ORIGINAL RESEARCH article
Front. Neurol.
Sec. Artificial Intelligence in Neurology
DenseLes: Slice-Wise Dense Network for Multiple Sclerosis Lesion Segmentation and Classication
Melinda Katona
Bence Bozsik
Péter Bodnár
Krisztián Kocsis
Eszter Tóth
Nikoletta Szabó
András Király
Péter Faragó
László G. Nyúl
Dániel Veréb
Zsigmond Tamás Kincses
University of Szeged, Szeged, Hungary
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Abstract
Accurate and reliable segmentation of multiple sclerosis (MS) lesions from magnetic resonance imaging (MRI) is essential for diagnosis and monitoring disease progression. Therefore, a robust and ecient au-tomated approach can provide information about the patient rapidly. We propose a convolutional neural network-based method to segment lesions from FLAIR images. The DenseLes system includes two stages: pre-processing of image data (brain extraction, standardization) then segmentation of MS lesions using an end-to-end slice-wise dense network. We also identify the segmented lesions in specic locations (periventric-ular, (juxta)cortical, infratentorial, spinal). DenseLes is evaluated and compared to other methods on our assembled data and the public MSSEG 2016 MS challenge dataset. Our model demonstrates a signicant improvement in segmentation quality over previous approaches, achieving an average Dice score of 0.80% on the Szeged MS dataset. On the MSSEG 2016 data, our method produced Dice scores ranging from 0.32% to 0.73%, a performance that is comparable to that of human raters.
Summary
Keywords
brain extraction, brain MRI, Convolutio nal Neural Networks (CNN), lesion segmentation, multiple sclerois
Received
12 September 2025
Accepted
06 February 2026
Copyright
© 2026 Katona, Bozsik, Bodnár, Kocsis, Tóth, Szabó, Király, Faragó, Nyúl, Veréb and Kincses. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
*Correspondence: Zsigmond Tamás Kincses
Disclaimer
All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.