ObjectiveTo develop mobile phone terminal application software using artificial intelligence (AI) model of breast ultrasound so as to provide an opportunity for early diagnosis of patients with breast cancer irrespective of time and space. MethodsThe ultrasonic electronic images of patients underwent operation in the Department of Breast Surgery of West China Hospital of Sichuan University from January 2018 to April 2019 were collected. The neural network deep learning algorithm was used to train and test the breast ultrasonic electronic images at a ratio of 4∶1 to establish DeepBC model, and a mobile phone terminal application software was developed according to the trained DeepBC model, which included image reconstruction module, image classification module, and missed diagnosis module to identify and diagnose the uploaded ultrasonic electronic images. Results A total of 4 128 ultrasonic electronic images were collected in this study, including 3 302 in the training set and 826 in the test set. The accuracy, sensitivity, specificity, false positive rate, and false negative rate of the DeepBC model for the identification of malignant and non-malignant lesions in the breast ultrasound images were 93.70%, 93.10%, 94.08%, 5.92%, and 6.90%, respectively. The optimal cut-off value was 92.31% by receiver operating characteristic curve of DeepBC model and the area of receiver operating characteristic curve was 0.987. The DeepBC mobile phone terminal application software was developed according to the DeepBC model, and the web page was released in the mobile wechat. So far, more than 10 000 people had uploaded ultrasonic electronic images on the wechat web page, and the diagnosis had exceeded 30 000 times. ConclusionsIn this study, an AI DeepBC model is established successfully based on ultrasonic electronic images, each module of mobile phone terminal application software runs well and independently. And web page is simple and contents are easy to be comprehended.