MSLesSeg: baseline and benchmarking of a new Multiple Sclerosis Lesion Segmentation dataset
Abstract This paper presents MSLesSeg, a new, publicly accessible MRI dataset designed to advance research in Multiple Sclerosis (MS) lesion segmentation. The dataset comprises 115 scans of 75 patients including T1, T2 and FLAIR sequences, along with supplementary clinical data collected across diff...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-05-01
|
| Series: | Scientific Data |
| Online Access: | https://doi.org/10.1038/s41597-025-05250-y |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850243117855277056 |
|---|---|
| author | Francesco Guarnera Alessia Rondinella Elena Crispino Giulia Russo Clara Di Lorenzo Davide Maimone Francesco Pappalardo Sebastiano Battiato |
| author_facet | Francesco Guarnera Alessia Rondinella Elena Crispino Giulia Russo Clara Di Lorenzo Davide Maimone Francesco Pappalardo Sebastiano Battiato |
| author_sort | Francesco Guarnera |
| collection | DOAJ |
| description | Abstract This paper presents MSLesSeg, a new, publicly accessible MRI dataset designed to advance research in Multiple Sclerosis (MS) lesion segmentation. The dataset comprises 115 scans of 75 patients including T1, T2 and FLAIR sequences, along with supplementary clinical data collected across different sources. Expert-validated annotations provide high-quality lesion segmentation labels, establishing a reliable human-labeled dataset for benchmarking. Part of the dataset was shared with expert scientists with the aim to compare the last automatic AI-based image segmentation solutions with an expert-biased handmade segmentation. In addition, an AI-based lesion segmentation of MSLesSeg was developed and technically validated against the last state-of-the-art methods. The dataset, the detailed analysis of researcher contributions, and the baseline results presented here mark a significant milestone for advancing automated MS lesion segmentation research. |
| format | Article |
| id | doaj-art-b4ac993e078142838d6f20eccb523c2b |
| institution | OA Journals |
| issn | 2052-4463 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Data |
| spelling | doaj-art-b4ac993e078142838d6f20eccb523c2b2025-08-20T02:00:06ZengNature PortfolioScientific Data2052-44632025-05-0112111010.1038/s41597-025-05250-yMSLesSeg: baseline and benchmarking of a new Multiple Sclerosis Lesion Segmentation datasetFrancesco Guarnera0Alessia Rondinella1Elena Crispino2Giulia Russo3Clara Di Lorenzo4Davide Maimone5Francesco Pappalardo6Sebastiano Battiato7Department of Mathematics and Computer Science, University of CataniaDepartment of Mathematics and Computer Science, University of CataniaDepartment of Biomedical and Biotechnological Sciences, University of CataniaDepartment of Drug and Health Sciences, University of CataniaUOC Radiologia, ARNAS GaribaldiCentro Sclerosi Multipla, UOC Neurologia, Azienda Ospedaliera per l’Emergenza CannizzaroDepartment of Drug and Health Sciences, University of CataniaDepartment of Mathematics and Computer Science, University of CataniaAbstract This paper presents MSLesSeg, a new, publicly accessible MRI dataset designed to advance research in Multiple Sclerosis (MS) lesion segmentation. The dataset comprises 115 scans of 75 patients including T1, T2 and FLAIR sequences, along with supplementary clinical data collected across different sources. Expert-validated annotations provide high-quality lesion segmentation labels, establishing a reliable human-labeled dataset for benchmarking. Part of the dataset was shared with expert scientists with the aim to compare the last automatic AI-based image segmentation solutions with an expert-biased handmade segmentation. In addition, an AI-based lesion segmentation of MSLesSeg was developed and technically validated against the last state-of-the-art methods. The dataset, the detailed analysis of researcher contributions, and the baseline results presented here mark a significant milestone for advancing automated MS lesion segmentation research.https://doi.org/10.1038/s41597-025-05250-y |
| spellingShingle | Francesco Guarnera Alessia Rondinella Elena Crispino Giulia Russo Clara Di Lorenzo Davide Maimone Francesco Pappalardo Sebastiano Battiato MSLesSeg: baseline and benchmarking of a new Multiple Sclerosis Lesion Segmentation dataset Scientific Data |
| title | MSLesSeg: baseline and benchmarking of a new Multiple Sclerosis Lesion Segmentation dataset |
| title_full | MSLesSeg: baseline and benchmarking of a new Multiple Sclerosis Lesion Segmentation dataset |
| title_fullStr | MSLesSeg: baseline and benchmarking of a new Multiple Sclerosis Lesion Segmentation dataset |
| title_full_unstemmed | MSLesSeg: baseline and benchmarking of a new Multiple Sclerosis Lesion Segmentation dataset |
| title_short | MSLesSeg: baseline and benchmarking of a new Multiple Sclerosis Lesion Segmentation dataset |
| title_sort | mslesseg baseline and benchmarking of a new multiple sclerosis lesion segmentation dataset |
| url | https://doi.org/10.1038/s41597-025-05250-y |
| work_keys_str_mv | AT francescoguarnera mslessegbaselineandbenchmarkingofanewmultiplesclerosislesionsegmentationdataset AT alessiarondinella mslessegbaselineandbenchmarkingofanewmultiplesclerosislesionsegmentationdataset AT elenacrispino mslessegbaselineandbenchmarkingofanewmultiplesclerosislesionsegmentationdataset AT giuliarusso mslessegbaselineandbenchmarkingofanewmultiplesclerosislesionsegmentationdataset AT claradilorenzo mslessegbaselineandbenchmarkingofanewmultiplesclerosislesionsegmentationdataset AT davidemaimone mslessegbaselineandbenchmarkingofanewmultiplesclerosislesionsegmentationdataset AT francescopappalardo mslessegbaselineandbenchmarkingofanewmultiplesclerosislesionsegmentationdataset AT sebastianobattiato mslessegbaselineandbenchmarkingofanewmultiplesclerosislesionsegmentationdataset |