Interactive liver segmentation method based on geodesic distance and V-net

Abstract

The invention discloses an interactive liver segmentation method based on geodesic distance and V-net, and provides an interactive liver segmentation algorithm based on geodesic distance and V-net bytaking V-net as a basis and combining a geodesic distance interactive segmentation algorithm, which comprises the following steps: firstly, enhancing the contrast of a liver image by using a window adjustment algorithm, and suppressing noise interference through Gaussian filtering; secondly, utilizing a three-dimensional segmentation network V-net for considering the characteristics of spatial context information effectively, and obtainiing a preliminary segmentation result of the liver image; thirdly, forming artificial hard constraint to correct a V-net segmentation result by utilizing the characteristics that an interactive segmentation method based on geodesic distance is simple, easy to implement and good in liver boundary response, and further taking a super-pixel block formed by a watershed algorithm as a sample point for operation, so that the algorithm efficiency is improved. Experimental results show that the algorithm can accurately segment a complete liver region, realizesan interactive liver image segmentation framework which is convenient for doctors to use clinically and has less user intervention and short time, has a good clinical use effect and has a wide application prospect.

Description

technical field [0001] The invention belongs to the technical field of image processing and pattern recognition, in particular to an interactive liver segmentation method based on geodesic distance and V-net. Background technique [0002] With the rapid development and wide application of medical imaging technology, imaging examination has become one of the essential means in clinical diagnosis and is widely used in the diagnosis of liver diseases. Through imaging data, the size, Lesions and other information, so as to serve as the doctor's initial diagnosis and treatment basis. At present, accurate and effective segmentation of the liver area is an important prerequisite for liver preoperative planning in clinical practice, so as to assist doctors in the diagnosis of liver disease patients, form accurate preoperative planning, intraoperative guidance, postoperative evaluation, and clinical operations. play an important guiding role. [0003] At present, researchers have p...

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the above-mentioned defects in the prior art, the object of the present invention is to provide an interactive liver segmentation method based on geodesic distance and V-net, and the V-net three-dimensional segmentation network can improve the general two-dimensional convolutional network. Taking into account the defects of the spatial context, the segmentation accuracy is improved, and the geodesic distance interactive segmentation algorithm combined with the watershed algorithm is used to form artificial hard constraints, which reduces the phenomenon of mis-segmentation and improves the accuracy of liver segmentation results. The clinical effect is good and it has a wide range of applications. prospect

Images