Skin ultrasonic image segmentation method based on improved UNet network model

• Main Authors: WANG WENSAI, XING ENMING, ZHOU SHENG, YANG JUN, WANG XIAOCHUN, WANG LINGXIAO
• Format: Patent
• Language: Chinese; English
• Published: 25.12.2020
• Subjects: CALCULATING; COMPUTING; COUNTING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS

The invention discloses a skin ultrasonic image segmentation method based on an improved UNet network model, and the method comprises the steps: collecting a two-dimensional ultrasonic image of humanskin through a 50MHz skin ultrasonic biological microscope, and dividing the images into a verification set, a test set and a training set according to the proportion of 1: 1: 8; manually labeling theverification set, the test set and the training set to label a corium layer and an epidermal layer; performing data enhancement on the verification set and the training set after manual annotation through gray scale transformation and left and right overturning operation; inputting the verification set and the training set with enhanced data into the improved UNet model for training; and taking the model parameters obtained by training as a prediction model, and inputting the test set into the prediction model for image segmentation to obtain a segmentation result. According to the method, the network becomes wider an