Bendszus, Martin

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.

2026 Background: Validation of the 2016 RANO MRI scorecard for leptomeningeal metastasis failed for multiple reasons. Accordingly, this joint EORTC Brain Tumor Group and RANO effort sought to prospectively validate a revised MRI scorecard for response assessment in leptomeningeal metastasis. Methods: Coded paired cerebrospinal MRI of 20 patients with leptomeningeal metastases from solid cancers at baseline and follow-up after treatment and instructions for assessment were provided via the EORTC imaging platform. The Kappa coefficient was used to evaluate the inter-observer pairwise agreement. Results: Thirty-five raters participated, including 9 neuroradiologists, 17 neurologists, 4 radiation oncologists, 3 neurosurgeons and 2 medical oncologists. Among single leptomeningeal metastases-related imaging findings at baseline, the best median concordance was noted for hydrocephalus (Kappa = 0.63), and the worst median concordance for spinal linear enhancing disease (Kappa = 0.46). The median concordance of raters for the overall response assessment was moderate (Kappa = 0.44). Notably, the interobserver agreement for the presence of parenchymal brain metastases at baseline was fair (Kappa = 0.29) and virtually absent for their response to treatment. 394 of 700 ratings (20 patients x 35 raters, 56%) were fully completed. In 308 of 394 fully completed ratings (78%), the overall response assessment perfectly matched the summary interpretation of the single ratings as proposed in the scorecard instructions. Conclusions: This study confirms the principle utility of the new scorecard, but also indicates the need for training of MRI assessment with a dedicated reviewer panel in clinical trials. Electronic case report forms with “blocking options” may be required to enforce completeness and quality of scoring.

Abstract Background Validation of the 2016 RANO MRI scorecard for leptomeningeal metastasis failed for multiple reasons. Accordingly, this joint EORTC Brain Tumor Group and RANO effort sought to prospectively validate a revised MRI scorecard for response assessment in leptomeningeal metastasis. Methods Coded paired cerebrospinal MRI of 20 patients with leptomeningeal metastases from solid cancers at baseline and follow-up after treatment and instructions for assessment were provided via the EORTC imaging platform. The Kappa coefficient was used to evaluate the interobserver pairwise agreement. Results Thirty-five raters participated, including 9 neuroradiologists, 17 neurologists, 4 radiation oncologists, 3 neurosurgeons, and 2 medical oncologists. Among single leptomeningeal metastases-related imaging findings at baseline, the best median concordance was noted for hydrocephalus (Kappa = 0.63), and the worst median concordance for spinal linear enhancing disease (Kappa = 0.46). The median concordance of raters for the overall response assessment was moderate (Kappa = 0.44). Notably, the interobserver agreement for the presence of parenchymal brain metastases at baseline was fair (Kappa = 0.29) and virtually absent for their response to treatment. 394 of 700 ratings (20 patients x 35 raters, 56%) were fully completed. In 308 of 394 fully completed ratings (78%), the overall response assessment perfectly matched the summary interpretation of the single ratings as proposed in the scorecard instructions. Conclusion This study confirms the principle utility of the new scorecard, but also indicates the need for training of MRI assessment with a dedicated reviewer panel in clinical trials. Electronic case report forms with “blocking options” may be required to enforce completeness and quality of scoring.

Abstract BACKGROUND Validation of the 2016 LANO MRI scorecard for leptomeningeal metastasis failed for multiple reasons. The objective of this joint EORTC Brain Tumor Group and RANO effort was to validate the feasibility of the revised MRI scorecard for assessing response in leptomeningeal metastasis. METHODS Coded paired cerebrospinal MRI of 20 patients with leptomeningeal metastases from solid cancers at baseline and follow-up after treatment and instructions for assessment were provided via the EORTC imaging platform. The kappa coefficient (K) was used to evaluate inter-observer pairwise agreement. Statistical analyses were performed using SAS V9.4 software (Cary, NC). The sponsor of the study was the University Hospital Zurich (2018-00192). RESULTS Thirty-five raters participated, including 9 neuroradiologists, 17 neurologists, 4 radiation oncologists, 3 neurosurgeons and 2 medical oncologists. Among leptomeningeal metastases-related items at baseline, the best median concordance was noted for hydrocephalus (K=0.63), and the worst median for spinal linear enhancing disease (K=0.46). The median concordance for overall response was moderate (K=0.44). Notably, the interobserver agreement for the presence of parenchymal brain metastases at baseline was minimal (K=0.29). Significant differences were observed when considering the specialty of the raters. Only 394 of 700 ratings (56%) were fully completed. Among 394 fully completed ratings, perfect concordance was noted in 293 ratings (74%) when comparing the overall response according to the guidelines provided in the scorecard and the overall response provided by the raters. The main discordances were noted for partial response according to the rater versus stable disease according to the guidelines (n=44), followed by progression according to the raters versus stable disease according to the guidelines (n=23). CONCLUSION Electronic case report forms with "blocking solutions" are probably required to enforce completeness and quality of scoring. These results confirm the necessity of central review and the need for training of MRI assessment in clinical trials.

Limited data exist on clot composition and detailed characteristics of arterial thrombi associated with large vessel occlusion in acute ischemic stroke. Advances in endovascular thrombectomy and related imaging modalities have created a unique opportunity to analyze thrombi removed from cerebral arteries. Insights into thrombus composition, etiology, physical properties and neurovascular interactions may lead to future advancements in acute ischemic stroke treatment and improved clinical outcomes. Advances in imaging techniques may enhance clot characterization and inform therapeutic decision-making prior to treatment and reveal stroke etiology to guide secondary prevention. Current imaging techniques can provide some information about thrombi, but there remains much to evaluate about relationships that may exist among thrombus composition, occlusion characteristics and treatment outcomes. Improved pathophysiological characterization of clot types, their properties and how these properties change over time, together with clinical correlates from ongoing studies, may facilitate revascularization with thrombolysis and thrombectomy. Interdisciplinary approaches covering clinical, engineering and scientific aspects of thrombus research will be key to advancing the understanding of thrombi and improving acute ischemic stroke therapy. This consensus statement integrates recent research on clots and thrombi retrieved from cerebral arteries and provides a rationale for further analyses, including current opportunities and limitations.