ruoyuw22-byte/NeuroMorph-Assessment

An automated structural MRI morphometry system integrating CAT12 processing, brain tissue quantification, visualization, and automated report generation.

What it solves

NeuroMorph Assessment (NMA) automates the complex process of structural MRI morphometry and brain volume analysis. It eliminates the need to manually handle separate tools for data organization, tissue segmentation, and report generation by unifying them into a single workflow.

How it works

The system integrates with MATLAB, SPM12, and the CAT12 toolbox to process T1-weighted MRI images. It identifies the correct images, performs brain tissue segmentation, and extracts quantitative measurements for gray matter, white matter, cerebrospinal fluid, and total intracranial volume. The results are then visualized in a three-plane view and compiled into an automated PDF report.

Who it’s for

Researchers and clinicians who need to perform quantitative brain volume analysis and structural MRI morphometry using the CAT12 pipeline.

Highlights

  • End-to-end automation: Handles everything from MRI data import to final PDF report generation.
  • Quantitative extraction: Measures total intracranial volume (TIV), gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF).
  • Integrated visualization: Provides three-plane MRI visualization and processing progress monitoring.
  • Validation: Includes quantitative consistency validation during the result extraction phase.

Related

  • Project
    AI4EPS/PhaseNet

    A deep neural network-based method for automatically picking seismic arrival times (P and S waves) from raw seismic data.

  • Project
    NVlabs/SpatialClaw

    SpatialClaw is a training‑free, code‑as‑action framework for spatial‑reasoning agents. A VLM writes Python cells that run in a persistent Jupyter kernel pre‑loaded with perception tools (SAM‑3, Depth‑Anything‑3) and scientific libraries. The system loops through planning, code generation, safety‑checked execution, and observation until the agent returns an answer. Evaluated on 20 benchmarks, it reaches 59.9 % average accuracy, beating prior agents by 11.2 points, using the same prompt and tools across six VLM back‑ends. The repo provides full runtime, benchmark loaders, installation scripts, and SLURM support.

  • Project
    zju3dv/Murre

    A multi-view 3D reconstruction framework that combines SfM-guided monocular depth estimation with TSDF fusion to create accurate dense 3D models from images.

  • Project
    tudelft-iv/view-of-delft-dataset

    A multi-sensor automotive dataset containing synchronized LiDAR, camera, and 3+1D radar data with 3D bounding box annotations for road user detection in urban traffic.