Xiang Huiling, Wang Xi, Xu Min, Zhang Yuhua, Zeng Shue, Li Chunyan, Liu Lixian, Deng Tingting, Tang Guoxue, Yan Cuiju, Ou Jinjing, Lin Qingguang, He Jiehua, Sun Peng, Li Anhua, Chen Hao, Heng Pheng-Ann, Lin Xi
From the Departments of Ultrasound (H.X., C.L., L.L., T.D., C.Y., J.O., Q.L., A.L., X.L.) and Pathology (J.H., P.S.), Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangzhou, China; Zhejiang Laboratory, Hangzhou, China (X.W.); Department of Radiation Oncology, Stanford University School of Medicine, Stanford, Palo Alto, Calif (X.W.); Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, China (X.W., P.A.H.); Department of Ultrasound Medicine, The First Affiliated Hospital, College of Medicine, Zhejiang University, Hangzhou, China (M.X.); Key Laboratory of Precision Diagnosis and Treatment for Hepatobiliary and Pancreatic Tumor of Zhejiang Province, Hangzhou, China (M.X.); Department of Ultrasound Medicine, The Third People's Hospital of Zhengzhou, Cancer Hospital of Henan University, Zhengzhou, China (Y.Z.); Department of Ultrasound, Hubei Cancer Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China (S.Z.); Department of Ultrasound and Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, China (G.T.); and Department of Computer Science and Engineering and Department of Chemical and Biological Engineering, The Hong Kong University of Science and Technology, Hong Kong, China (H.C.).
Radiol Artif Intell. 2023 Jul 12;5(5):e220185. doi: 10.1148/ryai.220185. eCollection 2023 Sep.
To evaluate the diagnostic performance of a deep learning (DL) model for breast US across four hospitals and assess its value to readers with different levels of experience.
In this retrospective study, a dual attention-based convolutional neural network was built and validated to discriminate malignant tumors from benign tumors by using B-mode and color Doppler US images ( = 45 909, March 2011-August 2018), acquired with 42 types of US machines, of 9895 pathologic analysis-confirmed breast lesions in 8797 patients (27 men and 8770 women; mean age, 47 years ± 12 [SD]). With and without assistance from the DL model, three novice readers with less than 5 years of US experience and two experienced readers with 8 and 18 years of US experience, respectively, interpreted 1024 randomly selected lesions. Differences in the areas under the receiver operating characteristic curves (AUCs) were tested using the DeLong test.
The DL model using both B-mode and color Doppler US images demonstrated expert-level performance at the lesion level, with an AUC of 0.94 (95% CI: 0.92, 0.95) for the internal set. In external datasets, the AUCs were 0.92 (95% CI: 0.90, 0.94) for hospital 1, 0.91 (95% CI: 0.89, 0.94) for hospital 2, and 0.96 (95% CI: 0.94, 0.98) for hospital 3. DL assistance led to improved AUCs ( < .001) for one experienced and three novice radiologists and improved interobserver agreement. The average false-positive rate was reduced by 7.6% ( = .08).
The DL model may help radiologists, especially novice readers, improve accuracy and interobserver agreement of breast tumor diagnosis using US. Ultrasound, Breast, Diagnosis, Breast Cancer, Deep Learning, Ultrasonography © RSNA, 2023.
评估深度学习（DL）模型在四家医院对乳腺超声的诊断性能，并评估其对不同经验水平读者的价值。
在这项回顾性研究中，构建并验证了一种基于双重注意力的卷积神经网络，以使用B模式和彩色多普勒超声图像（n = 45909，2011年3月至2018年8月）区分恶性肿瘤和良性肿瘤，这些图像由42种超声机器采集，来自8797例患者（27名男性和8770名女性；平均年龄，47岁±12[标准差]）的9895例经病理分析证实的乳腺病变。在有和没有DL模型辅助的情况下，三名超声经验少于5年的新手读者和两名分别有8年和18年超声经验的有经验读者对1024个随机选择的病变进行了解读。使用DeLong检验测试受试者工作特征曲线（AUC）下面积的差异。
使用B模式和彩色多普勒超声图像的DL模型在病变水平上表现出专家级性能，内部数据集的AUC为0.94（95%CI：0.92，0.95）。在外部数据集中，医院1的AUC为0.92（95%CI：0.90，0.94），医院2的AUC为0.91（95%CI：0.89，0.94），医院3的AUC为0.96（95%CI：0.94，0.98）。DL辅助使一名有经验的放射科医生和三名新手放射科医生的AUC提高（P <.001），并提高了观察者间的一致性。平均假阳性率降低了7.6%（P =.08）。
DL模型可能有助于放射科医生，尤其是新手读者，提高使用超声诊断乳腺肿瘤的准确性和观察者间的一致性。超声、乳腺、诊断、乳腺癌、深度学习、超声检查 ©RSNA，2023。
