Children intussusception automatic detection system based on deep learning

The invention discloses a children intussusception automatic detection system based on deep learning, and the system comprises a trained concentric circle detection model, which is used for detecting concentric circles in a children abdominal ultrasonic image; wherein the concentric circle detection model comprises a feature extraction network, a region generation network RPN and an ROI Pooling layer; wherein the feature extraction network adopts a VGG16 convolutional neural network, a jump connection layer is added in the convolutional neural network, and shallow features and deep features of the convolutional neural network are combined through the jump connection layer. According to the model constructed by the invention, the concentric circle sign of a children abdominal intussusception ultrasonic image is automatically detected, a doctor is assisted in identification, and the diagnosis speed for a child intussusception patient is improved while the reading time of manual evaluation is shortened. 本发明公开了一种