OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Models

Nesvor

NeSVoR is an open-source Python package for GPU-accelerated rigid and deformable slice-to-volume reconstruction, especially for MRI. It combines slice registration and implicit-neural-representation reconstruction, with commands for preprocessing, quality assessment and sampling from trained models.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Nesvor — OpenViST project profile in AI Models.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use NeSVoR when a research or development workflow needs GPU-accelerated reconstruction of MRI slice stacks into 3D volumes, with registration or preprocessing in the same package.

Who it is for

  • Medical-imaging researchers reconstructing 3D volumes from multiple MRI slice stacks.
  • Developers building Python-based MRI registration and reconstruction workflows.

Documented uses

  • Reconstruct a 3D volume from multiple NIfTI stacks of 2D slices.
  • Register slices or stacks to correct motion before reconstruction.
  • Apply supported preprocessing such as fetal brain segmentation, bias-field correction or background thresholding.
  • Assess stack quality and motion, or sample volumes and slices from a trained model.
Before you choose

Requirements & limits

The repository is public and identifies the project as MIT-licensed. The README documents a Docker image and a source-installation path through the project documentation.

  • The Docker instructions require Docker and NVIDIA Container Toolkit and pass GPU access to the container.
  • The documented reconstruction inputs are NIfTI slice stacks and corresponding thickness values.
  • The package includes both rigid and deformable reconstruction, but the choice of workflow and preprocessing flags depends on the imaging task.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Run reconstruction from MRI stacks with Docker

Use the documented container command to reconstruct a 3D volume from NIfTI slice stacks.

Before you start

  • Docker and NVIDIA Container Toolkit installed.
  • The NeSVoR image, pulled with docker pull junshenxu/nesvor.
  • Input NIfTI stacks and their slice thicknesses, plus host directories for inputs and outputs.

Steps

  1. Pull the NeSVoR Docker image.

  2. Mount the input directory read-only at /incoming and the output directory read-write at /outgoing, passing GPU access with --gpus all and shared IPC with --ipc=host.

  3. Run nesvor reconstruct with --input-stacks, the corresponding --thicknesses, and --output-volume pointing to the mounted output location.

Expected outcome

The documented command is configured to write a reconstructed volume to the output path.

Guide limitations

  • The README says the latest image was built with CUDA 11.7.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
daviddmc/NeSVoR · Official homepage title · retained in its source language
How we review sourcesSuggest a correction