Ovarian neuroendocrine tumor metastasis on DOTATATE PET/CT

This case report follows a 63-year-old female patient with a history of a gastroenteropancreatic (GEP) neuroendocrine tumor of the terminal ileum who developed ovarian metastasis and later progressed to peritoneal carcinomatosis. The patient was found to have worsening metastasis on CT that was subsequently confirmed with (68Ga)-DOTATATE PET/CT imaging. This case outlines the rare metastatic nature of a primary ileal neuroendocrine tumor and emphasizes the efficacy of (68Ga)-DOTATATE PET/CT imaging in the localization, progression, and treatment of neuroendocrine metastatic disease.

Calcified Meningiomas Demonstrate Equivocal Grade, Proliferation, and Immediate Surgical Outcomes

BACKGROUND/OBJECTIVE

Meningioma calcification is thought to predict reduced growth potential and aggression. However, historical studies have primarily focused on correlating calcification in small meningiomas (diameter less than 2.5 cm) rather than analyzing characteristics of calcified meningiomas across all sizes. In this study, we investigate the pathologic and clinical implications of meningioma calcification.

METHODS

We utilized a historical database of 342 consecutive newly diagnosed intracranial meningiomas with preoperative computed tomography and magnetic resonance imaging scans treated at a single institution from 2005 to 2019. We correlated the presence of calcification with patient demographics, grade, Mindbomb Homolog-1 index, location, volume, Simpson grade, and recurrence using both univariate and multivariate generalized linear models.

RESULTS

On univariate analysis, no single variable correlated with tumor calcification. Notably, neither tumor 2021 World Health Organization grade (P = 0.91) nor Mindbomb Homolog-1 index (P = 0.62) predicted calcification. After accounting for demographic characteristics and tumor volume and location, there was no significant association between 2021 World Health Organization grade (P = 0.52) and Mindbomb Homolog-1 index (P = 0.54) and calcification. Calcification had no influence on resection grade (P = 0.59) or recurrence (P = 0.80).

CONCLUSIONS

In this series, calcified meningiomas exhibited similar 2021 World Health Organization tumor grading distribution, proliferation indexes, and immediate surgical outcomes compared to their noncalcified counterparts. These findings question the historical role of using meningioma calcification as an independent guide to their management.

The Brain Tumor Segmentation - Metastases (BraTS-METS) Challenge 2023: Brain Metastasis Segmentation on Pre-treatment MRI

The translation of AI-generated brain metastases (BM) segmentation into clinical practice relies heavily on diverse, high-quality annotated medical imaging datasets. The BraTS-METS 2023 challenge has gained momentum for testing and benchmarking algorithms using rigorously annotated internationally compiled real-world datasets. This study presents the results of the segmentation challenge and characterizes the challenging cases that impacted the performance of the winning algorithms. Untreated brain metastases on standard anatomic MRI sequences (T1, T2, FLAIR, T1PG) from eight contributed international datasets were annotated in stepwise method: published UNET algorithms, student, neuroradiologist, final approver neuroradiologist. Segmentations were ranked based on lesion-wise Dice and Hausdorff distance (HD95) scores. False positives (FP) and false negatives (FN) were rigorously penalized, receiving a score of 0 for Dice and a fixed penalty of 374 for HD95. The mean scores for the teams were calculated. Eight datasets comprising 1303 studies were annotated, with 402 studies (3076 lesions) released on Synapse as publicly available datasets to challenge competitors. Additionally, 31 studies (139 lesions) were held out for validation, and 59 studies (218 lesions) were used for testing. Segmentation accuracy was measured as rank across subjects, with the winning team achieving a LesionWise mean score of 7.9. The Dice score for the winning team was 0.65 ± 0.25. Common errors among the leading teams included false negatives for small lesions and misregistration of masks in space. The Dice scores and lesion detection rates of all algorithms diminished with decreasing tumor size, particularly for tumors smaller than 100 mm3. In conclusion, algorithms for BM segmentation require further refinement to balance high sensitivity in lesion detection with the minimization of false positives and negatives. The BraTS-METS 2023 challenge successfully curated well-annotated, diverse datasets and identified common errors, facilitating the translation of BM segmentation across varied clinical environments and providing personalized volumetric reports to patients undergoing BM treatment.

Prostate cancer brain metastases: Monitoring response to treatment with PSMA PET/CT

Prostate cancer brain metastases are rare but increasingly recognized with prostate-specific membrane antigen (PSMA) PET/CT. Distinguishing tumor response from postradiation changes are challenging on MRI. PSMA PET/CT may clarify equivocal brain lesions after radiotherapy. A 71-year-old man with metastatic prostate cancer developed 2 new brain lesions on PSMA PET/CT. Lesions were high PSMA-avid and MRI follow up showed enhancing masses with edema, consistent with metastases. He underwent whole-brain radiation. Follow-up PSMA PET/CT after radiotherapy demonstrated significantly decreased lesion size and activity, with activity lower than blood pool, indicating a treatment response. MRI also showed near-resolution of the lesions. This case highlights the potential utility of PSMA PET/CT for detecting prostate cancer brain metastases and monitoring treatment response. PSMA PET/CT provides valuable complementary information to MRI for managing irradiated prostate cancer brain metastases.

