基于CT的深度学习用于结直肠癌肿瘤分割及微卫星不稳定性预测:一项多中心队列研究
该多中心回顾性研究纳入2180例结直肠癌患者,开发并验证基于术前增强CT的深度学习模型用于肿瘤自动分割和微卫星不稳定性预测;分割模型在动脉期表现良好,联合临床病理因素的预测模型AUC达0.83和0.82,优于临床模型和影像模型。
要点
- 联合临床病理因素的模型预测MSI的AUC为0.83和0.82,优于临床模型(AUC=0.67)和两个影像模型(AUC=0.75和0.77),差异均P<0.001。
- 动脉期分割模型的斑块覆盖率为0.87,Dice系数为0.71,召回率为0.72,精确率为0.74,F1分数为0.71。
- 决策曲线分析显示联合模型在0.1至0.45的概率阈值范围内净获益高于其他模型。
核心结论
- 深度学习可提高肿瘤分割效率,且与增强CT及临床病理因素结合后,在预测结直肠癌MSI方面表现出良好的诊断性能。
研究设计与样本
- 多中心回顾性队列研究,纳入2018年1月至2023年4月期间接受手术或活检的结直肠癌患者2180例(中位年龄61岁±17[SD],男性1285例),分为训练组(n=1159)、验证组(n=289)和独立外部测试组(n=732);以三位腹部放射科医生手动勾画的动脉期和静脉期CT肿瘤轮廓作为金标准;分割采用nnU-Net,MSI预测采用ViT或卷积神经网络模型。
诊断标准与关键数值
- 外部测试集中,动脉期分割模型的斑块覆盖率、Dice系数、召回率、精确率和F1分数分别为0.87、0.71、0.72、0.74和0.71;MSI预测中,联合模型AUC=0.83和0.82,临床模型AUC=0.67,两个影像模型AUC=0.75和0.77,联合模型与临床模型及两个影像模型比较均p<0.001。
临床应用与阅片要点
- 作者认为,深度学习可提高肿瘤分割效率,且与增强CT及临床病理因素结合后,在预测结直肠癌MSI方面表现出良好的诊断性能。
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
PURPOSE: To develop and validate deep learning (DL) models using preoperative contrast-enhanced CT images for tumor auto-segmentation and microsatellite instability (MSI) prediction in colorectal cancer (CRC).
MATERIALS AND METHODS: Patients with CRC who underwent surgery or biopsy between January 2018 and April 2023 were retrospectively enrolled. Mismatch repair protein expression was determined via immunohistochemistry or fluorescence multiplex polymerase chain reaction-capillary electrophoresis. Manually delineated tumor contours using arterial and venous phase CT images by three abdominal radiologists are served as ground truth. Tumor auto-segmentation used nnU-Net. MSI prediction employed ViT or convolutional neural networks models, trained and validated with arterial and venous phase images (image model) or combined clinical-pathological factors (combined model). The segmentation model was evaluated using patch coverage ratio, Dice coefficient, recall, precision, and F1-score. The predictive models' efficacy was assessed using areas under the curves and decision curve analysis.
RESULTS: Overall, 2180 patients (median age: 61 years ± 17 [SD]; 1285 males) were divided into training (n = 1159), validation (n = 289), and independent external test (n = 732) groups. High-level MSI status was present in 435 patients (20%). In the external test set, the segmentation model performed well in the arterial phase, with patch coverage ratio, Dice coefficient, recall, precision, and F1-score values of 0.87, 0.71, 0.72, 0.74, and 0.71, respectively. For MSI prediction, the combined models outperformed the clinical model (AUC = 0.83 and 0.82 vs 0.67, p < 0.001) and two image models (AUC = 0.75 and 0.77, p < 0.001). Decision curve analysis confirmed the higher net benefit of the combined model compared to the other models across probability thresholds ranging from 0.1 to 0.45.
CONCLUSION: DL enhances tumor segmentation efficiency and, when integrated with contrast-enhanced CT and clinicopathological factors, exhibits good diagnostic performance in predicting MSI in CRC.
引用
- Chen W, Zheng K, Yuan W, et al. A CT-based deep learning for segmenting tumors and predicting microsatellite instability in patients with colorectal cancers: a multicenter cohort study. Radiol Med. 2024. PMID: 39586941. doi:10.1007/s11547-024-01909-5
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。