{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T18:14:27Z","timestamp":1793211267068,"version":"4.5.0"},"reference-count":55,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T00:00:00Z","timestamp":1769990400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,2,18]],"date-time":"2026-02-18T00:00:00Z","timestamp":1771372800000},"content-version":"vor","delay-in-days":16,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>In recent years, explainable methods for artificial intelligence (XAI) have tried to reveal and describe models\u2019 decision mechanisms in the case of classification and even for segmentation. However, XAI methods for semantic segmentation and in particular for single specific instances (e.g. one given lesion among others of the same class in medical imaging) have yet to be developed to understand what drove the detection and contouring of the latter, which is crucial for all multi-lesional diseases. We proposed instance-level explanation maps for semantic segmentation extending both SmoothGrad and Grad-CAM++ methods and yielding quantitative instance saliency for the former. The instance-level methods were applied to the segmentation of white matter lesions (WML), a magnetic resonance imaging (MRI) biomarker in multiple sclerosis (MS). 687 patients diagnosed with MS for a total of 4023 FLAIR and MPRAGE MRI scans were collected at the University Hospital of Basel, Switzerland. WM lesion masks were annotated by four expert clinicians on baseline and follow-up imaging. Three deep learning networks\u2014a 3D U-Net, nnU-Net, and Swin UNETR\u2014were trained and tested on these data (test normalized Dice score, respectively of 0.71, 0.78, 0.80; true positive rate of 79%, 78%, and 85%; false discovery rate of 37%, 38%, and 36%; false negative rate of 20%, 22%, and 14%), then saliency maps were computed. Consistent with clinical practice, the proposed instance saliency maps revealed that the model relied more on FLAIR than MPRAGE to segment WMLs, with positive saliency values inside a lesion and negative in its neighborhood. FLAIR hyperintensity combined with healthy WM around the lesion border was required for their detection. Beyond the aforementioned sanity checks, we observed that peak values of the generated saliency maps presented distributions that differ significantly between TP, FN, FP and TN predictions, suggesting that the quantitative nature of the proposed saliency could be used to identify errors. In conclusion, we introduced two XAI methods to generate quantitative instance-level explanations in semantic segmentation. The proposed XAI maps can be applied to any architecture and could serve as a basis to (i) improve model performance (e.g. reducing FPs), (ii) optimize their internal architecture (e.g. patch size), and (iii) justify the model\u2019s decisions to the end users, which are contextualized to a specific lesion instance of interest.<\/jats:p>","DOI":"10.1038\/s41598-026-36560-9","type":"journal-article","created":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T01:35:12Z","timestamp":1769996112000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Instance-level quantitative saliency in multiple sclerosis lesion segmentation"],"prefix":"10.1038","volume":"16","author":[{"given":"Federico","family":"Spagnolo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nataliia","family":"Molchanova","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meritxell