{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T17:01:06Z","timestamp":1786122066364,"version":"build-2736575974"},"reference-count":23,"publisher":"MDPI AG","issue":"16","license":[{"start":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T00:00:00Z","timestamp":1786060800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Imam Mohammad Ibn Saud Islamic University","award":["IMSIU-DDRSP2601"],"award-info":[{"award-number":["IMSIU-DDRSP2601"]}]},{"award":["IMSIU-DDRSP2601"],"award-info":[{"award-number":["IMSIU-DDRSP2601"]}],"id":[{"id":"https:\/\/ror.org\/05gxjyb39","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background: Multiple sclerosis (MS) is a chronic autoimmune demyelinating disease of the central nervous system, affecting more than 2.8 million individuals worldwide. Automated segmentation of white matter lesions on fluid-attenuated inversion recovery (FLAIR) magnetic resonance images (MRI) is essential for reproducible diagnosis and treatment monitoring, yet remains challenging due to extreme class imbalance, high lesion load variability, and poor contrast at lesion boundaries. Method: We propose a 2D U-Net with a ResNet50 encoder that exploits ImageNet-pretrained representations through a novel pseudo-RGB input strategy: three consecutive FLAIR slices centred on the target slice are stacked channel-wise to form a three-channel input, recovering inter-slice spatial context while enabling direct reuse of pretrained convolutional weights without modality-specific pretraining. A two-phase transfer-learning protocol first optimises only the decoder with the encoder frozen, then fine-tunes the upper encoder blocks at a reduced learning rate. Test-time augmentation (TTA) averaging over horizontal-flip and vertical-flip transformations further improves prediction robustness. Results: Evaluation on the held-out test set of the MSLesSeg2024 benchmark (12 patients, approximately 1650 axial slices) shows that the proposed model achieves a Dice similarity coefficient (DSC) of 0.714 (95% confidence interval (CI): 0.6845\u20130.7194), intersection-over-union (IoU) of 0.6571 (95% CI: 0.6272\u20130.6632), and area under the receiver operating characteristic (ROC) curve (AUC) of 0.9628 (95% CI: 0.9422\u20130.9793). Critically, the model records the lowest false-negative pixel count per slice (FNV = 33.6 px\/slice) across all ablation conditions, indicating superior sensitivity to lesion tissue; this is a property of direct clinical relevance for MS monitoring, where missed lesions carry the greatest diagnostic risk. A patient-matched comparison against a 3D nnU-Net baseline shows statistically comparable DSC (0.714 vs. 0.726; paired Wilcoxon p=0.68\u20130.79, not significant) alongside a substantially higher pixel-level AUC for the proposed model (0.963 vs. 0.773) and a true volumetric Hausdorff distance gap smaller than an earlier estimate (12.5 mm vs. 10.7 mm), showing an honest mixed-strengths result rather than an outright improvement. A supplementary ablation further shows that replicating a single FLAIR slice across all three channels significantly outperforms the pseudo-RGB adjacent-slice encoding (p&lt;0.001), indicating that the anticipated inter-slice-context benefit did not materialise here (see Discussion section). Cross-dataset evaluation on the independent MSSEG 2016 benchmark confirms generalisability: zero-shot transfer achieves DSC = 0.6562, recovering to DSC = 0.7046 after brief fine-tuning (30 epochs), within 1.5 percentage points of in-domain performance. Conclusions: The present study reveals that an optimized, lightweight 2D pipeline can rival the segmentation overlap of context-aware 3D baselines on specific datasets, doing so with a significantly reduced computational footprint. Given its strong pixel-wise discrimination, this methodology offers an effective and practical tool for routine automated MS lesion assessment in clinical settings.<\/jats:p>","DOI":"10.3390\/diagnostics16162494","type":"journal-article","created":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T08:01:36Z","timestamp":1786089696000},"page":"2494","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Pseudo-RGB Slice Stacking in 2D ResUNet for High-Sensitivity Multiple Sclerosis Lesion Segmentation"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-7566-0964","authenticated-orcid":false,"given":"Dhyey","family":"Desai","sequence":"first","affiliation":[{"name":"Department of Computer Science, USC Viterbi School of Engineering, University of Southern California, Los Angeles, CA 90089, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9593-5308","authenticated-orcid":false,"given":"Jayesh","family":"Gangrade","sequence":"additional","affiliation":[{"name":"School of Technology Management and Engineering (STME), SVKM\u2019s NMIMS Deemed to Be University, Indore 453112, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shweta","family":"Gangrade","sequence":"additional","affiliation":[{"name":"School of Technology Management and Engineering (STME), SVKM\u2019s NMIMS Deemed to Be University, Indore 453112, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5894-8895","authenticated-orcid":false,"given":"Atef","family":"Gharbi","sequence":"additional","affiliation":[{"name":"Department of Information Systems, Faculty of Computing and Information Technology, Northern Border University, Rafha 91911, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3405-1554","authenticated-orcid":false,"given":"Yassine","family":"Daadaa","sequence":"additional","affiliation":[{"name":"College of Computer and Information Sciences, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh 13318, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8011-1752","authenticated-orcid":false,"given":"Dhouha","family":"Ben Noureddine","sequence":"additional","affiliation":[{"name":"College of Computer and Information Sciences, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh 13318, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,7]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1502","DOI":"10.1016\/S0140-6736(08)61620-7","article-title":"Multiple sclerosis","volume":"372","author":"Compston","year":"2008","journal-title":"Lancet"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1816","DOI":"10.1177\/1352458520970841","article-title":"Rising prevalence of multiple sclerosis worldwide: Insights from the Atlas of MS, third edition","volume":"26","author":"Walton","year":"2020","journal-title":"Mult. Scler. J."