A multi-institutional meningioma MRI dataset for automated multi-sequence image segmentation

Meningiomas are the most common primary intracranial tumors and can be associated with significant morbidity and mortality. Radiologists, neurosurgeons, neuro-oncologists, and radiation oncologists rely on brain MRI for diagnosis, treatment planning, and longitudinal treatment monitoring. However, automated, objective, and quantitative tools for non-invasive assessment of meningiomas on multi-sequence MR images are not available. Here we present the BraTS Pre-operative Meningioma Dataset, as the largest multi-institutional expert annotated multilabel meningioma multi-sequence MR image dataset to date. This dataset includes 1,141 multi-sequence MR images from six sites, each with four structural MRI sequences (T2-, T2/FLAIR-, pre-contrast T1-, and post-contrast T1-weighted) accompanied by expert manually refined segmentations of three distinct meningioma sub-compartments: enhancing tumor, non-enhancing tumor, and surrounding non-enhancing T2/FLAIR hyperintensity. Basic demographic data are provided including age at time of initial imaging, sex, and CNS WHO grade. The goal of releasing this dataset is to facilitate the development of automated computational methods for meningioma segmentation and expedite their incorporation into clinical practice, ultimately targeting improvement in the care of meningioma patients.

Gradual normalization of superscan in prostate cancer: A case report and literature review

This report presents the imaging findings in a patient with advanced prostate cancer and bone metastases. A superscan pattern on the initial whole-body bone scan suggested extensive disease. The patient responded well to definitive treatment, exhibiting clinical improvement based on decreased PSA levels and CT findings in 6-month follow-up. However, serial follow-up bone scans showed normalization in about 18 months. This paper aims to discuss the limitations of bone scintigraphy in evaluating treatment responses in patients with prostate cancer.

Impact of Workflow and Educational Interventions on MR Safety in Radiation Oncology

PURPOSE/OBJECTIVE(S)

Magnetic resonance imaging (MRI) is becoming increasingly integrated into radiation oncology (RO) departments with the use of MRI-Linacs and MRI simulation. Due to the number of implants in patients with cancer, adoption of comprehensive patient screening and MR safety workflows in RO is critical. Identifying MR unsafe implants only at the time of MRI simulation leads to same-day cancellations, potentially delaying treatment, and can risk MR safety events (SEs). This quality improvement study evaluated the impact of workflow and educational interventions on MR safety in RO at a single institution.

MATERIALS/METHODS

In an effort to decrease same-day cancellations and improve safety surrounding use of a 3 Tesla MRI simulator at an academic center, three plan-see-do-act (PDSA) cycles were implemented from 4/18/22 - 1/19/23. MR safety oversight for the simulator was provided by a multidisciplinary team, with input from both radiology and RO. PDSA cycle 1 implemented a two-screen functional workflow, adapted from radiology at the same institution. The first screen is completed by the practice coordinator (PC) at the time of scheduling to triage high-risk patients into a work queue (WQ) for further evaluation by the MR safety team. The second screen is performed by the MR technologist (MRT) at the point of care. PDSA cycle 2 involved education for PCs. PDSA cycle 3 was a second PC educational intervention including a visual aide to assist with WQ use. Efficacy was determined by the number of same-day cancellations, patients in the WQ (a measure of the number of patients identified at the initial screen as having an implant), and SEs in each PDSA cycle.

RESULTS

PDSA cycle 1 spanned 56 workdays during which 91 MR simulations were scheduled with 6 cancellations (6.5%). PDSA cycle 2 spanned 84 days during which 173 MR simulations were scheduled with 18 cancellations (10.4%). PDSA cycle 3 spanned 39 workdays and had 94 MR simulations, with 7 cancellations (7.4%). The cancellation rate during each PDSA cycle was 0.11, 0.21, and 0.17 cancellations/day, respectively. The number of patients in the WQ during each PDSA cycle, representing successfully screened high-risk patients, was 0, 0, and 3, respectively. There were no SEs during the study.

CONCLUSION

In this study, an MR safety workflow from radiology was successfully implemented in RO. There were no SEs during the study, but the number of patients successfully screened as high-risk and placed in the WQ increased after repeat PC education. Further increases in WQ use would decrease the demand for implant assessment at point of care, which could decrease burden on the MRT, same day cancellations, and potentially SEs. This will be especially important if case load increases. Future work could expand educational efforts to additional staff.

DeepSWI: Using Deep Learning to Enhance Susceptibility Contrast on T2*-Weighted MRI

BACKGROUND

Although susceptibility-weighted imaging (SWI) is the gold standard for visualizing cerebral microbleeds (CMBs) in the brain, the required phase data are not always available clinically. Having a postprocessing tool for generating SWI contrast from T2*-weighted magnitude images is therefore advantageous.

PURPOSE

To create synthetic SWI images from clinical T2*-weighted magnitude images using deep learning and evaluate the resulting images in terms of similarity to conventional SWI images and ability to detect radiation-associated CMBs.

STUDY TYPE

Retrospective.

POPULATION

A total of 145 adults (87 males/58 females; 43.9 years old) with radiation-associated CMBs were used to train (16,093 patches/121 patients), validate (484 patches/4 patients), and test (2420 patches/20 patients) our networks.

FIELD STRENGTH/SEQUENCE

3D T2*-weighted, gradient-echo acquired at 3 T.

ASSESSMENT

Structural similarity index (SSIM), peak signal-to-noise-ratio (PSNR), normalized mean-squared-error (nMSE), CMB counts, and line profiles were compared among magnitude, original SWI, and synthetic SWI images. Three blinded raters (J.E.V.M., M.A.M., B.B. with 8-, 6-, and 4-years of experience, respectively) independently rated and classified test-set images.

