Lung tumor recognition method based on support vector machine MRI image segmentation

[0026] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments, but the present invention is not limited to the following specific embodiments.

[0027] A lung tumor identification method based on support vector machine MRI image segmentation, that is, a support vector machine MRI image segmentation method used in the lung tumor identification process, which is essentially a segmentation optimization method for lung MRI images, It includes the following steps:

[0028] (1), establish the standard signal-to-noise ratio data collection of known lung MRI images;

[0029] A, segment a plurality of lung MRI images by traditional method; Described traditional method is mark watershed method, also can be other conventional image segmentation methods;

[0030] B. Judging by the doctor's naked eyes whether the image segmented in step A is accurate, and if it is accurate, it will be included in the correct image set;