Slice image processing method and device, training method and device and storage medium

Abstract

The invention provides a slice image processing method and device, a training method and device and a storage medium. The method comprises the steps of obtaining a slice image of a case; and processing the slice image by using a preset slice image analysis model so as to sketch the lymphatic drainage area of the case in the slice image. It is understandable that although CTVs (Clinical Target Volume, clinical target regions) of cervical cancer, prostate cancer, bladder cancer and the like are different,, the range of lymphatic drainage regions in CTVs of the tumors is common; therefore, the slice image analysis model can be set for the lymphatic drainage areas of the tumors, the slice images are processed through the slice image analysis model, the lymphatic drainage areas of the tumors are accurately and automatically sketched, the sketching workload of doctors is reduced, and the sketching efficiency is improved. In addition, by automatically sketching the lymphatic drainage area, standard sketching of the lymphatic drainage area can be further standardized.

Description

technical field [0001] The present application relates to the technical field of image processing, and in particular, to a processing method, training method, device, and storage medium for sliced ​​images. Background technique [0002] Pelvic tumors include a variety of common primary tumors, including: rectal cancer, cervical cancer, prostate cancer, and more. In order to implement precise radiotherapy, for these tumors, doctors need to outline the areas where the radiotherapy target areas of these tumors are located in the patient's slice images. [0003] There are two main difficulties in the delineation of the tumor target volume. The first is that the CTV (Clinical Target Volume, clinical target volume) of different tumors is quite different, and it is impossible to unify the CTV of these different tumors. It is difficult for machine learning to accurately and automatically delineate the CTV. The second is to adopt the method of manually delineating the target area l...

AI Technical Summary

Problems solved by technology

[0003] There are two main difficulties in the delineation of the tumor target volume. The first is that the CTV (Clinical Target Volume, clinical target volume) of different tumors is quite different, and it is impossible to unify the CTV of these different tumors. Machine learning struggles to accurately and automatically delineate CTV

The second is to adopt the method of manually drawing the target area layer by layer by doctors, which often takes several hours to complete a case, which is time-consuming and laborious

Therefore, in the current situation where medical resources are becoming more and more tense, continuing to use manual delineation of target volumes can no longer meet the actual clinical needs, and it is necessary to explore and study more reasonable and efficient automatic target delineation methods

Images