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"162","DOI":"10.1016\/S1474-4422(17)30470-2","article-title":"Diagnosis of multiple sclerosis: 2017 revisions of the McDonald criteria","volume":"17","author":"Thompson","year":"2018","journal-title":"Lancet Neurol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1858","DOI":"10.1093\/brain\/awz144","article-title":"Assessment of lesions on magnetic resonance imaging in multiple sclerosis: Practical guidelines","volume":"142","author":"Filippi","year":"2019","journal-title":"Brain"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"118589","DOI":"10.1016\/j.neuroimage.2021.118589","article-title":"Multiple sclerosis lesions segmentation from multiple experts: The MICCAI 2016 challenge dataset","volume":"244","author":"Commowick","year":"2021","journal-title":"NeuroImage"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation. Proceedings of the Medical Image Computing and Computer-Assisted Intervention (MICCAI), Munich, Germany, 5\u20139 October 2015, Springer.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1016\/j.neuroimage.2017.04.034","article-title":"Improving automated multiple sclerosis lesion segmentation with a cascaded 3D convolutional neural network approach","volume":"155","author":"Valverde","year":"2017","journal-title":"NeuroImage"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.neuroimage.2019.03.068","article-title":"Multi-branch convolutional neural network for multiple sclerosis lesion segmentation","volume":"196","author":"Aslani","year":"2019","journal-title":"NeuroImage"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Zhang, H., and Oguz, I. (2021). Multiple sclerosis lesion segmentation\u2014A survey of supervised CNN-based methods. arXiv.","DOI":"10.1007\/978-3-030-72084-1_2"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","article-title":"nnU-Net: A self-configuring method for deep learning-based biomedical image segmentation","volume":"18","author":"Isensee","year":"2021","journal-title":"Nat. Methods"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"e70085","DOI":"10.1111\/jon.70085","article-title":"A Novel Convolutional Neural Network for Automated Multiple Sclerosis Brain Lesion Segmentation","volume":"35","author":"Dereskewicz","year":"2025","journal-title":"J. Neuroimaging"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"e70024","DOI":"10.1111\/jon.70024","article-title":"Subject-Based Transfer Learning in Longitudinal Multiple Sclerosis Lesion Segmentation","volume":"35","author":"Gaj","year":"2025","journal-title":"J. Neuroimaging"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Jain, S., Rajpal, N., and Soni, P.K. (2026). MS-DASPNet: Multiple Sclerosis lesion segmentation from brain MRI using dual attention and spatial pyramid pooling with transfer learning. Front. Comput. Neurosci., 19.","DOI":"10.3389\/fncom.2025.1713766"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., and Fei-Fei, L. (2009, January 20\u201325). ImageNet: A large-scale hierarchical image database. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Miami, FL, USA.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_16","unstructured":"MSLesSeg2024 Challenge Organizers (2026, June 22). MSLesSeg2024: ICPR 2024 Competition on Multiple Sclerosis Lesion Segmentation. ICPR 2024 Competition. Available online: https:\/\/iplab.dmi.unict.it\/mfs\/ms-les-seg\/."},{"key":"ref_17","first-page":"240","article-title":"Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations","volume":"Volume 10553","author":"Sudre","year":"2017","journal-title":"Proceedings of the Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support (DLMIA 2017)"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., and Doll\u00e1r, P. (2017, January 22\u201329). Focal Loss for Dense Object Detection. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref_19","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1016\/j.neucom.2019.01.103","article-title":"Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks","volume":"338","author":"Wang","year":"2019","journal-title":"Neurocomputing"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"297","DOI":"10.2307\/1932409","article-title":"Measures of the amount of ecologic association between species","volume":"26","author":"Dice","year":"1945","journal-title":"Ecology"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"850","DOI":"10.1109\/34.232073","article-title":"Comparing images using the Hausdorff distance","volume":"15","author":"Huttenlocher","year":"1993","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"80","DOI":"10.2307\/3001968","article-title":"Individual Comparisons by Ranking Methods","volume":"1","author":"Wilcoxon","year":"1945","journal-title":"Biom. Bull."}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/16\/2494\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T08:19:14Z","timestamp":1786090754000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/16\/2494"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,7]]},"references-count":23,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["diagnostics16162494"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics16162494","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,7]]}}}