Jiangsu Key Laboratory of Big Data Analysis Technique, School of Automation, Nanjing University of Information Science and Technology, 219 Ning Liu Road, Nanjing, Jiangsu Province 210044, China.
Department of Radiology, Changhai Hospital, Changhai Road 168, Shanghai 200434, China.
Acad Radiol. 2020 Dec;27(12):e272-e281. doi: 10.1016/j.acra.2020.01.002. Epub 2020 Feb 6.
Tumor grading of nonfunctional pancreatic neuroendocrine tumors (NF-pNETs) determines the choice of clinical treatment and management. The pathological grade of pancreatic neuroendocrine tumors is usually assessed on postoperative specimens. The goal of our study is to establish a tumor grade (G) prediction model for preoperative G1/2 NF-pNETs using radiomics for multislice spiral CT image analysis.
This retrospective study included a primary cohort of 59 patients and an independent validation cohort of 40 consecutive patients; their multislice spiral CT images were collected from October 2012 to October 2016 and October 2016 to June 2018, respectively. All 99 patients were diagnosed with clinicopathologically confirmed NF-pNETs. Most significant radiomic features were selected using the minimum redundancy and maximum relevance algorithm. Support vector machine classifier with a radial basis function-based predictive model was subsequently developed for clinical use.
A total of 585 radiomics features were extracted from every phase for each patient. Six of these radiomics features were identified as most discriminant features for G1 and G2 tumors and used to construct the tumor grade prediction model. The prediction model resulted in the area under the curve values of 0.968 (95% CI: 0.900-0.991) and 0.876 (95% CI: 0.700-0.963) for the training cohort and validation cohort, respectively. Sensitivity and specificity were 96.4% and 83.9%, and 90.9% and 88.9% for the training and validation cohorts, respectively. The decision curves indicated that if the threshold probability is above 0.1, using the rad-score in the current study on G1/2 NF-pNETs is more beneficial than the treat-all-patients scheme or the treat-none scheme.
Radiomics developed with a combination of nonenhanced and portal venous phases can achieve favorable predictive accuracy for histological grade for G1/G2 NF-pNETs.
非功能性胰腺神经内分泌肿瘤（NF-pNETs）的肿瘤分级决定了临床治疗和管理的选择。胰腺神经内分泌肿瘤的病理分级通常是基于术后标本进行评估的。我们的研究目的是通过对多层螺旋 CT 图像进行分析，建立一种用于术前 G1/2 NF-pNET 肿瘤分级（G）预测的影像组学模型。
本回顾性研究纳入了一组 59 例患者的原始队列和一组连续 40 例患者的独立验证队列；他们的多层螺旋 CT 图像分别于 2012 年 10 月至 2016 年 10 月和 2016 年 10 月至 2018 年 6 月采集。所有 99 例患者均经临床病理证实为 NF-pNETs。采用最小冗余最大相关性算法选择最显著的影像组学特征。随后，采用基于径向基函数的支持向量机分类器建立预测模型，用于临床应用。
每位患者的各个时相均提取了 585 个影像组学特征。其中 6 个特征被确定为 G1 和 G2 肿瘤最具鉴别力的特征，并用于构建肿瘤分级预测模型。该预测模型在训练队列和验证队列中的曲线下面积分别为 0.968（95%置信区间：0.900-0.991）和 0.876（95%置信区间：0.700-0.963）。训练队列和验证队列的灵敏度和特异度分别为 96.4%和 83.9%，90.9%和 88.9%。决策曲线表明，如果阈值概率高于 0.1，那么使用当前研究中基于非增强和门静脉期的 rad-score 对 G1/2 NF-pNET 进行分级预测，比治疗所有患者方案或不治疗方案更有利。
联合使用非增强期和门静脉期的影像组学可以实现对 G1/G2 NF-pNET 组织学分级的良好预测准确性。
