Rib fracture detection method and device, terminal equipment and readable storage medium

Abstract

The embodiment of the invention provides a rib fracture detection method and device, and the method comprises the steps: obtaining a to-be-detected chest image which is a direct digital X-ray image; inputting the chest image to be detected into a pre-trained rib fracture detection model, and determining a rib detection result; wherein the rib fracture detection model is obtained by training an initial neural network model by adopting chest images at multiple angles; according to the rib detection result, the rib fracture position in the chest image or the rib without fracture in the chest image can be judged, the chest images at different angles can be obtained, whether rib fracture exists in the chest images at different angles or not is detected independently, and the accuracy of rib fracture detection is improved. And then the chest images at several shooting angles are integrated to determine whether a fracture phenomenon exists, so that the recognition efficiency can be improved.

Description

technical field [0001] The present invention relates to the field of computer technology, and in particular, to a rib fracture detection method, device, terminal device and readable storage medium. Background technique [0002] Thoracic rib fractures are one of the common injuries, often occurring in middle-aged and elderly people. At present, it mainly uses imaging knowledge for screening. Most of the commonly used imaging screening methods in clinical practice are multi-slice spiral CT imaging. Multi-slice spiral CT images scan the human lungs one by one. It is very clear to find the specific location and deformation of rib fractures, which is helpful for accurate diagnosis and treatment; [0003] With the surge in the number of films taken in hospitals, the time-consuming and labor-intensive shortcomings of CT imaging diagnosis are increasingly unable to meet people's needs. Doctors are prone to misdiagnosis and missed diagnosis when they are tired, delaying the examinat...

AI Technical Summary

Problems solved by technology

[0003] With the rapid increase in the number of films taken in hospitals, the shortcomings of time-consuming and labor-intensive CT imaging diagnosis are increasingly unable to meet people's needs. Doctors are prone to misdiagnosis and missed diagnosis after fatigue, which delays the examination and treatment of rib fractures.

Based on this, most of the existing technical solutions are based on deep learning to detect rib fractures in CT image data. It needs to collect a large amount of CT image data in advance for 3D labeling, and then use deep convolutional neural network to perform rib fracture detection. Segmentation and judgment of rib fractures, and finally output the location and shape of rib fractures. In this way, not only a large number of sample images are required, but the training process is also relatively complicated. If there are a large number of images to be identified, the location of rib fractures cannot be quickly identified

Images