Automated Parts Segmentation of Sperm via a Contrastive Learning-Based Part Matching Network

Sperm morphology measurement is vital for diagnosing male infertility, which involves quantification of multiple subcellular parts for each sperm. Instance-aware part segmentation networks have been introduced to address this task by automatically identifying individual sperm and segmenting their subcellular parts. However, major limitations of state-of-the-art instance-aware part segmentation networks include: 1) they are time-consuming and computational expensive due to sequential processing and multi-stage frameworks; 2) they perform poorly for densely packed sperm that overlap or cross over one another. To overcome these challenges, this paper proposes 1) integrating instance identification and subcellular part segmentation within a single-stage framework to save inference time and memory usage; 2) dividing a sperm target into simpler components (head and tail) to improve prediction accuracy, followed by a contrastive learning-based matching method to pair the head and tail. Experimental results on our clinically collected human sperm dataset demonstrated that the proposed network not only outperformed state-of-the-art CP-Net (by 3.5% $\mathrm{AP}^{p}_{vol}$ ) but also achieved real-time inference (48.0 frames per second), effectively meeting the clinical requirements for automated parts segmentation of sperm. Note to Practitioners—This work aims to automate the tedious and highly subjective process of manual sperm’s parts measurement. State-of-the-art methods employ instance-aware part segmentation; however their speed and accuracy cannot satisfy clinical requirements. To address theses issues, this paper introduces two key innovations. 1) Inspired by single-stage instance segmentation network, we develop an instance-aware part prediction branch. The proposed branch directly predicts part-encoded coefficients from the feature map, which are subsequently combined with prototype masks to produce final part segmentation results. 2) Since the sperm head and tail have simpler shapes, they are detected separately to improve segmentation accuracy. A contrastive learning-based method is then designed to pair head and tail based on similarity of feature embeddings extracted from the proposed instance prediction branch. The proposed method significantly outperformed existing networks, particularly in handling densely packed sperm. The presented method has applicability to analyzing sperm and more broadly other cell types.