Nakajo Masatoyo, Jinguji Megumi, Tani Atsushi, Kikuno Hidehiko, Hirahara Daisuke, Togami Shinichi, Kobayashi Hiroaki, Yoshiura Takashi
Department of Radiology, Kagoshima University, Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan.
Department of Management Planning Division, Harada Academy, 2-54-4 Higashitaniyama, Kagoshima, 890-0113, Japan.
Mol Imaging Biol. 2021 Oct;23(5):756-765. doi: 10.1007/s11307-021-01599-9. Epub 2021 Mar 24.
To examine the prognostic significance of pretreatment 2-deoxy-2-[F]fluoro-D-glucose ([F]-FDG) positron emission tomography (PET)-based radiomic features using a machine learning approach in patients with endometrial cancers.
Included in this retrospective study were 53 patients with endometrial cancers who underwent [F]-FDG PET/X-ray computed tomography (CT) before treatment. Since two different PET scanners were used, post-reconstruction harmonization was performed for all PET parameters using the ComBat harmonization method. Four clinical (age, histological type, stage, and treatment method) and 40 [F]-FDG PET-based radiomic features were ranked, and a subset of useful features was selected based on the decrease in the Gini impurity in terms of associations with disease progression. The machine learning algorithms (random forest, neural network, k-nearest neighbors (kNN), naive Bayes, logistic regression, and support vector machine) were compared using the areas under the receiver operating characteristic curve (AUC) and validated by the random sampling method. Progression-free survival (PFS) and overall survival (OS) were assessed by the Cox regression analysis.
The five best predictors of disease progression were coarseness, gray-level run length nonuniformity, stage, treatment method, and gray-level zone length nonuniformity. The kNN model obtained the best performance classifier for predicting the disease progression (AUC =0.890, accuracy =0.849, F1 score =0.848, precision =0.857, and recall =0.849). Coarseness which was the first ranked radiomic feature was selected for survival analyses, and only coarseness remained as a significant and independent factor for both PFS (hazard ratios (HR), 0.65; 95 % confidence interval [CI], 0.49-0.86; p=0.003) and OS (HR, 0.52; 95 % CI, 0.36-0.76; p<0.001) at multivariate Cox regression analysis.
[F]-FDG PET-based radiomic analysis using a machine learning approach may be useful for predicting tumor progression and prognosis in patients with endometrial cancers.
采用机器学习方法研究基于治疗前2-脱氧-2-[F]氟-D-葡萄糖（[F]-FDG）正电子发射断层扫描（PET）的影像组学特征在子宫内膜癌患者中的预后意义。
本回顾性研究纳入了53例治疗前接受[F]-FDG PET/X线计算机断层扫描（CT）的子宫内膜癌患者。由于使用了两种不同的PET扫描仪，采用ComBat归一化方法对所有PET参数进行重建后归一化。对4项临床特征（年龄、组织学类型、分期和治疗方法）和40项基于[F]-FDG PET的影像组学特征进行排序，并根据与疾病进展相关性的基尼杂质减少情况选择有用特征子集。使用受试者操作特征曲线（AUC）下面积比较机器学习算法（随机森林、神经网络、k近邻（kNN）、朴素贝叶斯、逻辑回归和支持向量机），并通过随机抽样方法进行验证。采用Cox回归分析评估无进展生存期（PFS）和总生存期（OS）。
疾病进展的5个最佳预测因素为粗糙度、灰度游程长度不均匀性、分期、治疗方法和灰度区域长度不均匀性。kNN模型在预测疾病进展方面获得了最佳性能分类器（AUC =0.890，准确率 =0.849，F1分数 =0.848，精确率 =0.857，召回率 =0.849）。将排名第一的影像组学特征粗糙度用于生存分析，在多变量Cox回归分析中，只有粗糙度仍然是PFS（风险比（HR），0.65；95%置信区间[CI]，0.49 - 0.86；p =0.003）和OS（HR，0.52；95%CI，0.36 - 0.76；p <0.001）的显著且独立因素。
采用机器学习方法的基于[F]-FDG PET的影像组学分析可能有助于预测子宫内膜癌患者的肿瘤进展和预后。
