提高放射科医生对结直肠癌淋巴血管侵犯诊断准确性的多中心CT研究启示
该多中心回顾性研究纳入四家机构1409例病理确诊结直肠癌患者,基于CT影像提取放射组学特征并采用DRSN-CW算法构建淋巴血管侵犯预测模型,模型在训练和验证队列中AUC达0.896、0.849、0.845和0.799,放射科医生参考模型后诊断表现显著提升,模型预测LVI阴性患者总生存期显著长于阳性患者。
要点
- 基于CT的DRSN-CW模型在训练和验证队列中诊断LVI的AUC分别为0.896、0.849、0.845和0.799。
- 放射科医生参考模型输出后诊断LVI的准确性显著提高。
- 模型预测LVI阴性患者总生存期显著长于预测阳性者(训练队列p=0.012;内部验证队列p=0.046)。
核心结论
- 基于CT的预测模型显著提高放射科医生准确诊断结直肠癌LVI的能力,且模型预测LVI与总生存期相关,为临床决策提供有价值工具。
研究设计与样本
- 回顾性分析四家机构1409例病理确诊结直肠癌患者,从CT肿瘤区域提取放射组学特征,采用DRSN-CW算法构建预测模型,并以SHAP解释关键特征影响。
诊断标准与关键数值
- 模型诊断LVI的AUC在训练队列为0.896(95%CI 0.866-0.923),验证队列分别为0.849(0.782-0.908)、0.845(0.782-0.901)和0.799(0.709-0.881)。
临床应用与阅片要点
- 放射科医生可参考该模型输出辅助诊断结直肠癌LVI,模型预测LVI阴性者总生存期显著更长(训练队列p=0.012;内部验证队列p=0.046)。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
BACKGROUND: The current standard of subjective assessment by radiologists for lymphovascular invasion (LVI) in colorectal cancer (CRC) using CT images often falls short in diagnostic accuracy. This study introduces an advanced CT-based prediction model aimed at providing support for radiologists' assessment to accurately diagnose LVI.
METHODS: We conducted a retrospective analysis of 1409 patients with pathologically confirmed CRC from four institutions. Radiomics features were extracted from tumor areas on CT images, and Deep Residual Shrinkage Networks with Channel-wise Thresholds (DRSN-CW) algorithm was utilized to build prediction model. We assessed the model's impact on enhancing radiologists' diagnostic performance and employed Shapley Additive Explanation (SHAP) to interpret the influence of key features on predictions.
RESULTS: The prediction model achieved strong prediction performance with AUCs of 0.896 (95% CI: 0.866-0.923), 0.849 (0.782-0.908), 0.845 (0.782-0.901) and 0.799 (0.709-0.881) in the training and validation cohorts. Crucially, when informed by the model, radiologists demonstrated a significant improvement in diagnosing LVI. SHAP analysis provided detailed insights into the model's decision-making process, enhancing its clinical relevance. We also observed that patients predicted to be LVI-negative by the model had significantly longer overall survival (OS) compared to those LVI-positive (training cohort, p = 0.012; internal validation cohort, p = 0.046).
CONCLUSIONS: This study introduces a CT-based prediction model that significantly enhances radiologists' ability to accurately diagnose LVI in CRC. By improving diagnostic accuracy and demonstrating the association between LVI predictions and OS, the model provides a valuable tool for clinical decision-making, with the potential to improve patient outcomes.
引用
- Diao W, Hou K, Chen X, et al. Improving radiologists' diagnostic accuracy for lymphovascular invasion in colorectal cancer: insights from a multicenter CT-based study. Abdom Radiol (NY). 2025. PMID: 40208287. doi:10.1007/s00261-025-04884-1
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。