STATISTICAL TESTS

Kruskall-Wallis and Wilcoxon signed-rank tests were used to compare SSIM, PSNR, nMSE, and CMB counts among magnitude, original SWI, and predicted synthetic SWI images. Intraclass correlation assessed interrater variability. P values <0.005 were considered statistically significant.

RESULTS

SSIM values of the predicted vs. original SWI (0.972, 0.995, 0.9864) were statistically significantly higher than that of the magnitude vs. original SWI (0.970, 0.994, 0.9861) for whole brain, vascular structures, and brain tissue regions, respectively; 67% (19/28) CMBs detected on original SWI images were also detected on the predicted SWI, whereas only 10 (36%) were detected on magnitude images. Overall image quality was similar between the synthetic and original SWI images, with less artifacts on the former.

CONCLUSIONS

This study demonstrated that deep learning can increase the susceptibility contrast present in neurovasculature and CMBs on T2*-weighted magnitude images, without residual susceptibility-induced artifacts. This may be useful for more accurately estimating CMB burden from magnitude images alone.

EVIDENCE LEVEL

3.

TECHNICAL EFFICACY

Stage 2.

Adjuvant Chemoradiotherapy within One Year of Resection for Molecularly Defined Astrocytoma

PURPOSE/OBJECTIVE(S)

Treatments for diffuse low-grade gliomas (LGG) are controversial. Level I evidence supports the use of adjuvant radiotherapy (RT) and PCV chemotherapy for histologic LGG, but integration of molecular biomarkers in recent WHO classification and the emergence of temozolomide chemotherapy for gliomas necessitates additional investigation of the optimal treatment and timing of postoperative interventions. We hypothesized molecularly-defined LGG (IDH-mutant astrocytoma (astro) and IDH-mutant, 1p/19q-codeleted oligodendroglioma (oligo)) may have different clinical outcomes following adjuvant RT (aRT) with chemotherapy (aRT+chemo) vs observation or chemo alone.

MATERIALS/METHODS

A retrospective analysis of consecutive adult patients diagnosed with WHO Grade 2 astrocytoma or oligodendroglioma who underwent initial resection at a single institution from January 1998 to November 2017 was performed. Wilcoxon rank sum and Chi-squared tests were used to compare continuous and categorical variables, respectively. Survival analyses were performed using the Kaplan-Meier method and Cox proportional hazards models. Patients without clinical progression or death were censored at the date of last follow-up. Pre-operative and post-operative T2 FLAIR hyperintense tumor volumes were quantified using 3D Slicer to calculate extent of resection (EOR).

RESULTS

A total of 342 patients with molecularly-defined LGG (178 astro, 164 oligo) were identified with a median follow up of 9.1 yr. 171 (50%) patients received RT during their treatment course, of which 31 (18%) were treated with aRT within 1 year of diagnosis. The median aRT dose was 54 Gy (range: 40-60 Gy). aRT was more likely for astro (58%) vs oligo (41%, p = 0.001) and for patients who had resections with lower median EOR (88% vs 95%, p = 0.014). 53 patients (15%) were treated with chemo alone, and 136 patients (40%) were treated with aRT+chemo. Temozolomide was used for 161 patients (85%). For astro, aRT+chemo was associated with longer PFS (median 14.9 yr) compared to observation (4.8 yr, p = 0.05), aRT without chemo (5.2 yr, p = 0.01), or chemo alone (4.7 yr, p = 0.02). For oligo, aRT+chemo was associated with longer PFS (median not reached) compared to aRT without chemo (1.6 yr, p = 0.03), but not when compared to observation (median not reached, p = 0.47), or chemo alone (7.9 yr, p = 0.45). Multivariate analysis showed preoperative tumor volume, EOR, and aRT+chemo (but not aRT or chemo alone) were independently associated with astro PFS compared to observation. Propensity matching based on pre-operative tumor volume, EOR, and age demonstrated longer astro PFS after aRT+chemo (14.9 yr) compared to observation or chemo alone (4.5 yr, p = 0.015), without significant difference in OS (18.2 vs. 11.5 yr, p = 0.40).

CONCLUSION

Retrospective data from a single institution support the use of adjuvant radiotherapy with chemotherapy for patients with molecular astrocytomas, while the role of this approach for oligodendrogliomas is unclear in this cohort.

Association of partial T2-FLAIR mismatch sign and isocitrate dehydrogenase mutation in WHO grade 4 gliomas: results from the ReSPOND consortium

PURPOSE

While the T2-FLAIR mismatch sign is highly specific for isocitrate dehydrogenase (IDH)-mutant, 1p/19q-noncodeleted astrocytomas among lower-grade gliomas, its utility in WHO grade 4 gliomas is not well-studied. We derived the partial T2-FLAIR mismatch sign as an imaging biomarker for IDH mutation in WHO grade 4 gliomas.

METHODS

Preoperative MRI scans of adult WHO grade 4 glioma patients (n = 2165) from the multi-institutional ReSPOND (Radiomics Signatures for PrecisiON Diagnostics) consortium were analyzed. Diagnostic performance of the partial T2-FLAIR mismatch sign was evaluated. Subset analyses were performed to assess associations of imaging markers with overall survival (OS).

