Blastomere segmentation and 3D morphology measurements of early embryos from hoffman modulation contrast image stacks

Authors:
Alessandro Giusti;Giorgio Corani;Luca Gambardella;Cristina Magli;Luca Gianaroli
Affiliations:
Dalle Molle Institute for Artificial Intelligence and International Institute for Reproductive Medicine, Lugano, Switzerland;Dalle Molle Institute for Artificial Intelligence and International Institute for Reproductive Medicine, Lugano, Switzerland;Dalle Molle Institute for Artificial Intelligence and International Institute for Reproductive Medicine, Lugano, Switzerland;Dalle Molle Institute for Artificial Intelligence and International Institute for Reproductive Medicine, Lugano, Switzerland;Dalle Molle Institute for Artificial Intelligence and International Institute for Reproductive Medicine, Lugano, Switzerland
Venue:
ISBI'10 Proceedings of the 2010 IEEE international conference on Biomedical imaging: from nano to Macro
Year:
2010

Citing 2
Cited 1

Spatially coherent clustering using graph cuts

CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
Snakes, shapes, and gradient vector flow

IEEE Transactions on Image Processing

3D localization of pronuclei of human zygotes using textures from multiple focal planes

MICCAI'10 Proceedings of the 13th international conference on Medical image computing and computer-assisted intervention: Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

Monitoring of embryos is an important activity during In Vitro Fertilization (IVF) procedures. A critical stage is that of the early embryo, which is formed by a small number of cells (blastomeres): the morphology of such cells is considered to be a powerful indicator of the embryo viability. We deal with the challenging problem of automatically segmenting the different blastomeres in the early embryo while simultaneously determining their depth, by processing a Z-stack of images acquired by means of an Hoffman Modulation Contrast (HMC) microscope.We discuss experimental results on 53 embryo image stacks, and elaborate on the advantages and limitations of our approach, also briefly describing it is being integrated in the workflow of an IVF laboratory.