Morphology Classification of Live Unstained Human Sperm Using Ensemble Deep Learning

Abstract

Sperm morphology analysis is crucial in infertility diagnosis and treatment. However, current clinical analytical methods use either chemical stains that render cells unusable for treatment or rely on subjective manual inspection. Here, an ensemble deep-learning model is presented for classification of live, unstained human sperm using whole-cell morphology. This model achieves an accuracy and precision of 94% benchmarked against the consensus of three andrology scientists who classified the images independently. The model loses less than a 12% prediction performance even when image resolution is reduced by over sixfold. This ensures compatibility across varied clinical imaging setups. This model also provides a high certainty and robust classification of challenging images, which divided the experts. By providing a consistent, automated approach for classifying live, unstained cells using quantitative data, this model offers promising future opportunities for enhancing clinical sperm selection practices and reducing day-to-day variability in clinics.