Glomerular cell image recognition method based on deep neural network

Abstract

The invention discloses a glomerular cell image recognition method based on a deep neural network, and the method comprises the steps: obtaining a to-be-detected pathological image based on an artificial intelligence and deep learning technology; preprocessing the pathological image to obtain a plurality of slice images; inputting each slice image into a preset neural network model for identification and segmentation to obtain a glomerular region map; carrying out cell counting on the glomerular region map; Sub-images of the glomerulus in the kidney in the pathological image can be quickly andaccurately segmented, and cells in the glomerulus are counted by using a traditional method and a deep learning fusion model, so that the problems of large workload, low efficiency and high misdiagnosis rate of artificial identification of the glomerulus in the pathological image are solved; the invention optimizes the algorithm of glomerular sub-image segmentation and glomerular cell counting inpathological images, uses more data training algorithms, improves the accuracy of segmentation and counting, and relates to the field of biomedical image processing.

Description

technical field [0001] The invention relates to the technical fields of biomedical image processing and deep learning, in particular to a glomerular cell image recognition method based on a deep neural network. Background technique [0002] The rapid development of modern medicine has made detection methods and display methods more accurate, more intuitive and more perfect. Medical images of the human body contain extremely rich human body information. After the images are obtained with the help of medical imaging technology, they need to be analyzed, identified, segmented, calibrated, classified, and interpreted. For the clinical application of medical images and the medical problems that need to be solved, determine Which parts should be enhanced or which features should be extracted to provide more intuitive data. It can be used as the basis for rationally arranging patient examination procedures, so as to achieve the most objective diagnosis purpose with the fastest spe...

AI Technical Summary

Problems solved by technology

At present, the accuracy of glomerulus segmentation and its cell segmentation and technology still needs to be improved, and it cannot reach the practical level. Further optimization is needed to improve the accuracy of glomerulus segmentation and realize intrasphere cell counting.

It has three main defects: 1. The traditional way of identifying glomeruli in pathological images by doctors with naked eyes is heavy workload and low efficiency, and as the fatigue of observers increases, the rate of misdiagnosis will also increase

2. The accuracy of the current glomerular segmentation and glomerular cell counting algorithms is not high, and needs to be optimized to improve the accuracy of segmentation and counting

3. Due to the large size of the pathological image and the dense cells in the glomerulus, the recognition rate is low with the traditional single neural network method, and it needs to be better recognized through a specific post-processing method after deep learning segmentation

Images