评估机器学习肿瘤分割在神经肿瘤治疗反应分类中用于自动纵向疗效评估的效用与局限性
研究用4162例治疗前后脑肿瘤MRI训练nnU-Net分割模型,在60例患者233对纵向MRI上按RANO标准自动分类疗效。模型区分进展与非进展的准确率为77.7%,敏感度92.1%、特异度60.4%,但对部分缓解等非进展类别准确性很低,假阳性进展多因手术腔周围强化变化所致。
要点
- 自动分割按RANO分类时区分进展与非进展准确率77.7%,敏感度92.1%、特异度60.4%。
- 非进展类别准确性低,部分缓解仅14.3%,患者平均准确率66.9%。
- 假阳性进展常因手术腔周围强化形态和位置变化,占疾病稳定分类的32.8%。
核心结论
- 自动肿瘤分割正用于疗效评估,但训练良好的分割模型在全自动疗效评估中仍受术后强化及时间点间位置与形态变化等细节限制。
研究设计与样本
- 用4162例治疗前后脑肿瘤MRI训练nnU-Net分割模型;另取91例患者数据做配准和纵向病灶追踪,排除因T2/FLAIR编辑偏好变化或临床标准判为进展者后,对60例患者共233对MRI比较做自动分割与RANO分类,并与专家参考标准比较。
关键影像表现/征象
- 假阳性进展预测常因手术腔周围变化影响强化形态和位置,占疾病稳定分类的32.8%。
- 其他错误原因包括强化形态改变但体积相近、非典型部位病灶被遗漏以及放射性坏死。
诊断标准与关键数值
- 以自动分割肿瘤掩模按原RANO标准基于2D病灶大小、可测量标准、新病灶出现及随时间变化分为进展、部分缓解、疾病稳定和完全缓解。
- 模型区分进展与非进展准确率77.7%(95%CI 70.6%-84.2%),敏感度92.1%(95%CI 86.2%-97.3%),特异度60.4%(95%CI 43.4%-74.7%)。
- 各类别准确率以进展最高为92.1%(95%CI 86.2%-97.3%),部分缓解最低为14.3%(95%CI 0.0%-38.5%),患者平均准确率66.9%(95%CI 58.2%-75.3%)。
临床应用与阅片要点
- 作者指出自动分割模型在全自动RANO疗效评估中仍受术后强化及时间点间位置与形态变化等细节限制。
局限性
- 作者指出训练良好的分割模型在全自动疗效评估中仍受术后强化及时间点间位置与形态变化等细节限制。
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)。
英文原文(摘要)· 点击展开
BACKGROUND AND PURPOSE: Machine learning segmentation has emerged in tumor assessment with high performance in volumetric evaluation of brain tumors. It is unclear, however, if such methods can be translated into full end-to-end clinical tools for assessing treatment response. This study aims to assess the ability and current limitations of machine learning for performing a fully automated longitudinal Response Assessment in Neuro-Oncology (RANO).
MATERIALS AND METHODS: An nnU-Net model was trained for segmentation on 4162 MRIs of pre- and posttreatment brain tumors. A separate data set of 91 patients was preprocessed, including coregistration for longitudinal lesion tracking. The nnU-Net model was used to segment enhancing tumor on the longitudinal data set. After excluding patients classified as having progression due to T2/FLAIR per editorial preference changes or clinical criteria, 233 pair-wise MRI comparisons remained for 60 patients. Using auto-segmented tumor masks, comparisons were classified into progressive disease (PD), partial response (PR), stable disease (SD), and complete response (CR) according to the original RANO criteria based on 2D lesion size, measurable criteria, the appearance of new lesions, and changes over time. Model results were compared with expert ground truth and evaluated for accuracy in classifying PD and non-PD disease, per-class accuracy, and a variety of performance metrics. All discrepant cases were manually reviewed to classify the cause of the error.
RESULTS: The model was 77.7% (95% CI, 70.6%-84.2%) accurate in distinguishing PD and non-PD disease, with a sensitivity of 92.1% (86.2%-97.3%) and a specificity of 60.4% (43.4%-74.7%). The highest per-class accuracy was PD at 92.1% (86.2%-97.3%), with much lower performance for non-PD categories, and worst for PR at 14.3% (0.0%-38.5%). Patient-averaged accuracy was 66.9% (58.2%-75.3%). False-positive PD predictions were commonly due to evolving changes around the resection cavity, affecting the morphology and location of enhancement, accounting for 32.8% of SD classifications. Other causes of error included changing morphology but a similar volume of enhancement, missed lesions in less typical locations, and radiation necrosis.
CONCLUSIONS: Automated tumor segmentation is emerging in treatment response assessment, although highly trained segmentation models still have limitations in fully automated response assessment due to nuances such as postsurgical enhancement and comparing location and morphologic changes between time points.
引用
- Kamel P, Naeem A, Salim H, et al. Evaluating the Utility and Limitations of Machine Learning Tumor Segmentation for Automated Longitudinal Response Assessment in Neuro-Oncology Treatment Response Classification. AJNR Am J Neuroradiol. 2026. PMID: 42034563. doi:10.3174/ajnr.A9372
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。