BACKGROUND:Choroidal fissure cysts (CFCs) are considered benign, static lesions within the brain's choroidal fissure. However, their behavior over time remains incompletely understood. OBJECTIVE:To investigate longitudinal changes in CFC size and morphology and assess associated hippocampal mass effect. METHODS:This retrospective longitudinal study included patients with CFCs measuring ≥2 mm on initial magnetic resonance imaging (MRI) who also had follow-up MRI. Changes in cyst size were categorized as increase, decrease, or no change, with significant change defined as ≥0.2 mL from baseline. To account for the confounding effects of rapid brain growth, patients younger than 5 years were analyzed separately from those aged 5 years and older. RESULTS:A total of 42 patients with 43 cysts were included. Among 35 patients aged ≥5 years (mean age, 18 years; range, 5-54 years), mean cyst volume was 1.1 mL, with diameters ranging from 3 to 31 mm. Appreciable hippocampal mass effect was present in 21 cases (60%). Mean follow-up interval was 5.7 years (range, 1 month to 23.6 years). Cyst size increased in 2 cases (6%), decreased in 11 (31%), and remained stable in 22 (63%). In patients younger than 5 years (7 patients, 8 cysts), cysts increased in 3 (38%), decreased in 3 (38%), and remained unchanged in 2 (25%). CONCLUSION:CFCs can demonstrate significant interval size changes, challenging the traditional view of these lesions as static. More than one-third of cysts in patients aged ≥5 years changed over time, and appreciable hippocampal mass effect was common.

Stroke diagnoses may be missed or delayed in patients presenting to the emergency department (ED) with acute dizziness or vertigo. Even in patients who do not receive acute stroke treatment, accurate diagnosis is still essential to improve outcomes to ensure appropriate risk stratification and initiation of secondary prevention strategies. High-field MRI is the most sensitive imaging modality, but is not immediately available at many EDs. To investigate the cost-effectiveness of alternate neuroimaging approaches in the evaluation of patients presenting to the emergency department (ED) with dizziness when high-field MRI is not available. A Markov decision-analytic model was constructed from a healthcare system perspective for evaluation of a patient presenting to the ED with acute vestibular syndrome (AVS) – the dizziness subtype most concerning for stroke. Six diagnostic strategies were compared: non-contrast head CT, head and neck CTA (added to non-contrast CT), whole brain perfusion CT (CTP) added to CT and CTA, low-field portable MRI, admission to observation for high-field MRI, and inter-facility transport to high-field MR. Differing long-term costs and outcomes related to stroke detection and secondary prevention were compared. Cost-effectiveness was calculated in terms of lifetime expenditures in 2024 U.S. dollars for each quality-adjusted life year (QALY); deterministic and probabilistic sensitivity analyses were performed. Observation for high-field MRI resulted in the highest QALYs and was the most cost-effective strategy. Transport to high-field MRI had an incremental cost of 5402, but negative marginal utility (-0.0047 QALYs) compared to observation. CTP (added to CTA and CT) had the next-highest health benefit, although was dominated by extension, at an incremental cost of1022 for an additional 0.02 QALYs, compared to low-field MRI. CTA and non-contrast CT alone had the lowest utility. In the deterministic sensitivity analyses, observation for high-field MRI remained the most cost-effective strategy across a wide range of model parameters. Relative benefit was largely driven by differences in imaging sensitivity. Probabilistic sensitivity analyses yielded similar results to the base-case analysis. Observation for high-field MRI in patients presenting to the ED with AVS-type dizziness can is more cost-effective and improves long-term outcomes compared to CT and CTA. When high-field MRI is not available via observation or transport, both CTP and low-field MRI are reasonable alternatives. When high-field MRI is not immediately available, short delays in imaging associated with observation or transport do not alter the preference for MRI-based evaluation. CTP and low-field MRI are preferred to CTA or CT alone. In this Markov decision-analytic model, when high-field MRI is not available, admission to observation for conventional MRI was associated with the highest QALYs. CT perfusion (added to CT and CTA) was associated with the next highest QALYs; low-field portable MRI had similar utility and cost-effectiveness. CTA-only and CT-only imaging had the lowest utility. Cost-effectiveness was largely driven by differences in sensitivity of imaging modalities. Choosing the imaging modality with the highest sensitivity for stroke to evaluate patients with dizziness/vertigo is likely to be cost-effective in the long-term, even if sensitive testing requires greater upfront costs.

