Header
Header
Article

Super-Focus: Domain Adaptation for Embryo Imaging via Self-supervised Focal Plane Regression



He, Chloe;

Jacques, Celine;

Chambost, Jerome;

Malmsten, Jonas;

Wouters, Koen;

Freour, Thomas;

Zaninovic, Nikica;

Vasconcelos, Francisco; + view all

He, Chloe;

Jacques, Celine;

Chambost, Jerome;

Malmsten, Jonas;

Wouters, Koen;

Freour, Thomas;

Zaninovic, Nikica;

Hickman, Cristina;

Vasconcelos, Francisco;

– view fewer

(2022)

Super-Focus: Domain Adaptation for Embryo Imaging via Self-supervised Focal Plane Regression.

In: Wang, L and Dou, Q and Fletcher, PT and Speidel, S and Li, S, (eds.)
Medical Image Computing and Computer Assisted Intervention – MICCAI 2022 25th International Conference. Proceedings, Part II.

(pp. pp. 732-742).

Springer: Cham, Switzerland.


Text

Super_resolution_MICCAI.pdf
– Accepted Version

Access restricted to UCL open access staff until 17 September 2023.

Download (36MB)

Abstract

In recent years, the field of embryo imaging has seen an influx of work using machine learning. These works take advantage of large microscopy datasets collected by fertility clinics as routine practice through relatively standardised imaging setups. Nevertheless, systematic variations still exist between datasets and can harm the ability of machine learning models to perform well across different clinics. In this work, we present Super-Focus, a method for correcting systematic variations present in embryo focal stacks by artificially generating focal planes. We demonstrate that these artificially generated planes are realistic to human experts and that using Super-Focus as a pre-processing step improves the ability of a cell instance segmentation model to generalise across multiple clinics.

Download activity – last month
Download activity – last 12 months
Downloads by country – last 12 months

Archive Staff Only

View Item View Item



Source link

Back to top button