Bach","family":"Cuadra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mario","family":"Ocampo-Pineda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lester","family":"Melie-Garcia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cristina","family":"Granziera","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vincent","family":"Andrearczyk","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adrien","family":"Depeursinge","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,2,2]]},"reference":[{"key":"36560_CR1","doi-asserted-by":"publisher","first-page":"1068421","DOI":"10.3389\/fpsyg.2022.1068421","volume":"13","author":"A Ko\u0142tuniuk","year":"2023","unstructured":"Ko\u0142tuniuk, A., Pawlak, B., Kr\u00f3wczy\u0144ska, D. & Chojdak-\u0141ukasiewicz, J. The quality of life in patients with multiple sclerosis - Association with depressive symptoms and physical disability: A prospective and observational study. Front. Psychol. 13, 1068421. https:\/\/doi.org\/10.3389\/fpsyg.2022.1068421 (2023).","journal-title":"Front. Psychol."},{"key":"36560_CR2","doi-asserted-by":"publisher","first-page":"5877","DOI":"10.3390\/ijms23115877","volume":"23","author":"J Yang","year":"2022","unstructured":"Yang, J. et al. Current and future biomarkers in multiple sclerosis. Int. J. Mol. Sci. 23, 5877. https:\/\/doi.org\/10.3390\/ijms23115877 (2022).","journal-title":"Int. J. Mol. Sci."},{"key":"36560_CR3","doi-asserted-by":"publisher","first-page":"850","DOI":"10.1016\/S1474-4422(17)30470-2","volume":"17","author":"A Thompson","year":"2017","unstructured":"Thompson, A. et al. Diagnosis of multiple sclerosis: 2017 revisions of the McDonald criteria. Lancet Neurol. 17, 850\u2013865. https:\/\/doi.org\/10.1016\/S1474-4422(17)30470-2 (2017).","journal-title":"Lancet Neurol."},{"key":"36560_CR4","first-page":"28969","volume":"8","author":"C Hemond","year":"2018","unstructured":"Hemond, C. & Bakshi, R. Magnetic resonance imaging in multiple sclerosis. Cold Spring Harbor Persp. Med. 8, 28969 (2018).","journal-title":"Cold Spring Harbor Persp. Med."},{"key":"36560_CR5","doi-asserted-by":"publisher","first-page":"995","DOI":"10.1111\/ene.12931","volume":"23","author":"X Ayrignac","year":"2016","unstructured":"Ayrignac, X. et al. Brain magnetic resonance imaging helps to differentiate atypical multiple sclerosis with cavitary lesions and vanishing white matter disease. Eur. J Neurol 23, 995. https:\/\/doi.org\/10.1111\/ene.12931 (2016).","journal-title":"Eur. J Neurol"},{"key":"36560_CR6","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0144693","volume":"10","author":"C Thaler","year":"2015","unstructured":"Thaler, C. et al. T1- thresholds in black holes increase clinical-radiological correlation in multiple sclerosis patients. PLOS ONE 10, e0144693. https:\/\/doi.org\/10.1371\/journal.pone.0144693 (2015).","journal-title":"PLOS ONE"},{"key":"36560_CR7","doi-asserted-by":"publisher","unstructured":"Alrabai, A., Echtioui, A. & Hamida, A. Multiple Sclerosis Segmentation using Deep Learning Models : Comparative Study. In 2022 6th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP), 1\u20136, https:\/\/doi.org\/10.1109\/ATSIP55956.2022.9805983 (2022).","DOI":"10.1109\/ATSIP55956.2022.9805983"},{"key":"36560_CR8","doi-asserted-by":"publisher","DOI":"10.3389\/fninf.2020.610967","volume":"14","author":"C Zeng","year":"2020","unstructured":"Zeng, C., Gu, L., Liu, Z. & Zhao, S. Review of deep learning approaches for the segmentation of multiple sclerosis lesions on brain MRI. Front. Neuroinform. 14, 610967. https:\/\/doi.org\/10.3389\/fninf.2020.610967 (2020).","journal-title":"Front. Neuroinform."},{"issue":"6","key":"36560_CR9","doi-asserted-by":"publisher","first-page":"2680","DOI":"10.1109\/JBHI.2022.3151741","volume":"26","author":"Y Ma","year":"2022","unstructured":"Ma, Y. et al. Multiple Sclerosis lesion analysis in brain magnetic resonance images: techniques and clinical applications. IEEE J. Biomed. Health Inform. 