Jun Li1, Tian Sang2, Wen-Hui Yu3, Meng Jiang4, Shu-Yan Hunag5, Chun-Li Cao6, Ming Chen7, Yu-Wen Cao8, Xin-Wu Cui9, Christoph F Dietrich10. 1. Department of Ultrasound, the First Affiliated Hospital of Medical College, Shihezi University, Xinjiang, China. 1287424798@qq.com. 2. Department of Ultrasound, the First Affiliated Hospital of Medical College, Shihezi University, Xinjiang, China. 775153562@qq.com. 3. Department of Medical Ultrasound, Wuchang Hospital affiliated Wuhan University of Science and Technology, Wuhan, China. wuhanyuwenhui@sina.com. 4. Department of Medical Ultrasound, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan China. jiangmenghust@163.com. 5. Department of Ultrasound, The First People's Hospital of Huaihua, University of South China, Huaihua, China. shuyanh@163.com. 6. Department of Medical Ultrasound, the First Affiliated Hospital of Medical College, Shihezi University, Shihezi, China. 1820706964@qq.com. 7. Department of Medical Ultrasound, the First Affiliated Hospital of Medical College, Shihezi University, Shihezi, China. 894983774@qq.com. 8. Department of Medical Ultrasound, the First Affiliated Hospital of Medical College, Shihezi University, Shihezi, China. cywwb@126.com. 9. Department of Medical Ultrasound, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China. cuixinwu@live.cn. 10. Department of Internal Medicine, Hirslanden Clinic, Bern, Switzerland. christoph.dietrich@ckbm.de.
Abstract
AIM: To evaluate the value of S-Detect (a computer aided diagnosis system using deep learning) in breast ultrasound (US) for discriminating benign and malignant breast masses. MATERIAL AND METHODS: A literature search was performed and relevant studies using S-Detect for the differential diagnosis of breast masses were selected. The quality of included studies was assessed using a Quality Assessment of Diagnostic Accuracy Studies (QUADAS) questionnaire. Two review authors independently searched the articles and assessed the eligibility of the reports. RESULTS: A total of ten studies were included in the meta-analysis. The pooled estimates of sensitivity and specificity were 0.82 (95%CI: 0.77-0.87) and 0.86 (95%CI: 0.76-0.92), respectively. In addition, the diagnostic odds ratios, positive likelihood ratio and negative likelihood ratio were 28 (95%CI: 16- 49), 5.7 (95%CI: 3.4-9.5), and 0.21 (95%CI: 0.16-0.27), respectively. Area under the curve was 0.89 (95%CI: 0.86-0.92). No significant publication bias was observed. CONCLUSIONS: S-Detect exhibited a favourable diagnostic value in assisting physicians discriminating benign and malignant breast masses and it can be considered as a useful complement for conventional US.
AIM: To evaluate the value of S-Detect (a computer aided diagnosis system using deep learning) in breast ultrasound (US) for discriminating benign and malignant breast masses. MATERIAL AND METHODS: A literature search was performed and relevant studies using S-Detect for the differential diagnosis of breast masses were selected. The quality of included studies was assessed using a Quality Assessment of Diagnostic Accuracy Studies (QUADAS) questionnaire. Two review authors independently searched the articles and assessed the eligibility of the reports. RESULTS: A total of ten studies were included in the meta-analysis. The pooled estimates of sensitivity and specificity were 0.82 (95%CI: 0.77-0.87) and 0.86 (95%CI: 0.76-0.92), respectively. In addition, the diagnostic odds ratios, positive likelihood ratio and negative likelihood ratio were 28 (95%CI: 16- 49), 5.7 (95%CI: 3.4-9.5), and 0.21 (95%CI: 0.16-0.27), respectively. Area under the curve was 0.89 (95%CI: 0.86-0.92). No significant publication bias was observed. CONCLUSIONS: S-Detect exhibited a favourable diagnostic value in assisting physicians discriminating benign and malignant breast masses and it can be considered as a useful complement for conventional US.