可变视觉Transformer模型鉴别透明细胞肾细胞癌与其他肾肿瘤的性能
本研究基于C4KC-KiTS数据集构建可变视觉Transformer(vViT),利用患者特征、影像组学特征和动脉期CT图像鉴别透明细胞肾细胞癌(ccRCC)与非ccRCC。训练集153例1636幅图像,测试集39例402幅图像。vViT在测试集上准确率0.82,AUC-ROC 0.91,显著高于VGG16、AlexNet和GoogleNet,与CNN性能相当。
要点
- vViT鉴别ccRCC与非ccRCC的AUC达0.91,准确率0.82。
- 模型同时分析非图像信息与医学图像,可评估输入因素与结局的关联。
核心结论
- vViT使用CT图像鉴别ccRCC与非ccRCC的性能与CNN相当。
研究设计与样本
- 回顾性研究,使用2019年KiTS挑战赛(C4KC-KiTS)训练集数据构建训练集和测试集。
- 训练集153例患者1636幅图像(818 ccRCC,818 non-ccRCC),测试集39例患者402幅图像(201 ccRCC,201 non-ccRCC)。
- vViT模型输入包括患者特征、影像组学特征和动脉期CT图像。
- 以患者为单位计算准确率和AUC-ROC,并与VGG16、AlexNet、GoogleNet比较,使用DeLong检验。
诊断标准与关键数值
- vViT准确率0.82(95%CI 0.72-0.86),AUC-ROC 0.91(95%CI 0.81-0.99)。
- VGG16准确率0.72(95%CI 0.62-0.78),AUC-ROC 0.70(95%CI 0.51-0.89)。
- AlexNet准确率0.54(95%CI 0.45-0.62),AUC-ROC 0.53(95%CI 0.34-0.72)。
- GoogleNet准确率0.61(95%CI 0.52-0.69),AUC-ROC 0.66(95%CI 0.46-0.85)。
临床应用与阅片要点
- vViT可同时利用动脉期CT图像、影像组学特征和患者特征辅助鉴别ccRCC与非ccRCC。
- vViT性能优于传统CNN模型,但需外部验证后方可用于临床。
局限性
- 测试集样本量较小(39例患者402幅图像)。
- 数据来源于单一公开挑战赛数据集,缺乏外部验证。
- 仅使用动脉期CT图像,未评估其他期相或多种影像模式。
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
OBJECTIVES: To examine the performance of the variable Vision Transformer (vViT) in comparison with that of convolutional neural networks (CNNs) in the task of differentiating clear cell renal cell carcinoma (ccRCC) and non-ccRCC using CT images.
METHODS: The vViT was designed to use patient characteristics, radiomic features, and arterial phase CT images. The training and test datasets were constructed from the training set of the 2019 Kidney and Kidney Tumor Segmentation Challenge (C4KC-KiTS) dataset. The training dataset contained 153 patients with 1636 images (818 ccRCC, 818 non-ccRCC) and the test dataset contained 39 patients with 402 images (201 ccRCC, 201 non-ccRCC). After training, metrics including accuracy and the area under the curve of the receiver-operating characteristics (AUC-ROC) were calculated using the test dataset for vViT, Visual Geometry Group (VGG) 16, AlexNet, and GoogleNet in a patient-based approach. The metrics were calculated using CT images containing kidney and tumor. The AUC-ROC of vViT was compared with those of other models using the DeLong test.
RESULTS: vViT, VGG16, AlexNet, and GoogleNet achieved accuracies of 0.82 (95% CI, 0.72-0.86), 0.72 (0.62-0.78), 0.54 (0.45-0.62), and 0.61 (0.52-0.69), respectively. AUC-ROC values for vViT, VGG16, AlexNet, and GoogleNet were 0.91 (0.81-0.99), 0.70 (0.51-0.89), 0.53 (0.34-0.72), and 0.66 (0.46-0.85), respectively. The AUC-ROC of vViT was higher than that of VGG16, AlexNet, and GoogleNet (P < .05).
CONCLUSIONS: Variable Vision Transformer achieved comparable performance to CNN using CT images in the task of differentiating ccRCC and non-ccRCC.
ADVANCES IN KNOWLEDGE: We developed a new deep learning model termed vViT that simultaneously analyzes non-image information and medical images. Variable Vision Transformer can evaluate associations between input factors and outcome.
引用
- Usuzaki T, Takahashi K, Takagi H, et al. Performance of a self-attention-based model in the task of differentiating clear cell renal cell carcinoma from other renal tumors: variable Vision Transformer. Br J Radiol. 2026. PMID: 42162958. doi:10.1093/bjr/tqag118
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。