Abstract
Unpredictable fetal motion during MRI scans can result in oblique 2D slices that are difficult to interpret and often leads to prolonged scan times. Slice-to-volume reconstruction (SVR) methods align 2D oblique slices from multiple slice stacks into a coherent 3D volume. We propose a convolutional network that predicts slice poses by performing multiscale, unrolled optimization and further refines them and super-resolves the volume using model-based optimization. Our convolutional feed-forward SVR network achieves accuracy on par with state-of-the-art results while offering significant speedup, paving the way for scanner-side use of SVR. The code is available publicly:\ \url{https://anonymous.4open.science/r/cSVR-5DD4}.
Links to Paper and Supplementary Materials
Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/PIPPI_025.pdf
SharedIt Link: Not yet available
SpringerLink (DOI): Not yet available
Supplementary Material: Not Submitted
Link to Open Review
BibTex
@InProceedings{FirMar_cSVR_MICCAISAT2026,
author = { Firenze, Margherita AND Young, Sean I. AND Wang, Clinton AND Adalsteinsson, Elfar AND Yun, HyukJin AND Grant, P. Ellen AND Im, Kiho AND Golland, Polina},
title = { { cSVR: Convolutional Slice-to-Volume Reconstruction } },
booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026 Workshops and Challenges},
year = {2026},
publisher = {Springer Nature Switzerland},
volume = {LNCS 17257},
month = {pending},
page = {pending}
}