Sperm YOLOv8E-TrackEVD: A Novel Approach for Sperm Detection and Tracking

Overview

Journal Sensors (Basel)

Publisher MDPI

Specialty Biotechnology

Date 2024 Jun 19

PMID 38894284

Authors

Chongming Zhang

Yaxuan Zhang

Zhanyuan Chang

Chuanjiang Li

Affiliations

Soon will be listed here.

Abstract

Male infertility is a global health issue, with 40-50% attributed to sperm abnormalities. The subjectivity and irreproducibility of existing detection methods pose challenges to sperm assessment, making the design of automated semen analysis algorithms crucial for enhancing the reliability of sperm evaluations. This paper proposes a comprehensive sperm tracking algorithm (Sperm YOLOv8E-TrackEVD) that combines an enhanced YOLOv8 small object detection algorithm (SpermYOLOv8-E) with an improved DeepOCSORT tracking algorithm (SpermTrack-EVD) to detect human sperm in a microscopic field of view and track healthy sperm in a sample in a short period effectively. Firstly, we trained the improved YOLOv8 model on the VISEM-Tracking dataset for accurate sperm detection. To enhance the detection of small sperm objects, we introduced an attention mechanism, added a small object detection layer, and integrated the SPDConv and Detect_DyHead modules. Furthermore, we used a new distance metric method and chose IoU loss calculation. Ultimately, we achieved a 1.3% increase in precision, a 1.4% increase in recall rate, and a 2.0% improvement in mAP@0.5:0.95. We applied SpermYOLOv8-E combined with SpermTrack-EVD for sperm tracking. On the VISEM-Tracking dataset, we achieved 74.303% HOTA and 71.167% MOTA. These results show the effectiveness of the designed Sperm YOLOv8E-TrackEVD approach in sperm tracking scenarios.

References

Gallagher M, Smith D, Kirkman-Brown J . CASA: tracking the past and plotting the future. Reprod Fertil Dev. 2018; 30(6):867-874. DOI: 10.1071/RD17420. View

Zou S, Li C, Sun H, Xu P, Zhang J, Ma P . TOD-CNN: An effective convolutional neural network for tiny object detection in sperm videos. Comput Biol Med. 2022; 146:105543. DOI: 10.1016/j.compbiomed.2022.105543. View

Abbasi A, Miahi E, Mirroshandel S . Effect of deep transfer and multi-task learning on sperm abnormality detection. Comput Biol Med. 2020; 128:104121. DOI: 10.1016/j.compbiomed.2020.104121. View

Li Y, Lu T, Wu Z, Wang Z, Yu T, Wang H . Trends in sperm quality by computer-assisted sperm analysis of 49,189 men during 2015-2021 in a fertility center from China. Front Endocrinol (Lausanne). 2023; 14:1194455. PMC: 10390301. DOI: 10.3389/fendo.2023.1194455. View

Mahali M, Leu J, Darmawan J, Avian C, Bachroin N, Prakosa S . A Dual Architecture Fusion and AutoEncoder for Automatic Morphological Classification of Human Sperm. Sensors (Basel). 2023; 23(14). PMC: 10385996. DOI: 10.3390/s23146613. View

Abou Ghayda R, Cannarella R, Calogero A, Shah R, Rambhatla A, Zohdy W . Artificial Intelligence in Andrology: From Semen Analysis to Image Diagnostics. World J Mens Health. 2023; 42(1):39-61. PMC: 10782130. DOI: 10.5534/wjmh.230050. View

Sang Q, Ray P, Wang L . Understanding the genetics of human infertility. Science. 2023; 380(6641):158-163. DOI: 10.1126/science.adf7760. View

Shaker F, Monadjemi S, Alirezaie J, Naghsh-Nilchi A . A dictionary learning approach for human sperm heads classification. Comput Biol Med. 2017; 91:181-190. DOI: 10.1016/j.compbiomed.2017.10.009. View

Valiuskaite V, Raudonis V, Maskeliunas R, Damasevicius R, Krilavicius T . Deep Learning Based Evaluation of Spermatozoid Motility for Artificial Insemination. Sensors (Basel). 2020; 21(1). PMC: 7795243. DOI: 10.3390/s21010072. View

10.

Staine L, Kohn J, Kohn T . Automated identification of rare sperm becomes possible: Is sperm selection the next frontier in male infertility?. Fertil Steril. 2022; 118(1):100. DOI: 10.1016/j.fertnstert.2022.05.005. View

11.

Auger J, Eustache F, Chevrier C, Jegou B . Spatiotemporal trends in human semen quality. Nat Rev Urol. 2022; 19(10):597-626. PMC: 9383660. DOI: 10.1038/s41585-022-00626-w. View

12.

Lee R, Witherspoon L, Robinson M, Lee J, Duffy S, Flannigan R . Automated rare sperm identification from low-magnification microscopy images of dissociated microsurgical testicular sperm extraction samples using deep learning. Fertil Steril. 2022; 118(1):90-99. DOI: 10.1016/j.fertnstert.2022.03.011. View

13.

Lian J, Yin Y, Li L, Wang Z, Zhou Y . Small Object Detection in Traffic Scenes Based on Attention Feature Fusion. Sensors (Basel). 2021; 21(9). PMC: 8123487. DOI: 10.3390/s21093031. View

14.

Agarwal A, Sharma R, Gupta S, Finelli R, Parekh N, Panner Selvam M . Sperm Morphology Assessment in the Era of Intracytoplasmic Sperm Injection: Reliable Results Require Focus on Standardization, Quality Control, and Training. World J Mens Health. 2021; 40(3):347-360. PMC: 9253798. DOI: 10.5534/wjmh.210054. View

15.

Sato T, Kishi H, Murakata S, Hayashi Y, Hattori T, Nakazawa S . A new deep-learning model using YOLOv3 to support sperm selection during intracytoplasmic sperm injection procedure. Reprod Med Biol. 2022; 21(1):e12454. PMC: 8979154. DOI: 10.1002/rmb2.12454. View

16.

Thambawita V, Hicks S, Storas A, Nguyen T, Andersen J, Witczak O . VISEM-Tracking, a human spermatozoa tracking dataset. Sci Data. 2023; 10(1):260. PMC: 10167330. DOI: 10.1038/s41597-023-02173-4. View

17.

Zheng Y, Yin H, Zhou C, Zhou W, Huan Z, Ma W . A Hand-Held Platform for Boar Sperm Viability Diagnosis Based on Smartphone. Biosensors (Basel). 2023; 13(11). PMC: 10669104. DOI: 10.3390/bios13110978. View

18.

Mazzilli R, Rucci C, Vaiarelli A, Cimadomo D, Ubaldi F, Foresta C . Male factor infertility and assisted reproductive technologies: indications, minimum access criteria and outcomes. J Endocrinol Invest. 2023; 46(6):1079-1085. PMC: 10185595. DOI: 10.1007/s40618-022-02000-4. View

19.

Haugen T, Witczak O, Hicks S, Bjorndahl L, Andersen J, Riegler M . Sperm motility assessed by deep convolutional neural networks into WHO categories. Sci Rep. 2023; 13(1):14777. PMC: 10484948. DOI: 10.1038/s41598-023-41871-2. View

20.

Baldi E, Gallagher M, Krasnyak S, Kirkman-Brown J . Extended semen examinations in the sixth edition of the WHO Laboratory Manual for the Examination and Processing of Human Semen: contributing to the understanding of the function of the male reproductive system. Fertil Steril. 2022; 117(2):252-257. DOI: 10.1016/j.fertnstert.2021.11.034. View