Vestibular schwannomas (VS) are monitored for growth after stereotactic radiosurgery (SRS) using serial MRI. Conventional measurements often miss internal regrowth within necrotic/cystic tumor components—a subtle and difficult-to-detect imaging scenario that may indicate treatment failure. We evaluated a custom AI-based segmentation tool to detect internal tumor regrowth after SRS, comparing it with expert segmentation for spatial agreement, volumetric change, and radiographic failure classification (≥ 20

BACKGROUND:Vestibular schwannomas (VS) are benign tumors that can lead to hearing loss, balance issues, and tinnitus. Gamma Knife Radiosurgery (GKS) is a common treatment for VS, aimed at halting tumor growth and preserving neurological function. Accurate monitoring of VS volume before and after GKS is essential for assessing treatment efficacy. PURPOSE:To evaluate the accuracy of an artificial intelligence (AI) algorithm, originally developed to identify NF2-SWN-related VS, in segmenting non-NF2-SWN-related VS and detecting volume changes pre- and post-GKS. We hypothesize this AI algorithm, trained on NF2-SWN-related VS data, will accurately apply to non-NF2-SWN VS and VS treated with GKS. METHODS:In this retrospective cohort study, we reviewed data from an established Gamma Knife database, identifying 16 patients who underwent GKS for VS and had pre- and post-GKS scans. Contrast-enhanced T1-weighted MRI scans were analyzed with both manual segmentation and the AI algorithm. DICE similarity coefficients were computed to compare AI and manual segmentations, and a paired t-test was used to assess statistical significance. Volume changes for pre- and post-GKS scans were calculated for both segmentation methods. RESULTS:The mean DICE score between AI and manual segmentations was 0.91 (range 0.79-0.97). Pre- and post-GKS DICE scores were 0.91 (range 0.79-0.97) and 0.92 (range 0.81-0.97), indicating high spatial overlap. CONCLUSION:AI-segmented VS volumes pre- and post-GKS were consistent with manual measurements, with high DICE scores indicating strong spatial overlap. The AI algorithm processed scans within 5 min, suggesting it offers a reliable, efficient alternative for clinical monitoring. CLINICAL IMPORTANCE:DICE scores showed high similarity between manual and AI segmentations. The pre- and post-GKS VS volume percentage changes were also similar between manual and AI-segmented VS volumes, indicating that our AI algorithm can accurately detect changes in tumor growth.

Despite continuous advancements in cancer treatment, brain metastatic disease remains a significant complication of primary cancer and is associated with an unfavorable prognosis. One approach for improving diagnosis, management, and outcomes is to implement algorithms based on artificial intelligence for the automated segmentation of both pre- and post-treatment MRI brain images. Such algorithms rely on volumetric criteria for lesion identification and treatment response assessment, which are still not available in clinical practice. Therefore, it is critical to establish tools for rapid volumetric segmentations methods that can be translated to clinical practice and that are trained on high quality annotated data. The BraTS-METS 2025 Lighthouse Challenge aims to address this critical need by establishing inter-rater and intra-rater variability in dataset annotation by generating high quality annotated datasets from four individual instances of segmentation by neuroradiologists while being recorded on video (two instances doing "from scratch" and two instances after AI pre-segmentation). This high-quality annotated dataset will be used for testing phase in 2025 Lighthouse challenge and will be publicly released at the completion of the challenge. The 2025 Lighthouse challenge will also release the 2023 and 2024 segmented datasets that were annotated using an established pipeline of pre-segmentation, student annotation, two neuroradiologists checking, and one neuroradiologist finalizing the process. It builds upon its previous edition by including post-treatment cases in the dataset. Using these high-quality annotated datasets, the 2025 Lighthouse challenge plans to test benchmark algorithms for automated segmentation of pre-and post-treatment brain metastases (BM), trained on diverse and multi-institutional datasets of MRI images obtained from patients with brain metastases.

