{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T15:55:12Z","timestamp":1761062112172,"version":"build-2065373602"},"reference-count":49,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2025,8,13]],"date-time":"2025-08-13T00:00:00Z","timestamp":1755043200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"BRIEF\u2014Biorobotics Research and Innovation Engineering Facilities","award":["J13C22000400007"],"award-info":[{"award-number":["J13C22000400007"]}]},{"name":"European Union\u2014NextGenerationEU","award":["J13C22000400007"],"award-info":[{"award-number":["J13C22000400007"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["MAKE"],"abstract":"<jats:p>Accurate segmentation of deep brain structures is critical for preoperative planning in such neurosurgical procedures as Deep Brain Stimulation (DBS). Previous research has showcased successful pipelines for segmentation from T1-weighted (T1w) Magnetic Resonance Imaging (MRI) data. Nevertheless, the role of T2-weighted (T2w) MRI data has been underexploited so far. This study proposes and evaluates a fully automated deep learning pipeline based on nnU-Net for the segmentation of eight clinically relevant deep brain structures. A heterogeneous dataset has been prepared by gathering 325 paired T1w and T2w MRI scans from eight publicly available sources, which have been annotated by means of an atlas-based registration approach. Three 3D nnU-Net models\u2014unimodal T1w, unimodal T2w, and multimodal (encompassing both T1w and T2w)\u2014have been trained and compared by using 5-fold cross-validation and a separate test set. The outcomes prove that the multimodal model consistently outperforms the T2w unimodal model and achieves comparable performance with the T1w unimodal model. On our dataset, all proposed models significantly exceed the performance of the state-of-the-art DBSegment tool. These findings underscore the value of multimodal MRI in enhancing deep brain segmentation and offer a robust framework for accurate delineation of subcortical targets in both research and clinical settings.<\/jats:p>","DOI":"10.3390\/make7030084","type":"journal-article","created":{"date-parts":[[2025,8,13]],"date-time":"2025-08-13T15:53:27Z","timestamp":1755100407000},"page":"84","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["A Comparison Between Unimodal and Multimodal Segmentation Models for Deep Brain Structures from T1- and T2-Weighted MRI"],"prefix":"10.3390","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7353-4968","authenticated-orcid":false,"given":"Nicola","family":"Altini","sequence":"first","affiliation":[{"name":"Department of Electrical and Information Engineering, Polytechnic University of Bari, Via Giuseppe Re David 4, 70126 Bari, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Erica","family":"Lasaracina","sequence":"additional","affiliation":[{"name":"Department of Electrical and Information Engineering, Polytechnic University of Bari, Via Giuseppe Re David 4, 70126 Bari, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5259-0640","authenticated-orcid":false,"given":"Francesca","family":"Galeone","sequence":"additional","affiliation":[{"name":"Department of Electrical and Information Engineering, Polytechnic University of Bari, Via Giuseppe Re David 4, 70126 Bari, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michela","family":"Prunella","sequence":"additional","affiliation":[{"name":"Department of Electrical and Information Engineering, Polytechnic University of Bari, Via Giuseppe Re David 4, 70126 Bari, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5314-0093","authenticated-orcid":false,"given":"Vladimiro","family":"Suglia","sequence":"additional","affiliation":[{"name":"Department of Electrical and Information Engineering, Polytechnic University of Bari, Via Giuseppe Re David 4, 70126 Bari, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leonarda","family":"Carnimeo","sequence":"additional","affiliation":[{"name":"Department