RESULTS

One hundred twenty-one (5.6%) of 2165 grade 4 gliomas were IDH-mutant. Partial T2-FLAIR mismatch was present in 40 (1.8%) cases, 32 of which were IDH-mutant, yielding 26.4% sensitivity, 99.6% specificity, 80.0% positive predictive value, and 95.8% negative predictive value. Multivariate logistic regression demonstrated IDH mutation was significantly associated with partial T2-FLAIR mismatch (odds ratio [OR] 5.715, 95% CI [1.896, 17.221], p = 0.002), younger age (OR 0.911 [0.895, 0.927], p < 0.001), tumor centered in frontal lobe (OR 3.842, [2.361, 6.251], p < 0.001), absence of multicentricity (OR 0.173, [0.049, 0.612], p = 0.007), and presence of cystic (OR 6.596, [3.023, 14.391], p < 0.001) or non-enhancing solid components (OR 6.069, [3.371, 10.928], p < 0.001). Multivariate Cox analysis demonstrated cystic components (p = 0.024) and non-enhancing solid components (p = 0.003) were associated with longer OS, while older age (p < 0.001), frontal lobe center (p = 0.008), multifocality (p < 0.001), and multicentricity (p < 0.001) were associated with shorter OS.

CONCLUSION

Partial T2-FLAIR mismatch sign is highly specific for IDH mutation in WHO grade 4 gliomas.

The Brain Tumor Segmentation (BraTS) Challenge 2023: Brain MR Image Synthesis for Tumor Segmentation (BraSyn)

Automated brain tumor segmentation methods have become well-established and reached performance levels offering clear clinical utility. These methods typically rely on four input magnetic resonance imaging (MRI) modalities: T1-weighted images with and without contrast enhancement, T2-weighted images, and FLAIR images. However, some sequences are often missing in clinical practice due to time constraints or image artifacts, such as patient motion. Consequently, the ability to substitute missing modalities and gain segmentation performance is highly desirable and necessary for the broader adoption of these algorithms in the clinical routine. In this work, we present the establishment of the Brain MR Image Synthesis Benchmark (BraSyn) in conjunction with the Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2023. The primary objective of this challenge is to evaluate image synthesis methods that can realistically generate missing MRI modalities when multiple available images are provided. The ultimate aim is to facilitate automated brain tumor segmentation pipelines. The image dataset used in the benchmark is diverse and multi-modal, created through collaboration with various hospitals and research institutions.

The ASNR-MICCAI Brain Tumor Segmentation (BraTS) Challenge 2023: Intracranial Meningioma

Meningiomas are the most common primary intracranial tumor in adults and can be associated with significant morbidity and mortality. Radiologists, neurosurgeons, neuro-oncologists, and radiation oncologists rely on multiparametric MRI (mpMRI) for diagnosis, treatment planning, and longitudinal treatment monitoring; yet automated, objective, and quantitative tools for non-invasive assessment of meningiomas on mpMRI are lacking. The BraTS meningioma 2023 challenge will provide a community standard and benchmark for state-of-the-art automated intracranial meningioma segmentation models based on the largest expert annotated multilabel meningioma mpMRI dataset to date. Challenge competitors will develop automated segmentation models to predict three distinct meningioma sub-regions on MRI including enhancing tumor, non-enhancing tumor core, and surrounding nonenhancing T2/FLAIR hyperintensity. Models will be evaluated on separate validation and held-out test datasets using standardized metrics utilized across the BraTS 2023 series of challenges including the Dice similarity coefficient and Hausdorff distance. The models developed during the course of this challenge will aid in incorporation of automated meningioma MRI segmentation into clinical practice, which will ultimately improve care of patients with meningioma.

Interactive Effects of Molecular, Therapeutic, and Patient Factors on Outcome of Diffuse Low-Grade Glioma

PURPOSE

In patients with diffuse low-grade glioma (LGG), the extent of surgical tumor resection (EOR) has a controversial role, in part because a randomized clinical trial with different levels of EOR is not feasible.

METHODS

In a 20-year retrospective cohort of 392 patients with IDH-mutant grade 2 glioma, we analyzed the combined effects of volumetric EOR and molecular and clinical factors on overall survival (OS) and progression-free survival by recursive partitioning analysis. The OS results were validated in two external cohorts (n = 365). Propensity score analysis of the combined cohorts (n = 757) was used to mimic a randomized clinical trial with varying levels of EOR.

RESULTS

Recursive partitioning analysis identified three survival risk groups. Median OS was shortest in two subsets of patients with astrocytoma: those with postoperative tumor volume (TV) > 4.6 mL and those with preoperative TV > 43.1 mL and postoperative TV ≤ 4.6 mL. Intermediate OS was seen in patients with astrocytoma who had chemotherapy with preoperative TV ≤ 43.1 mL and postoperative TV ≤ 4.6 mL in addition to oligodendroglioma patients with either preoperative TV > 43.1 mL and residual TV ≤ 4.6 mL or postoperative residual volume > 4.6 mL. Longest OS was seen in astrocytoma patients with preoperative TV ≤ 43.1 mL and postoperative TV ≤ 4.6 mL who received no chemotherapy and oligodendroglioma patients with preoperative TV ≤ 43.1 mL and postoperative TV ≤ 4.6 mL. EOR ≥ 75% improved survival outcomes, as shown by propensity score analysis.

CONCLUSION

Across both subtypes of LGG, EOR beginning at 75% improves OS while beginning at 80% improves progression-free survival. Nonetheless, maximal resection with preservation of neurological function remains the treatment goal. Our findings have implications for surgical strategies for LGGs, particularly oligodendroglioma.

