Clavicle upper arm plexus nerve recognition method and system based on deep learning

Abstract

The invention relates to the technical field of neural ultrasonic image recognition, and discloses a clavicle upper arm plexus nerve recognition method and system based on deep learning, and the method comprises the steps: preprocessing an original medical image of clavicle upper arm plexus nerves, and forming a training image required for training a Pixel CNN + + convolutional neural network model; constructing a convolutional neural network, constructing a convolutional neural network by using a Pixel CNN + + algorithm, loading a training set into the Pixel CNN + + convolutional neural network model, determining model parameters of the Pixel CNN + + convolutional neural network, and deploying a trained Pixel CNN + + convolutional neural network model. The accuracy of recognition can be improved, the recognition speed of subsequent similar images can be increased, and recognition is more accurate and efficient.

Description

technical field [0001] The present invention relates to the technical field of nerve ultrasonic image recognition, and more specifically, it relates to a deep learning-based recognition method and system for the supraclavicular brachial plexus. Background technique [0002] With the rapid development of computer science and technology, people began to use the powerful computing power of computers to realize human recognition skills, especially in medical image processing and analysis and automatic recognition, which played an extremely important role in medical diagnosis. [0003] Ultrasound imaging can display images of the internal tissue structure of the human body in real time and non-invasively. It is very suitable for guiding various anesthesia puncture catheters and targeted drug injection techniques, and has been widely used in clinical anesthesia. When analyzing medical images, the clinician manually analyzes and aims at the target structure in the ultrasound image,...

AI Technical Summary

Problems solved by technology

Due to limited ultrasound resolution, many artifacts, common nerve variations, and the similarity of nerve echoes to those of surrounding connective tissue and fascia, it is difficult to identify the supraclavicular brachial plexus in ultrasound images, and operators need to have extensive experience to do so. Correct identification requires a lot of time and energy to receive relevant training, which is a job that can only be done by senior doctors

At the same time, in the traditional image processing method, the method of processing the image according to some operators is limited by many conditions, resulting in the inability to analyze the ultrasound image accurately and efficiently.

Images