Development of a deep-learning model for detecting positive tubules during sperm recovery for nonobstructive azoospermia

To enhance surgical testicular sperm retrieval outcome for men with nonobstructive azoospermia, a deep-learning model was developed to identify positive seminiferous tubules by labeling 110 images with sperm-containing tubules sampled during microdissection testicular sperm extraction as training and validation data. After training, the model achieved an average precision of 0.60.