多视角深度学习从18F-FDG PET/CT自动进行淋巴瘤分期:医师级准确性与高通量工作流
该研究回顾性分析227例淋巴瘤患者的基线18F-FDG PET/CT,构建基于多视角2D最大强度投影(MIP)的深度学习模型LASM-mMIP用于二分类分期(局限期 vs. 进展期),并与核医学科医师比较。模型准确率93.0%、AUC 0.942,显著优于1–3年资医师(84.58%,P < 0.05),与3–5年资医师(96.9%,P = 0.095)相当,且分期耗时显著缩短。
要点
- LASM-mMIP基于冠状、矢状、LAO和RAO四视角2D MIP图像,准确率93.0%、AUC 0.942。
- 模型准确率显著高于1–3年资医师(84.58%,P < 0.05),与3–5年资医师(96.9%,P = 0.095)无显著差异。
- 模型分期耗时(2.13 ± 0.31)秒,显著短于医师(17918.90 ± 56310.53)秒(P < 0.05)。
核心结论
- LASM-mMIP模型在淋巴瘤分期中表现出高准确率和显著的时间效率,性能与低年资核医学医师相当。
研究设计与样本
- 回顾性分析227例淋巴瘤患者的基线18F-FDG PET/CT扫描,构建2D MIP、3D PET和3D CT深度学习模型进行二分类分期。
- 采用5折交叉验证评估模型,以5–10年资高级核医学医师的分期结果作为参考标准。
- 使用ROC曲线评估分期性能,McNemar卡方检验比较最佳模型与1–3年及3–5年资核医学医师的差异。
主要发现
- LASM-mMIP模型准确率93.0%、AUC 0.942,优于基于单视角MIP和3D容积PET/CT的其他AI模型。
- 模型准确率显著高于1–3年资医师(84.58%,P < 0.05),与3–5年资医师(96.9%,P = 0.095)相似。
- 模型分期时间(2.13 ± 0.31)秒较医师(17918.90 ± 56310.53)秒缩短四个数量级(P < 0.05)。
- 失败分析显示假阴性多因隐匿性病灶,假阳性源于生理性高代谢。
临床怎么用
- 该AI工具可辅助低年资核医学医师进行淋巴瘤分期,减少观察者间变异并缩短判读时间。
- 未来需扩大患者队列、纳入额外临床预测因素并细化分期特异性分类以个性化淋巴瘤管理。
局限性
- 研究为回顾性设计,样本量227例,需未来扩大队列验证。
- 模型仅进行二分类分期(局限期 vs. 进展期),未细化Ann Arbor各期。
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
BACKGROUND: Lymphoma staging plays a pivotal role in guiding risk-adapted therapeutic strategies. While the Ann Arbor system is the standard for staging lymphoma, current manual PET/CT evaluations suffer from interobserver variability and time inefficiencies. Recent advancements in artificial intelligence (AI) offer opportunities to objectively automate this workflow. This study aimed to develop a deep-learning model based on multi-view 2D maximum intensity projection (MIP) images from 18F-FDG PET/CT to automate lymphoma staging and compare its performance with nuclear medicine physicians. METHODS: We retrospectively analyzed baseline 18F-FDG PET/CT scans of 227 patients with lymphoma. The deep learning models were constructed with 2D MIP, three dimensional (3D) PET and 3D CT images for binary classication (limited vs. advanced stage). The models were evaluated by 5-fold cross-validation. Ground truth were the stage results of senior nuclear medicine physicians (5–10 years). Staging performance of different models was assessed by Receiver operating characteristic (ROC) curves. McNemar’s chi-squared test was used to compare the staging differences between the best-performing model and the nuclear medicine physicians with early-career nuclear medicine physicians (1–3 and 3–5 years, respectively). RESULTS: The developed AI model, LASM-mMIP, utilized multi-view 2D MIP images across coronal, sagittal, left anterior oblique (LAO), and right anterior oblique (RAO) perspectives. It achieved an accuracy of 93.0% and an AUC of 0.942 for staging, outperforming other AI models based on single-view MIP images and 3D volumetric PET/CT data. LASM-mMIP exhibited significantly higher staging accuracy compared to junior nuclear medicine physicians (1–3 years, 84.58%, P < 0.05) and similar accuracy to intermediate-experience physicians (3–5 years, 96.9%, P = 0.095). Moreover, the model reduced staging time by four orders of magnitude compared to physicians [(2.13 ± 0.31) seconds vs. (17918.90 ± 56310.53) seconds, P < 0.05]. Failure analysis revealed that most false negatives were due to occult lesions, while false positives arose from physiological hypermetabolism. CONCLUSIONS: The LASM-mMIP model demonstrated high accuracy and significant temporal efficiency in lymphoma staging, offering performance comparable to early-career nuclear medicine physicians. By overcoming interobserver variability and reducing manual interpretation time, this AI-driven tool could streamline workflows and enhance decision-making in clinical settings. Future work should expand patient cohorts, explore additional clinical predictors, and refine stage-specific classification to further personalize lymphoma management.
引用
- Li D, Li R, Ma Y, et al. Multi-view deep learning for automated lymphoma staging from 18F-FDG PET/CT: physician-level accuracy with high-throughput workflow. EJNMMI Res. 2026. PMID: 41686381. doi:10.1186/s13550-025-01357-w
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。