Department of Magnetic Resonance Imaging Diagnostic, The 2nd Affiliated Hospital of Harbin Medical University, Baojian Road, Nangang District, Harbin, 150086, China.
Medical Imaging Center, the Xinjiang Production and Construction Corps Tenth Division Beitun Hospital, Beitun, 836099, China.
BMC Med Imaging. 2024 Oct 4;24(1):262. doi: 10.1186/s12880-024-01439-6.
The study aimed to identify the optimal model for predicting rectal cancer liver metastasis (RCLM). This involved constructing various prediction models to aid clinicians in early diagnosis and precise decision-making.
A retrospective analysis was conducted on 193 patients diagnosed with rectal adenocarcinoma were randomly divided into training set (n = 136) and validation set (n = 57) at a ratio of 7:3. The predictive performance of three models was internally validated by 10-fold cross-validation in the training set. Delineation of the tumor region of interest (ROI) was performed, followed by the extraction of radiomics features from the ROI. The least absolute shrinkage and selection operator (LASSO) regression algorithm and multivariate Cox analysis were employed to reduce the dimensionality of radiomics features and identify significant features. Logistic regression was employed to construct three prediction models: clinical, radiomics, and combined models (radiomics + clinical). The predictive performance of each model was assessed and compared.
KRAS mutation emerged as an independent predictor of liver metastasis, yielding an odds ratio (OR) of 8.296 (95%CI: 3.471-19.830; p < 0.001). 5 radiomics features will be used to construct radiomics model. The combined model was built by integrating radiomics model with clinical model. In both the training set (AUC:0.842, 95%CI: 0.778-0.907) and the validation set (AUC: 0.805; 95%CI: 0.692-0.918), the AUCs for the combined model surpassed those of the radiomics and clinical models.
Our study reveals that KRAS mutation stands as an independent predictor of RCLM. The radiomics features based on MR play a crucial role in the evaluation of RCLM. The combined model exhibits superior performance in the prediction of liver metastasis.
Not applicable.
本研究旨在确定预测直肠癌肝转移（RCLM）的最佳模型。这涉及构建各种预测模型，以帮助临床医生进行早期诊断和精确决策。
对 193 例直肠腺癌患者进行回顾性分析，采用 7：3 的比例随机分为训练集（n=136）和验证集（n=57）。在训练集中，通过 10 折交叉验证对内部分类模型的预测性能进行了内部验证。对感兴趣区域（ROI）进行肿瘤勾画，然后从 ROI 中提取放射组学特征。采用最小绝对值收缩和选择算子（LASSO）回归算法和多变量 Cox 分析对放射组学特征进行降维，并识别出显著特征。采用 Logistic 回归构建三个预测模型：临床模型、放射组学模型和联合模型（放射组学+临床模型）。评估并比较了每个模型的预测性能。
KRAS 突变是肝转移的独立预测因素，优势比（OR）为 8.296（95%CI：3.471-19.830；p<0.001）。选取 5 个放射组学特征构建放射组学模型。联合模型是通过整合放射组学模型和临床模型构建的。在训练集（AUC：0.842，95%CI：0.778-0.907）和验证集（AUC：0.805；95%CI：0.692-0.918）中，联合模型的 AUC 均优于放射组学模型和临床模型。
本研究表明，KRAS 突变是 RCLM 的独立预测因素。基于磁共振的放射组学特征在评估 RCLM 中起着重要作用。联合模型在预测肝转移方面具有更好的性能。
无。
