Automatic evaluation of human oocyte developmental potential from microscopy images

0553877 - FZÚ 2022 RIV US eng C - Conference Paper (international conference)
Baručić, D. - Kybic, J. - Teplá, O. - Topurko, Z. - Kratochvílová, Irena
Automatic evaluation of human oocyte developmental potential from microscopy images.
Proceedings of SPIE. Bellingham: SPIE, 2021 - (Rittner, L.; Lepore, N.; Brieva, J.; Linguraru, M.), č. článku 120881A. ISBN 978-151065052-7. ISSN 0277-786X. E-ISSN 1996-756X.
[International Symposium on Medical Information Processing and Analysis /17./. Campinas (BR), 17.11.2021-19.11.2021]
Institutional support: RVO:68378271
Keywords : human oocytes * fertilization * microscopy * classification * segmentation
OECD category: Robotics and automatic control
https://www.spiedigitallibrary.org/conference-proceedings-of-spie/12088/2604010/Automatic-evaluation-of-human-oocyte-developmental-potential-from-microscopy-images/10.1117/12.2604010.short?SSO=1

Infertility is becoming an issue for an increasing number of couples. The most common solution, in vitro fertilization, requires embryologists to carefully examine light microscopy images of human oocytes to determine their developmental potential. We propose an automatic system to improve the speed, repeatability, and accuracy of this process. We first localize individual oocytes and identify their principal components using CNN (U-Net) segmentation. Next, we calculate several descriptors based on geometry and texture. The final step is an SVM classifier. Both the segmentation and classification training is based on expert annotations. The presented approach leads to a classification accuracy of 70%.
Permanent Link: http://hdl.handle.net/11104/0328559