基于卷积神经网络与两中心迁移学习的DCE-MRI乳腺癌分子亚型预测
研究纳入244例乳腺癌患者,训练集99例于1.5 T扫描,测试集1为83例、测试集2为62例于3 T扫描,按激素受体和HER2状态分为HR+/HER2-、HER2+和三阴性三类,比较常规CNN与CLSTM在DCE序列上分类的准确性。训练集中CLSTM十折交叉验证平均准确率0.91高于CNN的0.79;独立测试时准确率仅0.4-0.5,经迁移学习再调参后测试集1平均准确率达CNN 0.91、CLSTM 0.83,测试集2由CNN 0.47提升至0.78、由CLSTM 0.39提升至0.74,总体迁移学习使分类准确率提升超过30%。
要点
- 训练集中CLSTM平均准确率0.91,高于常规CNN的0.79。
- 独立测试集直接应用模型准确率仅0.4-0.5。
- 迁移学习再调参后准确率提升超过30%。
核心结论
- CLSTM可追踪DCE采集过程中信号强度的变化,训练阶段准确率高于常规CNN,迁移学习可对模型再调参并提高不同采集设置数据集的准确率。
研究设计与样本
- 回顾性分析244例乳腺癌患者,训练集99例于1.5 T扫描,测试集1为83例、测试集2为62例于3 T扫描。
- 按激素受体和HER2受体状态分为HR+/HER2-、HER2+和三阴性三类亚型。
- 仅使用DCE序列图像,以覆盖肿瘤ROI的最小包围盒作为深度学习输入,采用常规CNN和卷积长短期记忆网络(CLSTM)建模。
- 在测试集1与测试集2之间相互应用迁移学习再调参并评估。
关键影像表现/征象
- 仅使用DCE序列图像,以覆盖肿瘤ROI的最小包围盒作为模型输入,未报告具体影像征象。
诊断标准与关键数值
- 训练集十折交叉验证平均准确率:CLSTM 0.91,CNN 0.79。
- 模型直接应用于独立测试集时准确率为0.4-0.5。
- 经测试集1再调参迁移学习后,平均准确率CNN达0.91、CLSTM达0.83。
- 测试集2准确率经迁移学习由CNN 0.47提升至0.78、由CLSTM 0.39提升至0.74。
- 总体迁移学习使分类准确率提升超过30%。
临床应用与阅片要点
- 原文未据此给出推荐。
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
OBJECTIVES: To apply deep learning algorithms using a conventional convolutional neural network (CNN) and a recurrent CNN to differentiate three breast cancer molecular subtypes on MRI.
METHODS: A total of 244 patients were analyzed, 99 in training dataset scanned at 1.5 T and 83 in testing-1 and 62 in testing-2 scanned at 3 T. Patients were classified into 3 subtypes based on hormonal receptor (HR) and HER2 receptor: (HR+/HER2-), HER2+, and triple negative (TN). Only images acquired in the DCE sequence were used in the analysis. The smallest bounding box covering tumor ROI was used as the input for deep learning to develop the model in the training dataset, by using a conventional CNN and the convolutional long short-term memory (CLSTM). Then, transfer learning was applied to re-tune the model using testing-1(2) and evaluated in testing-2(1).
RESULTS: In the training dataset, the mean accuracy evaluated using tenfold cross-validation was higher by using CLSTM (0.91) than by using CNN (0.79). When the developed model was applied to the independent testing datasets, the accuracy was 0.4-0.5. With transfer learning by re-tuning parameters in testing-1, the mean accuracy reached 0.91 by CNN and 0.83 by CLSTM, and improved accuracy in testing-2 from 0.47 to 0.78 by CNN and from 0.39 to 0.74 by CLSTM. Overall, transfer learning could improve the classification accuracy by greater than 30%.
CONCLUSIONS: The recurrent network using CLSTM could track changes in signal intensity during DCE acquisition, and achieved a higher accuracy compared with conventional CNN during training. For datasets acquired using different settings, transfer learning can be applied to re-tune the model and improve accuracy.
KEY POINTS: • Deep learning can be applied to differentiate breast cancer molecular subtypes. • The recurrent neural network using CLSTM could track the change of signal intensity in DCE images, and achieved a higher accuracy compared with conventional CNN during training. • For datasets acquired using different scanners with different imaging protocols, transfer learning provided an efficient method to re-tune the classification model and improve accuracy.
引用
- Zhang Y, Chen JH, Lin Y, et al. Prediction of breast cancer molecular subtypes on DCE-MRI using convolutional neural network with transfer learning between two centers. Eur Radiol. 2020. PMID: 33001309. doi:10.1007/s00330-020-07274-x
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。