Elucidating motion patterns in sperm cell motion with dynamic mode decomposition
Authors
Year
2026
Published
Journal of Biological Physics. 2026, 2026(52), ISSN 0092-0606.
Type
Article
Departments
Annotation
The study employs dynamic mode decomposition (DMD) to elucidate the underlying mechanisms contributing to the enhanced motility observed in sperm bundles, primarily focusing on the role of flagellar synchronization. The decomposition reveals that synchronized flagellar movements might be a key factor enabling sperm cells to attain higher velocities when connected in bundles. Through DMD, periodical characteristics of individual periodical motion patterns, such as frequency, amplitude, and modal growth/decay rates (from DMD eigenvalues), are characterized, elucidating main parameters of the dynamic behavior of these biological systems, such as dominant frequencies of periodical motion, as well as amplitudes and velocities. The implications of this research extend beyond understanding sperm bundle dynamics, as the methodology is adaptable for identifying healthy sperm cells based on their motility patterns. Additionally, the approach holds potential for broader applications in studying other flagellar-driven microorganisms, providing a valuable tool for comparative analysis across various species.
Machine Learning Based Tool for Automated Sperm Cell Tracking and Sperm Bundle Detection
Authors
Year
2024
Published
Machine Learning and Knowledge Discovery in Databases. Applied Data Science Track. Cham: Springer, 2024. p. 19-32. Lecture Notes in Computer Science. vol. 14950. ISSN 2945-9133. ISBN 978-3-031-70380-5.
Type
Proceedings paper
Departments
Annotation
This study introduces a novel machine learning-based methodology for automated detection and tracking of sperm cells within microscopic video recordings, aiming to elucidate the dynamics and motion patterns of individual sperm cells as well as sperm cell bundles. At first, the method identifies sperm cells across successive frames within a video sequence, facilitating the reconstruction of each cell's trajectory over time. Subsequently, we introduce a classification algorithm that distinguishes between solitary sperm cells, clusters of adjacent cells, and cohesive sperm cell bundles, addressing a gap in existing methodologies. Finally, we employ three conventional metrics for velocity assessment: Straight Line Velocity (VSL) and Average Path Velocity (VAP) and Curvilinear velocity (VCL), to quantify the movement speed of both individual sperm cells and bundles. The approach represents a significant advancement in the automated analysis of sperm motility and aggregation phenomena, providing a robust tool for researchers to study sperm behavior with enhanced accuracy and efficiency. The integration of machine learning techniques in sperm cell detection and tracking offers promising insights into reproductive biology and fertility studies.