直肠癌表征和预后预测中不同的放射学注释方法比较：一项两中性研究

为了探索放射线分析中多个注释的性能差异，并提供了大规模医学图像分析中肿瘤注释的参考。从两个接受了直肠癌根治切除的中心的342例患者进行了回顾性研究，并分为训练，内部验证，内部验证，外部验证和外部验证队列。进行了三个预测性的肿瘤T阶段（PT），淋巴结转移（PLNM）和无病生存期（PDF）的预测任务。 Twelve radiomics models were constructed using Lasso-Logistic or Lasso-Cox to evaluate and four annotation methods, 2D detailed annotation along tumour boundaries (2D), 3D detailed annotation along tumour boundaries (3D), 2D bounding box (2DBB), and 3D bounding box (3DBB) on T2-weighted images, were compared.放射学模型用于建立结合临床风险因素的合并模型。进行了DELONG测试，以比较使用接收器操作特征曲线的模型的性能。对于放射线模型，曲线值下的面积范围从0.627（0.518-0.728）到0.811到0.811到0.811（0.705-0.917）（0.705-0.917）（内部验证队列中），并在0.619（0.469-0.7554）中（0.469-7554）（0.89-824）外部验证队列。大多数基于四个注释的放射组模型没有显着差异，除了内部验证队列中PLNM的3D和3DBB模型之间（p = 0.0188）。对于合并的模型，只有2D模型与2dBb（P = 0.0372）和3D模型（P = 0.0380）的PDFS.Radiomics和2D和边界框注释构建的合并模型显示出与3D和详细的注释范围内的分析和详细的注释分析范围范围内的分析范围范围范围的分析，并表现出可比的表现，并显示出可比的性能。 2D最大肿瘤面积或边界盒注释具有代表性且易于操作，就像沿肿瘤边界沿肿瘤边界的3D整个肿瘤或详细注释一样。无论注释如何（2D，3D，详细或边界框），在放射组和组合模型中未观察到显着差异。优先选择更多的时间和节省努力的2D最大面积边界框注释。

To explore the performance differences of multiple annotations in radiomics analysis and provide a reference for tumour annotation in large-scale medical image analysis.A total of 342 patients from two centres who underwent radical resection for rectal cancer were retrospectively studied and divided into training, internal validation, and external validation cohorts. Three predictive tasks of tumour T-stage (pT), lymph node metastasis (pLNM), and disease-free survival (pDFS) were performed. Twelve radiomics models were constructed using Lasso-Logistic or Lasso-Cox to evaluate and four annotation methods, 2D detailed annotation along tumour boundaries (2D), 3D detailed annotation along tumour boundaries (3D), 2D bounding box (2DBB), and 3D bounding box (3DBB) on T2-weighted images, were compared. Radiomics models were used to establish combined models incorporating clinical risk factors. The DeLong test was performed to compare the performance of models using the receiver operating characteristic curves.For radiomics models, the area under the curve values ranged from 0.627 (0.518-0.728) to 0.811 (0.705-0.917) in the internal validation cohort and from 0.619 (0.469-0.754) to 0.824 (0.689-0.918) in the external validation cohort. Most radiomics models based on four annotations did not differ significantly, except between the 3D and 3DBB models for pLNM (p = 0.0188) in the internal validation cohort. For combined models, only the 2D model significantly differed from the 2DBB (p = 0.0372) and 3D models (p = 0.0380) for pDFS.Radiomics and combined models constructed with 2D and bounding box annotations showed comparable performances to those with 3D and detailed annotations along tumour boundaries in rectal cancer characterisation and prognosis prediction.For quantitative analysis of radiological images, the selection of 2D maximum tumour area or bounding box annotation is as representative and easy to operate as 3D whole tumour or detailed annotations along tumour boundaries.There is currently a lack of discussion on whether different annotation efforts in radiomics are predictively representative. No significant differences were observed in radiomics and combined models regardless of the annotations (2D, 3D, detailed, or bounding box). Prioritise selecting the more time and effort-saving 2D maximum area bounding box annotation.