Targeted gene expression profiling predicts meningioma outcomes and radiotherapy responses

Background

Surgery is the mainstay of treatment for meningioma, the most common primary intracranial tumor, but improvements in meningioma risk stratification are needed and current indications for postoperative radiotherapy are controversial. Recent studies have proposed prognostic meningioma classification systems using DNA methylation profiling, copy number variants, DNA sequencing, RNA sequencing, histology, or integrated models based on multiple combined features. Targeted gene expression profiling has generated robust biomarkers integrating multiple molecular features for other cancers, but is understudied for meningiomas.

Methods

Targeted gene expression profiling was performed on 173 meningiomas and an optimized gene expression biomarker (34 genes) and risk score (0 to 1) was developed to predict clinical outcomes. Clinical and analytical validation was performed on independent meningiomas from 12 institutions across 3 continents (N = 1856), including 103 meningiomas from a prospective clinical trial. Gene expression biomarker performance was compared to 9 other classification systems.

Results

The gene expression biomarker improved discrimination of postoperative meningioma outcomes compared to all other classification systems tested in the independent clinical validation cohort for local recurrence (5-year area under the curve [AUC] 0.81) and overall survival (5-year AUC 0.80). The increase in area under the curve compared to the current standard of care, World Health Organization 2021 grade, was 0.11 for local recurrence (95% confidence interval [CI] 0.07-0.17, P < 0.001). The gene expression biomarker identified meningiomas benefiting from postoperative radiotherapy (hazard ratio 0.54, 95% CI 0.37-0.78, P = 0.0001) and re-classified up to 52.0% meningiomas compared to conventional clinical criteria, suggesting postoperative management could be refined for 29.8% of patients.

Conclusions

A targeted gene expression biomarker improves discrimination of meningioma outcomes compared to recent classification systems and predicts postoperative radiotherapy responses.

MerlinS13 phosphorylation controls meningioma Wnt signaling and magnetic resonance imaging features

Meningiomas are the most common primary intracranial tumors and are associated with inactivation of the tumor suppressor NF2/Merlin, but one-third of meningiomas retain Merlin expression and typically have favorable clinical outcomes. Biochemical mechanisms underlying Merlin-intact meningioma growth are incompletely understood, and non-invasive biomarkers that predict meningioma outcomes and could be used to guide treatment de-escalation or imaging surveillance of Merlin-intact meningiomas are lacking. Here we integrate single-cell RNA sequencing, proximity-labeling proteomic mass spectrometry, mechanistic and functional approaches, and magnetic resonance imaging (MRI) across meningioma cells, xenografts, and human patients to define biochemical mechanisms and an imaging biomarker that distinguish Merlin-intact meningiomas with favorable clinical outcomes from meningiomas with unfavorable clinical outcomes. We find Merlin drives meningioma Wnt signaling and tumor growth through a feed-forward mechanism that requires Merlin dephosphorylation on serine 13 (S13) to attenuate inhibitory interactions with β-catenin and activate the Wnt pathway. Meningioma MRI analyses of xenografts and human patients show Merlin-intact meningiomas with S13 phosphorylation and favorable clinical outcomes are associated with high apparent diffusion coefficient (ADC) on diffusion-weighted imaging. In sum, our results shed light on Merlin posttranslational modifications that regulate meningioma Wnt signaling and tumor growth in tumors without NF2/Merlin inactivation. To translate these findings to clinical practice, we establish a non-invasive imaging biomarker that could be used to guide treatment de-escalation or imaging surveillance for patients with favorable meningiomas.

Detection of Malpositioned VP Shunt Catheter by Radionuclide CSF Cisternography

ABSTRACT

A 37-year-old man presented with a 2-week history of abdominal pain, headaches, nausea, vomiting, and leukocytosis. Medical history includes congenital hydrocephalus, with a ventriculoperitoneal shunt placed several years ago. Radionuclide cerebrospinal fluid cisternography shows curvilinear activity in the abdomen, in the pattern of small and large bowel loops, suggesting that the tip of the catheter is inside a small bowel loop. No activity is seen in the intraperitoneal compartment. CT of the abdomen and pelvis followed by laparoscopic surgery confirmed the findings.

Variant Sciatic Nerve Anatomy in Relation to the Piriformis Muscle on Magnetic Resonance Neurography: A Potential Etiology for Extraspinal Sciatica

OBJECTIVE

To assess the prevalence and clinical implications of variant sciatic nerve anatomy in relation to the piriformis muscle on magnetic resonance neurography (MRN), in patients with lumbosacral neuropathic symptoms.

MATERIALS AND METHODS

In this retrospective single-center study, 254 sciatic nerves, from 127 patients with clinical and imaging findings compatible with extra-spinal sciatica on MRN between 2003 and 2013, were evaluated for the presence and type of variant sciatic nerves, split sciatic nerve, abnormal T2-signal hyperintensity, asymmetric piriformis size and increased nerve caliber, and summarized using descriptive statistics. Two-tailed chi-square tests were performed to compare the anatomical variant type and clinical symptoms between imaging and clinical characteristics.

