Profiling of Circulating Tumor DNA for Noninvasive Disease Detection, Risk Stratification, and MRD Monitoring in Patients with CNS Lymphoma

Introduction: Clinical outcomes for patients with central nervous system lymphoma (CNSL) are remarkably heterogeneous, yet identification of patients at high risk for treatment failure remains challenging with existing methods. In addition, diagnosis of CNSL requires invasive neurosurgical biopsies that carry procedural risks and often cannot be performed in frail or elderly patients. Circulating tumor DNA (ctDNA) has shown great potential as a noninvasive biomarker in systemic lymphomas. Yet, previous studies revealed low ctDNA detection rates in blood plasma of CNSL patients. In this study, we utilized ultrasensitive targeted high-throughput sequencing technologies to explore the role of ctDNA for disease classification, MRD detection, and early prediction of clinical outcomes in patients with CNSL.

Methods: We applied Cancer Personalized Profiling by Deep Sequencing (CAPP-Seq) and Phased Variant Enrichment and Detection Sequencing (PhasED-Seq, Kurtz et al, Nat Biotech 2021) to 85 tumor biopsies, 131 plasma samples, and 62 CSF specimens from 92 CNSL patients and 44 patients with other brain cancers or inflammatory cerebral diseases, targeting 794 distinct genetic regions. Concentrations of ctDNA were correlated with radiological measures of tumor burden and tested for associations with clinical outcomes at distinct clinical time points. We further developed a novel classifier to noninvasively distinguish CNS lymphomas from other CNS tumors based on their mutational landscapes in plasma and CSF, using supervised training of a machine learning approach from tumor whole genome sequencing data and own genotyping analyses, followed by its independent validation.

Results: We identified genetic aberrations in 100% of CNSL tumor biopsies (n=63), with a median of 262 mutations per patient. Pretreatment plasma ctDNA was detectable in 78% of plasma samples and in 100% of CSF specimens (Fig. 1a), with ctDNA concentrations ranging from 0.0004 - 5.94% allele frequency (AF, median: 0.01%) in plasma and 0.0049 - 50.47% AF (median: 0.62%) in CSF (Fig. 1b). Compared to ctDNA concentrations in patients with systemic diffuse large B-cell lymphoma (DLBCL, data from Kurtz et al., J Clin Oncol, 2018), plasma ctDNA levels in CNSL were in median more than 200-fold lower (Fig. 1b). We observed a significant correlation of ctDNA concentrations with total radiographic tumor volumes (TRTV) measured by MRI (Fig. 1c,d), but no association with clinical risk scores (i.e., MSKCC score) or concurrent steroid treatment. Assessment of ctDNA at pretreatment time points predicted progression-free survival (PFS) and overall survival (OS), both as continuous and binary variable (Fig. 1e,f). Notably, patients could be stratified into risk groups with particularly favorable or poor prognoses by combining ctDNA and TRTV as pretreatment biomarkers (Fig. 1g). Furthermore, ctDNA positivity during curative-intent induction therapy was significantly associated with clinical outcomes, both PFS and OS (Fig. 1h). Finally, we applied our novel machine learning classifier to 207 specimens from an independent validation cohort of CNSL and Non-CNSL patients. We observed high specificity (100%) and positive predictive value (100%) for noninvasive diagnosis of CNSL, with a sensitivity of 57% for CSF and 21% for plasma, suggesting that a significant subset of CNSL patients might be able to forego invasive surgical biopsies.

Conclusions: We demonstrate robust and ultrasensitive detection of ctDNA at various disease milestones in CNSL. Our findings suggest that ctDNA accurately mirrors tumor burden and serves as a valuable clinical biomarker for risk stratification, outcome prediction, and surgery-free lymphoma classification in CNSL. We foresee an important potential future role of ctDNA as a decision-making tool to guide treatment in patients with CNSL.

Figure 1

View largeDownload slide

Figure 1

View largeDownload slide

Close modal