Radiomic features define risk and are linked to DNA methylation attributes in primary CNS lymphoma.

Background: The prognostic roles of clinical and laboratory markers have been exploited to model risk in patients with primary CNS lymphoma, but these approaches do not fully explain the observed variation in outcome. To date, neuroimaging or molecular information is not used. The aim of this study was to determine the utility of radiomic features to capture clinically relevant phenotypes, and to link those to molecular profiles for enhanced risk stratification. Methods: In this retrospective study, we investigated 133 patients across 9 sites in Austria (2005-2018) and an external validation site in South Korea (44 patients, 2013-2016). We used T1-weighted contrast-enhanced MRI and an L1-norm regularized Cox proportional hazard model to derive a radiomic risk score. We integrated radiomic features with DNA methylation profiles using machine learning-based prediction, and validated the most relevant biological associations in tissues and cell lines. Results: The radiomic risk score, consisting of 20 mostly textural features, was a strong and independent predictor of survival (multivariate hazard ratio = 6.56 [3.64-11.81]) that remained valid in the external validation cohort. Radiomic features captured gene regulatory differences such as in BCL6 binding activity, which was put forth as testable treatment target for a subset of patients. Conclusions: The radiomic risk score was a robust and complementary predictor of survival and reflected characteristics in underlying DNA methylation patterns. Leveraging imaging phenotypes to assess risk and inform epigenetic treatment targets provides a concept on which to advance prognostic modeling and precision therapy for this aggressive cancer.

Sex-Specific Differences in Primary CNS Lymphoma.

Sex-specific differences have been increasingly recognized in many human diseases including brain cancer, namely glioblastoma. Primary CNS lymphoma (PCNSL) is an exceedingly rare type of brain cancer that tends to have a higher incidence and worse outcomes in male patients. Yet, relatively little is known about the reasons that contribute to these observed sex-specific differences. Using a population-representative cohort of patients with PCNSL with dense magnetic resonance (MR) imaging and digital pathology annotation (n = 74), we performed sex-specific cluster and survival analyses to explore possible associations. We found three prognostically relevant clusters for females and two for males, characterized by differences in (i) patient demographics, (ii) tumor-associated immune response, and (iii) MR imaging phenotypes. Upon a multivariable analysis, an enhanced FoxP3+ lymphocyte-driven immune response was associated with a shorter overall survival particularly in female patients (HR 1.65, p = 0.035), while an increased extent of contrast enhancement emerged as an adverse predictor of outcomes in male patients (HR 1.05, p < 0.01). In conclusion, we found divergent prognostic constellations between female and male patients with PCNSL that suggest differential roles of tumor-associated immune response and MR imaging phenotypes. Our results further underline the importance of continued sex-specific analyses in the field of brain cancer.