Xie Jiang, Shi Huachan, Du Chengrun, Song Xiangshuai, Wei Jinzhu, Dong Qi, Wan Caifeng
School of Computer Engineering and Science, Shanghai University, Shanghai, China.
Department of Radiation Oncology, Fudan University Shanghai Cancer Center, Shanghai, China.
Front Oncol. 2022 Apr 7;12:812463. doi: 10.3389/fonc.2022.812463. eCollection 2022.
The early prediction of a patient's response to neoadjuvant chemotherapy (NAC) in breast cancer treatment is crucial for guiding therapy decisions. We aimed to develop a novel approach, named the dual-branch convolutional neural network (DBNN), based on deep learning that uses ultrasound (US) images for the early prediction of NAC response in patients with locally advanced breast cancer (LABC). This retrospective study included 114 women who were monitored with US during pretreatment (NAC ) and after one cycle of NAC (NAC). Pathologic complete response (pCR) was defined as no residual invasive carcinoma in the breast. For predicting pCR, the data were randomly split into a training set and test set (4:1). DBNN with US images was proposed to predict pCR early in breast cancer patients who received NAC. The connection between pretreatment data and data obtained after the first cycle of NAC was considered through the feature sharing of different branches. Moreover, the importance of data in various stages was emphasized by changing the weight of the two paths to classify those with pCR. The optimal model architecture of DBNN was determined by two ablation experiments. The diagnostic performance of DBNN for predicting pCR was compared with that of four methods from the latest research. To further validate the potential of DBNN in the early prediction of NAC response, the data from NAC and NAC were separately assessed. In the prediction of pCR, the highest diagnostic performance was obtained when combining the US image information of NAC and NAC (area under the receiver operating characteristic curve (AUC): 0.939; 95% confidence interval (CI): 0.907, 0.972; F1-score: 0.850; overall accuracy: 87.5%; sensitivity: 90.67%; and specificity: 85.67%), and the diagnostic performance with the combined data was superior to the performance when only NAC (AUC: 0.730; 95% CI: 0.657, 0.802; F1-score: 0.675; sensitivity: 76.00%; and specificity: 68.38%) or NAC (AUC: 0.739; 95% CI: 0.664, 0.813; F1-score: 0.611; sensitivity: 53.33%; and specificity: 86.32%) (p<0.01) was used. As a noninvasive prediction tool, DBNN can achieve outstanding results in the early prediction of NAC response in patients with LABC when combining the US data of NAC and NAC.
在乳腺癌治疗中，早期预测患者对新辅助化疗（NAC）的反应对于指导治疗决策至关重要。我们旨在基于深度学习开发一种名为双分支卷积神经网络（DBNN）的新方法，该方法使用超声（US）图像对局部晚期乳腺癌（LABC）患者的NAC反应进行早期预测。这项回顾性研究纳入了114名女性，她们在预处理（NAC）期间和NAC一个周期后接受了超声监测。病理完全缓解（pCR）定义为乳腺中无残留浸润性癌。为了预测pCR，数据被随机分为训练集和测试集（4:1）。提出了利用US图像的DBNN来早期预测接受NAC的乳腺癌患者的pCR。通过不同分支的特征共享来考虑预处理数据与NAC第一个周期后获得的数据之间的联系。此外，通过改变两条路径的权重来强调不同阶段数据的重要性，以对pCR患者进行分类。DBNN的最佳模型架构通过两个消融实验确定。将DBNN预测pCR的诊断性能与最新研究中的四种方法进行了比较。为了进一步验证DBNN在早期预测NAC反应方面的潜力，分别评估了NAC 和NAC的数据。在预测pCR时，结合NAC 和NAC的US图像信息可获得最高的诊断性能（受试者操作特征曲线下面积（AUC）：0.939；95%置信区间（CI）：0.907, 0.972；F1分数：0.850；总体准确率：87.5%；灵敏度：90.67%；特异性：85.67%），并且结合后的数据的诊断性能优于仅使用NAC （AUC：0.730；95% CI：0.657, 0.802；F1分数：0.675；灵敏度：76.00%；特异性：68.38%）或NAC（AUC：0.739；95% CI：0.664, 0.813；F1分数：0.611；灵敏度：53.33%；特异性：86.32%）时的性能（p<0.01）。作为一种非侵入性预测工具，当结合NAC 和NAC的US数据时，DBNN在早期预测LABC患者的NAC反应方面可取得出色结果。
