基于18F-FDG PET/CT的机器学习模型鉴别肿块型胰腺淋巴瘤与胰腺癌的初步研究
本研究纳入86例患者的88个病灶,按4:1随机分为训练集和验证集,基于18F-FDG PET/CT的代谢参数和影像组学特征构建逻辑回归、支持向量机和随机森林模型,用于鉴别肿块型胰腺淋巴瘤与胰腺癌。所有模型均表现出较强的鉴别能力,AUC范围为0.727至0.978,其中PET/CT联合影像组学特征表现最佳,训练集AUC为LR 0.994、SVM 0.994、RF 0.989,验证集AUC为LR 0.909、SVM 0.883、RF 0.844。作者认为这些模型有希望区分胰腺癌与肿块型胰腺淋巴瘤,但在临床实际应用前需要在更大的队列中进一步验证。
要点
- 基于18F-FDG PET/CT代谢参数和影像组学的机器学习模型可用于鉴别肿块型胰腺淋巴瘤与胰腺癌。
- PET/CT联合影像组学特征表现最佳,验证集AUC为LR 0.909、SVM 0.883、RF 0.844。
- 所有模型AUC范围为0.727至0.978,但作者指出需在更大队列中进一步验证后方可临床实际应用。
核心结论
- 基于18F-FDG PET/CT代谢参数和影像组学的机器学习模型在鉴别胰腺癌与肿块型胰腺淋巴瘤方面显示出前景,但在临床实际应用前需要在更大的队列中进一步验证。
研究设计与样本
- 回顾性纳入86例患者的88个病灶,按4:1随机分为训练集和验证集,使用ITK-SNAP分割感兴趣区,3Dslicer和PYTHON提取PET代谢参数和影像组学特征,构建逻辑回归、支持向量机和随机森林模型。
诊断标准与关键数值
- 所有模型AUC范围为0.727至0.978。
- PET/CT影像组学模型训练集AUC:逻辑回归0.994、支持向量机0.994、随机森林0.989。
- PET/CT影像组学模型验证集AUC:逻辑回归0.909、支持向量机0.883、随机森林0.844。
临床应用与阅片要点
- 作者认为基于18F-FDG PET/CT代谢参数和影像组学的机器学习模型有希望区分胰腺癌与肿块型胰腺淋巴瘤。
- 作者指出在临床实际应用前需要在更大的队列中进一步验证。
局限性
- 作者指出在临床实际应用前需要在更大的队列中进一步验证。
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
PURPOSE: The objective of this study was to preliminarily assess the ability of metabolic parameters and radiomics derived from 18F-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) to distinguish mass-forming pancreatic lymphoma from pancreatic carcinoma using machine learning.
METHODS: A total of 88 lesions from 86 patients diagnosed as mass-forming pancreatic lymphoma or pancreatic carcinoma were included and randomly divided into a training set and a validation set at a 4-to-1 ratio. The segmentation of regions of interest was performed using ITK-SNAP software, PET metabolic parameters and radiomics features were extracted using 3Dslicer and PYTHON. Following the selection of optimal metabolic parameters and radiomics features, Logistic regression (LR), support vector machine (SVM), and random forest (RF) models were constructed for PET metabolic parameters, CT radiomics, PET radiomics, and PET/CT radiomics. Model performance was assessed in terms of area under the curve (AUC), accuracy, sensitivity, and specificity in both the training and validation sets.
RESULTS: Strong discriminative ability observed in all models, with AUC values ranging from 0.727 to 0.978. The highest performance exhibited by the combined PET and CT radiomics features. AUC values for PET/CT radiomics models in the training set were LR 0.994, SVM 0.994, RF 0.989. In the validation set, AUC values were LR 0.909, SVM 0.883, RF 0.844.
CONCLUSION: Machine learning models utilizing the metabolic parameters and radiomics of 18F-FDG PET/CT show promise in distinguishing between pancreatic carcinoma and mass-forming pancreatic lymphoma. Further validation on a larger cohort is necessary before practical implementation in clinical settings.
引用
- Wang J, Zhou Y, Zhou J, et al. Preliminary study on the ability of the machine learning models based on 18F-FDG PET/CT to differentiate between mass-forming pancreatic lymphoma and pancreatic carcinoma. Eur J Radiol. 2024. PMID: 38820949. doi:10.1016/j.ejrad.2024.111531
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。