Background:Previous attempts to classify lymphoma subtypes based on metabolic features extracted from18F-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.Methods:We collected multi-center data comprising18F-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.Results: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 (p> 0.05). These results were obtained using a multimodal model that integrated anterior and lateral maximum intensity projection (MIP) images with clinical data.Conclusions:This study demonstrates the potential of a deep learning-based approach for lymphoma subtype classification using non-invasive18F-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.
背景：先前基于18F-FDG PET成像提取的代谢特征对淋巴瘤亚型进行分类的尝试，常因成像方案、扫描仪类型及机构间差异导致的不一致性而受阻。为克服这些局限，我们提出一种多模态深度学习框架，将标准化PET成像特征与结构化临床信息相整合。该框架旨在通过两个连续的二元分类任务，对具有临床意义的淋巴瘤亚型进行分层分类。
方法：我们收集了包含淋巴瘤患者18F-FDG PET图像和结构化临床变量的多中心数据。为减轻不同扫描仪制造商引起的域偏移，我们引入了扫描仪条件归一化模块，该模块利用制造商特异性参数自适应地协调特征分布。通过内部与外部队列验证模型性能，并使用DeLong检验和基于bootstrap的置信区间分析评估性能增益的统计学意义。
结果：所提模型在霍奇金淋巴瘤与非霍奇金淋巴瘤分类中曲线下面积达0.89（内部）和0.84（外部），在弥漫大B细胞淋巴瘤与滤泡性淋巴瘤分类中达0.84（内部）和0.76（外部）（p>0.05）。这些结果通过整合前位及侧位最大强度投影图像与临床数据的多模态模型获得。
结论：本研究证明了基于深度学习的方法结合无创性18F-FDG PET成像与临床数据进行淋巴瘤亚型分类的潜力。尽管仍需在更大规模、更多样化的队列中进一步验证以应对罕见亚型与生物学异质性的挑战，但LymphoMAP为开发早期临床决策辅助工具迈出了重要一步。这些发现强调了在个性化淋巴瘤管理中，使用自动化流程支持而非取代传统诊断工作流的可行性。
肿瘤(癌症)患者之家