Validation of an Artificial Intelligence Tool for the Detection of Sperm DNA Fragmentation Using the TUNEL In Situ Hybridization Assay

TL;DR

This study addresses the challenge of assessing sperm DNA fragmentation ($SDF$) without destroying the sample by leveraging phase-contrast microscopy and the $TUNEL$ assay as a reference. It introduces a morphology-assisted ensemble AI pipeline that combines image-derived features with a transformer-based GC-ViT model to predict $SDF$ from non-destructive images. The ensemble approach yields a balanced performance with $Sensitivity=0.60$, $Specificity=0.75$, and $Accuracy=0.69$, outperforming single-model baselines and offering potential for real-time sperm selection in assisted reproductive technologies. The work also characterizes intra-expert variance and highlights the need for more data and clinical validation to translate this method into routine practice.

Abstract

Sperm DNA fragmentation (SDF) is a critical parameter in male fertility assessment that conventional semen analysis fails to evaluate. This study presents the validation of a novel artificial intelligence (AI) tool designed to detect SDF through digital analysis of phase contrast microscopy images, using the terminal deoxynucleotidyl transferase dUTP nick end labeling (TUNEL) assay as the gold standard reference. Utilising the established link between sperm morphology and DNA integrity, the present work proposes a morphology assisted ensemble AI model that combines image processing techniques with state-of-the-art transformer based machine learning models (GC-ViT) for the prediction of DNA fragmentation in sperm from phase contrast images. The ensemble model is benchmarked against a pure transformer `vision' model as well as a `morphology-only` model. Promising results show the proposed framework is able to achieve sensitivity of 60\% and specificity of 75\%. This non-destructive methodology represents a significant advancement in reproductive medicine by enabling real-time sperm selection based on DNA integrity for clinical diagnostic and therapeutic applications.

Figures (13)

• Figure 1: Model Architecture
• Figure 2: Ensemble Model Confusion Matrix
• Figure 3: Ensemble Model Learning Curves
• Figure 4: Ensemble Model ROC Curve
• Figure 5: Morphology Model Confusion Matrix