Improving Human Sperm Head Morphology Classification with Unsupervised Anatomical Feature Distillation
This work addresses male infertility diagnosis by improving classification accuracy and robustness, though it is incremental as it builds on existing deep learning methods with novel training techniques.
The paper tackles the problem of sperm head morphology classification for clinical diagnosis by introducing an unsupervised anatomical feature distillation framework, achieving state-of-the-art performances of 65.9% SCIAN accuracy and 96.5% HuSHeM accuracy on public datasets.
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).