文献速递淋巴瘤

基于深度学习的18F-氟脱氧葡萄糖正电子发射断层扫描对18F-氟脱氧葡萄糖高摄取非霍奇金淋巴瘤的自动Lugano代谢反应评估

Automated Lugano Metabolic Response Assessment in 18F-Fluorodeoxyglucose-Avid Non-Hodgkin Lymphoma With Deep Learning on 18F-Fluorodeoxyglucose-Positron Emission Tomography.
PubMed 文献 · J Clin Oncol · 2024-06-06

本研究提出一种基于深度学习的四阶段算法,用于按照Lugano 2014分类全自动评估18F-氟脱氧葡萄糖高摄取非霍奇金淋巴瘤的治疗反应。算法在多国临床试验中训练并在三个独立多中心多国家测试集中验证,与裁决的影像学反应评估高度一致(总体反应评估一致率分别为93%、87%和85%),且对结局的预后价值强于裁决的影像学反应。放射科医生复核算法评估的中位时间为1.38分钟/次,与裁决反应的一致程度无统计学显著差异。

要点

  • 深度学习算法可全自动输出基线和随访病灶,总体反应评估与裁决影像学反应一致率在三个测试集中分别为93%、87%和85%。
  • 算法判定的治疗结束时代谢完全缓解(CMR)对死亡风险的预后强于裁决的CMR,风险比分别为0.123、0.054和0.205。
  • 放射科医生复核算法评估的中位时间为1.38分钟/次,与裁决反应的一致程度无统计学显著差异。

核心结论

  • 所提出的方法可整合入肿瘤影像的影像学反应评估工作流程,显著节省时间且性能与训练有素的医学专家相似。

研究设计与样本

  • 研究提出一种基于深度学习的四阶段算法,用于按照Lugano 2014分类全自动评估治疗反应。
  • 算法在多国临床试验(ClinicalTrials.gov标识NCT01287741)中训练,并在三个独立多中心多国家测试集(ClinicalTrials.gov标识NCT02257567、NCT02500407;NCT01287741中20%留出集)中测试,涵盖不同非霍奇金淋巴瘤亚型和不同治疗线数。

主要发现

  • 总体反应评估与裁决影像学反应的一致率在NCT01287741、NCT02500407和NCT02257567中分别为93%、87%和85%。
  • 治疗结束时代谢完全缓解(CMR)对死亡风险的风险比在NCT01287741、NCT02500407和NCT02257567中分别为0.123、0.054和0.205,而裁决的CMR分别为0.226、0.292和0.272。
  • 放射科医生复核算法评估的中位时间为1.38分钟/次,放射科医生与模型反应的一致程度相比与裁决反应的一致程度无统计学显著差异。

关键数值与推荐

  • 按照Lugano 2014分类进行全自动治疗反应评估,输出基线和随访检测到的病灶以供放射科医生重点复核。

临床怎么用

  • 所提出的方法可整合入肿瘤影像的影像学反应评估工作流程,显著节省时间且性能与训练有素的医学专家相似。

局限性

  • 原文未报告局限性

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: Artificial intelligence can reduce the time used by physicians on radiological assessments. For 18F-fluorodeoxyglucose-avid lymphomas, obtaining complete metabolic response (CMR) by end of treatment is prognostic. METHODS: Here, we present a deep learning-based algorithm for fully automated treatment response assessments according to the Lugano 2014 classification. The proposed four-stage method, trained on a multicountry clinical trial (ClinicalTrials.gov identifier: NCT01287741) and tested in three independent multicenter and multicountry test sets on different non-Hodgkin lymphoma subtypes and different lines of treatment (ClinicalTrials.gov identifiers NCT02257567, NCT02500407; 20% holdout in ClinicalTrials.gov identifier NCT01287741), outputs the detected lesions at baseline and follow-up to enable focused radiologist review. RESULTS: The method's response assessment achieved high agreement with the adjudicated radiologic responses (eg, agreement for overall response assessment of 93%, 87%, and 85% in ClinicalTrials.gov identifiers NCT01287741, NCT02500407, and NCT02257567, respectively) similar to inter-radiologist agreement and was strongly prognostic of outcomes with a trend toward higher accuracy for death risk than adjudicated radiologic responses (hazard ratio for end of treatment by-model CMR of 0.123, 0.054, and 0.205 in ClinicalTrials.gov identifiers NCT01287741, NCT02500407, and NCT02257567, compared with, respectively, 0.226, 0.292, and 0.272 for CMR by the adjudicated responses). Furthermore, a radiologist review of the algorithm's assessments was conducted. The radiologist median review time was 1.38 minutes/assessment, and no statistically significant differences were observed in the level of agreement of the radiologist with the model's response compared with the level of agreement of the radiologist with the adjudicated responses. CONCLUSION: These results suggest that the proposed method can be incorporated into radiologic response assessment workflows in cancer imaging for significant time savings and with performance similar to trained medical experts.

来源:J Clin Oncol,查看原文。版权归原作者所有。

引用

  1. Jemaa S, Ounadjela S, Wang X, et al. Automated Lugano Metabolic Response Assessment in 18F-Fluorodeoxyglucose-Avid Non-Hodgkin Lymphoma With Deep Learning on 18F-Fluorodeoxyglucose-Positron Emission Tomography. J Clin Oncol. 2024. PMID: 38843483. doi:10.1200/JCO.23.01978

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。