Cell detection segmentation system and method based on a deep learning neural network

Abstract

The invention provides a cell detection segmentation system and method based on a deep learning neural network. A deep learning method is used for detecting a cell pathological image. Normal cells, inflammatory cells, trichomonad cells, atrophy cells, HPV viruses and other cells in the picture are segmented out. Each type is marked and the number of each type is counted. A judgment is made as to whether a patient is infected or inflammatory or not and reliable and efficient auxiliary diagnosis is provided for pathologists. The invention has the advantages of simplicity, effectiveness, less required hardware configuration and low implementation cost.

Description

technical field [0001] The present invention relates to the application of deep learning technology in medical image processing, in particular to a system and method for cell detection and segmentation based on deep learning neural network. Background technique [0002] Cervical cancer is an important killer of women's health. Its incidence rate ranks second among female malignant tumors, second only to breast cancer. Statistics show that about 20,000 to 30,000 people die from cervical cancer every year, and it is on the rise and younger. TCT cervical anti-cancer examination is an important examination method, which can detect cervical cancer cells, as well as some precancerous lesions and microbial infections such as mold, trichomonas, viruses, and chlamydia. However, pathological images are usually super-large pixel images. Traditional methods require pathologists to check the entire film, which takes a long time and a lot of energy. Deep learning technology has develop...

AI Technical Summary

Problems solved by technology

However, pathological images are usually super-large pixel images. The traditional method requires a pathologist to check the entire film, which takes a long time and a lot of energy

Images