Bell, Robert

Abstract INTRODUCTION Glioblastoma is the most common malignant adult brain tumor with poor prognosis, largely due to its heterogeneous landscape. The AI-RANO and RANO-RGP groups organized the BraTS-Pathology 2024 challenge, providing a publicly-available dataset and a benchmarking environment for AI models to automatically identify six clinically-relevant histopathologic sub-regions in H&E-stained whole slide images (WSIs). METHODS We reclassified the TCGA-GBM and TCGA-LGG data according to the WHO 2021 criteria and identified diagnostic WSIs of 188 glioblastoma (IDH-wt, CNS WHO Gr.4) patients. A well-defined annotation protocol was communicated to eight neuropathologists, across eight institutions, who created “ground truth” annotations for Cellular Tumor (CT), Geographic Necrosis, Cortical Infiltration, Pseudopalisading Necrosis (PN), Microvascular Proliferation, and Penetration into White Matter (PWM). Comprehensive WSI curation for elimination of artifactual content and follow up partitioning resulted in approximately 300,000 data samples/patches. FINDINGS Inter-observer variability assessment highlighted difficulties in establishing a “gold standard”. The least annotated sub-regions (PWM and PN) were the most challenging to the participating methods, whereas all methods achieved their highest accuracy in the most annotated sub-region (CT). The highest average performance across sub-regions was obtained by a foundation model-based method. However, this top-ranked solution achieved an F1 score of 0.51 (Accuracy=0.65, Sensitivity=0.56, Specificity=0.93). CONCLUSIONS Our findings suggest that achieving state-of-the-art performance, in automatically identifying clinically-relevant glioblastoma sub-regions, remains an unsolved research problem. Analysis of the ground-truth annotations underscores the critical need for more precisely defined and neuropathologically standardized annotation protocol. Current AI algorithms are facing difficulties in addressing glioblastoma’s heterogeneous histologic landscape in the absence of large, comprehensively, and consistently annotated data. Building upon these findings, and towards developing more accurate AI algorithms, the 2025 iteration of the BraTS-Path challenge is currently on-going by leveraging two million data samples, aiming to enhance our disease understanding and improve diagnostic accuracy, ultimately contributing to improved patient outcomes.

We investigated the prognostic impact of blast counts, TP53 allelic state determinants (number of hits, del(17p), variant allele frequency, complex karyotype),and a novel karyotypic clonal cell fraction (≤50% clonal cells vs >50% clonal cells (termed ‘CK50’)) in 495 individuals with TP53- mutated ( TP53 MUT ) myeloid neoplasms. Outcome examined was 24-month survival (OS24). The cohort (median age 71) included 29% (144/495) myelodysplastic syndromes (MDS)/MDS-acute myeloid leukaemia (AML) (1%–19% blasts) and 71% (351/495) AML (≥20% blasts), with 18% (81/460) having low CK50. Overall, 83% received front-line hypomethylating agents. Higher blast counts (<20% vs ≥20%) were marginally associated with CK50 (p=0.08). In the OS24 analysis, blast count showed a marginal association with OS24 (HR 1.3 (95% CI 1.0 to 1.6); p=0.07), while CK50 predicted significantly inferior outcomes (HR=1.7 (95% CI 1.2 to 2.3); p=0.002). In a multivariable model including all TP53 allelic state determinants, only CK50 and complex karyotype remained relevant for predicting adverse outcomes.

SummaryTo assess the relevance of co‐occurring somatic mutations in TP53‐mutated myeloid neoplasms with ≥10% blasts, we pooled 325 individuals from 10 centres. We focused on comparing three published somatic co‐alteration signatures comprising (1) nine MDS‐related genes (‘ICC‐MDSR’), (2) ICC‐MDSR + additional secondary mutations‐related genes (‘Tazi signature’) and (3) EPI6 (comprising six genes). Outcomes examined were 24‐month overall survival (OS24) and front‐line complete response (CR1). The median age was 69 years with 77% receiving front‐line hypomethylating agents (HMA). All three signatures ICC‐MDSR (p = 0.009), Tazi signature (p = 0.001) and EPI6 (p = 0.025) predicted inferior CR1. In the low‐intensity (HMA) subgroup, only Tazi signature (p = 0.026) predicted inferior CR1. In OS24 analysis of the HMA‐treated subgroup (N = 200), only Tazi signature was adverse (hazard ratio, HR = 1.6 [1.1–2.2]; p = 0.011). However, a forward stepwise multivariable age‐adjusted Cox model including all three signatures picked EPI6 as the sole significant adverse predictor in the entire cohort (p = 0.0001) as well as within the HMA‐treated subgroup (p = 0.0071). These data confirm the value of testing co‐occurring somatic alterations even within a high‐grade TP53‐mutated myeloid neoplasm cohort.