Cerebrospinal fluid cell image automatic identification and counting method

Abstract

The invention discloses a cerebrospinal fluid cell image automatic identification and counting method. The method comprises the following steps: 1, preprocessing an original cerebrospinal fluid cell image and storing the original cerebrospinal fluid cell image as an original image set; 2, segmenting a single cell image from the cerebrospinal fluid cell original image set obtained in the step 1 according to a labeling result, and storing the single cell image as a segmented image set according to a cell type; 3, correspondingly dividing the cerebrospinal fluid cell original image set obtained in the step 1 and the cerebrospinal fluid cell segmented image set obtained in the step 2 into a training set, a verification set and a test set; 4, constructing a convolutional neural network by usinga Pytorch deep learning framework; 5, constructing a convolutional neural network by using a Pytorch deep learning framework; 6, inputting a segmented test set obtained in the step 4 into the classification network obtained in the step 5; and 7, obtaining the positions of the cells in the segmented test set and segmentation, classification and counting results obtained in the step 5 according tothe single cerebrospinal fluid cell original image. According to the method, the accuracy of cell identification can be improved under the condition that the number of samples is small, and automaticidentification and counting are achieved.

Description

technical field [0001] The invention belongs to the technical field of cytological detection of cerebrospinal fluid, in particular to a method for automatic identification and counting of cerebrospinal fluid cell images. Background technique [0002] Cerebrospinal fluid is a colorless, transparent, viscous fluid located between the arachnoid and meninges of the meninges and in the spinal cord. It is produced by specialized ependymal cells in the choroidal plexus of the ventricle and is taken up by arachnoid granules. There is about 125mL of cerebrospinal fluid in each human body, and about 500mL is produced every day. It is a pure physiological saline containing microglial cells, mainly used as a mechanical buffer for the cerebral cortex, providing basic mechanical and immune protection for the brain inside the skull, and also plays a vital role in the automatic regulation of cerebral blood flow in the brain important role. Cerebrospinal fluid occupies the subarachnoid sp...

AI Technical Summary

Problems solved by technology

The method of automatic cerebrospinal fluid cell recognition only cuts the border of the cells. This method will make the recognition results affected by the cell background and surrounding cells, and it is more prone to errors when the cells are dense.

Affected by cerebrospinal fluid cell samples, the number of certain types of cells is very small, and the identification accuracy of these cells is often low

Images