Purpose: To assess the potential value of LiqBio as a complementary tool for diagnosis and surveillance of BCL. Methods: This prospective multi-center study included 78 patients (25 follicular lymphomas (FL) and 53 large B-cell lymphomas (LBCL)). We performed next-generation sequencing (NGS) of cfDNA LiqBio and paired gDNA tissue biopsies at diagnosis and compared the mutational statuses. Also, through NGS of LiqBio, we identified MRD biomarkers and compared this novel LiqBio–MRD method with PET/CT in detecting MRD at follow-up. Results: We identified mutations in 71% of LiqBio and 95% of tissue biopsies, and found a correlation between variant allele frequency of somatic mutations. Additionally, we identified mutations in 73% of LiqBio from patients with no available tissue samples or no mutations in them. Regarding the utility of LiqBio–MRD as a dynamic monitoring tool, when compared with the PET/CT method, a lower sensitivity was observed for LiqBio–MRD at 92.3% (vs. 100% for PET/CT), but a higher specificity of 91.3% (vs. 86.9% for PET/CT). Conclusion: Genetic profiling of tumor cfDNA in plasma LiqBio is a complementary tool for BCL diagnosis and MRD surveillance.

Non-Hodgkin lymphoma is a heterogeneous group of cancers that triggers bone marrow infiltration in 20–40% of cases. Bone marrow biopsy in combination with a visual assessment of [¹⁸F]FDG PET/CT images is used to assess the marrow status. Despite the potential of both techniques, they still have limitations due to the subjectivity of visual assessment. The present study aims to develop models based on bone marrow uptake in [¹⁸F]FDG PET/CT images at the time of diagnosis to differentiate bone marrow status. For this purpose, a model trained for skeleton segmentation and based on the U-Net architecture is retrained for bone marrow segmentation from CT images. The mask obtained from this segmentation together with the [¹⁸F]FDG PET image is used to extract radiomics features with which 11 machine learning models for marrow status differentiation are trained. The segmentation model yields very satisfactory results with Jaccard and Dice index values of 0.933 and 0.964, respectively. As for the classification models, a maximum F1_score_weighted and F1_score_macro of 0.962 and 0.747, respectively, are achieved. This highlights the potential of these features for bone marrow assessment, laying the foundation for a new clinical decision support system.