Related Experiment Video
Updated: Jul 15, 2025
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
Published on: April 21, 2023
Deep Learning-assisted Diagnosis of Breast Lesions on US Images: A Multivendor, Multicenter Study
Huiling Xiang1, Xi Wang1, Min Xu1
1From 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.).
Purpose:
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.
Materials And Methods:
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 (n = 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.
Results:
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 (P < .001) for one experienced and three novice radiologists and improved interobserver agreement. The average false-positive rate was reduced by 7.6% (P = .08).
Conclusion:
The DL model may help radiologists, especially novice readers, improve accuracy and interobserver agreement of breast tumor diagnosis using US.Keywords: Ultrasound, Breast, Diagnosis, Breast Cancer, Deep Learning, Ultrasonography Supplemental material is available for this article. © RSNA, 2023.
Related Concept Videos
01:24Imaging Studies II: Ultrasonography
01:17Ultrasonography
During an ultrasonography procedure, a handheld device called...