While most small B-cell lymphomas (SBCLs) can be diagnosed using routine methods, challenges exist. For example, marginal zone lymphomas (MZLs) can be difficult to rule-in, in large part because there is no widely-available, sensitive, and specific biomarker for the marginal zone cell-of-origin. In this study, we hypothesize that DNA methylation array profiling can assist with the classification of SBCLs, including MZLs. Extramedullary SBCLs, including challenging cases, were reviewed internally for pathology consensus and profiled. By combining the resulting array dataset with datasets from other groups, a set of 26 informative probes was selected, and used to train machine learning models to classify four common SBCLs: chronic lymphocytic leukemia/small lymphocytic lymphoma, follicular lymphoma, mantle cell lymphoma, and MZL. Applying a prediction probability cutoff to separate classifiable from unclassifiable cases, we found that the trained model was able to classify 95% of independent test cases (264/279). The concordance between model predictions and pathology diagnoses was 99.6% (262/263) among classifiable test cases. One validation reference test case was re-classified based on model prediction. The model was also used to predict the diagnoses of two challenging SBCLs. Although the differential examined and data on difficult cases are limited, our results support accurate methylation-based classification of SBCLs. Further, high specificities of predictions suggest that methylation signatures can be used to rule-in MZLs.
Copyright © 2021. Published by Elsevier Inc.

Author