Medical sperm image recognition system based on deep learning

Abstract

The invention belongs to the technical field of image recognition, and particularly relates to a medical sperm image recognition system based on deep learning. The system comprises an input module, apositioning module and a classification module, wherein the input module is used for collecting sperm pictures after graying processing of a detector; the positioning module is used for positioning asperm head on the sperm picture by utilizing a YOLO v3 model in a deep learning and image recognition method according to the sperm picture acquired in the input module; the classification module adopts the constructed VGG-sense block classification model to carry out positive anomaly judgment on the sperm heads positioned in the positioning module, and outputs normal sperms and abnormal sperms. The system is short in sperm picture detection time, greatly reduces the workload of doctors, is high in accuracy, reduces errors caused by subjectivity, can assist and partially replace the doctors toperform sperm morphology evaluation, and has a good application prospect.

Description

technical field [0001] The invention belongs to the technical field of image recognition, and in particular relates to a medical sperm image recognition system based on deep learning. Background technique [0002] Infertility affects nearly 10% of the reproductive-age population worldwide, with at least 30-50% of cases being male-related. Semen analysis and evaluation of sperm morphology are an important means of diagnosing male infertility. At present, the evaluation of sperm in medical sperm pictures is done manually, which has defects such as strong subjectivity, loose standards, and time-consuming. Therefore, how to quickly and accurately detect the position and positive abnormality of sperm in a large number of medical sperm pictures has become an early diagnosis of infertility. It is an inevitable development trend to use machine learning and deep learning algorithms to conduct computer-assisted medical image analysis. Contents of the invention [0003] In order to...

AI Technical Summary

Problems solved by technology

At present, the evaluation of sperm in medical sperm pictures is performed manually, which has defects such as strong subjectivity, loose standards, and time-consuming. Therefore, how to quickly and accurately detect the position and normal abnormality of sperm in a large number of medical sperm pictures has become an early diagnosis of infertility. It is an inevitable development trend to use machine learning and deep learning algorithms to analyze medical pictures with computer assistance.

Images