Ensembling noisy segmentation masks of blurred sperm images

Emilia Lewandowska; Daniel Węsierski; Magdalena Mazur-Milecka; Joanna Liss; Anna Jezierska

doi:10.1016/j.compbiomed.2023.107520

Ensembling noisy segmentation masks of blurred sperm images

Comput Biol Med. 2023 Sep 22:166:107520. doi: 10.1016/j.compbiomed.2023.107520. Online ahead of print.

Authors

Emilia Lewandowska¹, Daniel Węsierski², Magdalena Mazur-Milecka³, Joanna Liss⁴, Anna Jezierska⁵

Affiliations

¹ Cameras and Algorithms Lab, Gdańsk University of Technology, Poland.
² Cameras and Algorithms Lab, Gdańsk University of Technology, Poland; Multimedia Systems Department, Faculty of Electronics, Telecommunication, and Informatics, Gdańsk University of Technology, Poland.
³ Department of Biomedical Engineering, Faculty of Electronics, Telecommunications, and Informatics, Gdańsk University of Technology, Poland.
⁴ Invicta Research and Development Center, Sopot, Poland; Department of Medical Biology and Genetics, University of Gdańsk, Poland.
⁵ Cameras and Algorithms Lab, Gdańsk University of Technology, Poland; Department of Biomedical Engineering, Faculty of Electronics, Telecommunications, and Informatics, Gdańsk University of Technology, Poland; Department of Modelling and Optimization of Dynamical Systems, Systems Research Institute Warsaw, Poland. Electronic address: anna.jezierska@ibspan.waw.pl.

PMID: 37804777
DOI: 10.1016/j.compbiomed.2023.107520

Abstract

Background: Sperm tail morphology and motility have been demonstrated to be important factors in determining sperm quality for in vitro fertilization. However, many existing computer-aided sperm analysis systems leave the sperm tail out of the analysis, as detecting a few tail pixels is challenging. Moreover, some publicly available datasets for classifying morphological defects contain images limited only to the sperm head. This study focuses on the segmentation of full sperm, which consists of the head and tail parts, and appear alone and in groups.

Methods: We re-purpose the Feature Pyramid Network to ensemble an input image with multiple masks from state-of-the-art segmentation algorithms using a scale-specific cross-attention module. We normalize homogeneous backgrounds for improved training. The low field depth of microscopes blurs the images, easily confusing human raters in discerning minuscule sperm from large backgrounds. We thus propose evaluation protocols for scoring segmentation models trained on imbalanced data and noisy ground truth.

Results: The neural ensembling of noisy segmentation masks outperforms all single, state-of-the-art segmentation algorithms in full sperm segmentation. Human raters agree more on the head than tail masks. The algorithms also segment the head better than the tail.

Conclusions: The extensive evaluation of state-of-the-art segmentation algorithms shows that full sperm segmentation is challenging. We release the SegSperm dataset of images from Intracytoplasmic Sperm Injection procedures to spur further progress on full sperm segmentation with noisy and imbalanced ground truth. The dataset is publicly available at https://doi.org/10.34808/6wm7-1159.

Keywords: Computer-aided sperm analysis; Ensembling; Full sperm segmentation; Inter-rater agreement; Microscopic images; Noisy labels.