26(6), 2680\u20132692 (2022).","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"36560_CR10","doi-asserted-by":"publisher","first-page":"2103","DOI":"10.1007\/s00234-022-03019-3","volume":"64","author":"M Diaz-Hurtado","year":"2022","unstructured":"Diaz-Hurtado, M. et al. Recent advances in the longitudinal segmentation of multiple sclerosis lesions on magnetic resonance imaging: a review. Neuroradiology 64, 2103. https:\/\/doi.org\/10.1007\/s00234-022-03019-3 (2022).","journal-title":"Neuroradiology"},{"key":"36560_CR11","doi-asserted-by":"publisher","first-page":"1176625","DOI":"10.3389\/fnins.2023.1176625","volume":"17","author":"O Commowick","year":"2023","unstructured":"Commowick, O., Comb\u00e8s, B., Cervenansky, F. & Dojat, M. Editorial: Automatic methods for multiple sclerosis new lesions detection and segmentation. Front. Neurosci. 17, 1176625. https:\/\/doi.org\/10.3389\/fnins.2023.1176625 (2023).","journal-title":"Front. Neurosci."},{"key":"36560_CR12","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1186\/s41747-020-00159-0","volume":"4","author":"G Baselli","year":"2020","unstructured":"Baselli, G., Codari, M. & Sardanelli, F. Opening the black box of machine learning in radiology: Can the proximity of annotated cases be a way?. Eur. Radiol. Exp. 4, 30. https:\/\/doi.org\/10.1186\/s41747-020-00159-0 (2020).","journal-title":"Eur. Radiol. Exp."},{"key":"36560_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.nicl.2023.103491","volume":"39","author":"F Spagnolo","year":"2023","unstructured":"Spagnolo, F. et al. How far MS lesion detection and segmentation are integrated into the clinical workflow? A systematic review. NeuroImage Clin. 39, 103491. https:\/\/doi.org\/10.1016\/j.nicl.2023.103491 (2023).","journal-title":"NeuroImage Clin."},{"key":"36560_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.107620","volume":"129","author":"K Kobayashi","year":"2024","unstructured":"Kobayashi, K. & Alam, S. B. Explainable, interpretable, and trustworthy ai for an intelligent digital twin: A case study on remaining useful life. Eng. Appl. Artif. Intell. 129, 107620. https:\/\/doi.org\/10.1016\/j.engappai.2023.107620 (2024).","journal-title":"Eng. Appl. Artif. Intell."},{"key":"36560_CR15","doi-asserted-by":"publisher","first-page":"1074","DOI":"10.1007\/s00415-015-7689-4","volume":"262","author":"L Jonkman","year":"2015","unstructured":"Jonkman, L. et al. Can MS lesion stages be distinguished with MRI? A postmortem MRI and histopathology study. J. Neurol. 262, 1074. https:\/\/doi.org\/10.1007\/s00415-015-7689-4 (2015).","journal-title":"J. Neurol."},{"key":"36560_CR16","doi-asserted-by":"publisher","unstructured":"Varatharasan, V. et al. Workshop on Research. Education and Development of Unmanned Aerial Systems (RED UAS) 78\u201385, 2019. https:\/\/doi.org\/10.1109\/REDUAS47371.2019.8999695 (2019).","DOI":"10.1109\/REDUAS47371.2019.8999695"},{"key":"36560_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.dajour.2023.100230","volume":"7","author":"A Saranya","year":"2023","unstructured":"Saranya, A. & Subhashini, R. A systematic review of explainable artificial intelligence models and applications: Recent developments and future trends. Decis. Anal. J. 7, 100230. https:\/\/doi.org\/10.1016\/j.dajour.2023.100230 (2023).","journal-title":"Decis. Anal. J."},{"key":"36560_CR18","unstructured":"Simonyan, K., Vedaldi, A. & Zisserman, A. Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps. 2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, April 14-16, 2014, Workshop Track Proceedings (2013)."