基于CT的影像组学术前预测膀胱癌肌层浸润状态及其与放射科医生评估的比较
研究回顾性纳入188例经病理确诊膀胱癌的增强CT静脉期图像,随机分为训练集120例和测试集68例,构建影像组学模型预测肌层浸润状态。模型在训练集和测试集AUC分别为0.979和0.894,优于两位放射科医生的视觉评估;模型特异度高于放射科医生(85.3-96.7% vs 47.1-58.3%,均p<0.05),敏感度与放射科医生相当(79.4-90% vs 91.2-96.7%,均p>0.05)。
要点
- 影像组学模型在测试集预测膀胱癌肌层浸润的AUC为0.894(95%CI 0.796-0.956),高于两位放射科医生的0.766和0.826。
- 影像组学模型特异度85.3-96.7%,高于放射科医生的47.1-58.3%(均p<0.05),敏感度与放射科医生相当(79.4-90% vs 91.2-96.7%,均p>0.05)。
- 模型基于增强CT静脉期图像手动标注提取特征,训练集AUC 0.979(95%CI 0.935-0.996)。
核心结论
- 基于增强CT静脉期图像的影像组学模型在预测膀胱癌肌层浸润状态方面优于放射科医生的视觉评估。
研究设计与样本
- 回顾性研究,纳入2018年11月至2019年12月经病理确诊膀胱癌的增强CT图像188例,随机分为训练集120例和测试集68例;由一名普通放射科医生和一名经验丰富放射科医生分别在静脉期手动标注并验证,进行影像组学特征提取和模型开发,同批图像由两位放射科医生评估,采用ROC曲线分析比较诊断性能。
诊断标准与关键数值
- 影像组学模型AUC在训练集为0.979(95%CI 0.935-0.996)、测试集为0.894(95%CI 0.796-0.956);放射科医生A训练集AUC 0.865(95%CI 0.791-0.921)、测试集0.766(95%CI 0.647-0.860);放射科医生B训练集AUC 0.894(95%CI 0.824-0.943)、测试集0.826(95%CI 0.715-0.907);影像组学模型特异度85.3-96.7%高于放射科医生47.1-58.3%(均p<0.05),敏感度79.4-90%与放射科医生91.2-96.7%相当(均p>0.05)。
临床应用与阅片要点
- 在增强CT静脉期图像上可参考影像组学模型辅助预测膀胱癌肌层浸润状态,模型特异度高于放射科医生视觉评估,敏感度与放射科医生相当。
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
AIM: To develop a radiomics model to predict the muscle-invasive status of bladder cancer (BC) in contrast-enhanced computed tomography (CECT) images, compared with radiologists' interpretations.
MATERIALS AND METHODS: One hundred and eighty-eight CECT images with histopathologically confirmed BC were retrieved retrospectively from November 2018 to December 2019 and were divided randomly into the training (n=120) and test dataset (n=68). The BC were annotated manually and validated on the venous phase by a general radiologist and an experienced radiologist, respectively. The radiomics analysis included radiomics feature extraction and model development. The same images were also evaluated by two radiologists. The diagnostic performance of radiomics was evaluated using receiver operating characteristic (ROC) curve analysis and the area under the ROC curve (AUC), sensitivity, and specificity were calculated. The predictive performance of radiomics was then compared to visual assessments of the two radiologists.
RESULTS: The radiomics model reached an AUC (95% confidence interval [CI]) of 0.979 (0.935-0.996) and 0.894 (0.796-0.956) in the training and test dataset, respectively. The radiomics model outperformed the visual assessment of radiologist A and B both in the training (0.865 [0.791-0.921], 0.894 [0.824-0.943]) and test dataset (0.766 [0.647-0.860], 0.826 [0.715-0.907]). Pairwise comparisons showed that the specificities of the radiomics model were higher than the radiologists (85.3-96.7% versus 47.1-58.3%, all p<0.05), but the sensitivities were comparable between the radiomics and the radiologists (79.4-90% versus 91.2-96.7%; all p>0.05).
CONCLUSIONS: A radiomics model was developed that outperformed the radiologists' visual assessment in predicting the muscle-invasive status of BC in the venous phase of CT images.
引用
- Cui, Sun, Liu, et al. CT-based radiomics for the preoperative prediction of the muscle-invasive status of bladder cancer and comparison to radiologists' assessment. Clin Radiol. 2022. PMID: 35367051. doi:10.1016/j.crad.2022.02.019
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。