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.
CONCLUSIONS: 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.
方法:纳入86例诊断为肿块型胰腺淋巴瘤或胰腺癌患者的88个病灶,并以4比1的比例随机分为训练集和验证集。使用ITK-SNAP软件进行感兴趣区域的分割,使用3Dslicer和PYTHON提取PET代谢参数和影像组学特征。在选择最佳代谢参数和影像组学特征之后,Logistic回归(LR),支持向量机(SVM),并构建了PET代谢参数的随机森林(RF)模型,CT影像组学,PET影像组学,和PET/CT影像组学。根据曲线下面积(AUC)评估模型性能,准确度,灵敏度,以及训练集和验证集的特异性。
结果:在所有模型中观察到强大的辨别能力,AUC值范围为0.727至0.978。结合PET和CT影像组学特征表现出的最高性能。训练集中PET/CT影像组学模型的AUC值分别为LR0.994、SVM0.994、RF0.989。在验证集中,AUC值为LR0.909,SVM0.883,RF0.844。
结论:利用18F-FDGPET/CT的代谢参数和影像组学的机器学习模型在区分胰腺癌和肿块形成的胰腺淋巴瘤方面显示出希望。在临床环境中实际实施之前,需要对更大的队列进行进一步验证。