Information processing method, device and equipment for detecting sperm quality and medium
By using microfluidic chips and multi-device parallel acquisition technology, combined with deep learning models and feature fusion, the problems of low efficiency and large errors in existing sperm quality testing have been solved, achieving efficient and accurate sperm quality testing.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- RUIJIN HOSPITAL AFFILIATED TO SHANGHAI JIAO TONG UNIV SCHOOL OF MEDICINE
- Filing Date
- 2026-02-10
- Publication Date
- 2026-05-29
AI Technical Summary
Existing sperm quality testing methods rely on manual preprocessing, which leads to low efficiency and is prone to human error. Stepwise multimodal data acquisition results in data distortion, affecting the accuracy of test results.
The method employs highly automated synchronous multimodal data acquisition and deep fusion analysis. Samples are diluted using a microfluidic chip, and multimodal data is acquired in parallel using multiple acquisition devices. Feature fusion is performed by combining a deep learning model and a feature weight allocation network to generate sperm quality parameters.
It enables efficient and accurate sperm quality testing without manual preprocessing, reducing human error and data distortion, and improving testing efficiency and result reliability.
Smart Images
Figure CN122115371A_ABST