of Electrical and Information Engineering, Polytechnic University of Bari, Via Giuseppe Re David 4, 70126 Bari, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vito","family":"Triggiani","sequence":"additional","affiliation":[{"name":"Masmec Biomed SpA, Via delle Violette 14, 70026 Bari, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniele","family":"Ranieri","sequence":"additional","affiliation":[{"name":"Masmec Biomed SpA, Via delle Violette 14, 70026 Bari, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gioacchino","family":"Brunetti","sequence":"additional","affiliation":[{"name":"Masmec Biomed SpA, Via delle Violette 14, 70026 Bari, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3088-0788","authenticated-orcid":false,"given":"Vitoantonio","family":"Bevilacqua","sequence":"additional","affiliation":[{"name":"Department of Electrical and Information Engineering, Polytechnic University of Bari, Via Giuseppe Re David 4, 70126 Bari, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,8,13]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"114","DOI":"10.1016\/j.mri.2019.09.004","article-title":"Generation of Human Thalamus Atlases from 7 T Data and Application to Intrathalamic Nuclei Segmentation in Clinical 3 T T1-Weighted Images","volume":"65","author":"Liu","year":"2020","journal-title":"Magn. Reson. Imaging"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Isaacs, B.R., Keuken, M.C., Alkemade, A., Temel, Y., Bazin, P.-L., and Forstmann, B.U. (2020). Methodological Considerations for Neuroimaging in Deep Brain Stimulation of the Subthalamic Nucleus in Parkinson\u2019s Disease Patients. J. Clin. Med., 9.","DOI":"10.3390\/jcm9103124"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"762","DOI":"10.1002\/hbm.26097","article-title":"DBSegment: Fast and Robust Segmentation of Deep Brain Structures Considering Domain Generalization","volume":"44","author":"Baniasadi","year":"2023","journal-title":"Hum. Brain Mapp."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"256","DOI":"10.1159\/000507028","article-title":"Comparison of Automatic Segmentation Algorithms for the Subthalamic Nucleus","volume":"98","author":"Polanski","year":"2020","journal-title":"Stereotact. Funct. Neurosurg."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"497","DOI":"10.1093\/ons\/opz015","article-title":"Automatic Segmentation of the Subthalamic Nucleus: A Viable Option to Support Planning and Visualization of Patient-Specific Targeting in Deep Brain Stimulation","volume":"17","author":"Reinacher","year":"2019","journal-title":"Oper. Neurosurg."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"e472","DOI":"10.1016\/j.wneu.2023.07.103","article-title":"Automatic Localization of Key Structures for Subthalamic Nucleus\u2013Deep Brain Stimulation Surgery via Prior-Enhanced Multi-Object Magnetic Resonance Imaging Segmentation","volume":"178","author":"Chen","year":"2023","journal-title":"World Neurosurg."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Kim, J., Duchin, Y., Sapiro, G., Vitek, J., and Harel, N. (2015, January 27\u201330). Clinical Deep Brain Stimulation Region Prediction Using Regression Forests from High-Field MRI. Proceedings of the 2015 IEEE International Conference on Image Processing (ICIP), Quebec City, QC, Canada.","DOI":"10.1109\/ICIP.2015.7351248"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"35","DOI":"10.5603\/RPOR.a2021.0005","article-title":"T1-Weighted and T2-Weighted MRI Image Synthesis with Convolutional Generative Adversarial Networks","volume":"26","author":"Kawahara","year":"2021","journal-title":"Rep. Pract. Oncol. Radiother."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1007\/s11548-012-0675-8","article-title":"Automated Segmentation of Basal Ganglia and Deep Brain Structures in MRI of Parkinson\u2019s Disease","volume":"8","author":"Haegelen","year":"2013","journal-title":"Int. J. CARS"},{"key":"ref_10","unstructured":"Lima, T., Varga, I., Bak\u0161tein, E., Nov\u00e1k, D., and Alves, V. (2024). Subthalamic Nucleus Segmentation in High-Field Magnetic Resonance Data. Is Space Normalization by Template Co-Registration Necessary?. arXiv."