# Improving Human Sperm Head Morphology Classification with Unsupervised Anatomical Feature Distillation

arXiv: https://arxiv.org/abs/2202.07191 · HTML: https://mlsanity.com/paper/2202.07191/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 18 references that are in the map.
- First posted on arXiv 15 Feb 2022.

## Builds on (most cited first, 5 of 5)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results](https://mlsanity.com/paper/1703.01780/) (2017)
- [Transformation Consistent Self-ensembling Model for Semi-supervised Medical Image Segmentation](https://mlsanity.com/paper/1903.00348/) (2019)

## Built on by (most cited first, 1 of 1)

- [SHMC-Net: A Mask-guided Feature Fusion Network for Sperm Head Morphology Classification](https://mlsanity.com/paper/2402.03697/) (2024)

## Abstract (arXiv)

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).