Aboian, Mariam

Abstract BACKGROUND Volumetric analysis of brain metastatic lesions is of great relevance in neuro-oncology. Since manual annotation of a lesion is a laborious and time-consuming task, utilizing artificial intelligence (AI) tools for automated segmentation of brain metastases has shown promising potential, but published algorithms are not incorporated into clinical practice because of poor generalizability across institutions. Large publicly available and well-annotated datasets from across the world are critical for further clinical translation. MATERIAL AND METHODS The Brain Tumor Segmentation - Metastases (BraTS-METS) 2025 Lighthouse Challenge provides a competitive environment where scientists from various disciplines can benchmark their AI-based algorithms for automatic segmentation of pre- and post-treatment brain metastases on a well-curated publicly available brain metastasis dataset comprising 1,778 multiparametric brain MRI cases. Each case consists of T1-weighed, T1 post-contrast and FLAIR sequences. The cases were retrospectively obtained from 8 institutions in the USA and overseas, and underwent 3D nnU-Net pre-segmentation, followed by manual refinements performed by medical students and neuroradiologists, and a final approval by two independent board-certified neuroradiologists. A testing dataset was prepared through four rounds of annotation: two completed ‘from scratch’ and two following 3D nnU-Net pre-segmentation, all conducted by two independent neuroradiologists, with the segmentation process screen recorded for future analysis. This allowed us to establish inter- and intra-rater variability in brain metastases segmentation and create a reference standard dataset that will be publicly available after the conclusion of the challenge. The model performance of the participating teams in the challenge will be assessed via the following metrics: Dice Similarity Coefficient (DSC), Normalized Surface Distance (NSD), sensitivity, and precision of the model. RESULTS A multi-annotator testing dataset of 75 MRI cases of brain metastases and 300 segmentations (150 created ‘from scratch’ and 150 from 3D nnU-Net pre-segmentations of the cases) was developed as a new reference standard. The mean intra- and inter-rater DSC for the segmentations ‘from scratch’ were 0.68 and 0.59, respectively. The mean intra- and inter-rater DSC for the segmentations built upon 3D nnU-Net pre-segmentations were 0.88 and 0.77, respectively. CONCLUSION The BraTS-METS 2025 Lighthouse Challenge is a key initiative designed to advance the use of AI to improve characterization of brain metastases by providing algorithms for automatic segmentation of all lesions and peritumoral edema that are measured against a novel reference standard based on rigorous multi-annotator brain MRI segmentations.

Pediatric central nervous system tumors are the leading cause of cancer-related deaths in children. The five-year survival rate for high-grade glioma in children is less than 20%. The development of new treatments is dependent upon multi-institutional collaborative clinical trials requiring reproducible and accurate centralized response assessment. We present the results of the BraTS-PEDs 2023 challenge, the first Brain Tumor Segmentation (BraTS) challenge focused on pediatric brain tumors. This challenge utilized data acquired from multiple international consortia dedicated to pediatric neuro-oncology and clinical trials. BraTS-PEDs 2023 aimed to evaluate volumetric segmentation algorithms for pediatric brain gliomas from magnetic resonance imaging using standardized quantitative performance evaluation metrics employed across the BraTS 2023 challenges. The top-performing AI approaches for pediatric tumor analysis included ensembles of nnU-Net and Swin UNETR, Auto3DSeg, or nnU-Net with a self-supervised framework. The BraTS-PEDs 2023 challenge fostered collaboration between clinicians (neuro-oncologists, neuroradiologists) and AI/imaging scientists, promoting faster data sharing and the development of automated volumetric analysis techniques. These advancements could significantly benefit clinical trials and improve the care of children with brain tumors.

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 environments and providing the tools for future development of personalized volumetric reports to patients undergoing BM treatment.

