Li Chunxiao, Guo Yuanfan, Jia Liqiong, Yao Minghua, Shao Sihui, Chen Jing, Xu Yi, Wu Rong
Department of Ultrasound, Shanghai General Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
Shanghai Key Lab of Digital Media Processing and Transmission, Shanghai Jiao Tong University, Shanghai, China.
Front Physiol. 2022 Jun 2;13:882648. doi: 10.3389/fphys.2022.882648. eCollection 2022.
A convolutional neural network (CNN) can perform well in either of two independent tasks [classification and axillary lymph-node metastasis (ALNM) prediction] based on breast ultrasound (US) images. This study is aimed to investigate the feasibility of performing the two tasks simultaneously. We developed a multi-task CNN model based on a self-built dataset containing 5911 breast US images from 2131 patients. A hierarchical loss (HL) function was designed to relate the two tasks. Sensitivity, specificity, accuracy, precision, F1-score, and analyses of receiver operating characteristic (ROC) curves and heatmaps were calculated. A radiomics model was built by the PyRadiomics package. The sensitivity, specificity and area under the ROC curve (AUC) of our CNN model for classification and ALNM tasks were 83.5%, 71.6%, 0.878 and 76.9%, 78.3%, 0.836, respectively. The inconsistency error of ALNM prediction corrected by HL function decreased from 7.5% to 4.2%. Predictive ability of the CNN model for ALNM burden (≥3 or ≥4) was 77.3%, 62.7%, and 0.752, and 66.6%, 76.8%, and 0.768, respectively, for sensitivity, specificity and AUC. The proposed multi-task CNN model highlights its novelty in simultaneously distinguishing breast lesions and indicating nodal burden through US, which is valuable for "personalized" treatment.
卷积神经网络（CNN）基于乳腺超声（US）图像，在两项独立任务（分类和腋窝淋巴结转移（ALNM）预测）中的任何一项上都能表现出色。本研究旨在探讨同时执行这两项任务的可行性。我们基于一个自建数据集开发了一个多任务CNN模型，该数据集包含来自2131名患者的5911幅乳腺US图像。设计了一种分层损失（HL）函数来关联这两项任务。计算了灵敏度、特异性、准确率、精确率、F1分数，并对接收器操作特征（ROC）曲线和热图进行了分析。通过PyRadiomics软件包建立了一个放射组学模型。我们的CNN模型在分类和ALNM任务中的灵敏度、特异性和ROC曲线下面积（AUC）分别为83.5%、71.6%、0.878和76.9%、78.3%、0.836。经HL函数校正后，ALNM预测的不一致误差从7.5%降至4.2%。CNN模型对ALNM负荷（≥3或≥4）的预测能力，在灵敏度、特异性和AUC方面分别为77.3%、62.7%和0.752，以及66.6%、76.8%和0.768。所提出的多任务CNN模型突出了其通过超声同时区分乳腺病变和指示淋巴结负荷的新颖性，这对“个性化”治疗具有重要价值。
