Automatic Tracking and Motility Analysis of Human Sperm in Time-Lapse Images

Abstract

We present a fully automated multi-sperm tracking algorithm. It has the demonstrated capability to detect and track simultaneously hundreds of sperm cells in recorded videos while accurately measuring motility parameters over time and with minimal operator intervention. Algorithms of this kind may help in associating dynamic swimming parameters of human sperm cells with fertility and fertilization rates. Specifically, we offer an image processing method, based on radar tracking algorithms, that detects and tracks automatically the swimming paths of human sperm cells in timelapse microscopy image sequences of the kind that is analyzed by fertility clinics. Adapting the well-known joint probabilistic data association filter (JPDAF), we automatically tracked hundreds of human sperm simultaneously and measured their dynamic swimming parameters over time. Unlike existing CASA instruments, our algorithm has the capability to track sperm swimming in close proximity to each other and during apparent cell-to-cell collisions. Collecting continuously parameters for each sperm tracked without sample dilution (currently impossible using standard CASA systems) provides an opportunity to compare such data with standard fertility rates. The use of our algorithm thus has the potential to free the clinician from having to rely on elaborate motility measurements obtained manually by technicians, speed up semen processing, and provide medical practitioners and researchers with more useful data than are currently available.

Sperm migration in the genital tract -in silicoexperiments identify key factors for reproductive success

“…Box model reproduces in vitro dynamics of sperm. Using results of elaborated sperm cell tracking techniques (21,22) and a descriptive set of movement parameters as defined within the Computer Assisted Sperm Analysis (CASA)(23), we simulated agent movement in a box with a height of 20 µm representing a typical specimen chamber ( Fig. 2) and tested different phenomena as described below.…”

“…Although elaborated sperm tracking techniques exist (21,22) and a descriptive set of movement parameters is defined within the Computer Assisted Sperm Analysis (CASA) framework (23), knowledge is sparse on the angular deflection of sperm per time. Within the CASA framework, straightness (STR) is calculated by the vector length of displacement divided by the contour length of a sperm trajectory.…”

A Survey on Multisperm Tracking for Sperm Motility Measurement

“…7, No. 5, October 2017 Recently in 2016 Urbano et al [34] proposed a more reliable and fully automated multisperm tracking method. At the detection stage, the Gaussian filter was used as much as n times to reduce noise.…”

Multi-Target Tracking of Human Spermatozoa in Phase-Contrast Microscopy Image Sequences using a Hybrid Dynamic Bayesian Network

“…With this approach, the computational complexity of the algorithm is a function of the size of the reference manually extracted dataset and the gated hypotheses set. It is also well worth mentioning that the dataset of this study is quite large and has 36 image sequences and a variety of cell counts, ranging from 4 to 96, while many other methods use achieved good results in less than 10 cells in reported results 6 or used very few sample sequences (just two sequences in 7 ). The dataset of the current study consists of 1,659 cell tracks.…”

“…Hence, the main problem here involves multiple-target tracking (MTT) to extract the tracks of the spermatozoa. Most of the current CASA algorithms are based on simple methods that were first developed in the past decades and may fail in complex situations like high density samples 7 . There are many MTT algorithms developed and applied to solve many problems such as human tracking 8 , visual object tracking 9 , stem cell tracking 10 , spermatozoa tracking 11 , etc., but spermatozoa tracking is a special problem that should be solved in its appropriate way.…”