We describe the design and results from the BraTS 2023 Intracranial Meningioma Segmentation Challenge. The BraTS Meningioma Challenge differed from prior BraTS Glioma challenges in that it focused on meningiomas, which are typically benign extra-axial tumors with diverse radiologic and anatomical presentation and a propensity for multiplicity. Nine participating teams each developed deep-learning automated segmentation models using image data from the largest multi-institutional systematically expert annotated multilabel multi-sequence meningioma MRI dataset to date, which included 1000 training set cases, 141 validation set cases, and 283 hidden test set cases. Each case included T2, FLAIR, T1, and T1Gd brain MRI sequences with associated tumor compartment labels delineating enhancing tumor, non-enhancing tumor, and surrounding non-enhancing FLAIR hyperintensity. Participant automated segmentation models were evaluated and ranked based on a scoring system evaluating lesion-wise metrics including dice similarity coefficient (DSC) and 95% Hausdorff Distance. The top ranked team had a lesion-wise median dice similarity coefficient (DSC) of 0.976, 0.976, and 0.964 for enhancing tumor, tumor core, and whole tumor, respectively and a corresponding average DSC of 0.899, 0.904, and 0.871, respectively. These results serve as state-of-the-art benchmarks for future pre-operative meningioma automated segmentation algorithms. Additionally, we found that 1286 of 1424 cases (90.3%) had at least 1 compartment voxel abutting the edge of the skull-stripped image edge, which requires further investigation into optimal pre-processing face anonymization steps.

Abstract Background Although response in pediatric low-grade glioma (pLGG) includes volumetric assessment, more simplified 2D-based methods are often used in clinical trials. The study’s purpose was to compare volumetric to 2D methods. Methods An expert neuroradiologist performed solid and whole tumor (including cyst and edema) volumetric measurements on MR images using a PACS-based manual segmentation tool in 43 pLGG participants (213 total follow-up images) from the Pacific Pediatric Neuro-Oncology Consortium (PNOC-001) trial. Classification based on changes in volumetric and 2D measurements of solid tumor were compared to neuroradiologist visual response assessment using the Brain Tumor Reporting and Data System (BT-RADS) criteria for a subset of 65 images using receiver operating characteristic (ROC) analysis. Longitudinal modeling of solid tumor volume was used to predict BT-RADS classification in 54 of the 65 images. Results There was a significant difference in ROC area under the curve between 3D solid tumor volume and 2D area (0.96 vs 0.78, P = .005) and between 3D solid and 3D whole volume (0.96 vs 0.84, P = .006) when classifying BT-RADS progressive disease (PD). Thresholds of 15–25% increase in 3D solid tumor volume had an 80% sensitivity in classifying BT-RADS PD included in their 95% confidence intervals. The longitudinal model of solid volume response had a sensitivity of 82% and a positive predictive value of 67% for detecting BT-RADS PD. Conclusions Volumetric analysis of solid tumor was significantly better than 2D measurements in classifying tumor progression as determined by BT-RADS criteria and will enable more comprehensive clinical management.

Abstract Radiographic response assessment in neuro-oncology is critical in clinical practice and trials. Conventional criteria, such as the MacDonald and response assessment in neuro-oncology (RANO) criteria, rely on bidimensional (2D) measurements of a single tumor cross-section. Although RANO criteria are established for response assessment in clinical trials, there is a critical need to address the complexity of brain tumor treatment response with multiple new approaches being proposed. These include volumetric analysis of tumor compartments, structured MRI reporting systems like the Brain Tumor Reporting and Data System, and standardized approaches to advanced imaging techniques to distinguish tumor response from treatment effects. In this review, we discuss the strengths and limitations of different neuro-oncology response criteria and summarize current research findings on the role of novel response methods in neuro-oncology clinical trials and practice.

Abstract BACKGROUND Gliomas with CDKN2A mutations are known to have worse prognosis but imaging features of these gliomas are unknown. Our goal is to identify CDKN2A specific qualitative imaging biomarkers in glioblastomas using a new informatics workflow that enables rapid analysis of qualitative imaging features with Visually AcceSAble Rembrandtr Images (VASARI) for large datasets in PACS. Gliomas with CDKN2A mutations are known to have worse prognosis but imaging features of these gliomas are unknown. Our goal is to identify CDKN2A specific qualitative imaging biomarkers in glioblastomas using a new informatics workflow that enables rapid analysis of qualitative imaging features withVisually AcceSAble Rembrandtr Images (VASARI) for large datasets in PACS. MATERIAL AND METHODS Sixty nine patients undergoing GBM resection with CDKN2A status determined by whole-exome sequencing were included. GBMs on magnetic resonance images were automatically 3D segmented using deep learning algorithmsincorporated within PACS. VASARI features were assessed using FHIR forms integrated within PACS. RESULTS GBMs without CDKN2A alterations were significantly larger (64% vs. 30%, p=0.007) compared to tumors with homozygous deletion (HOMDEL) and heterozygous loss (HETLOSS). Lesions larger than 8 cm were four times more likely to have no CDKN2A alteration (OR: 4.3; 95% CI:1.5-12.1; p<0.001). The pial invasion was predictive of HOMDEL (OR: 8.1, 95% CI: 1.8-53.2; p<0.012) as tumors with pial invasion were eight times more likely to be HOMDEL, even after adjusting for deep white matter and subependymal invasion. CONCLUSION We developed a novel integrated PACS informatics platform for the assessment of GBM molecular subtypes and show that tumors with HOMDEL are more likely to have radiographic evidence of pial invasion and less likely to have deep white matter invasion or subependymal invasion. These imaging features may allow noninvasive identification of CDKN2A allele status.

