Robust Multimodal Deep Learning for Lymphoma Subtype Classification Using 18F-FDG PET Maximum Intensity Projection Images and Clinical Data: A Multi-Center Study

<b>Background:</b> Previous attempts to classify lymphoma subtypes based on metabolic features extracted from ¹⁸F-FDG PET imaging have been hindered by inconsistencies in imaging protocols, scanner types, and inter-institutional variability. To overcome these limitations, we propose a multimodal deep learning framework that integrates harmonized PET imaging features with structured clinical information. The proposed framework is designed to perform hierarchical classification of clinically meaningful lymphoma subtypes through two sequential binary classification tasks. <b>Methods:</b> We collected multi-center data comprising ¹⁸F-FDG PET images and structured clinical variables of patients with lymphoma. To mitigate domain shifts caused by different scanner manufacturers, we integrated a Scanner-Conditioned Normalization (SCN) module, which adaptively harmonizes feature distributions using manufacturer-specific parameters. Performance was validated using internal and external cohorts, with the statistical significance of performance gains assessed via DeLong's test and bootstrap-based CI analysis. <b>Results:</b> The proposed model achieved an area under the curve (AUC) of 0.89 (internal) and 0.84 (external) for Hodgkin lymphoma versus non-Hodgkin lymphoma classification and 0.84 (internal) and 0.76 (external) for diffuse large B-cell lymphoma versus follicular lymphoma classification (<i>p</i> > 0.05). These results were obtained using a multimodal model that integrated anterior and lateral maximum intensity projection (MIP) images with clinical data. <b>Conclusions:</b> This study demonstrates the potential of a deep learning-based approach for lymphoma subtype classification using non-invasive ¹⁸F-FDG PET imaging combined with clinical data. While further validation in larger, more diverse cohorts is necessary to address the challenges of rare subtypes and biological heterogeneity, LymphoMAP serves as a meaningful step toward developing assistive tools for early clinical decision-making. These findings underscore the feasibility of using automated pipelines to support, rather than replace, conventional diagnostic workflows in personalized lymphoma management.