},{"key":"36560_CR19","doi-asserted-by":"publisher","first-page":"1180773","DOI":"10.3389\/fmed.2023.1180773","volume":"10","author":"B de Vries","year":"2023","unstructured":"de Vries, B. et al. Explainable artificial intelligence (XAI) in radiology and nuclear medicine: A literature review. Front. Med. 10, 1180773. https:\/\/doi.org\/10.3389\/fmed.2023.1180773 (2023).","journal-title":"Front. Med."},{"key":"36560_CR20","unstructured":"Smilkov, D., Thorat, N., Kim, B., Vi\u00e9gas, F. & Wattenberg, M. SmoothGrad: removing noise by adding noise. CoRR (2017)."},{"key":"36560_CR21","doi-asserted-by":"publisher","unstructured":"Goh, G. S.\u00a0W., Lapuschkin, S., Weber, L., Samek, W. & Binder, A. Understanding Integrated Gradients with SmoothTaylor for Deep Neural Network Attribution. In 2020 25th International Conference on Pattern Recognition (ICPR), 4949\u20134956, https:\/\/doi.org\/10.1109\/ICPR48806.2021.9413242 (2021).","DOI":"10.1109\/ICPR48806.2021.9413242"},{"key":"36560_CR22","doi-asserted-by":"publisher","unstructured":"Agarwal, S. et al. Towards the unification and robustness of perturbation and gradient based explanations. In Proceedings of the 38th International Conference on Machine Learning, vol. 139, 110\u2013119, https:\/\/doi.org\/10.48550\/arXiv.2102.10618 (2021).","DOI":"10.48550\/arXiv.2102.10618"},{"key":"36560_CR23","doi-asserted-by":"publisher","unstructured":"Selvaraju, R.\u00a0R. et al. Grad-cam: Visual explanations from deep networks via gradient-based localization. In 2017 IEEE International Conference on Computer Vision (ICCV), 618\u2013626, https:\/\/doi.org\/10.1109\/ICCV.2017.74 (2017).","DOI":"10.1109\/ICCV.2017.74"},{"key":"36560_CR24","doi-asserted-by":"publisher","unstructured":"Chattopadyhay, A., Sarkar, A., Howlader, P. & Balasubramanian, V.\u00a0N. Grad-CAM++: Generalized Gradient-Based Visual Explanations for Deep Convolutional Networks. In 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), 839\u2013847, https:\/\/doi.org\/10.1109\/WACV.2018.00097 (2018).","DOI":"10.1109\/WACV.2018.00097"},{"key":"36560_CR25","doi-asserted-by":"publisher","unstructured":"Rajpurkar, P. et al. CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning. arXiv https:\/\/doi.org\/10.48550\/arXiv.1711.05225 (2017).","DOI":"10.48550\/arXiv.1711.05225"},{"key":"36560_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102551","volume":"81","author":"D Mahapatra","year":"2022","unstructured":"Mahapatra, D., Poellinger, A. & Reyes, M. Interpretability-guided inductive bias for deep learning based medical image. Med. Image Anal. 81, 102551. https:\/\/doi.org\/10.1016\/j.media.2022.102551 (2022).","journal-title":"Med. Image Anal."},{"key":"36560_CR27","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2021200267","volume":"3","author":"N Arun","year":"2021","unstructured":"Arun, N. et al. Assessing the (Un)trustworthiness of saliency maps for localizing abnormalities in medical imaging. Radiol. Artif. Intell. 3, e200267. https:\/\/doi.org\/10.1148\/ryai.2021200267 (2021).","journal-title":"Radiol. Artif. Intell."},{"key":"36560_CR28","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0276836","volume":"17","author":"RK Singh","year":"2022","unstructured":"Singh, R. K., Gorantla, R., Allada, S. & Narra, P. SkiNet: A deep learning framework for skin lesion diagnosis with uncertainty estimation and explainability. PloS one 17, e0276836. https:\/\/doi.org\/10.1371\/journal.pone.0276836 (2022).","journal-title":"PloS one"},{"key":"36560_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.101619","volume":"60","author":"K Wickstr\u00f8m","year":"2020","unstructured":"Wickstr\u00f8m, K., Kampffmeyer, M. & Jenssen, R. Uncertainty and interpretability in convolutional neural networks for semantic segmentation of colorectal polyps. Med. Image Anal. 60, 101619. https:\/\/doi.org\/10.1016\/j.media.2019.101619 (2020).","journal-title":"Med. Image Anal."