Li-Fraumeni syndrome (LFS) is a rare autosomal dominant hereditary disorder most frequently caused by pathogenic variants in the TP53 tumor suppressor gene, resulting in impaired regulation of cellular proliferation and apoptosis. Individuals with LFS are predisposed to a spectrum of malignancies affecting multiple organ systems, including the lungs. Lung adenocarcinoma is among the recognized neoplasms that may arise in this population and can be driven by activating mutations in the epidermal growth factor receptor (EGFR) gene. While the coexistence of TP53 and EGFR mutations have been reported, the underlying mechanisms contributing to this association is poorly understood. We present a case of a patient with LFS who developed synchronous bilateral lung adenocarcinomas harboring distinct activating EGFR mutations: L858R point mutation and exon 19 deletion.

BACKGROUND AND PURPOSE:Despite the widespread research application of radiomics, there is a knowledge gap regarding the optimal voxel intensity normalization strategy for FDG-PET radiomics. We investigated the impact of 3 normalization strategies on the prognostic utility of individual radiomic features and machine learning models in patients with oropharyngeal squamous cell carcinoma (OPSCC). MATERIALS AND METHODS:We included n=330 (overall survival [OS] study group), n=335 (progression-free survival [PFS] study group), and n=309 (locoregional progression [LRP] study group) patients with OPSCC. Three FDG-PET intensity normalization strategies were applied: the conventional body weight-corrected standardized uptake value (SUV), and standardized uptake ratios to the lentiform nucleus and to the cerebellum. The raw PET voxel intensities were also analyzed. To quantify and compare the features' association with oncologic outcome, we fitted univariate Cox regression models, calculated Harrell concordance index (C-index), and fitted random survival forest (RSF) machine learning algorithms. RESULTS:All normalization strategies tended to improve the prognostic value of radiomic features. Features from lentiform nucleus-normalized PET demonstrated the highest prognostic improvement, with n=750/1037, n=809/1037, and n=652/1037 primary tumor features attaining a significant association with OS, PFS, and LRP, respectively, compared with n=0, n=211, and n=1 SUV-based PET features, respectively. The median C-index of lentiform nucleus-normalized PET features was 0.64, 0.61, and 0.62 for OS, PFS, and LRP, respectively, while SUV-based PET features reached 0.59, 0.58, and 0.60, respectively. The best performing lentiform nucleus-normalization RSF model significantly outperformed the raw PET RSF model in predicting OS (C-index = 0.66 versus C-index = 0.57; P = .019), with model comparisons for PFS and LRP approaching statistical significance (P = .053 and P = .084, respectively). In contrast, the best performing SUV-based RSF models were not significantly different from raw PET models. CONCLUSIONS:Normalizing PET intensities, especially to the lentiform nucleus, improves the prognostic performance of individual radiomic features and machine learning models in predicting oncologic outcome.

BACKGROUND:Obstructive sleep apnea (OSA) may be more prevalent in people with multiple sclerosis (MS) and previous work suggests possible association with demyelinating brainstem lesions. OBJECTIVES:The objectives of this study were to assess the relationship between demyelinating brainstem lesions in patients with MS referred for polysomnography (PSG) and the severity of the apnea-hypopnea index (AHI). METHODS:A total of 122 people with MS or clinically isolated syndrome (CIS) who underwent PSG due to concern for OSA or hypersomnia at two institutions between 2010 and 2022 were included. AHI was associated with the number of and presence of brainstem demyelinating lesions on magnetic resonance imaging (MRI) obtained within 1 year of PSG after controlling for body mass index (BMI), age, sleep study type, study center, and study year. RESULTS:Having one brainstem lesion was significantly associated with mildly elevated AHI (5 ⩽ AHI < 15; odds ratio (OR) = 2.71, 95% confidence interval (CI) = 1.29-5.67) and two or more lesions was associated with higher odds of mildly elevated AHI (OR = 3.27, 95% CI = 1.83-5.85) and moderately/severely elevated AHI (AHI > 15; OR = 3.23, 95% CI = 1.91-5.47). The presence of brainstem demyelinating lesion(s) conferred a higher odds of mildly elevated AHI (OR = 3.00, 95% CI = 1.75-5.16) and moderately/severely elevated AHI (OR = 1.65, 95% CI = 1.08-2.52). CONCLUSIONS:These data suggest that brainstem lesions may be associated with elevated AHI in people with MS.

