双阶段深度学习模型用于CT图像上腺结节检测:一项回顾性研究
本研究为回顾性研究(2000年1月至2020年12月),开发并测试了一种双阶段深度学习模型,用于在腹部CT图像上自动描绘肾上腺结节,并模拟其与人工判读联合的分诊性能。模型在内部测试集1(n=153)中检测右侧和左侧肾上腺结节的AUC分别为0.98和0.93,在外部测试集(n=12080)中分别为0.98和0.97,在内部测试集2(n=1214)中分别为0.90和0.89。模型与人工判读联合达到高敏感度(最高100%)和高特异度(最高99%),分诊性能为0.77至0.98。
要点
- 双阶段深度学习模型在CT上检测右侧肾上腺结节的AUC为0.90–0.98,左侧为0.89–0.97。
- 结节分割的中位交并比右侧为0.64,左侧为0.53。
- 模型与人工判读联合敏感度最高达100%,特异度最高达99%。
核心结论
- 该深度学习模型表现出高性能,并有潜力改善偶发肾上腺结节的检测。
研究设计与样本
- 回顾性研究(2000年1月至2020年12月),使用内部数据集(共995例患者)进行模型训练和测试,并使用外部数据集(n=12080)进行进一步模拟测试以结合人工判读;模型为双阶段架构,即序贯检测和分割模型,分别针对右侧和左侧肾上腺进行训练。
关键影像表现/征象
- 模型检测右侧肾上腺结节在内部测试集1(n=153)的AUC为0.98(95%CI:0.96,1.00;P<.001),左侧为0.93(95%CI:0.87,0.98;P<.001)。
- 模型检测右侧肾上腺结节在外部测试集(n=12080)的AUC为0.98(95%CI:0.97,0.99;P<.001),左侧为0.97(95%CI:0.96,0.97;P<.001)。
- 模型检测右侧肾上腺结节在内部测试集2(n=1214)的AUC为0.90(95%CI:0.84,0.95;P<.001),左侧为0.89(95%CI:0.85,0.94;P<.001)。
- 右侧肾上腺结节分割的中位交并比为0.64(IQR,0.43-0.71),左侧为0.53(IQR,0.40-0.64)。
- 模型与人工判读联合达到高敏感度(最高100%)和高特异度(最高99%),分诊性能为0.77至0.98。
诊断标准与关键数值
- 结节检测性能以受试者工作特征曲线下面积(AUC)评估,右侧和左侧肾上腺结节在内部测试集1的AUC分别为0.98和0.93。
- 结节分割性能以交并比评估,右侧中位交并比为0.64,左侧为0.53。
- 模型与人工判读联合的分诊性能范围为0.77至0.98,敏感度最高100%,特异度最高99%。
临床应用与阅片要点
- 该模型有潜力改善偶发肾上腺结节的检测,可模拟与人工判读联合的分诊流程。
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 detection and classification of adrenal nodules are crucial for their management. Purpose To develop and test a deep learning model to automatically depict adrenal nodules on abdominal CT images and to simulate triaging performance in combination with human interpretation. Materials and Methods This retrospective study (January 2000-December 2020) used an internal dataset enriched with adrenal nodules for model training and testing and an external dataset reflecting real-world practice for further simulated testing in combination with human interpretation. The deep learning model had a two-stage architecture, a sequential detection and segmentation model, trained separately for the right and left adrenal glands. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC) for nodule detection and intersection over union for nodule segmentation. Results Of a total of 995 patients in the internal dataset, the AUCs for detecting right and left adrenal nodules in internal test set 1 (n = 153) were 0.98 (95% CI: 0.96, 1.00; P < .001) and 0.93 (95% CI: 0.87, 0.98; P < .001), respectively. These values were 0.98 (95% CI: 0.97, 0.99; P < .001) and 0.97 (95% CI: 0.96, 0.97; P < .001) in the external test set (n = 12 080) and 0.90 (95% CI: 0.84, 0.95; P < .001) and 0.89 (95% CI: 0.85, 0.94; P < .001) in internal test set 2 (n = 1214). The median intersection over union was 0.64 (IQR, 0.43-0.71) and 0.53 (IQR, 0.40-0.64) for right and left adrenal nodules, respectively. Combining the model with human interpretation achieved high sensitivity (up to 100%) and specificity (up to 99%), with triaging performance from 0.77 to 0.98. Conclusion The deep learning model demonstrated high performance and has the potential to improve detection of incidental adrenal nodules. © RSNA, 2025 Supplemental material is available for this article. See also the editorial by Malayeri and Turkbey in this issue.
引用
- Ahn CH, Kim T, Jo K, et al. Two-Stage Deep Learning Model for Adrenal Nodule Detection on CT Images: A Retrospective Study. Radiology. 2025. PMID: 40035671. doi:10.1148/radiol.231650
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。