文献速递肿瘤 PET/CT

神经网络在乳腺癌FDG PET-CT预后预测中的表现:是否只是「聪明汉斯」效应?

Just another "Clever Hans"? Neural networks and FDG PET-CT to predict the outcome of patients with breast cancer.
PubMed 文献 · Eur J Nucl Med Mol Imaging · 2021-03-05

本研究回顾性纳入50例连续乳腺癌患者,评估在淋巴瘤和肺癌数据上训练的PARS神经网络在乳腺癌18F-FDG PET/CT中检测病灶、定位及量化肿瘤体积的准确性。结果显示,对PERCIST可测量病灶,每患者灵敏度和特异度分别为92%和98%;但对所有FDG高摄取病灶灵敏度降至39%。AI得出的全身MTV及淋巴结、肝脏MTV均为总生存的显著预后因素。

要点

  • PARS对PERCIST可测量病灶检测灵敏度92%、特异度98%。
  • 以全部FDG高摄取病灶为参考时,灵敏度降至39%。
  • AI得出的全身MTV与手动分割MTV高度相关(R2=0.91)。

核心结论

  • 在淋巴瘤和肺癌上训练的PARS神经网络对乳腺癌PERCIST可测量病灶检测准确度高,未表现出明显的「聪明汉斯」效应。
  • 但以全部手动分割病灶为参考标准时,网络检测准确度较差。
  • AI得出的全身及器官层面MTV是晚期乳腺癌总生存的显著预后因素。

研究设计与样本

  • 回顾性分析纳入50例连续接受18F-FDG PET/CT的乳腺癌患者。
  • 使用在淋巴瘤和肺癌18F-FDG PET/CT数据上训练的PARS神经网络原型检测病灶并确定解剖位置。
  • 以两位核医学医师共识阅片结合随访数据为诊断参考标准,手动分割1072个FDG高摄取病灶。
  • 评估网络在病灶检测、解剖定位和总肿瘤体积量化方面的准确性。

主要发现

  • 对PERCIST可测量病灶,网络每患者检测可疑FDG病灶的灵敏度为92%(CI=79-97%),特异度为98%(CI=94-99%)。
  • 以全部FDG高摄取病灶为参考时,灵敏度降至39%(CI=30-50%)。
  • 定位准确率:身体部位98%(CI=95-99%),区域88%(CI=84-90%),亚区域79%(CI=74-84%)。
  • AI得出与手动分割的MTV高度相关(R2=0.91;p<0.001)。
  • AI得出的全身MTV(HR=1.275;CI=1.208-1.713;p<0.001)、淋巴结MTV(HR=1.190;CI=1.022-1.384;p=0.025)和肝脏MTV(HR=1.149;CI=1.001-1.318;p=0.048)为总生存的显著预后因素,其中淋巴结和肝脏MTV在多变量分析中可预测总生存。

关键数值与推荐

  • PERCIST可测量病灶:网络每患者灵敏度92%(CI=79-97%),特异度98%(CI=94-99%)。
  • 全部FDG高摄取病灶:网络灵敏度39%(CI=30-50%)。
  • 定位准确率:身体部位98%(CI=95-99%)、区域88%(CI=84-90%)、亚区域79%(CI=74-84%)。
  • AI与手动MTV相关性:R2=0.91;p<0.001。
  • 预后:全身MTV HR=1.275(CI=1.208-1.713;p<0.001);淋巴结MTV HR=1.190(CI=1.022-1.384;p=0.025);肝脏MTV HR=1.149(CI=1.001-1.318;p=0.048)。

临床怎么用

  • 该神经网络可辅助核医学医师在乳腺癌FDG PET/CT中检测PERCIST可测量病灶并量化MTV。
  • AI得出的全身及器官层面MTV具有预后价值,可能用于风险分层。
  • 对非PERCIST可测量病灶的检测灵敏度低,临床解读时需谨慎。

局限性

  • 回顾性研究,样本量50例。
  • 网络训练数据来自淋巴瘤和肺癌,未使用乳腺癌数据训练。
  • 以全部手动分割病灶为参考时网络准确度较差,提示参考标准选择影响性能评估。

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: Manual quantification of the metabolic tumor volume (MTV) from whole-body 18F-FDG PET/CT is time consuming and therefore usually not applied in clinical routine. It has been shown that neural networks might assist nuclear medicine physicians in such quantification tasks. However, little is known if such neural networks have to be designed for a specific type of cancer or whether they can be applied to various cancers. Therefore, the aim of this study was to evaluate the accuracy of a neural network in a cancer that was not used for its training. METHODS: Fifty consecutive breast cancer patients that underwent 18F-FDG PET/CT were included in this retrospective analysis. The PET-Assisted Reporting System (PARS) prototype that uses a neural network trained on lymphoma and lung cancer 18F-FDG PET/CT data had to detect pathological foci and determine their anatomical location. Consensus reads of two nuclear medicine physicians together with follow-up data served as diagnostic reference standard; 1072 18F-FDG avid foci were manually segmented. The accuracy of the neural network was evaluated with regard to lesion detection, anatomical position determination, and total tumor volume quantification. RESULTS: If PERCIST measurable foci were regarded, the neural network displayed high per patient sensitivity and specificity in detecting suspicious 18F-FDG foci (92%; CI = 79-97% and 98%; CI = 94-99%). If all FDG-avid foci were regarded, the sensitivity degraded (39%; CI = 30-50%). The localization accuracy was high for body part (98%; CI = 95-99%), region (88%; CI = 84-90%), and subregion (79%; CI = 74-84%). There was a high correlation of AI derived and manually segmented MTV (R2 = 0.91; p < 0.001). AI-derived whole-body MTV (HR = 1.275; CI = 1.208-1.713; p < 0.001) was a significant prognosticator for overall survival. AI-derived lymph node MTV (HR = 1.190; CI = 1.022-1.384; p = 0.025) and liver MTV (HR = 1.149; CI = 1.001-1.318; p = 0.048) were predictive for overall survival in a multivariate analysis. CONCLUSION: Although trained on lymphoma and lung cancer, PARS showed good accuracy in the detection of PERCIST measurable lesions. Therefore, the neural network seems not prone to the clever Hans effect. However, the network has poor accuracy if all manually segmented lesions were used as reference standard. Both the whole body and organ-wise MTV were significant prognosticators of overall survival in advanced breast cancer.

来源:Eur J Nucl Med Mol Imaging,查看原文。版权归原作者所有。

引用

  1. Weber M, Kersting D, Umutlu L, et al. Just another "Clever Hans"? Neural networks and FDG PET-CT to predict the outcome of patients with breast cancer. Eur J Nucl Med Mol Imaging. 2021. PMID: 33674891. doi:10.1007/s00259-021-05270-x

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。