Soft tissue sarcoma grade judgment method based on machine learning

Abstract

The invention provides a soft tissue sarcoma grade judgment method based on machine learning. The method comprises the steps of carrying out the typical feature extraction of a soft tissue sarcoma image, obtaining the typical features of the soft tissue sarcoma images of all patients in a sampling sample, forming a sample data set, carrying out the preprocessing of the sample data set, dividing the preprocessed sample data set into a test set and a training set, based on the generated training set, constructing machine learning models by adopting different machine learning algorithms respectively and training the machine learning models, and substituting the generated test set into the plurality of constructed machine learning models respectively for calculation to obtain a predicted valuecalculated by each machine learning model, calculating the difference between the predicted value and a true value, and selecting the machine learning model with the minimum difference as a soft tissue sarcoma grade judgment model. Excellent experience of doctors and experts can be accumulated so as to be conveniently copied to other small cities and small hospitals to be popularized and used, the diagnosis accuracy is improved, and then the cure rate of patients is increased.

Description

Technical field [0001] The invention belongs to the field of medical technology, and more particularly to a method of judgment based on machine-learning-based soft tissue grade judgment. Background technique [0002] Soft tissue sarcoma is derived from fat, fascia, muscle, fiber, lymph and blood vessels, and the incidence of about 3 / 100,000, which is highly malignant, can be found in any age, any part, if you don't get timely diagnosis and treatment, you have to Forced to be amputated, it has become an important threat to human health. Soft tissue sarcoma lesions are judged by nuclear magnetic resonance MRI image characteristics is an important basis for reasonable treatment programs. However, according to the nuclear magnetic resonance MRI image characteristics, the soft tissue sarcoma level judgment is achieved. There are mainly two aspects: (1) The accuracy of the sarcoma lesion is determined, and it is often dependent on the ability and experience of diagnosis of doctors. The...

AI Technical Summary

Problems solved by technology

[0003] The invention provides a method for judging the grade of soft tissue sarcoma based on machine learning, which solves the problem that the judgment accuracy rate is unstable due to the ability and experience of doctors to judge the grade of sarcoma lesions

Images