文献速递神经头颈MR

卷积神经网络在多中心垂体腺瘤术前海绵窦侵犯检测中的应用

Multi-center application of a convolutional neural network for preoperative detection of cavernous sinus invasion in pituitary adenomas.
PubMed 文献 · Neuroradiology · 2024-01-18

该研究回顾性纳入5个医疗中心2011年1月至2021年12月的729例垂体腺瘤患者(伴海绵窦侵犯543例,不伴186例),用两个垂体卓越中心的T1增强MRI训练卷积神经网络模型,在另外三个市级中心82例外部测试集评估,模型诊断海绵窦侵犯准确率0.89,AUC-ROC为0.92(95%CI 0.88-0.97),优于直径、长度及Knosp分级三种二分法的临床预测指标。

要点

  • 外部测试集CNN模型诊断海绵窦侵犯准确率0.89,AUC-ROC 0.92(95%CI 0.88-0.97)。
  • 模型AUC-ROC优于直径(0.75)、长度(0.80)及Knosp分级三种二分法(0.70-0.82)。
  • Knosp 3A级(n=24,侵犯率0.35)中模型准确率0.78,敏感度0.72、特异度0.78。

核心结论

  • 深度学习模型能够准确识别海绵窦侵犯,并令人满意地在多中心定位海绵窦侵犯区域。

研究设计与样本

  • 回顾性研究,共纳入5个医疗中心2011年1月至2021年12月729例垂体腺瘤患者,伴海绵窦侵犯543例、不伴186例;使用两个垂体卓越中心的T1增强MRI训练CNN模型(n=647),另三个市级中心82例作为外部测试集评估模型性能。

关键影像表现/征象

  • Grad-CAM结果显示模型关注区域集中在鞍区海绵窦侵犯部位。

诊断标准与关键数值

  • 外部测试集CNN模型诊断海绵窦侵犯准确率0.89,AUC-ROC 0.92(95%CI 0.88-0.97);直径AUC-ROC 0.75,长度AUC-ROC 0.80,Knosp分级三种二分法AUC-ROC 0.70-0.82;Knosp 3A级(n=24,侵犯率0.35)模型准确率0.78,敏感度0.72,特异度0.78。

临床应用与阅片要点

  • 作者认为该深度学习模型能够准确识别海绵窦侵犯,并能在多中心令人满意地定位海绵窦侵犯区域。

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

OBJECTIVE: Cavernous sinus invasion (CSI) plays a pivotal role in determining management in pituitary adenomas. The study aimed to develop a Convolutional Neural Network (CNN) model to diagnose CSI in multiple centers.

METHODS: A total of 729 cases were retrospectively obtained in five medical centers with (n = 543) or without CSI (n = 186) from January 2011 to December 2021. The CNN model was trained using T1-enhanced MRI from two pituitary centers of excellence (n = 647). The other three municipal centers (n = 82) as the external testing set were imported to evaluate the model performance. The area-under-the-receiver-operating-characteristic-curve values (AUC-ROC) analyses were employed to evaluate predicted performance. Gradient-weighted class activation mapping (Grad-CAM) was used to determine models' regions of interest.

RESULTS: The CNN model achieved high diagnostic accuracy (0.89) in identifying CSI in the external testing set, with an AUC-ROC value of 0.92 (95% CI, 0.88-0.97), better than CSI clinical predictor of diameter (AUC-ROC: 0.75), length (AUC-ROC: 0.80), and the three kinds of dichotomizations of the Knosp grading system (AUC-ROC: 0.70-0.82). In cases with Knosp grade 3A (n = 24, CSI rate, 0.35), the accuracy the model accounted for 0.78, with sensitivity and specificity values of 0.72 and 0.78, respectively. According to the Grad-CAM results, the views of the model were confirmed around the sellar region with CSI.

CONCLUSIONS: The deep learning model is capable of accurately identifying CSI and satisfactorily able to localize CSI in multicenters.

来源:Neuroradiology,查看原文。版权归原作者所有。

引用

  1. Fang Y, Wang H, Cao D, et al. Multi-center application of a convolutional neural network for preoperative detection of cavernous sinus invasion in pituitary adenomas. Neuroradiology. 2024. PMID: 38236424. doi:10.1007/s00234-024-03287-1

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。