Details

Autor(en) / Beteiligte

• Gomez, Alberto
• Zimmer, Veronika
• Toussaint, Nicolas
• Wright, Robert
• Clough, James R.
• Khanal, Bishesh
• van Poppel, Milou P. M.
• Skelton, Emily
• Matthews, Jackie
• Schnabel, Julia A.

Titel

Image Reconstruction in a Manifold of Image Patches: Application to Whole-Fetus Ultrasound Imaging

Ist Teil von

• Machine Learning for Medical Image Reconstruction, p.226-235

Ort / Verlag

Cham: Springer International Publishing

Link zum Volltext

Quelle

Alma/SFX Local Collection

Beschreibungen/Notizen

• We propose an image reconstruction framework to combine a large number of overlapping image patches into a fused reconstruction of the object of interest, that is robust to inconsistencies between patches (e.g. motion artefacts) without explicitly modelling them. This is achieved through two mechanisms: first, manifold embedding, where patches are distributed on a manifold with similar patches (where similarity is defined only in the region where they overlap) closer to each other. As a result, inconsistent patches are set far apart in the manifold. Second, fusion, where a sample in the manifold is mapped back to image space, combining features from all patches in the region of the sample. For the manifold embedding mechanism, a new method based on a Convolutional Variational Autoencoder (\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\beta $$\end{document}-VAE) is proposed, and compared to classical manifold embedding techniques: linear (Multi Dimensional Scaling) and non-linear (Laplacian Eigenmaps). Experiments using synthetic data and on real fetal ultrasound images yield fused images of the whole fetus where, in average, \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\beta $$\end{document}-VAE outperforms all the other methods in terms of preservation of patch information and overall image quality.