Department of Nuclear Medicine, Qilu Hospital of Shandong University, Jinan, China; Department of Nuclear Medicine, Dezhou People's Hospital, Dezhou, China.
Department of Nuclear Medicine, Qilu Hospital of Shandong University, Jinan, China.
Eur J Radiol. 2024 Jul;176:111531. doi: 10.1016/j.ejrad.2024.111531. Epub 2024 May 25.
The objective of this study was to preliminarily assess the ability of metabolic parameters and radiomics derived from F-fluorodeoxyglucose positron emission tomography/computed tomography (F-FDG PET/CT) to distinguish mass-forming pancreatic lymphoma from pancreatic carcinoma using machine learning.
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.
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.
Machine learning models utilizing the metabolic parameters and radiomics of F-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.
本研究旨在初步评估基于 F-氟脱氧葡萄糖正电子发射断层扫描/计算机断层扫描（F-FDG PET/CT）的代谢参数和放射组学特征在利用机器学习区分肿块型胰腺淋巴瘤和胰腺癌方面的能力。
共纳入 86 例经病理证实为肿块型胰腺淋巴瘤或胰腺癌患者的 88 个病灶，采用 4:1 的比例随机分为训练集和验证集。使用 ITK-SNAP 软件进行感兴趣区的分割，使用 3Dslicer 和 PYTHON 提取 PET 代谢参数和放射组学特征。在选择最佳代谢参数和放射组学特征后，构建了基于 LOGISTIC 回归（LR）、支持向量机（SVM）和随机森林（RF）的 PET 代谢参数、CT 放射组学、PET 放射组学和 PET/CT 放射组学模型。在训练集和验证集中，采用曲线下面积（AUC）、准确性、敏感性和特异性评估模型性能。
所有模型均表现出较强的判别能力，AUC 值范围为 0.727~0.978。联合 PET 和 CT 放射组学特征的性能最佳。训练集中，PET/CT 放射组学模型的 LR AUC 值为 0.994，SVM AUC 值为 0.994，RF AUC 值为 0.989。在验证集中，LR AUC 值为 0.909，SVM AUC 值为 0.883，RF AUC 值为 0.844。
基于 F-FDG PET/CT 的代谢参数和放射组学的机器学习模型在鉴别胰腺癌和肿块型胰腺淋巴瘤方面具有一定的应用潜力。在临床实践中应用之前，还需要在更大的队列中进行进一步验证。
