Qian Lang, Lv Zhikun, Zhang Kai, Wang Kun, Zhu Qian, Zhou Shichong, Chang Cai, Tian Jie
Department of Ultrasonography, Fudan University Shanghai Cancer Center, Shanghai, China.
Department of Oncology, Fudan University, Shanghai Medical College, Shanghai, China.
Ann Transl Med. 2021 Feb;9(4):295. doi: 10.21037/atm-20-3981.
To develop an ultrasound-based deep learning model to predict postoperative upgrading of pure ductal carcinoma in situ (DCIS) diagnosed by core needle biopsy (CNB) before surgery.
Of the 360 patients with DCIS diagnosed by CNB and identified retrospectively, 180 had lesions upstaged to ductal carcinoma in situ with microinvasion (DCISM) or invasive ductal carcinoma (IDC) postoperatively. Ultrasound images obtained from the hospital database were divided into a training set (n=240) and validation set (n=120), with a ratio of 2:1 in chronological order. Four deep learning models, based on the ResNet and VggNet structures, were established to classify the ultrasound images into postoperative upgrade and pure DCIS. We obtained the area under the receiver operating characteristic curve (AUROC), specificity, sensitivity, accuracy, positive predictive value (PPV), and negative predictive value (NPV) to estimate the performance of the predictive models. The robustness of the models was evaluated by a 3-fold cross-validation.
Clinical features were not significantly different between the training set and the test set (P value >0.05). The area under the receiver operating characteristic curve of our models ranged from 0.724 to 0.804. The sensitivity, specificity, and accuracy of the optimal model were 0.733, 0.750, and 0.742, respectively. The three-fold cross-validation results showed that the model was very robust.
The ultrasound-based deep learning prediction model is effective in predicting DCIS that will be upgraded postoperatively.
开发一种基于超声的深度学习模型，以预测术前经粗针穿刺活检（CNB）诊断的纯导管原位癌（DCIS）术后的病理升级情况。
回顾性纳入360例经CNB诊断为DCIS的患者，其中180例术后病理升级为伴有微浸润的导管原位癌（DCISM）或浸润性导管癌（IDC）。从医院数据库获取的超声图像按时间顺序以2:1的比例分为训练集（n = 240）和验证集（n = 120）。基于ResNet和VggNet结构建立了四个深度学习模型，将超声图像分类为术后升级和纯DCIS。我们通过计算受试者操作特征曲线下面积（AUROC）、特异性、敏感性、准确性、阳性预测值（PPV）和阴性预测值（NPV）来评估预测模型的性能。通过3折交叉验证评估模型的稳健性。
训练集和测试集的临床特征无显著差异（P值>0.05）。我们模型的受试者操作特征曲线下面积在0.724至0.804之间。最佳模型的敏感性、特异性和准确性分别为0.733、0.750和0.742。3折交叉验证结果表明该模型非常稳健。
基于超声的深度学习预测模型在预测术后会发生病理升级的DCIS方面是有效的。
