Intelligent medical auxiliary diagnosis system based on deep learning

Abstract

The invention discloses an intelligent medical auxiliary diagnosis system based on deep learning, wherein the system relates to the field of intelligent medical technology. The system comprises a consultation room upper computer, a laboratory upper computer, a film reading room upper computer, a blood drawing registering machine, a blood examination instrument and a CT instrument. The consultationroom upper computer is in wireless communication connection with the laboratory upper computer and the film reading room upper computer. The laboratory upper computer is in communication connection with the blood examination instrument. The film reading room upper computer is in communication connection with the CT instrument. According to the intelligent medical auxiliary diagnosis system, a blood examination analysis result is obtained through a DNN predicting module of the laboratory upper computer by means of a DNN characteristic model, and furthermore a U-net model segmenting module of the film reading room upper computer utilizes a U-net model for performing segmenting processing on a CT image for obtaining a segmenting graph. Finally an auxiliary diagnosis module of the consultation room upper computer analyzes a disease suffering probability according to the blood examination analysis result, the CT image and the segmenting graph thereof by means of a medical knowledge database, thereby reducing diagnosis difficulty, reducing error diagnosis probability and improving diagnosis accuracy.

Description

technical field [0001] The invention belongs to the field of intelligent medical technology, in particular to an intelligent medical auxiliary diagnosis system based on deep learning. Background technique [0002] In recent years, as deep learning has set off wave after wave in the field of artificial intelligence, many other disciplines have achieved breakthrough development. In the medical field, medical diagnosis in the past mainly relied on the subjective judgment of doctors. The accuracy of diagnosis depends on the knowledge and experience of doctors, and there is a lack of accurate quantitative analysis. Taking medical imaging CT as an example, it is difficult for even experienced doctors to accurately distinguish all diseased areas from normal areas, which makes diagnosis difficult and delays the treatment of patients and even affects surgery. Now, classification, detection, and segmentation based on deep learning have been widely used in various medical diagnoses du...

AI Technical Summary

Problems solved by technology

Taking medical imaging CT as an example, it is difficult for even experienced doctors to accurately distinguish all diseased areas from normal areas, which not only makes diagnosis difficult, but also delays the treatment of patients and even affects surgery.

Images