Bronchoscopic lung volume reduction (BLVR) is a minimally invasive intervention that improves dyspnea and quality of life in select individuals with emphysema. Echocardiography is the initial screening tool for pulmonary hypertension (PH) in patients evaluated for BLVR. Multiple BLVR and lung volume reduction surgery (LVRS) trials have used and right ventricular systolic pressure (RVSP) of 45 mm Hg as a cutoff for potential significant PH. However, PH is established hemodynamically by right heart catheterization (RHC), not echocardiography due to notoriously inaccurate RSVP values in patients with lung disease, especially those with COPD and suboptimal acoustic imaging windows. Over a 5-year period, all patients who met PFT criteria for BLVR underwent a routine screening echocardiogram for PH. Twenty-four patients with a RVSP >45 mm Hg or suspicion of significant PH on echocardiography were subjected to RHC. Twenty-one (88%) with suspicion for significant PH based on echocardiography did not have significant PH on RHC. Three patients (12%) had significant PH based on RHC precluding them from BLVR. Ten of the 21 patients with echo suspected PH, but RHC negative PH qualified for BLVR. Twelve-month follow-up data was available for 7 of these patients post-BLVR that included change in forced expiratory volume in 1 second (FEV1), 6-minute walk distance (6MWD), and St. George’s Respiratory Questionnaire (SGRQ). The mean change in FEV1 showed an increase of 0.154 L, 6MWD increase of 42 m, and SGRQ decrease of 11.5 points. On the basis of results from this study, all patients being evaluated for BLVR found to have a RVSP over 45 mm Hg on echocardiography should undergo RHC to confirm significant PH.

BACKGROUND:Bronchoscopic lung volume reduction (BLVR) is a minimally invasive procedure used to reduce shortness of breath and improve functionality in some patients with emphysema. While BLVR is often effective for improving dyspnea by causing target lobe atelectasis, the treatment effect can sometimes be lost. This study reviews the incidence of revision bronchoscopies in patients who lost or never achieved target lobe atelectasis following BLVR. METHODS:This retrospective, single-center analysis reviewed patients who underwent BLVR over a 5-year period. All patients were determined to be collateral ventilation negative by an intraprocedural Chartis system assessment. Treatment success was defined as radiographic target lobe atelectasis. For patients who underwent revision bronchoscopies, the EMR was used to review procedure notes, radiographic imaging, post-BLVR analyses, and outpatient clinic notes to collect data on the indication for revision bronchoscopy, intraprocedural observations accounting for loss of treatment effect, revision interventions performed, and outcomes of revision bronchoscopies. After a minimum of 10 postoperative days, at the discretion of the treating physician, an EBV revision bronchoscopy could be performed if target lobe atelectasis was lost or never developed after initial treatment. RESULTS:Forty-three total valve revision procedures were performed, based on first, second, and third bronchoscopies combined. The most common cause for revision bronchoscopy based on the intraoperative assessment was air leaking around one or more valves from either incorrect sizing of previous valves or airway stretching in 18 revision procedures (42%). Thirty-four revision procedures (79%) were performed for loss of previous atelectasis, and 24 (70%) resulted in the redevelopment of target lobe atelectasis. Nine revision procedures (21%) were performed for lack of initial target lobe atelectasis. Two of the 9 revision procedures (22%) performed for failure to achieve initial atelectasis resulted in new target lobe atelectasis. CONCLUSION:Post-BLVR revision bronchoscopies are necessary in ∼20% of patients for either loss of target lobe atelectasis or failure to achieve atelectasis after the initial BLVR procedure. In many cases, especially when atelectasis is lost, revision bronchoscopies can reestablish post-BLVR atelectasis.

