# An Artificial Intelligence‐Based Computer Vision Model for Human Sperm Concentration, Motility, and Kinematics Analysis

## TL;DR

An AI-based tool for analyzing sperm concentration and movement outperforms existing methods in accuracy and reliability.

## Contribution

An AI-driven computer vision model that improves sperm analysis accuracy and robustness compared to manual and commercial systems.

## Key findings

- The AI model showed strong correlation with manual tracking (R² = 0.93–0.98) and outperformed CASA in accuracy.
- Post-calibration reduced RMSE by 30–50% for key motility parameters like ALHmax and BCF.
- The AI system maintained consistency across duplicate samples and variable imaging conditions with deviations below ±2%.

## Abstract

Accurate assessment of sperm concentration and motility is critical for the diagnosis and management of male infertility. However, current methods, manual hemocytometer counting and commercial computer‐aided sperm analysis (CASA) systems, are limited by labor intensity, human error, and variable performance under diverse sample conditions. Here, we present an artificial intelligence (AI)‐driven computer vision tool for high‐resolution, quantitative analysis of sperm motility and concentration. In a prospective study of 26 semen samples (22 patients, 4 donors), we benchmarked the AI model against manual tracking (using Fiji software) and a commercial CASA system (Hamilton Thorne IVOS II). Our method computed concentration and motility parameters, including straight‐line velocity (VSL), curvilinear velocity (VCL), average path velocity (VAP), linearity (LIN), amplitude of lateral head displacement (ALHmax), and beat cross frequency (BCF). Calibration using donor samples enabled accurate mapping of tracked sperm counts to concentrations. The AI tool presented a strong linear correlation with manual tracking (R
2 = 0.93–0.98; Root Mean Square Error (RMSE) = 3.3–7.3 μm/s for VSL, VCL, VAP), and outperformed CASA in both accuracy and consistency across all motility parameters. Post‐calibration, ALHmax and BCF estimates improved substantially, with a 30%–50% reduction in RMSE. Grading of sperm motility by the AI model aligned closely with manual classification, avoiding the systematic misclassification typically observed with CASA. Furthermore, the AI system exhibited higher repeatability and robustness across duplicate samples and variable imaging conditions, with deviations below ± 2%. These findings demonstrate that our AI‐based tool offers a quantitative and reliable alternative to current semen analysis platforms, supporting improved fertility diagnostics and potentially a more informative treatment process.

A computer‐vision method measures sperm concentration and motility from recorded videos, benchmarked and calibrated against manual tracking to ensure consistency. It can potentially support routine fertility assessments with high accuracy.

We developed an AI‐driven computer vision model for automated analysis of human sperm concentration, motility, and kinematics.The model was benchmarked against both manual tracking and a commercial CASA system, demonstrating strong linear correlation (R
2 = 0.93–0.98) with manual results.Our calibrated AI model outperformed CASA in accuracy and repeatability for motility parameters such as VSL, VCL, VAP, and BCF.The calibrated AI model achieved high robustness to changes in imaging conditions and maintained consistency in repeated assessments.This AI‐based system provides a reliable, reproducible, and accessible alternative for clinical sperm analysis in fertility diagnostics.

We developed an AI‐driven computer vision model for automated analysis of human sperm concentration, motility, and kinematics.

The model was benchmarked against both manual tracking and a commercial CASA system, demonstrating strong linear correlation (R
2 = 0.93–0.98) with manual results.

Our calibrated AI model outperformed CASA in accuracy and repeatability for motility parameters such as VSL, VCL, VAP, and BCF.

The calibrated AI model achieved high robustness to changes in imaging conditions and maintained consistency in repeated assessments.

This AI‐based system provides a reliable, reproducible, and accessible alternative for clinical sperm analysis in fertility diagnostics.