Urinary sediment image recognition system and method based on deep learning

Abstract

The invention relates to the field of medical image processing, in particular to a urinary sediment image recognition system and a urinary sediment image recognition method based on deep learning. Animage acquisition module acquires the urine sample to obtain an original image. An image segmentation module performs segmentation processing on the original image to obtain a segmented urinary sediment component image. An image recognition module based on deep learning is used for recognizing the segmented urinary sediment component images and integrating recognition results of the three networkmodels to obtain output of the image recognition module based on deep learning. A counting module performs statistical processing on the output result to obtain a quantitative medical index reference.The system outputs the result of the image recognition module and the result of the counting module based on deep learning. According to the method, end-to-end feature extraction and classification can be automatically realized, and tiny features, which are difficult to find by naked eyes, in visible components of the urinary sediment are effectively extracted, so that the problem of complex classification of 11 urinary sediment components is solved with high quality, and the method has very high medical application value.

Description

technical field [0001] The invention relates to the field of medical image processing, in particular to a system and method for recognizing urine sediment images based on deep learning. Background technique [0002] Urine sediment detection technology refers to the use of a microscope to examine the sediment of the centrifuged urine sample, and to detect, classify and count the formed components in the sediment, so as to provide quantitative indicators for the judgment of related diseases. It is one of the routine testing items in hospitals. one. The urinary sediment components detected in the patient's urine sample will provide important reference information for the doctor's diagnosis, for example: increased red blood cells detected in the urine sediment will indicate urinary tract bleeding; increased white blood cells will indicate urinary system infection; red blood cells, oxalic acid A large number of calcium or calcium phosphate crystals and transparent casts can be i...

AI Technical Summary

Problems solved by technology

At present, deep learning has achieved remarkable research and application results in many medical fields. However, although there are some attempts in urine sediment recognition, they perform poorly in some evaluation indicators, and there are fewer types of effective classification, and the speed is slower. Slow, poor support for Windows platform, difficult to meet clinical needs

Images