IntroductionNeurofibromatosis type 2 related Schwannomatosis (NF2-SWN) is a genetic disorder characterized by the growth of vestibular schwannomas (VS), which often leads to progressive hearing loss and vestibular dysfunction. Accurate volumetric assessment of VS tumors is crucial for effective monitoring and treatment planning. Since tumor growth dynamics are often subtle, the resolution of MRI scans plays a critical role in detecting small volumetric changes that inform clinical decisions. This study evaluates the impact of MRI voxel resolution on the accuracy of manual and AI-driven volumetric segmentation of VS in NF2-SWN patients.MethodsTen patients with NF2-SWN, totaling 17 tumors, underwent high-resolution MRI scans with varying voxel sizes on different MRI machines at Yale New Haven Hospital. Tumors were segmented using both manual and AI-based methods, and the effect of voxel size on segmentation precision was quantified through volume measurements, Dice similarity coefficients, and Hausdorff distances.ResultsResults indicate that larger voxel sizes (1.2 × 0.9 × 4.0 mm) significantly reduced segmentation accuracy when compared to smaller voxel sizes (0.5 × 0.5 × 0.8 mm). In addition, AI-based segmentation outperformed manual methods, particularly at larger voxel sizes.DiscussionThese findings highlight the importance of optimizing voxel resolution for accurate tumor monitoring and suggest that AI-driven segmentation may improve consistency and precision in NF2-SWN tumor surveillance.

Traumatic brain injury (TBI) is a leading cause of disability worldwide. Yet, our understanding of the mechanisms of this condition is limited, especially in the acute setting. Here, we investigated the relationship between functional connectivity and common clinical assessments, like the Glasgow Coma Scale (GCS) at admission and modified Rankin scale at 3-months (mRS) to determine if functional connectivity can provide a broader representation of the brain's networks than these standard tests. We performed a retrospective analysis of resting state functional MRI and clinical data in 58 patients (41.28 ± 18.63) scanned acutely/subacutely (≤ 31 days). Then, for a secondary analysis, we included 50 more patients who presented after either a first or a repeat incident and were scanned either acutely/subacutely or chronically (<2 yrs) (all together 108 patients, 46.4 ± 20.1yrs). Using a 268-node functional atlas, we derived 35,778 unique edges, based on which we calculated the mean functional connectivity of 10 resting state networks and used those to establish a link to TBI severity and functional outcome. Our analysis showed that when dividing sub/acute patients (n=58) based on GCS severity, only the Subcortical network showed a significant discrimination between mild and moderate-severe GCS at admission (P<0.001), with hyperconnectivity noted in mild patients, and hypoconnectivity - in moderate-severe GCS patients. This difference appeared to be mainly driven by the thalami (Right, P=0.002; Left P<0.001). Similar results were observed when investigating GCS subscores at admission (Eyes, Motor, Verbal, all P<0.001). Further, when evaluating mRS outcomes at 3-months against functional connectivity, differences were noted within the Motor, Cerebellum and Medial-Frontal networks, though none survived multiple comparisons. Importantly, we found the DMN and mRS to be correlated but with a limited relationship (r 2 = 0.18). Lastly, we performed a post-hoc analysis (n=108) to investigate if the hyperconnectivity in the Subcortical network of sub/acute mild GCS patients remained irrespective of acuity of scanning (i.e. acute/ chronic) or frequency of TBI (i.e. first/ repeat). Our analysis showed that GCS severity appeared to be the main driver of functional connectivity within the Subcortical network, whereas acuity of scanning, alongside GCS severity contributed to the results of chronically scanned patients. While GCS and 3-month mRS scores offer some meaningful insights, their limited capture of the neural representation underscores the need to investigate whether other early clinical assessments correlate more robustly with early resting state networks or whether such networks themselves could predict future outcomes.

