Miyamoto Yuji, Nakaura Takeshi, Ohuchi Mayuko, Ogawa Katsuhiro, Kato Rikako, Maeda Yuto, Eto Kojiro, Iwatsuki Masaaki, Baba Yoshifumi, Hirai Toshinori, Baba Hideo
Department of Gastroenterological Surgery, Graduate School of Medical Sciences, Kumamoto University, Kumamoto, Japan.
Department of Diagnostic Radiology, Graduate School of Medical Sciences, Kumamoto University, Kumamoto, Japan.
J Anus Rectum Colon. 2025 Jan 25;9(1):117-126. doi: 10.23922/jarc.2024-077. eCollection 2025.
This study explored the clinical utility of CT radiomics-driven machine learning as a predictive marker for chemotherapy response in colorectal liver metastasis (CRLM) patients.
We included 150 CRLM patients who underwent first-line doublet chemotherapy, dividing them into a training cohort (n=112) and a test cohort (n=38). We manually delineated three-dimensional tumor volumes, selecting the largest liver metastasis for measurement, using pretreatment portal-phase CT images and extracted 107 radiomics features. Treatment response was classified as responder (complete or partial response) or non-responder (stable or progressive disease), based on the best overall response according to RECIST criteria, version 1.1. Employing Random Forest and Boruta algorithms, we identified significant features for responder-non-responder differentiation. Radiomics signatures were developed and validated in the training cohort using five-fold cross-validation, and performance was assessed using the area under the curve (AUC).
Among the patients, 91 (61%) were responders and 59 (39%) were non-responders. Variable selection with Boruta revealed three key parameters ("DependenceVariance," "ClusterShade," and "RunVariance"). In the training cohort, individual CT texture parameter AUCs ranged from 0.4 to 0.65, while the machine learning analysis incorporating all valid parameters exhibited a significantly higher AUC of 0.94 (p<0.01). The validation cohort also demonstrated strong predictive accuracy, with an AUC of 0.87 for treatment response.
This study highlights the potential of CT radiomics-driven machine learning in predicting chemotherapy responses among CRLM patients.
本研究探讨了CT影像组学驱动的机器学习作为预测结直肠癌肝转移（CRLM）患者化疗反应的生物标志物的临床应用价值。
我们纳入了150例接受一线双联化疗的CRLM患者，将其分为训练队列（n = 112）和测试队列（n = 38）。我们使用治疗前门静脉期CT图像手动勾勒三维肿瘤体积，选择最大的肝转移灶进行测量，并提取了107个影像组学特征。根据实体瘤疗效评价标准（RECIST）1.1版的最佳总体反应，将治疗反应分为反应者（完全或部分缓解）或无反应者（疾病稳定或进展）。采用随机森林和Boruta算法，我们确定了区分反应者与无反应者的显著特征。在训练队列中使用五折交叉验证开发并验证影像组学特征，并使用曲线下面积（AUC）评估性能。
在这些患者中，91例（61%）为反应者，59例（39%）为无反应者。Boruta变量选择揭示了三个关键参数（“DependenceVariance”、“ClusterShade”和“RunVariance”）。在训练队列中，单个CT纹理参数的AUC范围为0.4至0.65，而纳入所有有效参数的机器学习分析显示AUC显著更高，为0.94（p < 0.01）。验证队列也显示出很强的预测准确性，治疗反应的AUC为0.87。
本研究突出了CT影像组学驱动的机器学习在预测CRLM患者化疗反应方面的潜力。
