Clinical, Molecular Genotype, and Radiomics Features and Prediction of Outcomes Among Patients With Aggressive B-Cell Lymphoma

Results from a Retrospective Cohort Study

According to findings from a trial recently published in Blood Advances, the combination of clinical, molecular genotype, and radiomics features improved the prediction of patient outcomes with aggressive B-cell lymphoma, which aided in identifying poor prognosis patients. 

Jakoba J. Eertink, MD, Vrije Universiteit Amsterdam, Amsterdam, The Netherlands, and coauthors stated, “Whether baseline radiomics features differ between patients with aggressive B-cell lymphoma with molecular high-risk features, such as MYC-R, and patients without these high-risk features is still unknown.”

They explained, “the added value of radiomics features on the predictive value of MYC-R status has not been studied yet,” as the impetus for this study. Because of this gap in research, Dr Eertink and coauthors aimed to investigate whether combining clinical, molecular genotype, and radiomics features could improve the prediction of patient outcomes with aggressive B-cell lymphoma. 

323 patients with de novo aggressive B-cell lymphoma were enrolled in this study. MYC, BCL2, and BCL6 rearrangements were assessed and identified using fluorescence in situ hybridization (FISH). The predictive value of the International Prognostic Index (IPI), IPI plus MYC, IPI, MYC, and MTV, radiomics, and MYC plus radiomics models were tested using the cross-validated area under the curve (CV-AUC) and positive predictive values (PPVs).

After the assessment, patients with wild-type MYC were treated with rituximab, cyclophosphamide, doxorubicin, vincristine, and prednisone (R-CHOP), R-CHOP intensified with rituximab (RR-CHOP), or 2 cycles of R-CHOP consisting of high-dose methotrexate, cytarabine, hyper-fractionated cyclophosphamide and ifosfamide, split-dose doxorubicin and etoposide, vincristine, vindesine, and dexamethasone. Patients with MYC-SH and DH/TH were treated with R-CHOP combined with lenalidomide (R2-CHOP), R-CHOP, RR-CHOP, or the Burkitt protocol. PET/CT analyses were also performed to assess tumor lesions. 

Results of the International Prognostic Index (IPI) indicated a CV-AUC of 0.65 ± 0.07 with a positive predictive value (PPV) of 29.6%. The IPI plus MYC model had a CV-AUC of 0.68 ± 0.08. IPI, MYC, and MTV had a CV-AUC of 0.74 ± 0.08. PPV was 50% and highest for the MYC plus radiomics model and increased by 20% compared with the IPI of 29.6%. This indicated that adding radiomics features significantly improved model performance and PPV. 

Dr Eertink et al concluded, “radiomics features extracted from baseline 18F-FDG PET/CT scans accurately predict outcomes in aggressive B-cell lymphoma and an integrative approach with both molecular data and quantitative PET metrics could improve the prediction of prognosis and guide the choice of therapies.” 

They added, “robust and easy-to-use biomarkers for the early identification of poor responders in this patient group are essential” for the treatment and prediction of aggressive B-cell lymphoma. 

Source:

Eertink JJ, Zwezerijnen GJC, Wiegers SE, et al. Baseline radiomics features and MYC rearrangement status predict progression in aggressive B-cell lymphoma. Blood Advances. 2023;7(2):214-223. doi:https://doi.org/10.1182/bloodadvances.2022008629