RESULTS

Sixty-four variant sciatic nerves were identified with an equal number of right and left variants. Bilateral variants were noted in 15 cases. Abnormal T2-signal hyperintensity was seen significantly more often in variant compared to conventional anatomy (40/64 vs. 82/190; p = 0.01). A sciatic nerve split was seen significantly more often in variant compared to conventional anatomy (56/64 vs. 20/190; p < 0.0001). Increased nerve caliber, abnormal T2-signal hyperintensity, and asymmetric piriformis size were significantly associated with the clinically symptomatic side compared to the asymptomatic side (98:2, 98:2, and 97:3, respectively; p < 0.0001 for all). Clinical symptoms were correlated with variant compared to conventional sciatic nerve anatomy (64% vs. 46%; p = 0.01).

CONCLUSION

Variant sciatic nerve anatomy, in relation to the piriformis muscle, is frequently identified with MRN and is more likely to be associated with nerve signal changes and symptomatology.

Spectrum of Clinical Presentations, Imaging Findings, and HLA Types in Immune Checkpoint Inhibitor-Induced Hypophysitis

Context

Hypophysitis is a known immune-related adverse event (irAE) of immune checkpoint inhibitors (CPIs), commonly associated with CTLA-4 inhibitors and less often with PD-1/PD-L1 inhibitors.

Objective

We aimed to determine clinical, imaging, and HLA characteristics of CPI-induced hypophysitis (CPI-hypophysitis).

Methods

We examined the clinical and biochemical characteristics, magnetic resonance imaging (MRI) of the pituitary, and association with HLA type in patients with CPI-hypophysitis.

Results

Forty-nine patients were identified. Mean age was 61.3 years, 61.2% were men, 81.6% were Caucasian, 38.8% had melanoma, and 44.5% received PD-1/PD-L1 inhibitor monotherapy while the remainder received CTLA-4 inhibitor monotherapy or CTLA-4/PD-1 inhibitor combination therapy. A comparison of CTLA-4 inhibitor exposure vs PD-1/PD-L1 inhibitor monotherapy revealed faster time to CPI-hypophysitis (median 84 vs 185 days, P < .01) and abnormal pituitary appearance on MRI (odds ratio 7.00, P = .03). We observed effect modification by sex in the association between CPI type and time to CPI-hypophysitis. In particular, anti-CTLA-4 exposed men had a shorter time to onset than women. MRI changes of the pituitary were most common at the time of hypophysitis diagnosis (55.6% enlarged, 37.0% normal, 7.4% empty or partially empty) but persisted in follow-up (23.8% enlarged, 57.1% normal, 19.1% empty or partially empty). HLA typing was done on 55 subjects; HLA type DQ0602 was over-represented in CPI-hypophysitis relative to the Caucasian American population (39.4% vs 21.5%, P = 0.01) and CPI population.

Conclusion

The association of CPI-hypophysitis with HLA DQ0602 suggests a genetic risk for its development. The clinical phenotype of hypophysitis appears heterogenous, with differences in timing of onset, changes in thyroid function tests, MRI changes, and possibly sex related to CPI type. These factors may play an important role in our mechanistic understanding of CPI-hypophysitis.

Federated learning enables big data for rare cancer boundary detection

Although machine learning (ML) has shown promise across disciplines, out-of-sample generalizability is concerning. This is currently addressed by sharing multi-site data, but such centralization is challenging/infeasible to scale due to various limitations. Federated ML (FL) provides an alternative paradigm for accurate and generalizable ML, by only sharing numerical model updates. Here we present the largest FL study to-date, involving data from 71 sites across 6 continents, to generate an automatic tumor boundary detector for the rare disease of glioblastoma, reporting the largest such dataset in the literature (n = 6, 314). We demonstrate a 33% delineation improvement for the surgically targetable tumor, and 23% for the complete tumor extent, over a publicly trained model. We anticipate our study to: 1) enable more healthcare studies informed by large diverse data, ensuring meaningful results for rare diseases and underrepresented populations, 2) facilitate further analyses for glioblastoma by releasing our consensus model, and 3) demonstrate the FL effectiveness at such scale and task-complexity as a paradigm shift for multi-site collaborations, alleviating the need for data-sharing.

NIMG-46. TOWARDS PREDICTING TUMOR AGGRESSIVENESS WITH RADIOPATHOMIC ANALYSIS OF MULTI-PARAMETRIC ANATOMICAL, DIFFUSION-WEIGHTED, AND METABOLIC MRI IN PATIENTS WITH NEWLY-DIAGNOSED GLIOMAS

INTRODUCTION

Pathologically aggressive tumor biology can extend beyond the contrast-enhancing or non-enhancing anatomical lesions in patients with glioma. Identification of malignant regions can help guide diagnosis and subsequent treatment planning. This study leverages a unique multi-parametric MRI dataset with tissue samples of known spatial coordinates to noninvasively predict cellular proliferation (KI-67) and a novel index of tumor aggressiveness (TAI), that combines proliferation, cellularity, and tumor-score.

METHODS

420 tissue samples were collected from 162 patients with newly-diagnosed glioma (47% IDH-wildtype). Clinical imaging consisted of T2-weighted, T2-FLAIR, T1-weighted pre- and post-contrast images, and apparent diffusion coefficient (ADC) and fractional anisotropy (FA) from diffusion-weighted imaging. Mean normalized imaging metrics were quantified from 5mm spheres centered at the location of the tissue sample. A single spectrum was reconstructed at the location of each tissue sample from 3D 1H-MR Spectroscopic Imaging (MRSI) before quantifying normalized metabolite peak-heights for choline, creatine, NAA, lactate/lipid, and relative indices. Univariate mixed-effects linear regression models were employed and features with p&lt; 0.2 were selected for subsequent model building. Support vector machine (SVM), random forest, and gradient boosting machine-learning algorithms were trained and tested on a ⅔-⅓ train-test split with 4-fold cross-validation in training to predict a high/low KI-67 and TAI.

