弥漫大B细胞淋巴瘤FDG PET/CT病灶自适应分割方法
本研究基于HOVON-84试验中33例DLBCL患者的598个病灶,在基线、中期和治疗结束时FDG PET/CT上比较六种半自动分割方法,并推导出基于SUVpeak和SUVbg的病灶自适应决策规则。该规则在优选方法选择上达到0.82的病灶准确率,与最佳机器学习模型相当,且较单独SUV4.0提高了MTV一致性。
要点
- SUVpeak、TBRpeak和SUVbg是分割方法性能的关键预测因素。
- 决策规则:SUVpeak>8用SUV4.0,SUVbg>0.8用MV3,否则用MV2。
- 决策规则病灶优选准确率0.82,与最佳ML模型相当。
核心结论
- 基于SUVpeak和SUVbg的简单决策规则可为DLBCL各治疗阶段病灶选择优选分割方法,性能与ML相当且更简便。
研究设计与样本
- 回顾性分析HOVON-84试验中33例DLBCL患者的598个病灶,在基线、中期和治疗结束时FDG PET/CT上用六种半自动方法分割并由两名观察者独立评分。
主要发现
- 分割质量随病灶和方法而异,SUVpeak、TBRpeak和SUVbg是方法性能的关键预测因素。
- 最终决策规则病灶优选准确率为0.82,与最佳ML模型相当。
- 决策规则较单独SUV4.0提高了病灶水平MTV与参考的一致性(ρ=0.85 vs 0.82,最佳ML ρ=0.81)。
- 决策规则较单独SUV4.0减少了MTV偏差>10%的病灶比例(46.2% vs 63.5%,最佳ML 50.2%)。
- 总MTV与参考的一致性在所有策略中均高(所有ρ≥0.94),决策规则在中期和治疗结束时PET有适度增益。
关键数值与推荐
- 决策规则:若SUVpeak>8则用SUV4.0,若SUVbg>0.8则用MV3,否则用MV2。
- 病灶优选准确率0.82;病灶水平MTV一致性ρ=0.85;MTV偏差>10%病灶比例46.2%;总MTV一致性所有ρ≥0.94。
临床怎么用
- 在DLBCL各治疗阶段FDG PET/CT病灶分割中,可依据SUVpeak和SUVbg按决策规则选择分割方法,但仍需人工监督。
局限性
- 样本量较小(33例患者、598个病灶),决策规则仍需外部验证。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
PURPOSE: SUV4.0-based thresholding is widely used for baseline [¹⁸F]FDG PET-based metabolic tumor volume (MTV) assessment in diffuse large B-cell lymphoma (DLBCL), but its suitability at interim and end-of-treatment (EoT) PET, when residual uptake is heterogeneous and tumor-to-background contrast is lower, is uncertain. We aimed to define a lesion-adaptive decision rule approach for selecting the optimal segmentation method based on lesion-level features and treatment phase and, exploratorily, to compare its performance with ML-based selection models. METHODS: A total of 598 lesions from 33 DLBCL patients (HOVON-84 trial) were segmented at baseline, interim, and EoT [¹⁸F]FDG PET/CT using six semi-automated methods: SUV2.5, SUV4.0, 41%max, A50peak, MV2, and MV3. Segmentation quality was independently rated for each lesion by two observers (scale 1-5; 3 = preferred), with adjudication by a third reviewer. The influence of lesional SUVpeak, tumor-to-background ratio (TBRpeak), background uptake (SUVbg), treatment phase, and location on segmentation quality was assessed. Over six million rule-based combinations of key features were evaluated to derive a lesion-adaptive decision rule for preferred method selection. Exploratorily, ML classifiers were trained and compared with the decision-rule strategy. RESULTS: Segmentation quality varied across lesions and methods. SUVpeak, TBRpeak, and SUVbg were key predictors of method performance. The final lesion-adaptive rule, applying SUV4.0 if SUVpeak > 8, MV3 if SUVbg > 0.8, and otherwise MV2, achieved a lesion-wise accuracy of 0.82 for preferred method selection, matching the best-performing ML models. Versus SUV4.0 alone (benchmark), the Decision Rule improved lesion-level MTV agreement with the reference (ρ = 0.85 vs. 0.82 vs. best ML ρ = 0.81) and reduced the proportion of lesions with > 10% MTV deviation (46.2% vs. 63.5%; best ML 50.2%). Total-MTV agreements with the reference were uniformly high across all strategies (all ρ ≥ 0.94), with modest gains for the decision rule at interim and EoT PET. CONCLUSION: A straightforward decision-rule approach using SUVpeak and SUVbg successfully selects the preferred method for individual DLBCL lesions across treatment phases and matches ML performance with greater simplicity and clinical applicability. Although supervision remains necessary, this approach helps address the current gap in segmentation methodology for interim and EoT PET, where SUV4.0 may not always be appropriate.
引用
- Zwezerijnen GJC, Heymans MW, van Assema D, et al. A Lesion-adaptive Segmentation Approach for Tumor Delineation on FDG PET/CT in Diffuse Large B-cell Lymphoma Patients. Eur J Nucl Med Mol Imaging. 2026. PMID: 41689647. doi:10.1007/s00259-026-07768-8
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。