论文标题
2D和3D CT放射素特征性能比较胃癌的表征：一项多中心研究
2D and 3D CT Radiomic Features Performance Comparison in Characterization of Gastric Cancer: A Multi-center Study
论文作者
论文摘要
目的：放射组是一种用于医学图像分析的新兴工具，具有精确表征胃癌（GC）的潜力。无论是使用一板二维注释还是全册3D注释仍然是一个长期的争论，尤其是对于异质GC。我们通过三个任务全面比较了关于GC的2D和3D放射线特征的表示和歧视能力。 方法：四点539名GC患者被追溯入学并分为培训和验证队列。从放射科医生注释的2D或3D区域（ROI），分别提取了放射线特征。针对两种方式（2D或3D）和三个任务的每种组合定制了特征选择和模型构建程序。随后，对六个机器学习模型（model_2d^lnm，model_3d^lnm; model_2d^lvi，model_3d^lvi; model_2d^pt，model_3d^pt）进行了评估和评估，以反映表征GC表征表征的模态性能。此外，我们进行了辅助实验，以评估重新采样间距不同时的表现。 结果：关于三个任务，曲线下的屈服区域（AUC）为：model_2d^lnm的0.712（95％置信区间，0.613-0.811），model_3d^lnm的0.680（0.584-0.775）; model_2d^lvi的0.677（0.595-0.761），model_3d^lvi的0.615（0.528-0.703）; model_2d^pt的0.840（0.779-0.901），model_3d^pt的0.813（0.747-0.879）。此外，辅助实验表明，模型_2D比具有不同重采样间距的模型3D更有利。 结论：用2D放射线特征构建的模型显示出与3D特征在表征GC中构建的模型相当的性能。 意义：我们的工作表明，节省时间的2D注释将是GC中的更好选择，并提供了有关基于进一步的放射素学研究的相关参考。
Objective: Radiomics, an emerging tool for medical image analysis, is potential towards precisely characterizing gastric cancer (GC). Whether using one-slice 2D annotation or whole-volume 3D annotation remains a long-time debate, especially for heterogeneous GC. We comprehensively compared 2D and 3D radiomic features' representation and discrimination capacity regarding GC, via three tasks. Methods: Four-center 539 GC patients were retrospectively enrolled and divided into the training and validation cohorts. From 2D or 3D regions of interest (ROIs) annotated by radiologists, radiomic features were extracted respectively. Feature selection and model construction procedures were customed for each combination of two modalities (2D or 3D) and three tasks. Subsequently, six machine learning models (Model_2D^LNM, Model_3D^LNM; Model_2D^LVI, Model_3D^LVI; Model_2D^pT, Model_3D^pT) were derived and evaluated to reflect modalities' performances in characterizing GC. Furthermore, we performed an auxiliary experiment to assess modalities' performances when resampling spacing is different. Results: Regarding three tasks, the yielded areas under the curve (AUCs) were: Model_2D^LNM's 0.712 (95% confidence interval, 0.613-0.811), Model_3D^LNM's 0.680 (0.584-0.775); Model_2D^LVI's 0.677 (0.595-0.761), Model_3D^LVI's 0.615 (0.528-0.703); Model_2D^pT's 0.840 (0.779-0.901), Model_3D^pT's 0.813 (0.747-0.879). Moreover, the auxiliary experiment indicated that Models_2D are statistically more advantageous than Models3D with different resampling spacings. Conclusion: Models constructed with 2D radiomic features revealed comparable performances with those constructed with 3D features in characterizing GC. Significance: Our work indicated that time-saving 2D annotation would be the better choice in GC, and provided a related reference to further radiomics-based researches.