},{"key":"36560_CR30","doi-asserted-by":"publisher","unstructured":"Vinogradova, K., Dibrov, A. & Myers, G. Towards Interpretable Semantic Segmentation via Gradient-weighted Class Activation Mapping. In Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI 2020), vol.\u00a034, 13943\u201313944, https:\/\/doi.org\/10.1609\/aaai.v34i10.7244 (2020).","DOI":"10.1609\/aaai.v34i10.7244"},{"key":"36560_CR31","doi-asserted-by":"publisher","unstructured":"Cordts, M. et al. The Cityscapes Dataset for Semantic Urban Scene Understanding. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 3213\u20133223, https:\/\/doi.org\/10.1109\/CVPR.2016.350 (2016).","DOI":"10.1109\/CVPR.2016.350"},{"key":"36560_CR32","doi-asserted-by":"publisher","unstructured":"Spagnolo, F. et al. Exploiting XAI Maps to Improve MS Lesion Segmentation and Detection in MRI. In Celebi, M.\u00a0E., Reyes, M., Chen, Z. & Li, X. (eds.) Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2024 Workshops, 121\u2013131, https:\/\/doi.org\/10.1007\/978-3-031-77610-6_12 (Springer Nature Switzerland, Cham, 2025).","DOI":"10.1007\/978-3-031-77610-6_12"},{"key":"36560_CR33","doi-asserted-by":"publisher","unstructured":"Disanto, G. et al. The swiss multiple sclerosis cohort-study (SMSC): A prospective swiss wide investigation of key phases in disease evolution and new treatment options. PLoS One 11(3), https:\/\/doi.org\/10.1371\/journal.pone.0152347 (2016).","DOI":"10.1371\/journal.pone.0152347"},{"key":"36560_CR34","doi-asserted-by":"publisher","DOI":"10.1016\/j.nicl.2020.102335","volume":"27","author":"F La Rosa","year":"2020","unstructured":"La Rosa, F. et al. Multiple sclerosis cortical and WM lesion segmentation at 3T MRI: A deep learning method based on FLAIR and MP2RAGE. NeuroImage Clin. 27, 102335. https:\/\/doi.org\/10.1016\/j.nicl.2020.102335 (2020).","journal-title":"NeuroImage Clin."},{"key":"36560_CR35","doi-asserted-by":"publisher","unstructured":"\u00c7i\u00e7ek, O., Abdulkadir, A., Lienkamp, S.\u00a0S., Brox, T. & Ronneberger, O. 3D U-Net: Learning dense volumetric segmentation from sparse annotation. arXiv https:\/\/doi.org\/10.48550\/ARXIV.1606.06650 (2016).","DOI":"10.48550\/ARXIV.1606.06650"},{"key":"36560_CR36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41592-020-01008-z","volume":"18","author":"F Isensee","year":"2021","unstructured":"Isensee, F., Jaeger, P., Kohl, S., Petersen, J. & Maier-Hein, K. nnu-net: A self-configuring method for deep learning-based biomedical image segmentation. Nat. Methods 18, 1\u20139. https:\/\/doi.org\/10.1038\/s41592-020-01008-z (2021).","journal-title":"Nat. Methods"},{"key":"36560_CR37","doi-asserted-by":"publisher","unstructured":"Hatamizadeh, A. et al. Unetr: Transformers for 3d medical image segmentation. In Winter Conference on Applications of Computer Vision (WACV) https:\/\/doi.org\/10.1109\/WACV51458.2022.00181 (2022).","DOI":"10.1109\/WACV51458.2022.00181"},{"key":"36560_CR38","doi-asserted-by":"publisher","unstructured":"Raina, V. et al. Tackling Bias in the Dice Similarity Coefficient: Introducing NDSC for White Matter Lesion Segmentation. In 2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI), 1\u20135, https:\/\/doi.org\/10.1109\/ISBI53787.2023.10230755 (2023).","DOI":"10.1109\/ISBI53787.2023.10230755"},{"key":"36560_CR39","doi-asserted-by":"publisher","unstructured":"Kofler, F. et al. Blob loss: instance imbalance