Diffusion-Based Semantic Segmentation of Lumbar Spine MRI Scans of Lower Back Pain Patients

Maria Monzon, Thomas Iff, Ender Konukoglu, Catherine R. Jutzeler
11/16/2024
eess.IVcs.CVcs.LG

No official code found. Best implementation: BMDS-ETH/SpineSegDiff (0 stars, Apache-2.0, last commit 2026-03-17).

Abstract

This study introduces a diffusion-based framework for robust and accurate segmenton of vertebrae, intervertebral discs (IVDs), and spinal canal from Magnetic Resonance Imaging~(MRI) scans of patients with low back pain (LBP), regardless of whether the scans are T1w or T2-weighted. The results showed that SpineSegDiff achieved comparable outperformed non-diffusion state-of-the-art models in the identification of degenerated IVDs. Our findings highlight the potential of diffusion models to improve LBP diagnosis and management through precise spine MRI analysis.

View on arXivView PDF

Code Implementations(1)

BMDS-ETH/SpineSegDiffCommunity100%
Apache-2.0
00Shell, PythonMar 25, 20247 months agoApache-2.0

Similar Papers

Denoising diffusion-based MRI to CT image translation enables automated spinal segmentation

84% match1 repo452023

Lumbar spine segmentation in MR images: a dataset and a public benchmark

84% match1 repo232023

Introducing Shape Prior Module in Diffusion Model for Medical Image Segmentation

84% match2023

Pioneering Precision in Lumbar Spine MRI Segmentation with Advanced Deep Learning and Data Enhancement

84% match2024

Energy-Based Prior Latent Space Diffusion model for Reconstruction of Lumbar Vertebrae from Thick Slice MRI

81% match1 repo2024

Reconstruction of 3D lumbar spine models from incomplete segmentations using landmark detection

80% match2024

Cite this paper

@article{monzon2024diffusionbased,
  title  = {Diffusion-Based Semantic Segmentation of Lumbar Spine MRI Scans of Lower Back Pain Patients},
  author = {Maria Monzon and Thomas Iff and Ender Konukoglu and Catherine R. Jutzeler},
  year   = {2024},
  eprint = {2411.10755},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2411.10755v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2411.10755.svg)](https://codeofpaper.com/paper/2411.10755)

Discussion