End-to-end chest CT image segmentation method based on fully convolutional neural network

Abstract

The invention discloses an end-to-end chest CT image segmentation method based on a fully convolutional neural network. The method comprises the steps of firstly performing clinic scanning for obtaining k sets of chest CT images, and dividing each set of CT images according to each slice as a training sample; then performing manual cutting on each training sample and a testing sample by professional medical care personnel, dividing the image to four parts, namely a lung part, a tracheae art, a skin part and a background part; then constructing an end-to-end fully convolutional neural network for training marked chest CT training data, and obtaining a trained parameter model; separating the slices of the scanned CT image, and inputting the slices into the trained model one by one, and obtaining segmented output models; and finally combining the output models, thereby obtaining a segmented chest CT image model. The convolutional neural network model which utilizes an image neighborhood content for performing characteristic extraction can perform dense predication on the chest CT image and furthermore simplifies an image segmentation process.

Description

technical field [0001] The invention belongs to the field of medical image processing, and in particular relates to an end-to-end chest CT image segmentation method based on a fully convolutional neural network. Background technique [0002] With the continuous and rapid development of medical imaging and computer technology, the use of computer technology to analyze clinical image data has improved the probability of successful disease prevention and treatment. Computed tomography (CT) is most commonly used in the diagnosis and detection of thoracic diseases. Since CT can provide high-resolution scanning images for various organs or tissues of the chest, it is very important to make full use of CT scanning images for the detection of lung diseases, such as lung cancer, pulmonary nodules and other diseases. In the computer-aided diagnosis system, accurate segmentation of lung CT scan images is the basis and premise of subsequent chest function analysis and three-dimensional...

AI Technical Summary

Problems solved by technology

However, these segmentation methods also have certain shortcomings. The detection of concave and convex points is more sensitive to the deformation model. The parameters and initialization of each model in the curvature analysis method will have certain errors. The Snake model does not have a standardized segmentation process, and the segmentation results will appear. certain error

Images