M-SCAN: A Multistage Framework for Lumbar Spinal Canal Stenosis Grading Using Multi-View Cross Attention

Arnesh Batra, Arush Gumber, Anushk Kumar
3/3/2025
eess.IVcs.CV

No official code found. Best implementation: Deep-learning-exp/M-SCAN (4 stars, last commit 2024-09-10).

Abstract

The increasing prevalence of lumbar spinal canal stenosis has resulted in a surge of MRI (Magnetic Resonance Imaging), leading to labor-intensive interpretation and significant inter-reader variability, even among expert radiologists. This paper introduces a novel and efficient deep-learning framework that fully automates the grading of lumbar spinal canal stenosis. We demonstrate state-of-the-art performance in grading spinal canal stenosis on a dataset of 1,975 unique studies, each containing three distinct types of 3D cross-sectional spine images: Axial T2, Sagittal T1, and Sagittal T2/STIR. Employing a distinctive training strategy, our proposed multistage approach effectively integrates sagittal and axial images. This strategy employs a multi-view model with a sequence-based architecture, optimizing feature extraction and cross-view alignment to achieve an AUROC (Area Under the Receiver Operating Characteristic Curve) of 0.971 in spinal canal stenosis grading surpassing other state-of-the-art methods.

View on arXivView PDF

Code Implementations(1)

Deep-learning-exp/M-SCANCommunity100%
40Python, Jupyter NotebookSep 10, 20242 years ago

Similar Papers

SpineReport: Automated 3D Quantification and Reporting of Lumbar Spine Degeneration on MRI

86% match2026

SPINEPS -- Automatic Whole Spine Segmentation of T2-weighted MR images using a Two-Phase Approach to Multi-class Semantic and Instance Segmentation

84% match1 repo592024

PhenSPINE: A Standardized Benchmark for Spine Pathology Diagnosis

84% match2026

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

83% match2024

Submillimeter-Accurate 3D Lumbar Spine Reconstruction from Biplanar X-Ray Images: Incorporating a Multi-Task Network and Landmark-Weighted Loss

83% match2025

Accurate Cobb Angle Estimation via SVD-Based Curve Detection and Vertebral Wedging Quantification

82% match2025

Cite this paper

@article{batra2025mscan,
  title  = {M-SCAN: A Multistage Framework for Lumbar Spinal Canal Stenosis Grading Using Multi-View Cross Attention},
  author = {Arnesh Batra and Arush Gumber and Anushk Kumar},
  year   = {2025},
  eprint = {2503.01634},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2503.01634v1}
}

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/2503.01634.svg)](https://codeofpaper.com/paper/2503.01634)

Discussion