Brain MRI dataset of multiple sclerosis with consensus manual lesion segmentation and patient meta information

Ali M Muslim; Syamsiah Mashohor; Gheyath Al Gawwam; Rozi Mahmud; Marsyita Binti Hanafi; Osama Alnuaimi; Raad Josephine; Abdullah Dhaifallah Almutairi

doi:10.1016/j.dib.2022.108139

Brain MRI dataset of multiple sclerosis with consensus manual lesion segmentation and patient meta information

Data Brief. 2022 Apr 7:42:108139. doi: 10.1016/j.dib.2022.108139. eCollection 2022 Jun.

Authors

Ali M Muslim^{1

2}, Syamsiah Mashohor², Gheyath Al Gawwam³, Rozi Mahmud⁴, Marsyita Binti Hanafi², Osama Alnuaimi⁵, Raad Josephine⁵, Abdullah Dhaifallah Almutairi⁴

Affiliations

¹ Department of Computer Science, Dijlah University College, Baghdad, Iraq.
² Department of Computer and Communication System Engineering, Universiti Putra Malaysia, Serdang, Malaysia.
³ Department of Neurology, Baghdad University, Baghdad, Iraq.
⁴ Department of Imaging, Universiti Putra Malaysia, Serdang, Malaysia.
⁵ Department of Radiology and Medical Imaging, Elias Emergency University Hospital, Bucharest, Romania.

Abstract

Magnetic resonance imaging (MRI) provides a significant key to diagnose and monitor the progression of multiple sclerosis (MS) disease. Manual MS-lesion segmentation, expanded disability status scale (EDSS) and patient's meta information can provide a gold standard for research in terms of automated MS-lesion quantification, automated EDSS prediction and identification of the correlation between MS-lesion and patient disability. In this dataset, we provide a novel multi-sequence MRI dataset of 60 MS patients with consensus manual lesion segmentation, EDSS, general patient information and clinical information. On this dataset, three radiologists and neurologist experts segmented and validated the manual MS-lesion segmentation for three MRI sequences T1-weighted, T2-weighted and fluid-attenuated inversion recovery (FLAIR). The dataset can be used to study the relationship between MS-lesion, EDSS and patient clinical information. Furthermore, it also can be used for the development of automated MS-lesion segmentation, patient disability prediction using MRI and correlation analysis between patient disability and MRI brain abnormalities include MS lesion location, size, number and type.

Keywords: Automated MS-lesion segmentation; Expanded disability status scale (EDSS); Gold standard; Ground truth data; Lesion masks; T1-weighted; T2-weighted and fluid-attenuated inversion recovery (FLAIR).