RESULTS

Although none of the individual imaging metrics were significantly associated with KI-67 in the univariate analysis, all diffusion and several MRSI metrics (ncholine, nNAA, CNI, excess choline and creatine) were significantly associated with cellularity. Preliminary multivariate analyses to date suggest that the best radiopathomic model performance is achieved when an SVM was used along with T1-precontrast, nADC, and all metabolite levels (mean cross-validation AUC=0.73 and accuracy=.77).

CONCLUSION

Our results suggest that multi-parametric physiologic and metabolic MRI are useful for radiopathomic-mapping of tumor aggressiveness and are currently being optimized in a larger cohort.

NIMG-67. MULTI-PARAMETRIC MRI-BASED MACHINE LEARNING ANALYSIS FOR PREDICTION OF NEOPLASTIC INFILTRATION AND RECURRENCE IN PATIENTS WITH GLIOBLASTOMA: UPDATES FROM THE MULTI-INSTITUTIONAL RESPOND CONSORTIUM

PURPOSE

Glioblastoma is extremely infiltrative with malignant cells extending beyond the enhancing rim where recurrence inevitably occurs, despite aggressive multimodal therapy. We hypothesize that important characteristics of peritumoral tissue heterogeneity captured and analyzed by multi-parametric MRI and artificial intelligence (AI) methods are generalizable in the updated multi-institutional ReSPOND (Radiomics Signatures for PrecisiON Diagnostics) consortium and predictive of neoplastic infiltration and future recurrence.

METHODS

We used the most recent update of the ReSPOND consortium to evaluate and further refine generalizability of our methods with different scanners and acquisition settings. 179 de novo glioblastoma patients with available T1, T1Gd, T2, T2-FLAIR, and ADC sequences at pre-resection baseline and after complete resection with subsequent pathology-confirmed recurrence were included. To establish generalizability of the predictive models, training and testing of the refined AI model was performed through Leave-One-Institution-Out-Cross-Validation schema. The multi-institutional cohort consisted of the Hospital of the University of Pennsylvania (UPenn, 124), Case Western Reserve University/University Hospitals (CWRU/UH, 27), New York University (NYU, 13), Ohio State University (OSU, 13), and University Hospital Río Hortega (RH, 2). Features extracted from pre-resection MRI were used to build the model predicting the spatial pattern of subsequent tumor recurrence. These predictions were evaluated against regions of pathology-confirmed post-resection recurrence.

RESULTS

Our model predicted the locations that later harbored tumor recurrence with overall odds ratio (99% CI)/AUC (99% CI), 12.0(11.8-12.2)/0.80(0.76-0.85), and per institute, CWRU/UH, 11.0(10.7-11.3)/0.80 (0.64-0.97); NYU, 7.0(6.7-7.3)/0.78(0.56-1.00); OSU, 18.3(17.5-19.1)/0.83(0.54-1.00); RH, 40.0(35.3-45.5)/0.93(0.00-1.00); UPenn, 8.00(7.7-8.3)/0.80(0.75-0.84).

CONCLUSION

This study provides extensive multi-institutional validated evidence that machine learning tools can identify peritumoral neoplastic infiltration and predict location of future recurrence, by decrypting the MRI signal heterogeneity in peritumoral tissue. Our analyses leveraged the unique dataset of the ReSPOND consortium, which aims to develop and validate AI-based biomarkers for individualized prediction and prognostication and establish generalizability in a multi-institutional setting.

NIMG-61. IMPROVED GENERALIZABILITY OF RADIOPATHOMIC PROBABILISTIC MAPPING OF TREATMENT-INDUCED EFFECTS WITH PHYSIOLOGIC MR IMAGING AND DEEP LEARNING IN PATIENTS WITH RECURRENT GLIOBLASTOMA

Although physiologic (diffusion-weighted and perfusion-weighted) MRI has shown promise in identifying regions of recurrent tumor (rTumor) in patients with glioblastoma suspected of progression, distinguishing treatment-induced effects (TxE) from rTumor on anatomical MRI remains a challenge. Whereas prior larger-scale machine learning (ML)-based studies mostly utilize anatomical imaging alone and/or perform lesion-level predictions, this study aimed to develop a non-invasive, radiopathomic tool for regional probabilistic mapping of TxE using 208 tissue-samples (55 pathologically-confirmed TxE, 153 recurrent glioblastoma) acquired from 107 patients with known spatial coordinates on pre-surgical MRI. We tested the hypothesis that applying a deep-learning (DL) model that included physiological MRI can: 1) more accurately identify areas of TxE that mimic rTumor on anatomical MRI and 2) better generalize to an independent test set than ML-models or a DL-model that uses anatomical MRI alone. An 80/20 split for training/validation was used after 1/3 of the patients were withheld for testing. Oversampling of TxE samples was employed to address class imbalance and an equal proportion of TxE samples was maintained across all datasets. Three ML-models, their ensemble, and a deep 4D-convolutional-neural-network were trained based on normalized anatomical (post-contrast T1, T2-FLAIR), diffusion-weighted (ADC, FA), and DSC perfusion-weighted (PeakHeight, %recovery) images cropped to 10mm-cubic patches centered on the coordinates from where tissue was obtained. Although Random Forest and voting-ensembled ML-models using all imaging and the anatomical DL-model had the best validation performance (AUC=0.81-0.82), these models did not generalize (test AUC=0.58-0.59). The DL-model including physiologic images had slightly lower validation AUC (0.78) but the best overall test AUC (0.795), indicating superior generalizability. Elevated blood volume (nPeakHeight) was the most important feature. Our DL-model’s interpretability was also demonstrated by disrupting class separation after shuffling voxels within each input patch. These results suggest that using deep-learning with physiologic MRI can improve intratumoral classification of TxE from rTumor.

