Improving Human Sperm Head Morphology Classification with Unsupervised Anatomical Feature Distillation

TL;DR

This paper introduces an unsupervised anatomical feature distillation framework that improves sperm head morphology classification accuracy and robustness by leveraging priors and pseudo-masks, outperforming existing methods.

Contribution

The novel framework uses anatomical priors and pseudo-masks for unsupervised feature extraction, enhancing deep learning classification of sperm morphology without extra labeling.

Findings

Achieved state-of-the-art accuracy on two public datasets

Reduced noise and improved robustness in classification

Demonstrated effectiveness of unsupervised anatomical feature distillation

Abstract

With rising male infertility, sperm head morphology classification becomes critical for accurate and timely clinical diagnosis. Recent deep learning (DL) morphology analysis methods achieve promising benchmark results, but leave performance and robustness on the table by relying on limited and possibly noisy class labels. To address this, we introduce a new DL training framework that leverages anatomical and image priors from human sperm microscopy crops to extract useful features without additional labeling cost. Our core idea is to distill sperm head information with reliably-generated pseudo-masks and unsupervised spatial prediction tasks. The predicted foreground masks from this distillation step are then leveraged to regularize and reduce image and label noise in the tuning stage. We evaluate our new approach on two public sperm datasets and achieve state-of-the-art performances (e.g. 65.9% SCIAN accuracy and 96.5% HuSHeM accuracy).