF: 0.91 ± 0.03 $0.91 \pm 0.03$ and for nCBV: 0.98 ± 0.00 $0.98 \pm 0.00$ ). CONCLUSIONS:PINNs can be used to analyze perfusion MRI data and stably recover the response functions of the local vasculature with high accuracy.