A segmentation method, device and equipment based on image data

Abstract

The embodiment of this specification discloses a segmentation method, device and equipment based on image data. The method includes: acquiring CTA image data to be processed; inputting the CTA image data to be processed into a segmentation model, segmenting the CTA image data to be processed, and obtaining three segmentation results, wherein the segmentation model It is a three-segmentation model obtained in advance through neural network training based on a semi-automatic labeling method. The three-segmentation results are the segmentation results of bone tissue, blood vessels and calcified tissue of the CTA image data to be processed. By adopting the segmentation method provided in this manual, the segmentation of bone tissue, calcified tissue and blood vessels can be automatically realized, which greatly saves analysis time and has high accuracy.

Description

Technical field [0001] This specification relates to the field of medical imaging and computer technology, and more particularly to a segmentation method, apparatus, and apparatus based on image data. Background technique [0002] CTA (Computer Fault Scanning Blood Vections) Image data is important in the clinic, which can serve as auxiliary diagnostic means for clinical treatment of intracranial aneurysms. Since the bone tissue in the brain imaging affects the results of clinical diagnosis, in order to achieve better diagnostic results, the diagnostic error is reduced, and the bone tissue in the craniocerebral image data is often required. [0003] In the prior art, the bone of the CTA image data generally uses two sets of images, and the bone tissue is removed by decomposing. Specifically, the cleaning CT image data (NCCT) and the CTA video data are utilized, where the NCCT image is an image that does not need to inject the contrast agent, the CTA image is an image of the injec...

AI Technical Summary

Problems solved by technology

[0005] The embodiment of this specification provides a segmentation method, device, and equipment based on image data, which are used to solve the following technical problems: two CT scans are required, which increases the radiation dose of the patient; the position of the bone removal image does not match easily, resulting in bone removal The bone effect becomes worse, and even needs to be re-scanned; the error is large, and it is difficult to distinguish the calcified part from the bone tissue

Images