Department of Surgery and Science, Graduate School of Medical Sciences, Kyushu University, Fukuoka, Japan.
Ann Surg Oncol. 2021 Jun;28(6):2975-2985. doi: 10.1245/s10434-020-09581-5. Epub 2021 Jan 16.
The aim of this study was to develop a radiomics-based prediction model for the response of colorectal liver metastases to oxaliplatin-based chemotherapy.
Forty-two consecutive patients treated with oxaliplatin-based first-line chemotherapy for colorectal liver metastasis at our institution from August 2013 to October 2019 were enrolled in this retrospective study. Overall, 126 liver metastases were chronologically divided into the training (n = 94) and validation (n = 32) cohorts. Regions of interest were manually segmented, and the best response to chemotherapy was decided based on Response Evaluation Criteria in Solid Tumors (RECIST). Patients who achieved clinical complete and partial response according to RECIST were defined as good responders. Radiomics features were extracted from the pretreatment enhanced computed tomography scans, and a radiomics score was calculated using the least absolute shrinkage and selection operator regression model in a trial cohort.
The radiomics score significantly discriminated good responders in both the trial (area under the curve [AUC] 0.8512, 95% confidence interval [CI] 0.7719-0.9305; p < 0.0001) and validation (AUC 0.7792, 95% CI 0.6176-0.9407; p < 0.0001) cohorts. Multivariate analysis revealed that high radiomics scores greater than - 0.06 (odds ratio [OR] 23.803, 95% CI 8.432-80.432; p < 0.0001), clinical non-T4 (OR 6.054, 95% CI 2.164-18.394; p = 0.0005), and metachronous disease (OR 11.787, 95% CI 2.333-70.833; p = 0.0025) were independently associated with good response.
Radiomics signatures may be a potential biomarker for the early prediction of chemosensitivity in colorectal liver metastases. This approach may support the treatment strategy for colorectal liver metastasis.
本研究旨在建立基于放射组学的预测模型，用于预测结直肠癌肝转移患者对奥沙利铂为基础的化疗的反应。
本回顾性研究纳入了 2013 年 8 月至 2019 年 10 月在我院接受奥沙利铂为基础的一线化疗治疗的 42 例连续结直肠癌肝转移患者。共 126 个肝转移灶按时间顺序分为训练队列（n=94）和验证队列（n=32）。手动对感兴趣区进行分割，并根据实体瘤反应评价标准（RECIST）判断化疗的最佳反应。根据 RECIST 达到完全和部分缓解的患者被定义为良好应答者。从预处理增强 CT 扫描中提取放射组学特征，并使用最小绝对值收缩和选择算子回归模型在试验队列中计算放射组学评分。
在试验队列（AUC 0.8512，95%置信区间 [CI] 0.7719-0.9305；p<0.0001）和验证队列（AUC 0.7792，95%CI 0.6176-0.9407；p<0.0001）中，放射组学评分均能显著区分良好应答者。多变量分析显示，高放射组学评分（大于-0.06）（比值比 [OR] 23.803，95%CI 8.432-80.432；p<0.0001）、临床非 T4（OR 6.054，95%CI 2.164-18.394；p=0.0005）和异时性疾病（OR 11.787，95%CI 2.333-70.833；p=0.0025）是与良好应答相关的独立因素。
放射组学特征可能是结直肠癌肝转移化疗敏感性早期预测的潜在生物标志物。该方法可为结直肠癌肝转移的治疗策略提供支持。
