Search Results for author: Neel Dey

Found 20 papers, 14 papers with code

SE(3)-Equivariant and Noise-Invariant 3D Motion Tracking in Medical Images

1 code implementation21 Dec 2023 Benjamin Billot, Daniel Moyer, Neel Dey, Malte Hoffmann, Esra Abaci Turk, Borjan Gagoski, Ellen Grant, Polina Golland

Here we propose EquiTrack, the first method that uses recent steerable SE(3)-equivariant CNNs (E-CNN) for motion tracking.

Time Series

Intraoperative 2D/3D Image Registration via Differentiable X-ray Rendering

1 code implementation11 Dec 2023 Vivek Gopalakrishnan, Neel Dey, Polina Golland

Preoperatively, a CNN is trained to regress the pose of a randomly oriented synthetic X-ray rendered from the preoperative CT.

Image Registration

Shape-aware Segmentation of the Placenta in BOLD Fetal MRI Time Series

1 code implementation8 Dec 2023 S. Mazdak Abulnaga, Neel Dey, Sean I. Young, Eileen Pan, Katherine I. Hobgood, Clinton J. Wang, P. Ellen Grant, Esra Abaci Turk, Polina Golland

In this work, we propose a machine learning segmentation framework for placental BOLD MRI and apply it to segmenting each volume in a time series.

Placenta Segmentation Segmentation +1

Dynamic Neural Fields for Learning Atlases of 4D Fetal MRI Time-series

1 code implementation6 Nov 2023 Zeen Chi, Zhongxiao Cong, Clinton J. Wang, Yingcheng Liu, Esra Abaci Turk, P. Ellen Grant, S. Mazdak Abulnaga, Polina Golland, Neel Dey

We apply our method to learning subject-specific atlases and motion stabilization of dynamic BOLD MRI time-series of fetuses in utero.

Time Series

$E(3) \times SO(3)$-Equivariant Networks for Spherical Deconvolution in Diffusion MRI

1 code implementation12 Apr 2023 Axel Elaldi, Guido Gerig, Neel Dey

We present Roto-Translation Equivariant Spherical Deconvolution (RT-ESD), an $E(3)\times SO(3)$ equivariant framework for sparse deconvolution of volumes where each voxel contains a spherical signal.

Dual-Domain Self-Supervised Learning for Accelerated Non-Cartesian MRI Reconstruction

no code implementations18 Feb 2023 Bo Zhou, Jo Schlemper, Neel Dey, Seyed Sadegh Mohseni Salehi, Kevin Sheth, Chi Liu, James S. Duncan, Michal Sofka

To this end, we present a fully self-supervised approach for accelerated non-Cartesian MRI reconstruction which leverages self-supervision in both k-space and image domains.

MRI Reconstruction Self-Supervised Learning

Data Consistent Deep Rigid MRI Motion Correction

1 code implementation25 Jan 2023 Nalini M. Singh, Neel Dey, Malte Hoffmann, Bruce Fischl, Elfar Adalsteinsson, Robert Frost, Adrian V. Dalca, Polina Golland

Motion artifacts are a pervasive problem in MRI, leading to misdiagnosis or mischaracterization in population-level imaging studies.

Image Reconstruction

Local Spatiotemporal Representation Learning for Longitudinally-consistent Neuroimage Analysis

1 code implementation9 Jun 2022 Mengwei Ren, Neel Dey, Martin A. Styner, Kelly Botteron, Guido Gerig

Recent self-supervised advances in medical computer vision exploit global and local anatomical self-similarity for pretraining prior to downstream tasks such as segmentation.

One-Shot Segmentation Representation Learning +1

Q-space Conditioned Translation Networks for Directional Synthesis of Diffusion Weighted Images from Multi-modal Structural MRI

1 code implementation24 Jun 2021 Mengwei Ren, Heejong Kim, Neel Dey, Guido Gerig

Further, such approaches can restrict downstream usage of variably sampled DWIs for usages including the estimation of microstructural indices or tractography.


Equivariant Spherical Deconvolution: Learning Sparse Orientation Distribution Functions from Spherical Data

1 code implementation17 Feb 2021 Axel Elaldi, Neel Dey, Heejong Kim, Guido Gerig

We then show improved downstream performance on fiber tractography measures on the Tractometer benchmark dataset.

Group Equivariant Generative Adversarial Networks

no code implementations ICLR 2021 Neel Dey, Antong Chen, Soheil Ghafurian

Recent improvements in generative adversarial visual synthesis incorporate real and fake image transformation in a self-supervised setting, leading to increased stability and perceptual fidelity.

Cannot find the paper you are looking for? You can Submit a new open access paper.