文献速递肿瘤 PET/CT

基于RECOMIA人工智能的淋巴瘤总代谢肿瘤体积自动分割:一项回顾性研究

Automated RECOMIA AI-based total metabolic tumor volume in lymphoma - a retrospective study.
PubMed 文献 · EJNMMI Res · 2026-02-27

本研究开发并验证了一种基于3D U-Net卷积神经网络的RECOMIA人工智能工具,用于自动计算未经治疗的淋巴瘤患者FDG PET/CT的总代谢肿瘤体积(tMTV)。该工具在1500例淋巴瘤患者上训练,在117例未经治疗的霍奇金淋巴瘤和弥漫大B细胞淋巴瘤患者中测试,结果显示在85%(100/117)的患者中,AI分割与手动分割的差异在经验丰富的核医学医师的观察者间变异范围内。研究表明AI支持临床tMTV量化评估预后的可行性。

要点

  • RECOMIA AI工具在85%(100/117)的患者中达到与观察者间变异相当的分割相似性。
  • 手动tMTV中位数为321 cm3(IQR:92–689 cm3),两名医师间差异中位数为26 cm3(IQR:9–86 cm3)。
  • 85/117例患者中,两次手动tMTV测量中较接近AI值的那次更接近AI tMTV。

核心结论

  • RECOMIA AI工具在85%(100/117)的未经治疗淋巴瘤患者中达到了与经验丰富核医学医师观察者间变异相当的分割相似性。
  • 该研究证明了使用AI支持医师在临床实践中量化tMTV以评估预后的可行性。

研究设计与样本

  • 回顾性研究,开发并验证基于3D U-Net卷积神经网络的RECOMIA AI工具,用于自动分割FDG PET/CT中的代谢活跃肿瘤并计算tMTV。
  • 训练队列为1500例淋巴瘤患者,平均年龄52岁(范围10–88),44%为女性。
  • 测试组为2017–2018年及2019–2022年在Sahlgrenska大学医院接受FDG PET/CT的所有未经治疗霍奇金淋巴瘤和弥漫大B细胞淋巴瘤患者,共117例,平均年龄50岁(范围7–90),39%为女性。
  • 由9名核医学医师手动分割病灶计算tMTV,每例患者由两名医师独立分割。

主要发现

  • 手动tMTV中位数为321 cm3(IQR:92–689 cm3)。
  • 同一患者两名不同医师分割的tMTV差值中位数为26 cm3(IQR:9–86 cm3)。
  • 在117例患者中的85例,两次手动tMTV测量中较接近AI值的那次更接近AI tMTV。
  • 在其余32例患者中的15例,AI tMTV与手动tMTV的差异小于26 cm3(即同一患者两次手动tMTV差值的中位数)。

关键数值与推荐

  • AI工具分割相似性达到观察者间变异范围的患者比例为85%(100/117)。
  • 手动tMTV中位数321 cm3(IQR:92–689 cm3);两名医师间tMTV差值中位数26 cm3(IQR:9–86 cm3)。
  • 在15/32例患者中,AI与手动tMTV差异<26 cm3。

临床怎么用

  • RECOMIA AI工具可用于未经治疗淋巴瘤患者FDG PET/CT的tMTV自动计算,辅助医师进行预后评估。
  • AI分割结果与经验丰富医师手动分割的观察者间变异相当,可作为临床tMTV量化工作流程的支持工具。

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: Increasing evidence suggests that total metabolic tumor volume (tMTV) measured before treatment in lymphoma patients undergoing [18F]fluorodeoxyglucose (FDG) PET/CT scans can predict prognosis. However, there is a lack of fast, reliable, and easy-to-perform multilesional segmentation tools with an urgent need to improve tMTV segmentation workflow in clinical practice. Here, we develop an artificial intelligence (AI)-based tool that automatically calculates tMTV in untreated lymphoma patients undergoing FDG PET/CT. The RECOMIA AI-based tool is a 3D U-Net convolutional neural network trained on a cohort of 1,500 lymphoma patients, mean age 52 years (range 10–88), 44% were female. The model was optimized to segment metabolically active tumors in the FDG PET/CT scans, enabling automated tMTV measurements. The test group consisted of all untreated Hodgkin lymphoma (HL) patients and all Diffuse large B-cell lymphoma (DLBCL) patients who underwent FDG PET/CT at Sahlgrenska University Hospital between 2017–2018 and 2019–2022, respectively. There were 117 patients with mean age 50 years (range 7–90), 39% were female. Nine nuclear medicine physicians manually segmented lesions for tMTV calculations, with each patient independently segmented by two physicians. RESULTS: The median of the manual tMTV was 321 cm3 (interquartile range [IQR]: 92–689 cm3) and the median of the difference between two tMTV values segmented by different physicians for the same patient was 26 cm3 (IQR: 9–86 cm3). In 85 of the 117 patients, one of two manual tMTV measurements was closer to the AI tMTV value than the second manual tMTV measurement made by another physician. In 15 of the remaining 32 patients, the difference between the AI tMTV and the manual tMTV was small (< 26 cm3, the median difference between two manual tMTV values made on the same patient). CONCLUSION: The results of this study show that the RECOMIA AI-based tool achieved segmentation similarity within the inter-observer variability of experienced nuclear medicine physicians in 85% (100/117) of untreated lymphoma patients. This demonstrates the feasibility of using AI to support physicians in quantifying tMTV for assessment of prognosis in clinical practice.

来源:EJNMMI Res,查看原文。版权归原作者所有。

引用

  1. Sadik M, Mörk J, Lopez Urdaneta J, et al. Automated RECOMIA AI-based total metabolic tumor volume in lymphoma - a retrospective study. EJNMMI Res. 2026. PMID: 41758385. doi:10.1186/s13550-026-01403-1

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。