Zhu Xinyu, Lu Denglu, Wu Yang, Lu Yanqi, He Liang, Deng Yanyun, Mu Xingyu, Fu Wei
Department of Nuclear Medicine, The First Affiliated Hospital of Guilin Medical University, Guilin, Guangxi Zhuang Autonomous Region, 541001, China.
Department of Nuclear Medicine, Liuzhou Workers' Hospital, Liuzhou, Guangxi Zhuang Autonomous Region, 545000, China.
BMC Med Inform Decis Mak. 2025 Jul 15;25(1):264. doi: 10.1186/s12911-025-03110-8.
Accurate identification of bone marrow invasion (BMI) is critical for determining the prognosis of and treatment strategies for lymphoma. Although bone marrow biopsy (BMB) is the current gold standard, its invasive nature and sampling errors highlight the necessity for noninvasive alternatives. We aimed to develop and validate an interpretable machine learning model that integrates clinical data, F-fluorodeoxyglucose positron emission tomography/computed tomography (F-FDG PET/CT) parameters, radiomic features, and deep learning features to predict BMI in lymphoma patients.
We included 159 newly diagnosed lymphoma patients (118 from Center I and 41 from Center II), excluding those with prior treatments, incomplete data, or under 18 years of age. Data from Center I were randomly allocated to training (n = 94) and internal test (n = 24) sets; Center II served as an external validation set (n = 41). Clinical parameters, PET/CT features, radiomic characteristics, and deep learning features were comprehensively analyzed and integrated into machine learning models. Model interpretability was elucidated via Shapley Additive exPlanations (SHAPs). Additionally, a comparative diagnostic study evaluated reader performance with and without model assistance.
BMI was confirmed in 70 (44%) patients. The key clinical predictors included B symptoms and platelet count. Among the tested models, the ExtraTrees classifier achieved the best performance. For external validation, the combined model (clinical + PET/CT + radiomics + deep learning) achieved an area under the receiver operating characteristic curve (AUC) of 0.886, outperforming models that use only clinical (AUC 0.798), radiomic (AUC 0.708), or deep learning features (AUC 0.662). SHAP analysis revealed that PET radiomic features (especially PET_lbp_3D_m1_glcm_DependenceEntropy), platelet count, and B symptoms were significant predictors of BMI. Model assistance significantly enhanced junior reader performance (AUC improved from 0.663 to 0.818, p = 0.03) and improved senior reader accuracy, although not significantly (AUC 0.768 to 0.867, p = 0.10).
Our interpretable machine learning model, which integrates clinical, imaging, radiomic, and deep learning features, demonstrated robust BMI prediction performance and notably enhanced physician diagnostic accuracy. These findings underscore the clinical potential of interpretable AI to complement medical expertise and potentially reduce the reliance on invasive BMB for lymphoma staging.
准确识别骨髓侵犯（BMI）对于确定淋巴瘤的预后和治疗策略至关重要。尽管骨髓活检（BMB）是目前的金标准，但其侵入性和抽样误差凸显了非侵入性替代方法的必要性。我们旨在开发并验证一种可解释的机器学习模型，该模型整合临床数据、F-氟脱氧葡萄糖正电子发射断层扫描/计算机断层扫描（F-FDG PET/CT）参数、放射组学特征和深度学习特征，以预测淋巴瘤患者的BMI。
我们纳入了159例新诊断的淋巴瘤患者（118例来自中心I，41例来自中心II），排除了那些接受过先前治疗、数据不完整或年龄在18岁以下的患者。来自中心I的数据被随机分配到训练集（n = 94）和内部测试集（n = 24）；中心II作为外部验证集（n = 41）。对临床参数、PET/CT特征、放射组学特征和深度学习特征进行综合分析，并将其整合到机器学习模型中。通过Shapley加性解释（SHAPs）阐明模型的可解释性。此外，一项比较诊断研究评估了有无模型辅助时阅片者的表现。
70例（44%）患者确诊为BMI。关键的临床预测因素包括B症状和血小板计数。在测试的模型中，ExtraTrees分类器表现最佳。对于外部验证，联合模型（临床+PET/CT+放射组学+深度学习）的受试者工作特征曲线下面积（AUC）为0.886，优于仅使用临床特征（AUC 0.798）、放射组学特征（AUC 0.7由8）或深度学习特征（AUC 0.662）的模型。SHAP分析显示，PET放射组学特征（尤其是PET_lbp_3D_m1_glcm_DependenceEntropy）、血小板计数和B症状是BMI的重要预测因素。模型辅助显著提高了初级阅片者的表现（AUC从为0.663提高到0.818，p = 0.03），并提高了高级阅片者的准确性，尽管不显著（AUC从0.768提高到0.867，p = 0.10）。
我们的可解释机器学习模型整合了临床、影像、放射组学和深度学习特征，表现出强大的BMI预测性能，并显著提高了医生的诊断准确性。这些发现强调了可解释人工智能在补充医学专业知识方面的临床潜力，并可能减少淋巴瘤分期对侵入性BMB的依赖。
