Park Yong-Jin, Park Young Suk, Kim Seung Tae, Hyun Seung Hyup
Department of Nuclear Medicine, Samsung Medical Center, Sungkyunkwan University School of Medicine, 81, Irwon-ro, Gangnam-gu, Seoul, 06351, South Korea.
Department of Nuclear Medicine, Ajou University Medical Center, Ajou University School of Medicine, 164, Worldcup-ro, Yeongtong-gu, Suwon, 16499, South Korea.
Mol Imaging Biol. 2023 Oct;25(5):897-910. doi: 10.1007/s11307-023-01832-7. Epub 2023 Jul 3.
We sought to develop and validate machine learning (ML) models for predicting tumor grade and prognosis using 2-[F]fluoro-2-deoxy-D-glucose ([F]FDG) positron emission tomography (PET)-based radiomics and clinical features in patients with pancreatic neuroendocrine tumors (PNETs).
A total of 58 patients with PNETs who underwent pretherapeutic [F]FDG PET/computed tomography (CT) were retrospectively enrolled. PET-based radiomics extracted from segmented tumor and clinical features were selected to develop prediction models by the least absolute shrinkage and selection operator feature selection method. The predictive performances of ML models using neural network (NN) and random forest algorithms were compared by the areas under the receiver operating characteristic curves (AUROCs) and validated by stratified five-fold cross validation.
We developed two separate ML models for predicting high-grade tumors (Grade 3) and tumors with poor prognosis (disease progression within two years). The integrated models consisting of clinical and radiomic features with NN algorithm showed the best performances than the other models (stand-alone clinical or radiomics models). The performance metrics of the integrated model by NN algorithm were AUROC of 0.864 in the tumor grade prediction model and AUROC of 0.830 in the prognosis prediction model. In addition, AUROC of the integrated clinico-radiomics model with NN was significantly higher than that of tumor maximum standardized uptake model in predicting prognosis (P < 0.001).
Integration of clinical features and [F]FDG PET-based radiomics using ML algorithms improved the prediction of high-grade PNET and poor prognosis in a non-invasive manner.
我们试图开发并验证机器学习（ML）模型，以利用基于2-[F]氟-2-脱氧-D-葡萄糖（[F]FDG）正电子发射断层扫描（PET）的放射组学和临床特征来预测胰腺神经内分泌肿瘤（PNET）患者的肿瘤分级和预后。
回顾性纳入了58例接受治疗前[F]FDG PET/计算机断层扫描（CT）的PNET患者。通过最小绝对收缩和选择算子特征选择方法，从分割的肿瘤中提取基于PET的放射组学特征和临床特征，以开发预测模型。使用神经网络（NN）和随机森林算法的ML模型的预测性能通过受试者操作特征曲线下面积（AUROCs）进行比较，并通过分层五折交叉验证进行验证。
我们开发了两个独立的ML模型，分别用于预测高级别肿瘤（3级）和预后不良的肿瘤（两年内疾病进展）。由临床和放射组学特征与NN算法组成的综合模型表现出比其他模型（单独的临床或放射组学模型）更好的性能。NN算法综合模型的性能指标在肿瘤分级预测模型中的AUROC为0.864，在预后预测模型中的AUROC为0.830。此外，在预测预后方面，NN综合临床放射组学模型的AUROC显著高于肿瘤最大标准化摄取值模型（P < 0.001）。
使用ML算法整合临床特征和基于[F]FDG PET的放射组学，以非侵入性方式改善了对高级别PNET和不良预后的预测。
