{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T16:24:45Z","timestamp":1784391885604,"version":"3.55.0"},"reference-count":22,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T00:00:00Z","timestamp":1760313600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>Accurate segmentation of multiple sclerosis (MS) lesions from 3D MRI scans is essential for diagnosis, disease monitoring, and treatment planning. However, this task remains challenging due to the sparsity, heterogeneity, and subtle appearance of lesions, as well as the difficulty in obtaining high-quality annotations. In this study, we propose Efficient-Net3D-UNet, a deep learning framework that combines compound-scaled MBConv3D blocks with a lesion-aware patch sampling strategy to improve volumetric segmentation performance across multi-modal MRI sequences (FLAIR, T1, and T2). The model was evaluated against a conventional 3D U-Net baseline using standard metrics including Dice similarity coefficient, precision, recall, accuracy, and specificity. On a held-out test set, EfficientNet3D-UNet achieved a Dice score of 48.39%, precision of 49.76%, and recall of 55.41%, outperforming the baseline 3D U-Net, which obtained a Dice score of 31.28%, precision of 32.48%, and recall of 43.04%. Both models reached an overall accuracy of 99.14%. Notably, EfficientNet3D-UNet also demonstrated faster convergence and reduced overfitting during training. These results highlight the potential of EfficientNet3D-UNet as a robust and computationally efficient solution for automated MS lesion segmentation, offering promising applicability in real-world clinical settings.<\/jats:p>","DOI":"10.3390\/jimaging11100361","type":"journal-article","created":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T10:37:14Z","timestamp":1760438234000},"page":"361","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Lesion-Aware Patch Sampling Approach with EfficientNet3D-UNet for Robust Multiple Sclerosis Lesion Segmentation"],"prefix":"10.3390","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8297-2329","authenticated-orcid":false,"given":"Hind","family":"Almaaz","sequence":"first","affiliation":[{"name":"College of Computing and Information Technology, Shaqra University, Shaqra 11911, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1376-9607","authenticated-orcid":false,"given":"Samia","family":"Dardouri","sequence":"additional","affiliation":[{"name":"College of Computing and Information Technology, Shaqra University, Shaqra 11911, Saudi Arabia"},{"name":"InnoV\u2019COM Laboratory-Sup\u2019Com, University of Carthage, Ariana 2083, Tunisia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,10,13]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1016\/B978-0-323-95343-6.00006-6","article-title":"Neuroimaging in multiple sclerosis and related disorders: Advancements and concepts","volume":"1","author":"Sriwastava","year":"2024","journal-title":"Clin. Asp. Mult. Scler. Essent. Curr. Updates"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1186\/s40644-024-00675-x","article-title":"Automated segmentation of lesions and organs at risk on [68Ga] Ga-PSMA-11 PET\/CT images using self-supervised learning with Swin UNETR","volume":"24","author":"Yazdani","year":"2024","journal-title":"Cancer Imaging"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Wahlig, S.G., Nedelec, P., Weiss, D.A., Rudie, J.D., Sugrue, L.P., and Rauschecker, A.M. (2023). 3D U-Net for automated detection of multiple sclerosis lesions: Utility of transfer learning from other pathologies. Front. Neurosci., 17.","DOI":"10.3389\/fnins.2023.1188336"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Ashtari, P., Barile, B., Van Huffel, S., and Sappey-Marinier, D. (2022). New multiple sclerosis lesion segmentation and detection using pre-activation U-Net. Front. Neurosci., 16.","DOI":"10.3389\/fnins.2022.975862"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Krishnan, A.P., Song, Z., Clayton, D., Jia, X., De Crespigny, A., and Carano, R.A. (2023). Multi-arm U-Net with dense input and skip connectivity for T2 lesion segmentation in clinical trials of multiple sclerosis. Sci. Rep., 13.","DOI":"10.1038\/s41598-023-31207-5"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Zeng, C., Gu, L., Liu, Z., and Zhao, S. (2020). Review of deep learning approaches for the segmentation of multiple sclerosis lesions on brain MRI. Front. Neuroinform., 14.","DOI":"10.3389\/fninf.2020.610967"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"McKinley, R., Wepfer, R., Aschwanden, F., Grunder, L., Muri, R., Rummel, C., Verma, R., Weisstanner, C., Reyes, M., and Salmen, A. (2021). Simultaneous lesion and brain segmentation in multiple sclerosis using deep neural networks. Sci. Rep., 11.","DOI":"10.1038\/s41598-020-79925-4"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Naeeni Davarani, M., Arian