Design And Implementation Of B-Ultrasound Aided Diagnosis System For Muscle Strain

In modern medical diagnosis,it is a common diagnostic method to judge the specific condition of a patient through medical image detection.In the past,when doctors viewed B-ultrasound images of muscle strain,they often analyzed patient images with clinical knowledge and experience.Detection of patients in this way is more difficult and requires higher requirements for doctors.Through the investigation of medical image detection products at home and abroad,combined with the characteristics of B-ultrasound images,the needs of the B-ultrasound auxiliary diagnosis system for muscle strain were analyzed.The system is divided into five functional modules:personal information management,patient information management,B-ultrasound image management,B-ultrasound image detection and B-ultrasound image analysis.The personal information management module performs differentiated management for the users of the software.The patient information management and B-ultrasound image management module mainly manages and stores patient information and B-ultrasound images of patients.The B image detection and analysis module is combined with deep learning algorithms to complete the lesion detection for patients.The algorithm mainly uses the knowledge of deep learning,combined with the muscle strain detection data set of patients provided by the hospital,and is divided into two steps:detection and filtering.The detection algorithm adopts the single-target detection YoloV3 algorithm.The filtering algorithm mainly combines the characteristics of the B-ultrasound image for the candidate area.Further filtering makes the result more accurate.The system is developed based on the classic MVC framework.Finally,the function and performance of the system are tested respectively,and the test results show that the system meets the expectations.The muscle strain B-ultrasound auxiliary diagnosis system provides a brand-new detection service for doctors,which is an exploration of combining medical treatment and artificial intelligence.Through the system’s auxiliary detection,it can promote the improvement of doctors’ diagnostic level and reduce the work pressure of doctors.