Lymph node partitioning method, device and equipment and computer readable storage medium

Abstract

The invention provides a lymph node partitioning method which comprises the following steps: determining contour information of each sample organ and contour information of each target organ, each sample organ being each organ in thoracic cavities at two sides of a longitudinal diaphragm of a sample, and each target organ being each organ in thoracic cavities at two sides of a target longitudinaldiaphragm; generating a transformation matrix from the contour information of each sample organ to the contour information of each target organ; partitioning the target longitudinal diaphragm according to the transformation matrix to obtain a target longitudinal diaphragm partitioning result; and partitioning each target lymph node based on the target longitudinal partition result. Visibly, each target lymph node can be automatically partitioned, the defects of manual partitioning are avoided, and the accuracy of lymph node partitioning results is improved.

Description

technical field [0001] The present application relates to the field of computer technology, and in particular to a lymph node partition method, device, equipment and computer-readable storage medium. Background technique [0002] Cancer, also known as malignant tumor, is a serious threat to human health, among which lung cancer is one of the malignant tumors that threaten the health and life of the population the most. According to the statistics of cancer incidence and death in 2018, the incidence and mortality of lung cancer in Chinese men rank first, while the incidence and mortality among women rank second. At the same time, in the world, the morbidity and mortality of lung cancer are also at the top of the list. According to statistics, 90% of cancer-related death records are related to malignant tumor metastasis, which is one of the difficulties in current cancer research. [0003] Lymph nodes are important immune organs of the human body. The study of lung lymph nod...

AI Technical Summary

Problems solved by technology

For this reason, the International Association for the Study of Lung Cancer formulated the seventh edition of the standard in 2009, which divides thoracic lymph nodes into 14 regions for the purpose of guiding lymph node partitioning, standardizing inspection, and facilitating analysis of its metastasis path. However, the standard does not propose any The automatic partition algorithm only partitions the lymph nodes from a medical point of view

[0004] The existing lymph node division mainly relies on manual labeling by doctors, which not only takes a long time, but also consumes too much energy; in addition, from the perspective of image labeling, due to the large number of lymph nodes and large differences between individuals, and there are different Due to the large differences in doctors’ understanding of the divisions and the blurred areas between different divisions, the labeling results of different doctors may vary widely.

Images