Abstract BACKGROUND Differentiating radiation necrosis from tumour progression after radiation therapy (RT) for brain metastases (BM) remains clinically challenging, and accurate imaging is crucial to prevent unnecessary surgery or unwarranted changes in therapy. 18F-Fluciclovine is a PET radiopharmaceutical with low background uptake in the brain and increased uptake in BM. The PURSUE study (NCT04410367) aimed to establish image interpretation criteria (IIC) for detecting suspected recurrent BM after RT using 18F-fluciclovine PET, based on several measures of lesion uptake. MATERIAL AND METHODS Across 7 US sites, 23 patients with solid tumour BM and a previously irradiated ‘reference’ lesion equivocal for recurrence on MRI who were scheduled for craniotomy underwent 18F-fluciclovine PET (185 MBq) <42 days post-MRI and 1-21 days pre-craniotomy. Three independent, blinded readers qualitatively rated lesion 18F-fluciclovine uptake as ‘mild’ (up to blood pool), ‘moderate’ (above blood pool to parotid gland), or ‘marked’ (above parotid gland). The primary endpoint was the diagnostic performance of different thresholds of lesion uptake on qualitative (visual) reads vs central histopathology. Secondary endpoints included diagnostic performance, based on different thresholds, of quantitative (e.g., lesion standardized uptake value [SUV]), and dynamic measures. A committee, including two independent imaging physicians, reviewed all data to establish the IIC, which were subsequently used to evaluate the diagnostic performance of 18F-fluciclovine. RESULTS All 23 reference lesions underwent histopathological analysis, with 10 (43%) being pathologically confirmed BM recurrence. The highest performing qualitative measure of 18F-fluciclovine lesion uptake was ‘marked’, rendering 92-100% and variable (40-80%) across readers. SUVmax was a reader-independent, high-performing quantitative metric (AUC 0.87, SUVmax threshold 4.8, 80% sensitivity, 85% specificity). Dynamic measures did not add diagnostic value. Thus, the committee established IIC as: "Lesions with 18F-fluciclovine uptake of a SUVmax equal to or greater than 4.8, or visually greater than the parotid gland, should be considered suspicious for recurrence. Otherwise, recurrence should be considered unlikely." Application of these IIC resulted in 80% sensitivity, 77-85% specificity, 73-80% positive predictive value, and 83-85% negative predictive value across readers. CONCLUSION PURSUE is the first prospective, multicentre study to define IIC for 18F-fluciclovine PET for accurate identification of suspected recurrent BM after RT, verified by histopathology. In this initial cohort, the IIC convey excellent diagnostic performance for 18F-fluciclovine and will help evaluate 18F-fluciclovine PET in future studies. This study was sponsored by Blue Earth Diagnostics Ltd.

