Image processing device, method and equipment, ultrasonic system and readable storage medium

Abstract

The invention discloses an image processing device, method and equipment, ultrasonic equipment, an ultrasonic system and a readable storage medium, and the device comprises: an obtaining module whichis used for obtaining a to-be-processed ultrasonic image of the liver; the segmentation and classification module that is used for carrying out classification and segmentation on the to-be-processed liver ultrasonic image to obtain a segmentation image and a target classification result corresponding to the to-be-processed liver ultrasonic image, wherein the target classification result comprisesa lesion disease classification result or a liver lesion-free result, and the lesion disease classification result comprises a liver echinococcosis disease classification result or a non-liver echinococcosis disease classification result; and when the target classification result is a disease classification result of a focus, the segmented image comprises a liver contour segmentation line and a focus contour segmentation line. According to the invention, the segmentation and classification module is utilized to identify lesions of liver echinococcosis and other liver space occupying disease types, so that the misdiagnosis rate and the missed diagnosis rate are reduced; and the liver contour is segmented in the segmented image, so that the accuracy of the focus contour is improved.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to an image processing device, method, equipment, ultrasonic equipment, ultrasonic system and a readable storage medium. Background technique [0002] In recent years, with the vigorous development of deep learning technology, image recognition algorithms based on deep learning are gradually applied to ultrasound image diagnosis, which has the characteristics of high recognition rate and fast speed. Hepatic hydatid disease is a common zoonotic parasitic disease in pastoral areas, which has caused serious economic losses to corresponding countries and regions all year round. At present, the screening and diagnosis of hepatic echinococcosis mainly rely on imaging examinations. Among them, ultrasound imaging technology has the advantages of non-invasiveness, no radiation, and low price, and is the preferred technology for the diagnosis of hepatic echinococcosis. [0003] In ...

AI Technical Summary

Problems solved by technology

[0003] In the prior art, the deep learning-based liver echinococcosis image recognition system mainly uses algorithms such as target detection, which can only identify the lesions of the liver echinococcosis species, and can only identify the lesions of the liver echinococcosis species. The lesions of diseases such as hepatic cysts, hepatocellular carcinoma, and hilar cholangiocarcinoma have no ability to identify, the ability to identify is not high, and it is easy to cause problems such as misdiagnosis and missed diagnosis.

Images