motum/README.md

MOTUM Dataset

This is a public dataset presented at our manuscript titled "A Multi-Center, Multi-Parametric MRI Dataset of Primary and Secondary Brain Tumors" under review in Scientific Data

Description

We introduce a multi-center, multi-origin brain tumor MRI (MOTUM) imaging dataset obtained from 67 patients: 29 with high-grade gliomas, 20 with lung metastases, 10 with breast metastases, 2 with gastric metastasis, 4 with ovarian metastasis, and 2 with melanoma metastasis. This dataset includes anonymized digital imaging and communications in medicine (DICOM) files alongside processed FLAIR, T1-weighted, contrast-enhanced T1-weighted, T2-weighted sequences images, segmentation masks of two tumor regions, and clinical data. Our data-sharing initiative is to support the benchmarking of automated tumor segmentation, multi-modal machine learning, and disease differentiation of multi-origin brain tumors in a multi-center setting.

Data Organization

Multi-contrast MRI, segmentation masks, radiomics features and the acquisition parameters from individuals are stored with the following format. For example,

./sub-0001/anat/ stores four imaging sequences of Subject 0001 including FLAIR (sub-0001_flair.nii.gz), T1 (sub-0001_t1.nii.gz), T2 (sub-0001_t2.nii.gz), T1-contrast (sub-0001_t1ce.nii.gz) are stored.

./derivatives/ stores the segmentation masks, radiomics, and meta information of four modalities of all subjects.

Specifically, for Subject 0001, ./derivatives/sub-0001 stores two segmentation masks (flair_seg_label1.nii.gz and t1ce_seg_label2.nii.gz derived from FLAIR and T1-ce, respectively), radiomics features (flair_radiomics.csv, t1_radiomics.csv, t2_radiomics.csv, t1ce_radiomics.csv) and meta information (flair_param.json, t1_param.json, t2_param.json, and t1ce_param.json).

./Participants.xlsx stores the meta information of each subject.