TMET-04. DETECTING DYNAMIC PYRUVATE TUMOR METABOLISM IN PATIENTS WITH GLIOMA USING HYPERPOLARIZED CARBON-13 METABOLIC IMAGING

INTRODUCTION

Hyperpolarized carbon-13 (HP-13C) MR enables rapid dynamic imaging of metabolic pathways in the human brain using non-toxic, non-radioactive metabolites as tracers. This study presents our unique experience on the benefit of using [1-13C]pyruvate and [2-13C]pyruvate MR for evaluating patients with glioma.

METHODS

132 scans (71 using an integrated 13C /1H coil) including steady-state 1H-MRSI (~10 min) and dynamic HP-13C imaging (60 sec) following injection of HP [1-13C]pyruvate (N=125) or [2-13C]pyruvate (N=7) were acquired from 46 patients with glioma (18F/28M; 15 IDH-mutant, 27 IDH-wildtype, 4 IDH-status-unknown). Maps of temporally-summed 13C-metabolite signals, ratios, and kinetic rate constants were calculated for contrast-enhancing, nonenhancing, and normal-appearing-white-matter (NAWM) regions and compared to steady-state metabolic metrics.

RESULTS

The only adverse event, in a single patient, was a burning sensation after the injection that resolved after saline flush. The mean time-to-injection of HP probes was 58.6±14.0 sec. Signal-to-noise ratios of [1-13C]lactate and [13C]bicarbonate within the NAWM from the HP [1-13C]pyruvate data were 53±39 and 13±6, respectively. The SD/mean of repeated injections (N=3) for lactate/pyruvate and pyruvate-to-lactate conversion rates were 3.8±3.1% and 6.5±3.1% in the NAWM, respectively. Patients with progressive GBM had significantly higher lactate/pyruvate and lower bicarbonate/lactate (p&lt; 0.05) in contrast- and non-enhancing lesions compared to NAWM. Significantly elevated lactate/pyruvate and reduced bicarbonate/lactate (p&lt; 0.01) were found in contrast-enhancing compared to nonenhancing regions, whereas choline/NAA and steady-state 1H-lactate levels were similar. HP [2-13C]pyruvate data showed reduced glutamate/pyruvate and pyruvate-to-glutamate conversion rates in T2 lesions compared to contralateral normal-appearing brain in IDH-mutant gliomas, consistent with known metabolic reprogramming.

CONCLUSION

This study demonstrates the potential benefit of dynamic HP-13C MRI for evaluating patients with glioma, which provides unique and spatially distinct contrast compared to steady-state metabolic imaging. Ongoing studies will further characterize dynamic metabolism in specific glioma subtypes and provide biomarkers for evaluating responses to treatment.

SURG-05. SUPERVISED MACHINE LEARNING IDENTIFIES RISK FACTORS ASSOCIATED WITH LEPTOMENINGEAL DISEASE AFTER SURGICAL RESECTION OF BRAIN METASTASES

INTRODUCTION

Predictors of postoperative leptomeningeal disease (LMD) after resection of brain metastases (BMs) are not well defined.

OBJECTIVE

This study examined rates and predictors of LMD, including subtypes, in patients who underwent resection of a BM followed by postoperative radiation.Method: A retrospective, single-center study was conducted examining overall LMD, classical LMD (cLMD), and nodular LMD (nLMD) risk. Logistic regression and a Cox proportional hazards analyses were performed to identify risk factors associated with LMD. Random forest models were constructed to predict LMD and differentiate cLMD versus nLMD. Accuracy and the area under the receiver operating characteristic curve (AUROC) were calculated to evaluate the models.Result: Of the 217 patients in the cohort, 47 (21.7%) developed postoperative LMD with 19(8.8%) cLMD cases and 28(12.9%) nLMD cases . Six-, 12-, and 24-month LMD-free survival rates were 92.3%, 85.6%, and 71.4%, respectively. Patients with cLMD had worse survival outcomes from LMD diagnosis compared to nLMD (2.4 vs 6.9 mo, Log-rank p=0.02), and treatment of LMD was associated with improved survival for both cLMD and nLMD subtypes. Multivariate Cox hazard analysis identified cerebellar/insular/occipital location (HR 3.25, 95% CI 1.73-6.11, p=0.0003), absence of extracranial disease (HR 2.49, 95% CI 1.27-4.88, p=0.008), and ventricle contact (HR 2.82, 95% CI 1.5-5.3, p=0.001) to be associated with postoperative LMD. A predictive model using random forest analysis with an AUROC of 0.87 in a test cohort identified tumor location, systemic disease status, and tumor volume as the most important factors associated with LMD. Both regression analysis and random forest analysis identified postoperative systemic therapy exposure as the main factor differentiating cLMD from nLMD development.

CONCLUSION

Tumor location, absence of extracranial disease at the time of surgery, contact with a ventricle, and increased tumor volume are associated with LMD. Classical LMD is associated with worse prognosis compared to nLMD.