Darestani, A., Guillen Ca\u00f1as, V., Azimi, H., Havadaragh, S.H., Hashemi, H., and Harirchian, M.H. (2024). Efficient segmentation of active and inactive plaques in FLAIR-images using DeepLabV3Plus SE with efficientnetb0 backbone in multiple sclerosis. Sci. Rep., 14.","DOI":"10.1038\/s41598-024-67130-6"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Raab, F., Malloni, W., Wein, S., Greenlee, M.W., and Lang, E.W. (2023). Investigation of an efficient multi-modal convolutional neural network for multiple sclerosis lesion detection. Sci. Rep., 13.","DOI":"10.1038\/s41598-023-48578-4"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Preetha, R., Jasmine Pemeena Priyadarsini, M., and Nisha, J.S. (2025). Brain tumor segmentation using multi-scale attention U-Net with EfficientNetB4 encoder for enhanced MRI analysis. Sci. Rep., 15.","DOI":"10.1038\/s41598-025-94267-9"},{"key":"ref_11","unstructured":"Zhang, L., Wang, Y., Wang, X., Li, Z., Zhao, L., and Shi, F. (2023). EfficientNet3D-UNet with Lesion-Aware Patch Sampling for Accurate Multiple Sclerosis Lesion Segmentation. arXiv."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"2412","DOI":"10.38124\/ijisrt\/IJISRT24SEP1439","article-title":"F.sh: A 3D Recurrent Residual Attention U-Net for Automated Multiple Sclerosis Lesion Segmentation","volume":"IJISRT24SEP1439","author":"Shafaei","year":"2024","journal-title":"Int. J. Innov. Sci. Res. Technol. (IJISRT)"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"625","DOI":"10.1016\/j.aej.2023.04.069","article-title":"GAU U-Net for multiple sclerosis segmentation","volume":"73","author":"Gamal","year":"2023","journal-title":"Alex. Eng. J."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Rondinella, A., Crispino, E., Guarnera, F., Giudice, O., Ortis, A., Russo, G., Di Lorenzo, C., Maimone, D., Pappalardo, F., and Battiato, S. (2023). Boosting multiple sclerosis lesion segmentation through attention mechanism. arXiv.","DOI":"10.1016\/j.compbiomed.2023.107021"},{"key":"ref_15","first-page":"102080","article-title":"A dense residual U-net for multiple sclerosis lesions segmentation from multi-sequence 3D MR images","volume":"98","author":"Sarica","year":"2022","journal-title":"Comput. Med. Imaging Graph."},{"key":"ref_16","first-page":"10.1155","article-title":"Brain Tumor Detection Using a Deep CNN Model","volume":"2024","author":"Ben","year":"2024","journal-title":"Appl. Comput. Intell. Soft Comput."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Bai, L., Wang, D., Wang, H., Barnett, M., Cabezas, M., Cai, W., Calamante, F., Kyle, K., Liu, D., and Ly, L. (2023). Improving Multiple Sclerosis Lesion Segmentation Across Clinical Sites: A Federated Learning Approach with Noise-Resilient Training. arXiv.","DOI":"10.1016\/j.artmed.2024.102872"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"100235","DOI":"10.1016\/j.ynirp.2025.100235","article-title":"Enhancing Precision in Multiple Sclerosis Lesion Segmentation: A U-Net Based Machine Learning Approach with Data Augmentation","volume":"5","author":"Cetin","year":"2025","journal-title":"Neuroimage Rep."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Samia, D. (2025). An efficient method for early Alzheimer\u2019s disease detection based on MRI images using deep convolutional neural networks. Front. Artif. Intell., 8.","DOI":"10.3389\/frai.2025.1563016"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1459","DOI":"10.1007\/s11548-021-02327-y","article-title":"Multiple sclerosis lesion segmentation from brain MRI using U-Net based on wavelet pooling","volume":"16","author":"Alijamaat","year":"2021","journal-title":"Int. J. CARS"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Rondinella, A., Crispino, E., Guarnera, F., Giudice, O., Ortis, A., Russo, G., Di Lorenzo, C., Maimone, D., Pappalardo, F., and Battiato, S. (2024). ICPR 2024 Competition on Multiple Sclerosis Lesion Segmentation\u2014Methods and Results. arXiv.","DOI":"10.1007\/978-3-031-80139-6_1"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Greselin, M., Lu, P.-J., Melie-Garcia, L., Ocampo-Pineda, M., Galbusera, R., Cagol, A., Weigel, M., de Oliveira Siebenborn, N., Ruberte, E., and Benkert, P. (2024). Contrast Enhancing Lesion Segmentation in Multiple Sclerosis: A Deep Learning Approach Validated in a Multicentric Cohort. Bioengineering, 11.","DOI":"10.3390\/bioengineering11080858"}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/11\/10\/361\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T12:44:44Z","timestamp":1760445884000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/11\/10\/361"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,13]]},"references-count":22,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2025,10]]}},"alternative-id":["jimaging11100361"],"URL":"https:\/\/doi.org\/10.3390\/jimaging11100361","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,13]]}}}