Blood smear full-view intelligent analysis method

Abstract

The invention discloses a blood smear full-view intelligent analysis method which comprises the following steps: acquiring a plurality of original blood smear single-view images, establishing an original blood smear single-view image group, and establishing a blood smear full-view image based on the plurality of original blood smear single-view images; constructing an image restoration model basedon the first training set and the first verification set; constructing an image segmentation model based on the second training set and the second verification set, obtaining a third training set anda third verification set based on the plurality of segmented single blood cell images, and constructing an image recognition model; finally, acquiring a blood cell classification result. Full-view blood cells are analyzed on the basis of an artificial intelligence algorithm, interference of human factors is greatly reduced, objectivity of an inspection result is improved, and blood cell analysisand classification accuracy is high; recognition and analysis can be achieved for picture input meeting the requirements, the algorithm robustness and accuracy are higher than those of a traditional image recognition algorithm, an existing medical examination process is overturned, and the overall time is greatly shortened.

Description

technical field [0001] The invention relates to the technical field of blood cell testing, in particular to a full-view intelligent analysis method for a blood smear. Background technique [0002] In the current blood cell testing technology, the recognition rate of blood cells is low and there are many human interference factors. The existing equipment cannot analyze the full field of view of the blood smear, and the accuracy of the test results is not high. At present, the blood test process in the hospital is: blood sample - blood analyzer - push dye machine - manual microscopic examination, and the whole process takes 60 minutes. Manually draw blood from the patient to obtain blood samples; obtain various blood cell counts, white blood cell classification and hemoglobin content through a blood analyzer; dye and mark through a push-dye machine to obtain a blood smear for manual microscopic examination; finally, professional doctors After manual microscopic examination, t...

AI Technical Summary

Problems solved by technology

Comprehensive method: This type of instrument is a highly comprehensive application of a variety of advanced cell analysis techniques, with more analysis parameters for blood cells, but the objectivity of the test results is insufficient and the recognition accuracy is not high, and it cannot completely replace manual microscopy

[0004] In the existing technology, the efficiency of manual re-inspection is too low, and the subjective factors in the identification process are too large, which makes it extremely susceptible to interference from subjective experience and human factors

First, the analysis and counting of blood cells in the full field of view of the blood smear has not been realized, and the data sample size is not enough, resulting in one-sided results that are not comprehensive and accurate; second, the counting and classification algorithms are relatively traditional, and the effect of morphological analysis is poor, and the recognition accuracy is low. Not high; the third is that the subjectivity of manual microscopic examination doctors cannot be controlled, and the re-examination rate is high; the fourth is that the time is long and the efficiency is low

Images