A Machine Learning Framework for Automatic Prediction of Human Semen Motility

TL;DR

This paper presents a machine learning framework that automatically predicts human semen motility from video samples, achieving improved accuracy over previous methods by combining advanced feature extraction and regression models.

Contribution

The study introduces a novel approach using unsupervised sperm tracking and histogram features with SVR, significantly enhancing motility prediction accuracy on the visem dataset.

Findings

MAE reduced from 8.83 to 7.31 compared to previous best

Unsupervised sperm tracking improves feature quality

Bag-of-Words features enhance regression performance

Abstract

In this paper, human semen samples from the visem dataset collected by the Simula Research Laboratory are automatically assessed with machine learning methods for their quality in respect to sperm motility. Several regression models are trained to automatically predict the percentage (0 to 100) of progressive, non-progressive, and immotile spermatozoa in a given sample. The video samples are adopted for three different feature extraction methods, in particular custom movement statistics, displacement features, and motility specific statistics have been utilised. Furthermore, four machine learning models, including linear Support Vector Regressor (SVR), Multilayer Perceptron (MLP), Convolutional Neural Network (CNN), and Recurrent Neural Network (RNN), have been trained on the extracted features for the task of automatic motility prediction. Best results for predicting motility are achieved by using the Crocker-Grier algorithm to track sperm cells in an unsupervised way and extracting individual mean squared displacement features for each detected track. These features are then aggregated into a histogram representation applying a Bag-of-Words approach. Finally, a linear SVR is trained on this feature representation. Compared to the best submission of the Medico Multimedia for Medicine challenge, which used the same dataset and splits, the Mean Absolute Error (MAE) could be reduced from 8.83 to 7.31. For the sake of reproducibility, we provide the source code for our experiments on GitHub.