Interpretable multimodal PET/CT-EHR fusion via mixture-of-experts for prognostic stratification in mantle cell lymphoma: a multicenter study.
[BACKGROUND] Mantle cell lymphoma (MCL) is a rare, biologically heterogeneous B-cell malignancy with highly variable outcomes.
- p-value P < 0.001
- p-value P = 0.001
- HR 27.70
APA
Jiang C, Zhang Z, et al. (2026). Interpretable multimodal PET/CT-EHR fusion via mixture-of-experts for prognostic stratification in mantle cell lymphoma: a multicenter study.. BMC medicine. https://doi.org/10.1186/s12916-026-04865-1
MLA
Jiang C, et al.. "Interpretable multimodal PET/CT-EHR fusion via mixture-of-experts for prognostic stratification in mantle cell lymphoma: a multicenter study.." BMC medicine, 2026.
PMID
41992190
Abstract
[BACKGROUND] Mantle cell lymphoma (MCL) is a rare, biologically heterogeneous B-cell malignancy with highly variable outcomes. Existing prognostic tools are suboptimal. We developed an interpretable deep learning framework integrating baseline [F]FDG PET/CT and electronic health record (EHR) data for individualized risk stratification.
[METHODS] In this multicenter study, 187 treatment-naïve MCL patients were analyzed. A mixture-of-experts (MoE) fusion network integrated multimodal representations from PET/CT and EHR data. Expert modules comprising vision encoders, radiomics extractors, and a medical language model were integrated through an attention-based gating mechanism to construct multimodal radiomic signatures (R-signatures) predictive of progression-free survival (PFS) and overall survival (OS). R-signatures were validated and incorporated with clinical and metabolic factors into multiparametric models. Deep learning model interpretability was evaluated using attention visualization, expert-level contributions and pathologic correlation.
[RESULTS] R-signatures robustly discriminated relapse (AUC = 0.893 training, 0.755 validation) and death (AUC = 0.804 and 0.844), and independently predicted adverse outcomes (PFS: HR = 27.70, P < 0.001; OS: HR = 6.86, P = 0.001). Multiparametric models integrating R-signatures with total lesion glycolysis, β2-microglobulin, WBC, and Ki-67 outperformed conventional indices (C-indices: PFS 0.892 training, 0.781 validation; OS 0.877 training, 0.862 validation). Time-dependent ROC analyses consistently showed AUCs approaching or exceeding 0.800. Calibration and decision curve analyses confirmed excellent agreement and superior clinical net benefit. Attention maps localized high-weighted regions to hypermetabolic tumor areas, with higher R-signature values in blastoid and pleomorphic variants versus classical histology (P = 0.028 and P = 0.010).
[CONCLUSIONS] This interpretable PET/CT-EHR fusion framework substantially improves prognostic precision in MCL, providing a noninvasive, clinically translatable tool for risk-adapted management.
[METHODS] In this multicenter study, 187 treatment-naïve MCL patients were analyzed. A mixture-of-experts (MoE) fusion network integrated multimodal representations from PET/CT and EHR data. Expert modules comprising vision encoders, radiomics extractors, and a medical language model were integrated through an attention-based gating mechanism to construct multimodal radiomic signatures (R-signatures) predictive of progression-free survival (PFS) and overall survival (OS). R-signatures were validated and incorporated with clinical and metabolic factors into multiparametric models. Deep learning model interpretability was evaluated using attention visualization, expert-level contributions and pathologic correlation.
[RESULTS] R-signatures robustly discriminated relapse (AUC = 0.893 training, 0.755 validation) and death (AUC = 0.804 and 0.844), and independently predicted adverse outcomes (PFS: HR = 27.70, P < 0.001; OS: HR = 6.86, P = 0.001). Multiparametric models integrating R-signatures with total lesion glycolysis, β2-microglobulin, WBC, and Ki-67 outperformed conventional indices (C-indices: PFS 0.892 training, 0.781 validation; OS 0.877 training, 0.862 validation). Time-dependent ROC analyses consistently showed AUCs approaching or exceeding 0.800. Calibration and decision curve analyses confirmed excellent agreement and superior clinical net benefit. Attention maps localized high-weighted regions to hypermetabolic tumor areas, with higher R-signature values in blastoid and pleomorphic variants versus classical histology (P = 0.028 and P = 0.010).
[CONCLUSIONS] This interpretable PET/CT-EHR fusion framework substantially improves prognostic precision in MCL, providing a noninvasive, clinically translatable tool for risk-adapted management.
같은 제1저자의 인용 많은 논문 (5)
- Long Term Results of Proton Therapy in Adult Infradiaphragmatic Lymphoma.
- Metabolic Trojan Horse: Multivalent Glucose Ligand Modified Near-Infrared-Absorbing Gold Nanorods for Targeted Photothermal Therapy.
- Integrated Weighted Gene Co-Expression Network and Single-Cell RNA Sequencing Analyses Reveal the Prognostic Significance of Hypoxia in Gastric Cancer.
- Optimizing Mediastinal Lymph Node Dissection by Integrating Tumour Location, Consolidation Tumour Ratio, and Size for Lung Cancer.
- Letter to the Editor: "Lymphocyte-Monocyte Ratio Predicts Survival in Patients With Unresectable Hepatocellular Carcinoma Treated With Durvalumab Plus Tremelimumab: A Multicenter Analysis".