Automatic sketching method of medial lymphatic drainage area based on deep learning network

Abstract

The invention discloses an automatic sketching method of a medial lymphatic drainage area based on a deep learning network, the automatic sketching method is suitable for a CT image, and the automatic sketching method comprises the following steps: S1, collecting CT image data and a medial lymphatic drainage area image manually labeled by a doctor, and preprocessing the CT image data and the medial lymphatic drainage area image manually labeled by the doctor; S2, grouping the preprocessed CT image data to obtain a training set, a verification set and a test set; S3, performing data enhancement on the training set, the verification set and the test set; S4, constructing a deep learning segmentation model; and S5, inputting the CT image data in the training set and the image of the mediastinal lymphatic drainage area manually labeled by the doctor into the constructed deep learning segmentation model, after training iterative convergence, storing the segmentation model of the mediastinal lymphatic drainage area, and then performing identification and prediction of the mediastinal lymphatic drainage area to obtain a probability graph of each subarea of the mediastinal lymphatic drainage area. The network can better position and segment the small drainage area.

Description

technical field [0001] The invention relates to the field of medical images, in particular to an automatic delineation method of a mediastinal lymphatic drainage area based on a deep learning network. Background technique [0002] In the field of radiotherapy, precise tumor radiotherapy technology can effectively improve the curative effect of patients and reduce toxic and side effects, while precise radiotherapy relies on precise target contours. In the process of delineating the target area, it is necessary to carefully delineate the target area with reference to the drainage range of the drainage area. In addition, the mediastinal lymphatic drainage area also plays a very important role in the formulation of clinical staging and treatment principles for patients with lung cancer. Therefore, the automatic delineation of the drainage area has very important clinical significance. This method helps clinicians to delineate the mediastinal drainage area quickly, accurately a...

AI Technical Summary

Problems solved by technology

[0004] First, the sketching speed is slow, which consumes a lot of precious time for doctors; second, the accuracy of sketching depends on the doctor's clinical experience, and requires a lot of prior clinical knowledge; third, there are large differences in the results drawn by the same doctor in different states. difference

Fourth, human error is inevitable

Images