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"180063","DOI":"10.1038\/sdata.2018.63","article-title":"A High-Resolution Probabilistic in Vivo Atlas of Human Subcortical Brain Nuclei","volume":"5","author":"Pauli","year":"2018","journal-title":"Sci. Data"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"271","DOI":"10.1016\/j.neuroimage.2017.05.015","article-title":"Toward Defining Deep Brain Stimulation Targets in MNI Space: A Subcortical Atlas Based on Multimodal MRI, Histology and Structural Connectivity","volume":"170","author":"Ewert","year":"2018","journal-title":"NeuroImage"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1016\/j.neuroimage.2019.03.021","article-title":"Thalamus Optimized Multi Atlas Segmentation (THOMAS): Fast, Fully Automated Segmentation of Thalamic Nuclei from Structural MRI","volume":"194","author":"Su","year":"2019","journal-title":"NeuroImage"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1038\/nrn756","article-title":"The Problem of Functional Localization in the Human Brain","volume":"3","author":"Brett","year":"2002","journal-title":"Nat. Rev. Neurosci."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1016\/j.neuroimage.2014.12.002","article-title":"Lead-DBS: A Toolbox for Deep Brain Stimulation Electrode Localizations and Visualizations","volume":"107","author":"Horn","year":"2015","journal-title":"NeuroImage"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1016\/j.neuroimage.2018.08.068","article-title":"Lead-DBS v2: Towards a Comprehensive Pipeline for Deep Brain Stimulation Imaging","volume":"184","author":"Horn","year":"2019","journal-title":"NeuroImage"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"119862","DOI":"10.1016\/j.neuroimage.2023.119862","article-title":"Lead-DBS v3.0: Mapping Deep Brain Stimulation Effects to Local Anatomy and Global Networks","volume":"268","author":"Neudorfer","year":"2023","journal-title":"NeuroImage"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1029","DOI":"10.1007\/s11548-014-1119-4","article-title":"Patch-Based Label Fusion Segmentation of Brainstem Structures with Dual-Contrast MRI for Parkinson\u2019s Disease","volume":"10","author":"Xiao","year":"2015","journal-title":"Int. J. CARS"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1162\/imag_a_00304","article-title":"Automated Segmentation of Midbrain Nuclei Using Deep Learning and Multisequence MRI: A Longitudinal Study on Iron Accumulation with Age","volume":"2","author":"Falahati","year":"2024","journal-title":"Imaging Neurosci."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Altini, N., Rossini, M., Turkevi-Nagy, S., Pesce, F., Pontrelli, P., Prencipe, B., Berloco, F., Seshan, S., Gibier, J.-B., and Pedraza Dorado, A. (2023). Performance and Limitations of a Supervised Deep Learning Approach for the Histopathological Oxford Classification of Glomeruli with IgA Nephropathy. Comput. Methods Programs Biomed., 242.","DOI":"10.1016\/j.cmpb.2023.107814"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Bevilacqua, V., Altini, N., Prencipe, B., Brunetti, A., Villani, L., Sacco, A., Morelli, C., Ciaccia, M., and Scardapane, A. (2021). Lung Segmentation and Characterization in COVID-19 Patients for Assessing Pulmonary Thromboembolism: An Approach Based on Deep Learning and Radiomics. Electronics, 10.","DOI":"10.3390\/electronics10202475"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"102526","DOI":"10.1016\/j.compmedimag.2025.102526","article-title":"A Multimodal Framework for Assessing the Link between Pathomics, Transcriptomics, and Pancreatic Cancer Mutations","volume":"123","author":"Berloco","year":"2025","journal-title":"Comput. Med. Imaging Graph."