aware loss functions for semantic segmentation. arXiv https:\/\/doi.org\/10.48550\/ARXIV.2205.08209 (2022).","DOI":"10.48550\/ARXIV.2205.08209"},{"key":"36560_CR40","doi-asserted-by":"publisher","unstructured":"Maier-Hein, L. et al. Metrics reloaded: Pitfalls and recommendations for image analysis validation. arXiv.orghttps:\/\/doi.org\/10.48550\/arXiv.2206.01653 (2022).","DOI":"10.48550\/arXiv.2206.01653"},{"key":"36560_CR41","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1109\/TMI.2009.2035616","volume":"29","author":"S Klein","year":"2009","unstructured":"Klein, S., Staring, M., Murphy, K., Viergever, M. & Pluim, J. Elastix: A toolbox for intensity-based medical image registration. IEEE Trans. Med. Imaging 29, 196\u2013205. https:\/\/doi.org\/10.1109\/TMI.2009.2035616 (2009).","journal-title":"IEEE Trans. Med. Imaging"},{"key":"36560_CR42","doi-asserted-by":"publisher","first-page":"50","DOI":"10.3389\/fninf.2013.00050","volume":"7","author":"D Shamonin","year":"2014","unstructured":"Shamonin, D. et al. Fast parallel image registration on CPU and GPU for diagnostic classification of Alzheimer\u2019s disease. Front. Neuroinform. 7, 50. https:\/\/doi.org\/10.3389\/fninf.2013.00050 (2014).","journal-title":"Front. Neuroinform."},{"key":"36560_CR43","doi-asserted-by":"publisher","first-page":"1310","DOI":"10.1109\/TMI.2010.2046908","volume":"29","author":"N Tustison","year":"2010","unstructured":"Tustison, N. et al. N4ITK: improved N3 bias correction. Med. Imaging, IEEE Trans. 29, 1310\u20131320. https:\/\/doi.org\/10.1109\/TMI.2010.2046908 (2010).","journal-title":"Med. Imaging, IEEE Trans."},{"key":"36560_CR44","doi-asserted-by":"publisher","unstructured":"Depeursinge, A. et al. Standardised convolutional filtering for radiomics. arXiv https:\/\/doi.org\/10.48550\/arXiv.2006.05470 (2020).","DOI":"10.48550\/arXiv.2006.05470"},{"key":"36560_CR45","doi-asserted-by":"publisher","first-page":"840","DOI":"10.1002\/ana.20703","volume":"58","author":"CH Polman","year":"2005","unstructured":"Polman, C. H. et al. Diagnostic criteria for multiple sclerosis: 2005 revisions to the \u201cMcDonald Criteria\u2019\u2019. Annal. Neurol. 58, 840\u2013846. https:\/\/doi.org\/10.1002\/ana.20703 (2005).","journal-title":"Annal. Neurol."},{"key":"36560_CR46","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1016\/j.msard.2019.01.042","volume":"29","author":"S Grahl","year":"2019","unstructured":"Grahl, S. et al. Evidence for a white matter lesion size threshold to support the diagnosis of relapsing remitting multiple sclerosis. Multi. Sclerosis Related Disorders 29, 124\u2013129. https:\/\/doi.org\/10.1016\/j.msard.2019.01.042 (2019).","journal-title":"Multi. Sclerosis Related Disorders"},{"key":"36560_CR47","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1016\/j.nicl.2018.01.011","volume":"18","author":"MJ Fartaria","year":"2018","unstructured":"Fartaria, M. J. et al. Partial volume-aware assessment of multiple sclerosis lesions. NeuroImage Clin. 18, 245\u2013253. https:\/\/doi.org\/10.1016\/j.nicl.2018.01.011 (2018).","journal-title":"NeuroImage Clin."},{"key":"36560_CR48","doi-asserted-by":"publisher","first-page":"21348","DOI":"10.1038\/s41598-024-72649-9","volume":"14","author":"A De Rosa","year":"2024","unstructured":"De Rosa, A. et al. Consensus of algorithms for lesion segmentation in brain MRI studies of multiple sclerosis. Sci. Rep 14, 21348. https:\/\/doi.org\/10.1038\/s41598-024-72649-9 (2024).","journal-title":"Sci. Rep"},{"key":"36560_CR49","doi-asserted-by":"publisher","first-page":"576","DOI":"10.3389\/fnins.2016.00576","volume":"10","author":"S Jain","year":"2016","unstructured":"Jain, S. et al. Two time point MS lesion segmentation in brain MRI: An expectation-maximization framework. Front. Neurosci. 