PURPOSE:Anti-vascular endothelial growth factor therapy enhances PD-1 inhibitor activity in preclinical models and has been used to treat perilesional cerebral edema and radiation necrosis. METHODS:We conducted a two-institution phase II trial of bevacizumab and pembrolizumab in patients with untreated melanoma brain metastasis (MBM) (ClinicalTrials.gov identifier: NCT02681549). Patients were anti-PD-(L)-1-naïve, and had ≥one asymptomatic, nonhemorrhagic 5-20 mm MBM, not requiring immediate local therapy or steroids. RESULTS:Thirty-seven patients received four doses of bevacizumab and pembrolizumab every 3 weeks followed by up to 2 years of pembrolizumab. The brain metastasis response rate (primary end point) was 54.1% (95% CI, 36.9 to 70.5). The extracranial response rate was 56.3% (95% CI, 37.7 to 73.6). Median intracranial progression-free survival was 2.2 years (95% CI, 0.41 to not reached [NR]). Median overall survival (OS) was 4.3 years (95% CI, 1.6 to NR). Four-year OS rate was 51.6%. Grade 3 treatment-related adverse event rates from bevacizumab and pembrolizumab were 10.8% and 18.9%, respectively. Higher pretreatment vessel density in metastatic tumors and smaller on-therapy increases in circulating angiopoietin-2 were associated with response. CONCLUSION:Pembrolizumab with bevacizumab was well tolerated and demonstrated substantial activity in patients with untreated MBM with promising OS, justifying further evaluation of this regimen.

MRI is the preferred imaging modality for patients with acute dizziness when a central etiology is possible. Abbreviated protocols may improve access in urgent settings. This study assesses the diagnostic yield and utility of an abbreviated MRI protocol for patients presenting with dizziness to the emergency department (ED). This retrospective study included 613 adult patients presenting to the ED with dizziness from August 1, 2019 to August 31, 2023. The protocol included 3 mm coronal and axial DWI, axial FLAIR, and SWI sequences, with a duration of approximately 11 min. MRI findings were categorized as negative or positive for intracranial pathology; etiology and location were recorded. Charts were reviewed for concurrent CTA during the ED visit, and findings were assessed for correlation with MRI results. Of the 613 patients, clinically significant intracranial pathology was identified in 52 cases (8

Ischemic strokes can cause vertigo, particularly when involving the posterior circulation of the brain. Prior research has suggested that thin-section (3 mm) axial or coronal DWI may improve the detection of ischemic stroke compared to thick (5 mm) DWI. However, relative sensitivity of differing thin DWI sequences is unknown. In this retrospective cohort study, we compare the sensitivity of thin coronal DWI and thin axial DWI in detection of brain ischemia. Retrospective study at a single institution (2/18/2020–8/31/2023) of patients who presented to the emergency department with vertigo/dizziness and underwent an abbreviated MRI protocol (3 mm axial DWI, 3 mm coronal DWI, axial FLAIR, and axial SWI). For each case with an ischemic lesion, the visibility of infarct on thin axial and coronal DWIs was rated; location and size were also recorded. Visibility on either sequence was considered the reference standard. Sensitivity was compared with McNemar’s test. 615 abbreviated MRI examinations were performed; 24/615 (3.9

To explore how age and sex affect cerebrospinal fluid (CSF) dynamics, particularly examining the relationships between CSF production, meningeal lymphatic vessel (mLV) characteristics, and glymphatic function. To determine the impact of brain lymphatic function on processing speed and cognitive performance.

Bronchoscopic lung volume reduction treatment with Zephyr one-way valves is an effective guideline-based treatment option for patients with severe emphysema and hyperinflation. However, in some cases the treatment response is less than anticipated or there might be a loss of initial treatment effect.Reasons for the lack of response can include incorrect assessment of collateral ventilation, improper valve placement, or patient related factors. Loss of initial benefit can be due to granulation tissue formation and subsequent valve dysfunction, or there may be side effects such as excessive coughing or infectious problems.Careful follow-up after treatment with valves is important and evaluation with a CT scan and/or bronchoscopy is helpful if there is no improvement after treatment or loss of initial benefit. This paper aims to describe the most important causes and provide a strategy of how to approach and manage these patients.