文献速递乳腺乳腺X线

基于卷积神经网络算法在乳腺X线数据集上用于导管原位癌观察试验患者筛选的潜在作用

Potential Role of Convolutional Neural Network Based Algorithm in Patient Selection for DCIS Observation Trials Using a Mammogram Dataset.
PubMed 文献 · Acad Radiol · 2019-09-14

本研究为经IRB批准的回顾性研究,使用123例患者的246张乳腺X线放大图像训练卷积神经网络,以区分单纯导管原位癌与手术升级为浸润癌的导管原位癌。算法诊断准确率74.6%(95%CI ±5),AUC 0.71(95%CI ±0.04),特异度91.6%(95%CI ±5%),敏感度49.4%(95%CI ±6%)。结论认为应用卷积神经网络以高特异度区分单纯导管原位癌与伴浸润的导管原位癌是可行的。

要点

  • 卷积神经网络区分单纯DCIS与手术升级为浸润癌的DCIS,特异度91.6%、敏感度49.4%。
  • 算法使用CC和ML/LM两个标准乳腺X线放大视图的钙化灶,分割后缩放到128×128像素边界框。
  • 总体诊断准确率74.6%(95%CI ±5),AUC 0.71(95%CI ±0.04)。

核心结论

  • 应用卷积神经网络基于乳腺X线图像以高特异度区分单纯DCIS与伴浸润的DCIS是可行的。

研究设计与样本

  • 经IRB批准的回顾性研究,使用123例患者的246张独特图像;单纯DCIS组82例患者164张图像,隐匿浸润组41例患者82张图像;采用CC和ML/LM两个标准乳腺X线放大视图;以立体定向引导下钙化灶活检诊断及手术切除最终诊断为参考标准;使用3D Slicer分割钙化灶,15个隐藏层拓扑、5个残差层、每个卷积后dropout为0.25,五折交叉验证(训练集80%、验证集20%),Keras与TensorFlow在Linux工作站NVIDIA GTX 1070 Pascal GPU上实现。

关键影像表现/征象

  • 分析对象为乳腺X线放大视图(CC和ML/LM)上的钙化灶,经3D Slicer分割并缩放到128×128像素边界框。
  • 单纯DCIS组为立体定向引导下钙化灶活检诊断DCIS且手术切除时无升级的患者。
  • 隐匿浸润组为乳腺X线钙化灶最终手术升级诊断为隐匿性浸润癌的患者。

诊断标准与关键数值

  • 卷积神经网络预测单纯DCIS的总体诊断准确率74.6%(95%CI ±5)。
  • AUC为0.71(95%CI ±0.04)。
  • 特异度91.6%(95%CI ±5%),敏感度49.4%(95%CI ±6%)。

临床应用与阅片要点

  • 原文结论认为应用卷积神经网络以高特异度区分单纯DCIS与伴浸润的DCIS是可行的。

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: We investigated the feasibility of utilizing convolutional neural network (CNN) for predicting patients with pure Ductal Carcinoma In Situ (DCIS) versus DCIS with invasion using mammographic images.

MATERIALS AND METHODS: An IRB-approved retrospective study was performed. 246 unique images from 123 patients were used for our CNN algorithm. In total, 164 images in 82 patients diagnosed with DCIS by stereotactic-guided biopsy of calcifications without any upgrade at the time of surgical excision (pure DCIS group). A total of 82 images in 41 patients with mammographic calcifications yielding occult invasive carcinoma as the final upgraded diagnosis on surgery (occult invasive group). Two standard mammographic magnification views (CC and ML/LM) of the calcifications were used for analysis. Calcifications were segmented using an open source software platform 3D Slicer and resized to fit a 128 × 128 pixel bounding box. A 15 hidden layer topology was used to implement the neural network. The network architecture contained five residual layers and dropout of 0.25 after each convolution. Five-fold cross validation was performed using training set (80%) and validation set (20%). Code was implemented in open source software Keras with TensorFlow on a Linux workstation with NVIDIA GTX 1070 Pascal GPU.

RESULTS: Our CNN algorithm for predicting patients with pure DCIS achieved an overall diagnostic accuracy of 74.6% (95% CI, ±5) with area under the ROC curve of 0.71 (95% CI, ±0.04), specificity of 91.6% (95% CI, ±5%) and sensitivity of 49.4% (95% CI, ±6%).

CONCLUSION: It's feasible to apply CNN to distinguish pure DCIS from DCIS with invasion with high specificity using mammographic images.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Mutasa S, Chang P, Van Sant EP, et al. Potential Role of Convolutional Neural Network Based Algorithm in Patient Selection for DCIS Observation Trials Using a Mammogram Dataset. Acad Radiol. 2019. PMID: 31526687. doi:10.1016/j.acra.2019.08.012

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。