文献速递胸部CT

基于注意力机制的CT超分辨深度学习模型预测实性或部分实性肺腺癌气道播散

CT-Based Super-Resolution Deep Learning Models with Attention Mechanisms for Predicting Spread Through Air Spaces of Solid or Part-Solid Lung Adenocarcinoma.
PubMed 文献 · Acad Radiol · 2024-01-05

该回顾性研究纳入两个医学中心共602例肺腺癌患者,对CT图像行超分辨重建后训练SE-ResNet50模型并与ResNet50对比。SE-ResNet50在训练、验证及外部测试队列的AUC分别为0.933、0.783、0.806,外部测试准确率82.2%,较ResNet50提高10%。作者认为基于CT超分辨的SE-ResNet50模型对预测实性或部分实性肺腺癌STAS状态有较大潜力。

要点

  • SE-ResNet50外部测试AUC 0.806,高于ResNet50的0.695。
  • 外部测试准确率SE-ResNet50 82.2% vs ResNet50 72.2%,提高10%。
  • 模型基于CT超分辨图像,用于术前预测实性或部分实性肺腺癌STAS。

核心结论

  • 基于CT超分辨的SE-ResNet50模型对预测实性或部分实性肺腺癌STAS状态有较大潜力,预测性能优于传统深度学习模型。

研究设计与样本

  • 回顾性研究,共602例肺腺癌患者来自两个医学中心;中心1随机按7:3分为训练队列358例和验证队列154例,中心2为外部测试队列90例;对所有图像行超分辨重建获得高分辨率图像,用于训练SE-ResNet50模型并构建等参数ResNet50模型;以受试者工作特征曲线、AUC、准确率、精确率、敏感度、特异度比较两模型。

诊断标准与关键数值

  • SE-ResNet50与ResNet50在训练队列的AUC分别为0.933 vs 0.909。
  • SE-ResNet50与ResNet50在验证队列的AUC分别为0.783 vs 0.728。
  • SE-ResNet50与ResNet50在外部测试队列的AUC分别为0.806 vs 0.695。
  • 外部测试队列准确率SE-ResNet50 82.2% vs ResNet50 72.2%,SE-ResNet50提高10%。

临床应用与阅片要点

  • 作者认为基于CT超分辨的SE-ResNet50模型对预测实性或部分实性肺腺癌STAS状态有较大潜力。

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

RATIONALE AND OBJECTIVES: Spread through air space (STAS) is a novel invasive pattern of lung adenocarcinoma (LUAD), and preoperative knowledge of STAS status is helpful in choosing an appropriate surgical approach.

MATERIALS AND METHODS: This retrospective study collected and analyzed 602 patients diagnosed with LUAD from two medical centers: center 1 was randomly partitioned into training (n = 358) and validation cohorts (n = 154) at a 7:3 ratio; and center 2 was the external test cohort (n = 90). Super resolution was performed on all images to acquire high-resolution images, which were used to train the SE-ResNet50 model, before creating an equivalent parameter ResNet50 model. Disparities were compared between the two models using receiver operating characteristic curves, area under the curve, accuracy, precision, sensitivity, and specificity.

RESULTS: In this study, 512 and 90 patients with LUAD were enrolled from centers 1 and 2, respectively. The curve values of the SE-ResNet50 and ResNet50 models were compared for training, validation, and test cohorts, resulting in values of 0.933 vs 0.909, 0.783 vs 0.728, and 0.806 vs 0.695, respectively. In the external test cohort, the accuracy of the SE-ResNet50 model demonstrated a 10% improvement over the ResNet50 model (82.2% vs 72.2%).

CONCLUSION: The SE-ResNet50 model based on computed tomography super-resolution has great potential for predicting STAS status in patients with solid or partially solid LUAD, with superior predictive performance compared to traditional deep learning models.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Wang S, Liu X, Jiang C, et al. CT-Based Super-Resolution Deep Learning Models with Attention Mechanisms for Predicting Spread Through Air Spaces of Solid or Part-Solid Lung Adenocarcinoma. Acad Radiol. 2024. PMID: 38184418. doi:10.1016/j.acra.2023.12.034

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。