EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MTCA‐Net: Multi‐Task Cascade Analysis Network for Real‐Time Sperm Quality Analysis

Jiajin Li, Wenwen Sun, Jun He, Xinyu Fan, Xuecheng Ge, Fengya Lu, Yadan Wang, Yi Wang, Zhiguo Zhang, Qibing Wu, Jinhua Zhou

Advanced Intelligent Systems · 2026-05 · 8 (5)

DOI: 10.1002/aisy.202501452 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advanced Intelligent Systems, online erschienen am 22.03.2026. Verfasst von Jiajin Li und 10 weiteren Autor:innen. Die Arbeit nennt 83 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Intracytoplasmic sperm injection (ICSI) critically relies on selecting high‐quality sperm, which remains a labor‐intensive and subjective process in clinical practice. Current deep learning algorithms involve trade‐offs between accuracy and speed, resulting in inefficient real‐time performance of sperm morphology and motility analysis. A multi‐task cascaded analysis network (MTCA‐Net) that integrates a detection module, a tracking module, and a segmentation module is proposed for real‐time multi‐dimensional sperm quality assessment. In the detection module, an attention mixed feature downsampler is proposed to improve the utilization of spatial down‐sampling features. In the segmentation module, the proposed EffiFusion‐U 2 Net achieves high precision with minimal parameters by incorporating weighted feature fusion blocks to dynamically adjust fusion weights. To enhance the model's generalization ability, an augmentation strategy based on FastGAN and pix2pixGAN was implemented to synthesize sperm heads. Additionally, three datasets are provided containing a total of 3,563 images in various resolutions for sperm detection and segmentation. Comprehensive evaluations on our datasets and four public datasets demonstrate that MTCA‐Net achieves state‐of‐the‐art performance in all cases. MTCA‐Net is capable of performing high‐precision segmentation at 51 frames per second (FPS) and stable tracking at 94 FPS on high‐resolution images of 1920 × 1200 pixels, meeting the real‐time analysis requirements of clinical ICSI.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Li, J., Sun, W., He, J., Fan, X., Ge, X., Lu, F., Wang, Y., Wang, Y., Zhang, Z., Wu, Q., & Zhou, J. (2026). MTCA‐Net: Multi‐Task Cascade Analysis Network for Real‐Time Sperm Quality Analysis. Advanced Intelligent Systems, 8(5). https://doi.org/10.1002/aisy.202501452

Vancouver

Li J, Sun W, He J, Fan X, Ge X, Lu F, et al. MTCA‐Net: Multi‐Task Cascade Analysis Network for Real‐Time Sperm Quality Analysis. Advanced Intelligent Systems. 2026;8(5). doi:10.1002/aisy.202501452

BibTeX
@article{Li2026,
  author = {Li, Jiajin and Sun, Wenwen and He, Jun and Fan, Xinyu and Ge, Xuecheng and Lu, Fengya and Wang, Yadan and Wang, Yi and Zhang, Zhiguo and Wu, Qibing and Zhou, Jinhua},
  title = {MTCA‐Net: Multi‐Task Cascade Analysis Network for Real‐Time Sperm Quality Analysis},
  journal = {Advanced Intelligent Systems},
  year = {2026},
  volume = {8},
  number = {5},
  doi = {10.1002/aisy.202501452}
}
Kostenlos starten →