当前的研究旨在使用多种机器学习算法和多分段正电子发射断层扫描（PET）放射组学来预测非小细胞肺癌（NSCLC）患者的淋巴血管侵犯（LVI），为个性化治疗策略和改善患者预后提供新途径。 126 名 NSCLC 患者参加了这项研究。应用了各种自动和半自动 PET 图像分割方法，包括局部主动轮廓 (LAC)、模糊 C 均值 (FCM)、K 均值 (KM)、分水岭、区域生长 (RG) 和迭代阈值 (IT) ）具有不同百分比的阈值。从每个感兴趣区域 (ROI) 提取一百五个放射组学特征。多种特征选择方法，包括最小冗余最大相关性（MRMR）、递归特征消除（RFE）和Boruta，以及多种分类器，包括多层感知器（MLP）、逻辑回归（LR）、XGBoost（XGB）、朴素贝叶斯（NB） ）和随机森林（RF）被采用。合成少数过采样技术 (SMOTE) 也用于确定是否可以提高 ROC 曲线下面积 (AUC)、准确性 (ACC)、灵敏度 (SEN) 和特异性 (SPE)。我们的结果表明，SMOTE、IT（阈值 45%）、RFE 特征选择和 LR 分类器的组合表现出最佳性能（AUC = 0.93、ACC = 0.84、SEN = 0.85、SPE = 0.84），其次是 SMOTE、FCM 分割，MRMR特征选择和LR分类器（AUC = 0.92，ACC = 0.87，SEN = 1，SPE = 0.84）。最高的 ACC 属于 IT 分割（阈值分别为 45% 和 50%），以及 Boruta 特征选择和不带 SMOTE 的 NB 分类器（分别为 ACC = 0.9、AUC = 0.78 和 0.76、SEN = 0.7 和 SPE = 0.94）。我们的结果表明，选择适当的分割方法和机器学习算法可能有助于使用 PET 放射组学分析高精度成功预测 NSCLC 患者的 LVI。© 2024。作者。

The current study aimed to predict lymphovascular invasion (LVI) using multiple machine learning algorithms and multi-segmentation positron emission tomography (PET) radiomics in non-small cell lung cancer (NSCLC) patients, offering new avenues for personalized treatment strategies and improving patient outcomes. One hundred and twenty-six patients with NSCLC were enrolled in this study. Various automated and semi-automated PET image segmentation methods were applied, including Local Active Contour (LAC), Fuzzy-C-mean (FCM), K-means (KM), Watershed, Region Growing (RG), and Iterative thresholding (IT) with different percentages of the threshold. One hundred five radiomic features were extracted from each region of interest (ROI). Multiple feature selection methods, including Minimum Redundancy Maximum Relevance (MRMR), Recursive Feature Elimination (RFE), and Boruta, and multiple classifiers, including Multilayer Perceptron (MLP), Logistic Regression (LR), XGBoost (XGB), Naive Bayes (NB), and Random Forest (RF), were employed. Synthetic Minority Oversampling Technique (SMOTE) was also used to determine if it boosts the area under the ROC curve (AUC), accuracy (ACC), sensitivity (SEN), and specificity (SPE). Our results indicated that the combination of SMOTE, IT (with 45% threshold), RFE feature selection and LR classifier showed the best performance (AUC = 0.93, ACC = 0.84, SEN = 0.85, SPE = 0.84) followed by SMOTE, FCM segmentation, MRMR feature selection, and LR classifier (AUC = 0.92, ACC = 0.87, SEN = 1, SPE = 0.84). The highest ACC belonged to the IT segmentation (with 45 and 50% thresholds) alongside Boruta feature selection and the NB classifier without SMOTE (ACC = 0.9, AUC = 0.78 and 0.76, SEN = 0.7, and SPE = 0.94, respectively). Our results indicate that selection of appropriate segmentation method and machine learning algorithm may be helpful in successful prediction of LVI in patients with NSCLC with high accuracy using PET radiomics analysis.© 2024. The Author(s).