Lung subsection airway topology reconstruction method and system

Abstract

The invention discloses a lung subsection airway topology reconstruction method and system, and belongs to the technical field of medical image processing, and the method comprises the steps: obtaining a lung subsection airway path CT image; a 3D U-Net + + segmentation network is constructed, the network comprises an input layer, a down-sampling layer, an up-sampling layer and an output layer which are connected in sequence, the up-sampling layer comprises four up-sampling modules, and a bronchial tree topology constraint loss layer is arranged in each module; a target detection algorithm based on Faster R-CNN is adopted for the segmented image, and three-dimensional coordinates of the airway center point are obtained; the method comprises the following steps of: acquiring airway topological information by utilizing a topological constraint function based on coordinates, deeply fusing topological constraint into a 3D U-Net + + segmentation network, and combining a self-attention convolution mechanism and a target detection algorithm based on Faster R-CNN, thereby effectively solving the problems of airway fracture, topological errors and the like in a traditional method, and improving the accuracy of the method. The accuracy and integrity of lung subsection airway reconstruction are remarkably improved, and particularly, the reconstruction effect on subsection bronchus with the diameter larger than 0.8 mm is obvious.

Images