Rapid nodule matching method based on nodule characteristics

Abstract

The invention discloses a rapid nodule matching method based on nodule characteristics. The method comprises the steps that a first lung CT image and a second lung CT image which meet preset conditions are acquired; lung segmentation and lung frame scaling are performed on the first lung CT image and the second lung CT image, so that lung regions of the first lung CT image and the second lung CT image are aligned, and a transfer function is obtained; adjacent nodules of the two CT images are found out according to the transfer function, and a normalized cross correlation coefficient of the adjacent nodules is calculated; and whether the adjacent nodules are matched nodule pairs or not is judged according to the relationship between the normalized cross correlation coefficient and the threshold. According to the invention, a lung alignment method of lung segmentation and lung frame scaling is adopted, so that the time required for lung position alignment caused by an iterative algorithmis greatly reduced.

Description

technical field [0001] The invention relates to a method for matching pulmonary nodules, in particular to a fast nodule matching method based on nodule features. Background technique [0002] The existing nodule matching method mainly aligns the lung regions in the two CT images at different times by performing rigid body or non-rigid body registration on the lung images, so as to align the lung regions in the two images. The position points are matched, and finally the nodules with the closest position are selected as the matched nodule pairs. Chinese patent CN105913442A is a method for automatic matching of pulmonary nodules, which discloses the rigid body registration of two sets of images to align the image position information, obtain the deformation field, and perform nodule matching according to the nodule center and the deformation field. The rigid body registration of the above-mentioned patent adopts the gradient descent method, and the transformation coefficient ...

AI Technical Summary

Problems solved by technology

The rigid body registration of the above-mentioned patent adopts the gradient descent method, and the transformation coefficient is solved through an iterative process, and the iteration takes a lot of time

Moreover, the lung CT image is a relatively large 3D image, which makes the iterative algorithm more computationally intensive and time-consuming, and cannot meet the requirements of short-term calculation of large batches of data in clinical practice.

[0003] Secondly, the follow-up registration of nodules is only based on position matching. For some cases where the position is close, but the actual nodule has been absorbed or newly added, it will lead to wrong judgments.

Images