},{"key":"ref_23","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_24","doi-asserted-by":"crossref","unstructured":"Altini, N., Brunetti, A., Napoletano, V.P., Girardi, F., Allegretti, E., Hussain, S.M., Brunetti, G., Triggiani, V., Bevilacqua, V., and Buongiorno, D. (2022). A Fusion Biopsy Framework for Prostate Cancer Based on Deformable Superellipses and nnU-Net. Bioengineering, 9.","DOI":"10.3390\/bioengineering9080343"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"2862","DOI":"10.1002\/hbm.25409","article-title":"Deep-learning Based Fully Automatic Segmentation of the Globus Pallidus Interna and Externa Using Ultra-high 7 Tesla MRI","volume":"42","author":"Solomon","year":"2021","journal-title":"Hum. Brain Mapp."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"4809","DOI":"10.1002\/hbm.25604","article-title":"Automated Segmentation of Deep Brain Nuclei Using Convolutional Neural Networks and Susceptibility Weighted Imaging","volume":"42","author":"Beliveau","year":"2021","journal-title":"Hum. Brain Mapp."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"140003","DOI":"10.1038\/sdata.2014.3","article-title":"A High-Resolution 7-Tesla fMRI Dataset from Complex Natural Stimulation with an Audio Movie","volume":"1","author":"Hanke","year":"2014","journal-title":"Sci. Data"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"2222","DOI":"10.1016\/j.neuroimage.2012.02.018","article-title":"The Human Connectome Project: A Data Acquisition Perspective","volume":"62","author":"Ugurbil","year":"2012","journal-title":"NeuroImage"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"LaMontagne, P.J., Benzinger, T.L.S., Morris, J.C., Keefe, S., Hornbeck, R., Xiong, C., Grant, E., Hassenstab, J., Moulder, K., and Vlassenko, A.G. (2019). OASIS-3: Longitudinal Neuroimaging, Clinical, and Cognitive Dataset for Normal Aging and Alzheimer Disease. medRxiv.","DOI":"10.1101\/2019.12.13.19014902"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1016\/j.jalz.2005.06.003","article-title":"Ways toward an Early Diagnosis in Alzheimer\u2019s Disease: The Alzheimer\u2019s Disease Neuroimaging Initiative (ADNI)","volume":"1","author":"Mueller","year":"2005","journal-title":"Alzheimers Dement."},{"key":"ref_31","unstructured":"(2025, June 15). IXI Dataset\u2014Brain Development. Available online: https:\/\/brain-development.org\/ixi-dataset\/."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"489","DOI":"10.1038\/s41597-023-02400-y","article-title":"A Paired Dataset of T1- and T2-Weighted MRI at 3 Tesla and 7 Tesla","volume":"10","author":"Chen","year":"2023","journal-title":"Sci. Data"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1089\/brain.2012.0112","article-title":"MultiCenter Reliability of Diffusion Tensor Imaging","volume":"2","author":"Magnotta","year":"2012","journal-title":"Brain Connect."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"414","DOI":"10.1016\/j.bja.2024.07.039","article-title":"Neural Correlates of Systemic Lidocaine Administration in Healthy Adults Measured by Functional MRI: A Single Arm Open Label Study","volume":"134","author":"Vogt","year":"2025","journal-title":"Br. J. Anaesth."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Kausel, L., Figueroa-Vargas, A., Zamorano, F., Stecher, X., Asp\u00e9-S\u00e1nchez, M., Carvajal-Paredes, P., M\u00e1rquez-Rodr\u00edguez, V., Mart\u00ednez-Molina, M.P., Rom\u00e1n, C., and Soto-Fern\u00e1ndez, P. (2024). Patients Recovering from COVID-19 Who Presented with Anosmia during Their Acute Episode Have Behavioral, Functional, and Structural Brain Alterations. Sci. Rep., 14.","DOI":"10.1038\/s41598-024-69772-y"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"S102","DOI":"10.1016\/S1053-8119(09)70884-5","article-title":"Unbiased Nonlinear Average Age-Appropriate Brain Templates from Birth to Adulthood","volume":"47","author":"Fonov","year":"2009","journal-title":"NeuroImage"},{"key":"ref_37","unstructured":"(2025, May 21). 3D Slicer Image Computing Platform. Available online: https:\/\/slicer.org\/."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Baek, H.