The method and system are suitable for quality classification of spinal metastasis tumor sclerotin

Abstract

The invention provides a quality classification method and system suitable for spinal metastasis tumor sclerotin. The method comprises the following steps: obtaining CT image data of a patient from aDICOM file, and cutting an area of a vertebral body according to a threshold extraction method; modeling the bone quality classification task into an osteogenesis classification subtask and an osteolysis classification subtask, and combining results of the two subtasks by using a multi-layer perceptron; for each CT image with the cross section, a multi-task learning mode is used, a bone quality classification task and a rear outer side damage condition classification task are learned at the same time, and feature maps of different tasks are shared; a self-step learning mode is used, so that the model preferentially learns samples easy to learn and then gradually learns samples difficult to learn. According to the method, a plurality of related tasks are learned at the same time, features are shared, and a self-stepping learning method from easy to difficult is used, so that accurate classification of spinal metastasis tumor bone quality is realized.

Description

technical field [0001] The present invention relates to the field of computer vision and medical image analysis, in particular to a method and system suitable for bone mass classification of spinal metastatic tumors, especially a bone mass classification method for spinal metastatic tumors based on multi-task learning and self-paced learning Classification. Background technique [0002] The incidence and mortality of cancer in my country are increasing year by year. Since 2010, cancer has become the leading cause of death. Metastasis is the spread of cancer from one part of the body to another, and about two-thirds of cancer patients develop bone metastases. The spine is the most common site of bone metastases. Spinal metastases may cause pain, spinal instability, and nerve damage. Therefore, early diagnosis of spinal metastases is crucial to change patient prognosis and improve clinical outcomes. The Spinal Instability Tumor Scoring System (SINS) was proposed in 2017 to e...

AI Technical Summary

Problems solved by technology

The present invention cannot realize accurate classification of bone quality of spinal metastases

Images