10, 576. https:\/\/doi.org\/10.3389\/fnins.2016.00576 (2016).","journal-title":"Front. Neurosci."},{"key":"36560_CR50","unstructured":"McKnight, P.\u00a0E. & Najab, J. Mann-Whitney U Test (John Wiley & Sons, Ltd, 2010)."},{"key":"36560_CR51","doi-asserted-by":"crossref","unstructured":"Zhang, H. et al. Multiple sclerosis lesion segmentation with tiramisu and 2.5d stacked slices. In Shen, D. et al. (eds.) Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2019, 338\u2013346 (Springer International Publishing, 2019).","DOI":"10.1007\/978-3-030-32248-9_38"},{"key":"36560_CR52","unstructured":"Commowick, O., Cervenansky, F., Cotton, F. & Dojat, M. MSSEG-2 challenge proceedings: Multiple sclerosis new lesions segmentation challenge using a data management and processing infrastructure. In MICCAI 2021 - 24th International Conference on Medical Image Computing and Computer Assisted Intervention, 126 (2021)."},{"key":"36560_CR53","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1136\/jnnp.2005.073213","volume":"76","author":"SA Trip","year":"2005","unstructured":"Trip, S. A. & Miller, D. H. Imaging in multiple sclerosis. J. Neurol. Neurosurgery Psychiatry 76, 11\u201318. https:\/\/doi.org\/10.1136\/jnnp.2005.073213 (2005).","journal-title":"J. Neurol. Neurosurgery Psychiatry"},{"key":"36560_CR54","doi-asserted-by":"publisher","first-page":"1214","DOI":"10.1177\/1352458508094644","volume":"14","author":"F Nelson","year":"2008","unstructured":"Nelson, F., Poonawalla, A., Hou, P., Wolinsky, J. & Narayana, P. 3D MPRAGE improves classification of cortical lesions in multiple sclerosis. Multi. Sclerosis (Houndmills, Basingstoke, England) 14, 1214\u20139. https:\/\/doi.org\/10.1177\/1352458508094644 (2008).","journal-title":"Multi. Sclerosis (Houndmills, Basingstoke, England)"},{"key":"36560_CR55","doi-asserted-by":"publisher","unstructured":"Luo, W., Li, Y., Urtasun, R. & Zemel, R. Understanding the effective receptive field in deep convolutional neural networks. In 30th Conference on Neural Information Processing Systems (NIPS 2016), 839\u2013847, https:\/\/doi.org\/10.1109\/WACV.2018.00097 (2016).","DOI":"10.1109\/WACV.2018.00097"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-36560-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-36560-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-36560-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,18]],"date-time":"2026-02-18T11:56:57Z","timestamp":1771415817000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-36560-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,2]]},"references-count":55,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["36560"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-36560-9","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,2]]},"assertion":[{"value":"22 October 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 January 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 February 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The University Hospital Basel (USB) and the Research Center for Clinical neuroimmunology and Neuroscience (RC2NB), as the employers of Cristina Granziera, have received the following fees which were used exclusively for research support from Siemens, GeNeuro, Genzyme-Sanofi, Biogen, Roche. They also have received advisory board and consultancy fees from Actelion, Genzyme-Sanofi, Novartis, GeNeuro, Merck, Biogen and Roche; as well as speaker fees from Genzyme-Sanofi, Novartis, GeNeuro, Merck, Biogen and Roche.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"6917"}}