Urine visible component recognition method based on improved Alexnet model

Abstract

The invention relates to the field of medical image processing, in particular to a urine visible component recognition method based on an improved Alexnet model. The method comprises the following steps: 1, acquiring and expanding an image data set, and constructing a urinary sediment image training set and a test set; 2, constructing a urine visible component recognition network model based on anAlexnet network model; 3, setting training parameters of the urine visible component recognition network model; 4, training a urine visible component recognition network model based on an Alexnet network model; 5, testing a urine visible component recognition network model based on the Alexnet network model. The method is improved on the basis of an Alexnet network model and reduces the number ofnetwork training parameters. The method can automatically extract image features, has the characteristics of high recognition rate, short recognition time and strong generalization ability, and has important application prospects for assisting medical diagnosis and reducing the burden of doctors.

Description

technical field [0001] The invention relates to the field of medical image processing, in particular to a method for identifying urine formed components based on an improved Alexnet model. Background technique [0002] The formed components in the concentrated urine obtained by centrifugation are called urine sediment. The examination of urine formed components is one of the routine inspection items in the hospital. It can help clinicians understand the changes in various parts of the urinary system, and is helpful for assisting urinary system diseases. The localization diagnosis, differential diagnosis and prognosis judgment play an important role. There are many kinds of formed components visible under microscope in urine, some of which have clear pathological significance, such as bacteria, red blood cells, white blood cells, etc., which have very important diagnostic value. Therefore, the identification and accurate classification of urine formed elements play an import...

AI Technical Summary

Problems solved by technology

[0003] Since the conventional urine formed component detection method is to observe the picture under a microscope or take a picture through a camera device, observe and manually identify the picture, the workload of this method is heavy, the operation is cumbersome, and it is easily affected by the difference in the level of technicians, which is easy to cause The problem of missed detection and false detection, and the sharp increase in medical images also increases the difficulty of manual recognition

With the development of computer technology, many methods for automatic analysis of urine sediment images have emerged, but the existing methods still need to manually extract image features and manually select classifiers for classification

The working process of these automated methods is complex and easily affected by technicians, so more effective identification methods of urine formed components are needed to reduce the workload of pathologists

Images