ImplicitVol: Sensorless 3D Ultrasound Reconstruction with Deep Implicit Representation

arXiv (Cornell University)

Abstract

The objective of this work is to achieve sensorless reconstruction of a 3D volume from a set of 2D freehand ultrasound images with deep implicit representation. In contrast to the conventional way that represents a 3D volume as a discrete voxel grid, we do so by parameterizing it as the zero level-set of a continuous function, i.e. implicitly representing the 3D volume as a mapping from the spatial coordinates to the corresponding intensity values. Our proposed model, termed as ImplicitVol, takes a set of 2D scans and their estimated locations in 3D as input, jointly refining the estimated 3D locations and learning a full reconstruction of the 3D volume. When testing on real 2D ultrasound images, novel cross-sectional views that are sampled from ImplicitVol show significantly better visual quality than those sampled from existing reconstruction approaches, outperforming them by over 30% (NCC and SSIM), between the output and ground-truth on the 3D volume testing data. The code will be made publicly available.

Authors 6

1. Pak-Hei Yeung

   University of Oxford

   Affiliation as printed

   Department of Engineering Science , Institute of Biomedical Engineering , University of Oxford , Oxford , United Kingdom

   Oxford Machine Learning in NeuroImaging Lab , Department of Computer Science , University of Oxford , Oxford , United Kingdom

   University of Oxford

2. Linde S. Hesse

   University of Oxford

   Affiliation as printed

   Department of Engineering Science , Institute of Biomedical Engineering , University of Oxford , Oxford , United Kingdom

   Oxford Machine Learning in NeuroImaging Lab , Department of Computer Science , University of Oxford , Oxford , United Kingdom

3. Moska Aliasi Aachen Division of Fetal Medicine Department of Obstetrics, Leiden University Medical Center

   Leiden University Medical Center

   Affiliation as printed

   Division of Fetal Medicine , Department of Obstetrics , Leiden University Medical Center , 2333 ZA Leiden , The Netherlands

4. Monique C. Haak

   University of Oxford

   Affiliation as printed

   Nuffield Department of Women's and Reproductive Health , University of Oxford , Oxford , United Kingdom

5. Weidi Xie

   University of Oxford

   Affiliation as printed

   Department of Engineering Science , Institute of Biomedical Engineering , University of Oxford , Oxford , United Kingdom

   Visual Geometry Group , Department of Engineering Science , University of Oxford , Oxford , United Kingdom

6. Ana I. L. Namburete

   University of Oxford

   Affiliation as printed

   Oxford Machine Learning in NeuroImaging Lab , Department of Computer Science , University of Oxford , Oxford , United Kingdom