Deformity urine erythrocyte classification statistics method and system

Abstract

The invention belongs to the technical field of artificial intelligence assisted medical examination, and discloses a malformed urine erythrocyte classification statistics method and system. The method comprises the following steps: S1, collecting a microscope zoom video of a sample; S2, identifying abnormal urine erythrocytes on the frame with the highest definition in all frames of the microscope zoom video, and segmenting a plurality of abnormal urine erythrocyte zoom videos; S3, predicting the probability of each frame in each deformed urine erythrocyte zoom video under different classifications by utilizing a deep multi-example learning algorithm; and S4, realizing classification and quantity statistics of deformed urine erythrocytes through a target-shaped key frame priority principle. The method can accurately detect, classify and count the abnormal urine red blood cells in the sample, is accurate and reliable, and can be applied to the field of urine sample detection.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence-assisted medical examination, and specifically relates to a method of using the zoom video of a urine sample of a kidney disease patient under a microscope as analysis data, and combining with a deep multi-instance learning algorithm to classify abnormal urine red blood cells in the urine sample Methods of identification and quantification. Background technique [0002] Patients with kidney disease are often accompanied by occult blood in urine and hematuria. Under the microscope, there are a large number of deformed urine red blood cells caused by the extrusion of glomerulus and other tissues in the urine samples of patients with kidney disease. The abnormal type and quantity of urinary red blood cells can more accurately reflect the type and degree of renal lesions. Therefore, the classification and statistics of abnormal urinary red blood cells in urine samples of patients with ...

AI Technical Summary

Problems solved by technology

Therefore, it is difficult to accurately classify and count abnormal urine red blood cells based only on microscope image data and traditional digital image processing algorithms, and thus cannot effectively reduce the workload of professional physicians, and cannot effectively relieve the pressure of physical examination for kidney disease patients in areas where medical resources are scarce.

Images