Back to datasets
Dataset assetOpen Source CommunityMedical ImagingStroke Research

IST-3 CT Head Scans

The IST-3 CT head scan dataset was created by the Clinical Brain Sciences Centre at the University of Edinburgh, containing 10,659 CT series for research on intracranial arterial calcification segmentation. The dataset originates from the third International Stroke Trial (IST-3), involving non‑contrast CT scans of 3,035 acute ischemic stroke patients. During creation, registration to a template and quality control ensured validity and accuracy. The dataset primarily supports deep‑learning methods for stroke risk assessment, especially automatic quantification of intracranial arterial calcifications.

Source
arXiv
Created
Aug 2, 2024
Updated
Aug 2, 2024
Signals
575 views
Availability
Linked source ready
Overview

Dataset description and usage context

CT Scan Superimposition Tool

Installation

  1. Clone the repository:

    git clone https://github.com/bjin96/superimposition-tool.git
    
  2. Install dependencies:

    pip install -r requirements.txt
    
  3. Ensure Qt5 is installed following the instructions in the Qt documentation.

Running

Set variables in config.json:

VariableDescription
batch_sizeNumber of scans to overlay at once.
template_pathPath to the template (NIfTI format, .nii.gz) that all scans are registered to.
blacklist_pathPath to a JSON file storing blacklisted file paths. If the file does not exist, it will be created.
input_file_list_pathPath to a JSON file containing a list of CT scan paths to be analyzed.

Blacklist File Format

[
    {"file": "/path/to/the/blacklisted/file1.nii.gz", "reason": "First comment"},
    {"file": "/path/to/the/blacklisted/file2.nii.gz", "reason": "Second comment"}
    // ...
]

Input File List Format

[
    "/path/to/the/file1.nii.gz",
    "/path/to/the/file2.nii.gz",
    // ...
]

Launch the Tool

python run.py
Need downstream help?

Pair the dataset with AI analysis and content workflows.

Once the source passes your review, move straight into summarization, transformation, report drafting, or presentation generation with the JuheAI toolchain.

Explore AI studio