Lung segmentation method

Abstract

The invention provides a lung segmentation method, comprising following steps: step S1, inputting an original image, carrying out preprocessing to the original image; step S2, carrying out coarse segmentation to a lung region, wherein the step S2 comprises: step S201, setting a threshold value, using the threshold value to carrying out segmentation, carrying out binarization processing to the preprocessed image, extracting the lung region and partial background similar to the gray value of the lung region; step S202, carrying out background backfill starting from the edges at four corners of the image; step S203, finding out a layer of lung with maximum area in the z direction from the top of the head downwards; step S204, carrying out forward and backward layer-by-layer region growth in the z direction by the maximum layer of lung, judging layer by layer, preventing adhesion with the background; step S3, carrying out fine segmentation to the lung region so as to extract and remove trachea and separate left and right lungs. According to the settings, the segmentation speed is increased; and the segmentation effect is improved.

Description

technical field [0001] The invention relates to the processing of tomography (Computed Tomography, CT for short) images in the medical field, in particular to a method for segmenting lungs in the images. Background technique [0002] In recent years, because computed tomography technology can provide high-definition, high-contrast CT images, it is usually used in the diagnosis of lung diseases. The observation of lung structure and functional characteristics with the help of chest CT is an important auxiliary means for various lung diseases in clinical practice. The original chest CT images usually include background, lung tissue, fat, muscle, blood vessels, trachea, bones, etc., in order to provide doctors with To provide reliable diagnostic data, which is conducive to early detection and treatment of patients' conditions, it usually requires subsequent processing of chest CT images to extract and segment lung tissue images. [0003] In the prior art, for 3D CT data, (1) t...

AI Technical Summary

Problems solved by technology

This method can extract image features of some data, but requires a large number of training samples, the segmentation results are highly dependent on samples and features, and the processing time is long

(4) The method based on image registration and shape model, which generally works well, but it is affected by the training set data, which will lead to large variability in the results, difficulty in establishing the model, and a large amount of calculation, resulting in slow speed and difficulty Meet the real-time requirements of clinical applications

Images