Nasopharyngeal carcinoma three-dimensional dose distribution prediction method based on segmentation task assistance

Abstract

The invention relates to a nasopharyngeal carcinoma three-dimensional dose distribution prediction method based on segmentation task assistance. The nasopharyngeal carcinoma three-dimensional dose distribution prediction method specifically comprises the steps of collecting an original nasopharyngeal carcinoma image and marking the original nasopharyngeal carcinoma image; constructing a dose distribution prediction model, wherein the prediction model comprises an auxiliary segmentation network, a dose prediction network and an adversarial network, the segmentation network and the prediction network share encoder network parameters, shared representation information between a segmentation task and a dose prediction task are obtained through joint training of the segmentation task and the dose prediction task, the feature expression capability of a shared encoder is enhanced, and the network is promoted to mine essential features with an auxiliary function for dose prediction in the segmentation task to the maximum extent under limited training data. Meanwhile, in order to effectively utilize feature information of a prediction decoder under different scales, a multi-scale iterativefusion IMF strategy is provided at a prediction task decoder end, and a more accurate prediction result is obtained.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a segmentation task-assisted three-dimensional dose distribution prediction method for nasopharyngeal carcinoma. Background technique [0002] Medical image segmentation is an important field of image processing. The research purpose of this field is to segment the important information of the patient's condition in the medical image, and provide scientific basis for clinical diagnosis and treatment, which is of great value for doctors to judge the condition. In tumor treatment, radiation therapy is the most effective and safest treatment technique for patients' health, and its non-invasive and low-toxicity characteristics have also been affirmed by the medical community. Administering radiation therapy strictly according to the prescribed dose is the key to successful treatment. However, the dose control in clinical radiotherapy is a difficult topic, and the existing research re...

AI Technical Summary

Problems solved by technology

However, these two prediction models also have their own shortcomings. The former does not consider the impact of the organs at risk around the target area, and the latter cannot effectively use the anatomical characteristics of the tumor and organs at risk.

Images