Abstract BACKGROUND After radiation therapy (RT) for brain metastases (BM), differentiating radiation necrosis from tumor recurrence remains challenging. PURSUE (NCT04410367) evaluated various measures of lesion 18F-fluciclovine uptake to establish image interpretation criteria (IIC) for 18F-fluciclovine-PET to accurately diagnose recurrent BM. METHODS Patients with solid tumor BM and a previously irradiated ‘reference’ lesion equivocal for recurrence on MRI who were scheduled for craniotomy underwent 18F-fluciclovine-PET (185 MBq) <42 days post-MRI and 1-21 days pre-craniotomy. Lesion 18F-fluciclovine uptake was qualitatively rated as ‘mild’ (up to blood pool), ‘moderate’ (above blood pool to parotid gland), or ‘marked’ (above parotid gland) by three independent blinded readers. The primary endpoint was diagnostic performance of different uptake thresholds on qualitative reads vs central histopathology. Secondary endpoints included diagnostic performance, based on different thresholds, of quantitative (e.g., lesion standardized uptake value [SUV]) and dynamic measures. IIC were determined by committee and subsequently used to assess the diagnostic performance of 18F-fluciclovine. RESULTS All 23 reference lesions from 23 enrolled patients underwent histopathological analysis; 10 (43%) were pathologically-confirmed BM recurrence. The highest performing qualitative measure was ‘marked’, rendering 92-100% sensitivity and 40-80% specificity across readers. SUVmax was a reader-independent, high-performing quantitative metric (AUC 0.87, SUVmax threshold 4.8, 80% sensitivity, 85% specificity). Dynamic measures did not add diagnostic value. Thus, IIC was established as: “Lesions with 18F-fluciclovine uptake of SUVmax equal to or greater than 4.8, or visually greater than the parotid gland, should be considered suspicious for recurrence. Otherwise, recurrence should be considered unlikely.” Application of the IIC resulted in 80% sensitivity, 77-85% specificity, 73-80% PPV, and 83-85% NPV across the readers. CONCLUSIONS PURSUE is the first prospective, multicenter trial to establish IIC for 18F-fluciclovine-PET for suspected recurrent BM after RT, verified by histopathology. Finalized IIC demonstrated excellent diagnostic performance for 18F-fluciclovine and will help evaluate 18F-fluciclovine-PET in future studies.

2001 Background: Differentiating radiation necrosis from tumor progression remains one of the most commonly encountered and clinically challenging scenarios after radiation therapy (RT) for brain metastases (BM). PURSUE (NCT04410367) evaluated the diagnostic performance of 18F-fluciclovine, an amino acid PET radiopharmaceutical, based on various lesion metrics, to establish image interpretation criteria (IIC) for suspected recurrent BM after RT. Methods: Patients with solid tumor BM were enrolled across 7 US sites if they had a previously irradiated ‘reference’ lesion equivocal on MRI for recurrence and were planned for craniotomy. 18F-Fluciclovine PET (185 MBq) took place <42 days post-MRI and 1-21 days pre-craniotomy. The primary endpoint was the diagnostic performance (sensitivity, specificity, positive-, and negative-predictive value [PPV/NPV]) of different thresholds of lesion 18F-fluciclovine uptake on qualitative, visual reads vs central histopathological analysis. Lesion 18F-fluciclovine uptake was assessed qualitatively by 3 independent blinded readers who visually rated the uptake as ‘mild’ (up to blood pool), ‘moderate’ (above blood pool to parotid), or ‘marked’ (above parotid). Secondary endpoints included the diagnostic performance based on different thresholds of quantitative (e.g., lesion SUV) and dynamic measures of uptake. A committee, including 2 expert imaging physicians independent to PURSUE, reviewed all data in round-table meetings to establish the IIC, which were subsequently used to assess diagnostic performance. Results: All 23 reference lesions in 23 subjects underwent histopathological analysis, with 10 (43%) confirmed as recurrent tumor. The highest performing qualitative measure was ‘marked’, rendering a sensitivity of 92-100%, with variable specificity of 40-80% across readers. SUVmax was a reader-independent, high-performing quantitative metric on ROC analysis (AUC 0.87, SUVmax threshold 4.8 conferring a sensitivity of 80% and specificity of 85%). Dynamic measures did not provide added diagnostic value. After analyzing these metrics, the committee established IIC as: Lesions with 18F-fluciclovine uptake of a SUVmax equal to or greater than 4.8, or visually greater than the parotid gland, should be considered suspicious for recurrence. Otherwise, recurrence should be considered unlikely. Application of the IIC resulted in a sensitivity of 80%, specificity of 77-85%, PPV of 73-80%, and NPV of 83-85% across the readers. Conclusions: This is the first prospective multicenter trial to evaluate PET characteristics of suspected recurrent BM after RT, verified by histopathology. Qualitative and quantitative IIC show 18F-fluciclovine to be a high-performing diagnostic tool. These IIC will help evaluate the diagnostic performance of 18F-fluciclovine PET in future trials. Clinical trial information: NCT04410367 .