Deep learning estimation method and application thereof

Abstract

The invention belongs to the technical field of image imaging, and particularly relates to a deep learning estimation method and application thereof. A current novel coronavirus CT influence diagnosistechnology depends on a single image, and a doser needs to select a single image from CT sequence images to complete diagnosis estimation, so that a large amount of time of the doser is occupied; andfor a single patient, the error-tolerant rate of multi-frame continuous CT images for disease diagnosis is higher than that of a single image. The invention provides a deep learning estimation method. The deep learning estimation method comprises the steps of preprocessing symptom data and image data; fusing the symptom features and the image features; performing channel feature extraction on thefused data; designing a loss function; adopting an Adam optimization algorithm for optimization; constructing pairing as network input according to a patient data set; and training the network to obtain the deep learning estimation method. The accuracy can be improved by combining the symptom information of a patient, and meanwhile the symptom information of the patient can be rapidly obtained clinically.

Description

technical field [0001] The present application belongs to the field of image imaging technology, and in particular relates to a deep learning estimation method and its application. Background technique [0002] CT examination is a more advanced modern medical scanning examination technology, mainly for scanning the human brain. CT examinations generally include unenhanced CT, enhanced CT, and cisternal contrast CT. CT scans a layer of a certain thickness of a certain part of the human body with an X-ray beam. The X-rays that pass through this layer are received by the detector and converted into visible light, which is converted from photoelectricity into an electrical signal, and then passed through an analog / digital converter (analog / digitalconverter) into digital and input to computer for processing. [0003] Imaging examination is one of the quick and convenient means of medical diagnosis. Chest X-ray examination has a high rate of missed diagnosis. CT, especially hig...

AI Technical Summary

Problems solved by technology

[0006] Based on the fact that the current COVID-19 CT diagnosis technology relies on a single image, it is necessary for the pharmacist to select a single image from the CT sequence images to complete the diagnosis estimate, which takes up a lot of time for the pharmacist; Diagnosis is a problem with a higher error tolerance rate than a single image. This application provides a deep learning prediction method and its application

Images