Computer Science Unit, Faculty of Engineering, University of Mons, Mons, Belgium.
Jules Bordet Institute, Brussels, Belgium.
Int J Comput Assist Radiol Surg. 2020 Sep;15(9):1491-1500. doi: 10.1007/s11548-020-02209-9. Epub 2020 Jun 16.
Neoadjuvant chemotherapy (NAC) aims to minimize the tumor size before surgery. Predicting response to NAC could reduce toxicity and delays to effective intervention. Computational analysis of dynamic contrast-enhanced magnetic resonance images (DCE-MRI) through deep convolution neural network (CNN) has shown a significant performance to distinguish responders and no responder's patients. This study intends to present a new deep learning (DL) model predicting the breast cancer response to NAC based on multiple MRI inputs.
A cohort of 723 axial slices extracted from 42 breast cancer patients who underwent NAC therapy was used to train and validate the developed DL model. This dataset was provided by our collaborator institute of radiology in Brussels. Fourteen external cases were used to validate the best obtained model to predict pCR based on pre- and post-chemotherapy DCE-MRI. The model performance was assessed by area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, and feature map visualization.
The developed multi-inputs deep learning architecture was able to predict the pCR to NAC treatment in the validation dataset with an AUC of 0.91 using combined pre- and post-NAC images. The visual results showed that the most important extracted features from non-pCR tumors are in the peripheral region. The proposed method was more productive than the previous ones.
Even with a limited training dataset size, the proposed and developed CNN model using DCE-MR images acquired before and after the first chemotherapy was able to classify pCR and non-pCR patients with substantial accuracy. This model could be used hereafter in clinical analysis after its evaluation based on more extra data.
新辅助化疗（NAC）旨在手术前缩小肿瘤体积。预测对 NAC 的反应可以减少毒性和延迟有效干预。通过深度卷积神经网络（CNN）对动态对比增强磁共振成像（DCE-MRI）进行的计算分析已显示出区分应答者和无应答者患者的显著性能。本研究旨在提出一种新的深度学习（DL）模型，该模型基于多个 MRI 输入预测乳腺癌对 NAC 的反应。
使用从接受 NAC 治疗的 42 名乳腺癌患者中提取的 723 个轴向切片的队列来训练和验证所开发的 DL 模型。该数据集由我们在布鲁塞尔的放射学合作研究所提供。使用 14 个外部病例来验证基于化疗前后 DCE-MRI 预测 pCR 的最佳获得模型。通过接收者操作特征曲线（AUC）、准确性、灵敏度、特异性和特征图可视化评估模型性能。
所开发的多输入深度学习架构能够使用联合的化疗前后图像在验证数据集中预测 NAC 治疗的 pCR，AUC 为 0.91。可视化结果表明，来自非 pCR 肿瘤的最重要提取特征位于外周区域。该方法比以前的方法更有效。
即使使用有限的训练数据集大小，使用在第一次化疗前后获得的 DCE-MRI 图像的所提出和开发的 CNN 模型也能够以相当高的准确度对 pCR 和非 pCR 患者进行分类。该模型可以在基于更多额外数据进行评估后，用于以后的临床分析。
