Occlusion Robust Low-Contrast Sperm Tracking Using Switchable Weight Particle Filtering

Abstract

Sperm motility analysis has a particular place in male fertility diagnosis. Computerized sperm tracking has an important role in extracting sperm trajectory and measuring sperm's dynamic features. Due to free movements of sperms in three dimensions, occlusion has remained a challenging problem in this area. This paper aims to present a robust single sperm tracking method being able to handle misdetections in sperm occlusion scenes. In this paper, a robust method of segmentation was utilized to provide the required measurements for a switchable weight particle filtering which was designed for single sperm tracking. In each frame, the target sperm was categorized in one of these three stages: before occlusion, occlusion, and after occlusion where the occlusion had been detected based on sperm's physical characteristics. Depending on the target sperm stage, particles were weighted differently. In order to evaluate the algorithm, two groups of samples were studied where an expert had selected a single sperm of each sample to track manually and automatically. In the first group, the sperms with no occlusion along their trajectories were tracked to depict the general compatibility of the algorithm with sperm tracking. In the second group, the algorithm was applied on the sperms which had at least one occlusion during their path. The algorithm showed an accuracy of 95% on the first group and 86.66% on the second group which illustrate the robustness of the algorithm against occlusion.

A New Region-Based Adaptive Thresholding For Sperm Motility Segmentation

“…The aforementioned disadvantages have increased the complexity of the data interpretation and remark the need of objective, precise and repeatable techniques to study movement of the sperm. Therefore, the development of new methodologies is actively conducted where automated or semi-automated approaches have been proposed by researchers to track and identify human sperms [7][8][9][10][11][12][13][14][15], rat sperms [16,17], and boar sperms [18].…”

“…Smoothing filter such as Gaussian and mean filter were utilized to remove the unwanted noises [7,11,15,16,19,20]. The work of Ravanfar, et al [12] utilizes morphological filtering to improve quality of the image by enhancing the discriminative features. Researchers such as Carrillo, et al [10] and Vahid Reza, et al [15] also employ enhancement techniques prior to the segmentation process.…”

“…The features in this technique determined the threshold of the image and thus ensure its high accuracy. Ravanfar, et al [12] utilized watershed segmentation algorithm based on topography of intensity. Each area in the image was divided into three categories namely minimum regions, catchman basin and watershed lines.…”

A Survey on Multisperm Tracking for Sperm Motility Measurement

“…Microscopic examination can be done manually, however it takes a long inspection time to get more objective results because we must observe up to 10 fields of view per examination task [3]. In addition, the manual examination has other shortcomings: depending on the experience of the veterinarian [4], the occurrence of human error [4], subjective [5], [6], intra and inter observer variability [7], [8], and causing exhaustion to the observer. This paper discusses more primarily about the examination of motility.…”

“…Although sperm mass motion has a close relationship with fertility [5], the related papers are not numerous. As for the measurement of motility, in addition to having a significant role in fertility [4], [9], [10], there are many papers discussing it. Motility measurement is also still a big challenge because the cases listed above have not been handled well.…”