Ultrasound volume reconstruction from 2D freehand acquisitions using neural implicit representations - IRIT - Centre National de la Recherche Scientifique
Conference Poster Year : 2024

Ultrasound volume reconstruction from 2D freehand acquisitions using neural implicit representations

Abstract

The objective of this work is to propose an unsupervised deep learning approach for 3D ultrasound reconstruction. We took inspiration from the neural implicit representations (NIR), a family of approaches that learn volumetric functions from 3D samples [1]. Inspired by NIR this work aims to use its idea to create a 3D volume based on freehand 2D ultrasound sweep. This work is partly inspired and motivated by existing article around the same idea: ImplicitVol [2] optimizes the positions of the slice along the volume using a NIR network, and Ultra-NeRF [3] centers its study around a sophisticated render process.
Fichier principal
Vignette du fichier
_François__poster_ISBI-1.pdf (5.83 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04592493 , version 1 (29-05-2024)

Identifiers

  • HAL Id : hal-04592493 , version 1

Cite

François Gaits, Nicolas Mellado, Adrian Basarab. Ultrasound volume reconstruction from 2D freehand acquisitions using neural implicit representations. 21st IEEE International Symposium on Biomedical Imaging (ISBI 2024), May 2024, Athènes, Greece. . ⟨hal-04592493⟩
264 View
52 Download

Share

More