Tracking of Human Sperm in Time-Lapse Images

Wang, Chizhong; Choi, Jiho; Urbano, Leonardo F.; Masson, Puneet; VerMilyea, Matthew; Kam, Moshe

doi:10.1109/siprocess.2018.8600463

Cited by 3 publications

(4 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In GNN algorithms like Hungarian algorithm, to allow a track to be not assigned to any detection we need to double the cost matrix size. To explain that suppose that we have the following cost matrix with two detections and three tracks [ [11,15], [16,12], [11,61]] and the gate size for each track is 30. If we use Hungarian algorithm, we need to expand the matrix to allow tracks to be not assigned to any detection like this [ [11,15,30,30,30], [16,12,30,30,30], [11,61,30,30,30], [30, 30, 30, 30, 30], [30, 30, 30, 30, 30]].…”

Section: Kalman Filtermentioning

confidence: 99%

“…If we TABLE 3 The suggested tracking algorithm pseudo code 1. For each new frame: use Hungarian algorithm, we need to expand the matrix to allow tracks to be not assigned to any detection like this [ [11,15,30,30,30], [16,12,30,30,30], [11,61,30,30,30], [30, 30, 30, 30, 30], [30,30,30,30,30]]. Whereas the improved B&B can deal with the cost matrix without any expansion.…”

Section: Kalman Filtermentioning

confidence: 99%

“…In GNN algorithms like Hungarian algorithm, to allow a track to be not assigned to any detection we need to double the cost matrix size. To explain that suppose that we have the following cost matrix with two detections and three tracks [ [11,15], [16,12], [11,61]] and the gate size for each track is 30. If we TABLE 3 The suggested tracking algorithm pseudo code 1.…”

Section: Kalman Filtermentioning

confidence: 99%

“…Wang et al compared four algorithms Nearest Neighbour (NN), probabilistic data association (PDA), joint probabilistic data association (JPDA) and joint probability data association filter with track-coalescence-avoiding (JPDA*) [16], and they said that (JPDA*) has the best performance, but it has high Computational Complexity. In 2019, Mostajer et al presented a new sperm cells tracking method [17].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A robust sperm cell tracking algorithm using uneven lighting image fixing and improved branch and bound algorithm

Alabdulla

Haşıloğlu

Aksu

2021

IET Image Processing

View full text Add to dashboard Cite

An accurate and robust sperm cells tracking algorithm that is able to detect and track sperm cells in videos with high accuracy and efficiency is presented. It is fast enough to process approximately 30 frames per second. It can find the correct path and measure motility parameters for each sperm. It can also adapt with different types of images coming from different cameras and bad recording conditions. Specifically, a new way is offered to optimize uneven lighting images to improve sperm cells detection which gives us the ability to get more accurate tracking results. The shape of each detected object is used to specify collided sperms and utilized dynamic gates which become bigger and smaller according to the sperm cell's speed. For assigning tracks to the detected sperm cells positions an improved version of branch and bound algorithm which is faster than the normal one is offered. This sperm cells tracking algorithm outperforms many of the previous algorithms as it has lower error rate in both sperm detection and tracking. It is compared with six other algorithms, and it gives lower tracking error rates. This method will allow doctors and researchers to obtain sperm motility data instantly and accurately. How to cite this article: Alabdulla, AA, Haşıloglu, A, Aksu, EH: A robust sperm cell tracking algorithm using uneven lighting image fixing and improved branch and bound algorithm.

show abstract

Section: Kalman Filtermentioning

confidence: 99%

Section: Kalman Filtermentioning

confidence: 99%

“…In GNN algorithms like Hungarian algorithm, to allow a track to be not assigned to any detection we need to double the cost matrix size. To explain that suppose that we have the following cost matrix with two detections and three tracks [ [11,15], [16,12], [11,61]] and the gate size for each track is 30. If we TABLE 3 The suggested tracking algorithm pseudo code 1.…”

Section: Kalman Filtermentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A robust sperm cell tracking algorithm using uneven lighting image fixing and improved branch and bound algorithm

Alabdulla

Haşıloğlu

Aksu

2021

IET Image Processing

View full text Add to dashboard Cite

show abstract

Deep Learning-based Automated Assessment of Sperm Motility

Nguyen,

Ha Ngo,

Duong

et al. 2023

2023 1st International Conference on Health Science and Technology (ICHST)

View full text Add to dashboard Cite

A collective tracking method for preliminary sperm analysis

et al. 2019

View full text Add to dashboard Cite

BackgroundTotal motile sperm count (TMSC) and curvilinear velocity (VCL) are two important parameters in preliminary semen analysis for male infertility. Traditionally, both parameters are evaluated manually by embryologists or automatically using an expensive computer-assisted sperm analysis (CASA) instrument. The latter applies a point-tracking method using an image processing technique to detect, recognize and classify each of the target objects, individually, which is complicated. However, as semen is dense, manual counting is exhausting while CASA suffers from severe overlapping and heavy computation.MethodsWe proposed a simple frame-differencing method that tracks motile sperms collectively and treats their overlapping with a statistical occupation probability without heavy computation. The proposed method leads to an overall image of all of the differential footprint trajectories (DFTs) of all motile sperms and thus the overall area of the DFTs in a real-time manner. Accordingly, a theoretical DFT model was also developed to formulate the overall DFT area of a group of moving beads as a function of time as well as the total number and average speed of the beads. Then, using the least square fitting method, we obtained the optimal values of the TMSC and the average VCL that yielded the best fit for the theoretical DFT area to the measured DFT area.ResultsThe proposed method was used to evaluate the TMSC and the VCL of 20 semen samples. The maximum TMSC evaluated using the method is more than 980 sperms per video frame. The Pearson correlation coefficient (PCC) between the two series of TMSC obtained using the method and the CASA instrument is 0.946. The PCC between the two series of VCL obtained using the method and CASA is 0.771. As a consequence, the proposed method is as accurate as the CASA method in TMSC and VCL evaluations.ConclusionIn comparison with the individual point-tracking techniques, the collective DFT tracking method is relatively simple in computation without complicated image processing. Therefore, incorporating the proposed method into a cell phone equipped with a microscopic lens can facilitate the design of a simple sperm analyzer for clinical or household use without advance dilution.

show abstract

Tracking of Human Sperm in Time-Lapse Images

Cited by 3 publications

References 12 publications

A robust sperm cell tracking algorithm using uneven lighting image fixing and improved branch and bound algorithm

A robust sperm cell tracking algorithm using uneven lighting image fixing and improved branch and bound algorithm

Deep Learning-based Automated Assessment of Sperm Motility

A collective tracking method for preliminary sperm analysis

Contact Info

Product

Resources

About