机器学习在CT上分割肾上腺并分类正常与肾上腺肿块
本研究为回顾性研究,开发两阶段机器学习流程,在增强腹部CT上分割肾上腺并分类正常或含肿块。
要点
- 模型可自动分割肾上腺,Dice系数与放射科医生手动分割相当
- 分类正常与含肿块肾上腺的敏感度在开发集为83%,二次集为69%
- 特异度较高(89%和91%),有助于排除正常腺体
核心结论
- 两阶段机器学习流程能够分割肾上腺并区分正常肾上腺与含肿块肾上腺。
研究设计与样本
- 回顾性研究,开发数据集274例增强腹部CT(251例患者,中位年龄61岁,133例女性),二次测试集991例增强腹部CT(991例患者,中位年龄62岁,578例女性)。
- 开发数据集中肾上腺由放射科医生手动分割,两个数据集图像均手动分类为正常或含肿块。
- 深度学习分割与分类模型在开发数据集上训练,并在两个数据集上评估;分割性能用Dice相似系数(DSC)评价,分类性能用敏感度和特异度评价。
诊断标准与关键数值
- 开发测试集上模型分割中位DSC:正常腺体0.80(IQR 0.78-0.89),肾上腺肿块0.84(IQR 0.79-0.90)。
- 开发阅片者集上放射科医生手动分割中位读者间DSC:正常腺体0.89(IQR 0.78-0.93),肾上腺肿块0.89(IQR 0.85-0.97)。
- 开发测试集上模型分类敏感度83%(95%CI 55,95),特异度89%(95%CI 75,96)。
- 二次测试集上模型分类敏感度69%(95%CI 58,79),特异度91%(95%CI 90,92)。
临床应用与阅片要点
- 模型分割性能与放射科医生手动分割相当,可用于肾上腺自动分割以辅助阅片。
- 分类特异度较高(89%-91%),有助于识别正常肾上腺、减少不必要的进一步检查。
- 二次测试集敏感度降至69%,提示模型在外部数据上可能漏诊部分含肿块肾上腺,需结合人工阅片。
局限性
- 回顾性研究设计。
- 二次测试集敏感度(69%)低于开发测试集(83%),提示泛化性能有限。
- 原文未报告模型在不同CT设备或扫描参数下的表现。
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 Adrenal masses are common, but radiology reporting and recommendations for management can be variable. Purpose To create a machine learning algorithm to segment adrenal glands on contrast-enhanced CT images and classify glands as normal or mass-containing and to assess algorithm performance. Materials and Methods This retrospective study included two groups of contrast-enhanced abdominal CT examinations (development data set and secondary test set). Adrenal glands in the development data set were manually segmented by radiologists. Images in both the development data set and the secondary test set were manually classified as normal or mass-containing. Deep learning segmentation and classification models were trained on the development data set and evaluated on both data sets. Segmentation performance was evaluated with use of the Dice similarity coefficient (DSC), and classification performance with use of sensitivity and specificity. Results The development data set contained 274 CT examinations (251 patients; median age, 61 years; 133 women), and the secondary test set contained 991 CT examinations (991 patients; median age, 62 years; 578 women). The median model DSC on the development test set was 0.80 (IQR, 0.78-0.89) for normal glands and 0.84 (IQR, 0.79-0.90) for adrenal masses. On the development reader set, the median interreader DSC was 0.89 (IQR, 0.78-0.93) for normal glands and 0.89 (IQR, 0.85-0.97) for adrenal masses. Interreader DSC for radiologist manual segmentation did not differ from automated machine segmentation (P = .35). On the development test set, the model had a classification sensitivity of 83% (95% CI: 55, 95) and specificity of 89% (95% CI: 75, 96). On the secondary test set, the model had a classification sensitivity of 69% (95% CI: 58, 79) and specificity of 91% (95% CI: 90, 92). Conclusion A two-stage machine learning pipeline was able to segment the adrenal glands and differentiate normal adrenal glands from those containing masses. © RSNA, 2022 Online supplemental material is available for this article.
引用
- Robinson-Weiss, Patel, Bizzo, et al. Machine Learning for Adrenal Gland Segmentation and Classification of Normal and Adrenal Masses at CT. Radiology. 2022. PMID: 36125375. doi:10.1148/radiol.220101
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。