Shi Liming, Zhang Yang, Hu Jiamiao, Zhou Weiwen, Hu Xi, Cui Taoran, Yue Ning J, Sun Xiaonan, Nie Ke
Department of Radiation Oncology, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, Hangzhou 310019, China.
Department of Radiation Oncology, Rutgers-Cancer Institute of New Jersey, Rutgers-Robert Wood Johnson Medical School, 195 Little Albany St., New Brunswick, NJ 08903, USA.
Bioengineering (Basel). 2023 May 24;10(6):634. doi: 10.3390/bioengineering10060634.
(1) Background: An increasing amount of research has supported the role of radiomics for predicting pathological complete response (pCR) to neoadjuvant chemoradiation treatment (nCRT) in order to provide better management of locally advanced rectal cancer (LARC) patients. However, the lack of validation from prospective trials has hindered the clinical adoption of such studies. The purpose of this study is to validate a radiomics model for pCR assessment in a prospective trial to provide informative insight into radiomics validation. (2) Methods: This study involved a retrospective cohort of 147 consecutive patients for the development/validation of a radiomics model, and a prospective cohort of 77 patients from two institutions to test its generalization. The model was constructed using T2-weighted, diffusion-weighted, and dynamic contrast-enhanced MRI to understand the associations with pCR. The consistency of physicians' evaluations and agreement on pathological complete response prediction were also evaluated, with and without the aid of the radiomics model. (3) Results: The radiomics model outperformed both physicians' visual assessments in the prospective test cohort, with an area under the curve (AUC) of 0.84 (95% confidence interval of 0.70-0.94). With the aid of the radiomics model, a junior physician could achieve comparable performance as a senior oncologist. (4) Conclusion: We have built and validated a radiomics model with pretreatment MRI for pCR prediction of LARC patients undergoing nCRT.
（1）背景：越来越多的研究支持了影像组学在预测新辅助放化疗（nCRT）的病理完全缓解（pCR）方面的作用，以便为局部晚期直肠癌（LARC）患者提供更好的治疗管理。然而，前瞻性试验缺乏验证阻碍了此类研究在临床上的应用。本研究的目的是在前瞻性试验中验证一个用于pCR评估的影像组学模型，以便为影像组学验证提供有益的见解。（2）方法：本研究纳入了147例连续患者的回顾性队列用于影像组学模型的开发/验证，以及来自两个机构的77例患者的前瞻性队列用于测试其普遍性。该模型使用T2加权、扩散加权和动态对比增强MRI构建，以了解与pCR的关联。还评估了医生评估的一致性以及在有无影像组学模型辅助下对病理完全缓解预测的一致性。（3）结果：在前瞻性测试队列中，影像组学模型的表现优于医生的视觉评估，曲线下面积（AUC）为0.84（95%置信区间为0.70 - 0.94）。在影像组学模型的辅助下，初级医生可以达到与高级肿瘤学家相当的表现。（4）结论：我们构建并验证了一个基于治疗前MRI的影像组学模型，用于预测接受nCRT的LARC患者的pCR。