-M. (2023). Diffusion Measures of Subcortical Structures Using High-Field MRI. Brain Sci., 13.","DOI":"10.3390\/brainsci13030391"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"1310","DOI":"10.1109\/TMI.2010.2046908","article-title":"N4ITK: Improved N3 Bias Correction","volume":"29","author":"Tustison","year":"2010","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1016\/j.media.2007.06.004","article-title":"Symmetric Diffeomorphic Image Registration with Cross-Correlation: Evaluating Automated Labeling of Elderly and Neurodegenerative Brain","volume":"12","author":"Avants","year":"2008","journal-title":"Med. Image Anal."},{"key":"ref_41","unstructured":"Gulban, O.F., Nielson, D., Lee, J., Poldrack, R., Gorgolewski, C., and Markiewicz, C. (Poldracklab\/Pydeface: PyDeface, 2022). Poldracklab\/Pydeface: PyDeface, version 2.0.2."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1016\/j.neucom.2021.08.157","article-title":"Liver, Kidney and Spleen Segmentation from CT Scans and MRI with Deep Learning: A Survey","volume":"490","author":"Altini","year":"2022","journal-title":"Neurocomputing"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1111\/j.2517-6161.1995.tb02031.x","article-title":"Controlling the False Discovery Rate: A Practical and Powerful Approach to Multiple Testing","volume":"57","author":"Benjamini","year":"1995","journal-title":"J. R. Stat. Soc. Ser. B Stat. Methodol."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"1678","DOI":"10.1109\/JBHI.2013.2292858","article-title":"Semiautomatic Segmentation of Brain Subcortical Structures From High-Field MRI","volume":"18","author":"Kim","year":"2014","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Lee, J.-H., Yun, J.Y., Gregory, A., Hogarth, P., and Hayflick, S.J. (2020). Brain MRI Pattern Recognition in Neurodegeneration With Brain Iron Accumulation. Front. Neurol., 11.","DOI":"10.3389\/fneur.2020.01024"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"2666","DOI":"10.1016\/j.neubiorev.2013.09.002","article-title":"Deep Brain Stimulation in Dementia-Related Disorders","volume":"37","author":"Hescham","year":"2013","journal-title":"Neurosci. Biobehav. Rev."},{"key":"ref_47","unstructured":"(2025, July 09). Links Between COVID-19 and Parkinson\u2019s Disease\/Alzheimer\u2019s Disease: Reciprocal Impacts, Medical Care Strategies and Underlying Mechanisms | Translational Neurodegeneration | Full Text. Available online: https:\/\/translationalneurodegeneration.biomedcentral.com\/articles\/10.1186\/s40035-023-00337-1."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Altini, N., Marvulli, T.M., Zito, F.A., Caputo, M., Tommasi, S., Azzariti, A., Brunetti, A., Prencipe, B., Mattioli, E., and De Summa, S. (2023). The Role of Unpaired Image-to-Image Translation for Stain Color Normalization in Colorectal Cancer Histology Classification. Comput. Methods Programs Biomed., 234.","DOI":"10.1016\/j.cmpb.2023.107511"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Dayarathna, S., Islam, K.T., Zhuang, B., Yang, G., Cai, J., Law, M., and Chen, Z. (March, January 28). McCaD: Multi-Contrast MRI Conditioned, Adaptive Adversarial Diffusion Model for High-Fidelity MRI Synthesis. Proceedings of the 2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), Tucson, AZ, USA.","DOI":"10.1109\/WACV61041.2025.00075"}],"container-title":["Machine Learning and Knowledge Extraction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-4990\/7\/3\/84\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:26:40Z","timestamp":1760034400000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-4990\/7\/3\/84"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,13]]},"references-count":49,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["make7030084"],"URL":"https:\/\/doi.org\/10.3390\/make7030084","relation":{},"ISSN":["2504-4990"],"issn-type":[{"type":"electronic","value":"2504-4990"}],"subject":[],"published":{"date-parts":[[2025,8,13]]}}}