IXI Dataset

Dataset Overview

Dataset Name

• Preprocessed IXI Dataset

Dataset Description

• Contains nearly 600 MR images from healthy volunteers.

Acquisition Protocol

• Includes T1, T2, PD‑weighted images, MRA images, and 15‑direction diffusion‑weighted images.

Scan Sites

• Hammersmith Hospital using Philips 3T system
• Guy’s Hospital using Philips 1.5T system
• Institute of Psychiatry using GE 1.5T system

Dataset Reference

• The dataset is licensed under Creative Commons CC BY‑SA 3.0.
• For more details and download, see the IXI project official website.

Preprocessing Steps

Data Used

• T1 MRI data

Preprocessing Procedure

1. AC‑PC Realignment
2. GM, WM Tissue Segmentation
3. Non‑linear registration to MNI152 space
4. Normalization
5. Resampling
6. Modulation
7. 4 mm Smoothing

Preprocessing Results

• Generated standardized brain volume maps of size 121 × 145 × 121, each voxel representing tissue volume.

Software Environment

• Preprocessed with SPM12 in MATLAB R2018a.
• DARTEL used for normalization, non‑linear registration, resampling, modulation, and smoothing.

Preprocessing Reference

• Follows the paper by James H. Cole et al. "Predicting brain age with deep learning from raw imaging data results in a reliable and heritable biomarker".
• Detailed preprocessing tutorial: Voxel‑based Morphometry (VBM) tutorial.

Download Information

• The dataset can be accessed via the temporary link.