A Comparison Between Unimodal and Multimodal Segmentation Models for Deep Brain Structures from T1- and T2-Weighted MRI
Guardado en:
| Udgivet i: | Machine Learning and Knowledge Extraction vol. 7, no. 3 (2025), p. 84-108 |
|---|---|
| Hovedforfatter: | |
| Andre forfattere: | , , , , , , , , |
| Udgivet: |
MDPI AG
|
| Fag: | |
| Online adgang: | Citation/Abstract Full Text + Graphics Full Text - PDF |
| Tags: |
Ingen Tags, Vær først til at tagge denne postø!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 3254583170 | ||
| 003 | UK-CbPIL | ||
| 022 | |a 2504-4990 | ||
| 024 | 7 | |a 10.3390/make7030084 |2 doi | |
| 035 | |a 3254583170 | ||
| 045 | 2 | |b d20250701 |b d20250930 | |
| 100 | 1 | |a Altini Nicola |u Department of Electrical and Information Engineering, Polytechnic University of Bari, Via Giuseppe Re David 4, 70126 Bari, Italy; nicola.altini@poliba.it (N.A.); e.lasaracina@studenti.poliba.it (E.L.); f.galeone2@studenti.poliba.it (F.G.); m.prunella@phd.poliba.it (M.P.); vladimiro.suglia@poliba.it (V.S.); leonarda.carnimeo@poliba.it (L.C.) | |
| 245 | 1 | |a A Comparison Between Unimodal and Multimodal Segmentation Models for Deep Brain Structures from T1- and T2-Weighted MRI | |
| 260 | |b MDPI AG |c 2025 | ||
| 513 | |a Journal Article | ||
| 520 | 3 | |a 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—unimodal T1w, unimodal T2w, and multimodal (encompassing both T1w and T2w)—have 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. | |
| 610 | 4 | |a University of North Carolina | |
| 653 | |a Datasets | ||
| 653 | |a Neuroimaging | ||
| 653 | |a Alzheimer's disease | ||
| 653 | |a Deep learning | ||
| 653 | |a Image segmentation | ||
| 653 | |a Brain research | ||
| 653 | |a Magnetic resonance imaging | ||
| 653 | |a Brain | ||
| 653 | |a Data collection | ||
| 653 | |a Automation | ||
| 653 | |a Medical imaging | ||
| 653 | |a Longitudinal studies | ||
| 653 | |a Movement disorders | ||
| 653 | |a Parkinson's disease | ||
| 700 | 1 | |a Lasaracina Erica |u Department of Electrical and Information Engineering, Polytechnic University of Bari, Via Giuseppe Re David 4, 70126 Bari, Italy; nicola.altini@poliba.it (N.A.); e.lasaracina@studenti.poliba.it (E.L.); f.galeone2@studenti.poliba.it (F.G.); m.prunella@phd.poliba.it (M.P.); vladimiro.suglia@poliba.it (V.S.); leonarda.carnimeo@poliba.it (L.C.) | |
| 700 | 1 | |a Galeone Francesca |u Department of Electrical and Information Engineering, Polytechnic University of Bari, Via Giuseppe Re David 4, 70126 Bari, Italy; nicola.altini@poliba.it (N.A.); e.lasaracina@studenti.poliba.it (E.L.); f.galeone2@studenti.poliba.it (F.G.); m.prunella@phd.poliba.it (M.P.); vladimiro.suglia@poliba.it (V.S.); leonarda.carnimeo@poliba.it (L.C.) | |
| 700 | 1 | |a Prunella Michela |u Department of Electrical and Information Engineering, Polytechnic University of Bari, Via Giuseppe Re David 4, 70126 Bari, Italy; nicola.altini@poliba.it (N.A.); e.lasaracina@studenti.poliba.it (E.L.); f.galeone2@studenti.poliba.it (F.G.); m.prunella@phd.poliba.it (M.P.); vladimiro.suglia@poliba.it (V.S.); leonarda.carnimeo@poliba.it (L.C.) | |
| 700 | 1 | |a Suglia Vladimiro |u Department of Electrical and Information Engineering, Polytechnic University of Bari, Via Giuseppe Re David 4, 70126 Bari, Italy; nicola.altini@poliba.it (N.A.); e.lasaracina@studenti.poliba.it (E.L.); f.galeone2@studenti.poliba.it (F.G.); m.prunella@phd.poliba.it (M.P.); vladimiro.suglia@poliba.it (V.S.); leonarda.carnimeo@poliba.it (L.C.) | |
| 700 | 1 | |a Carnimeo Leonarda |u Department of Electrical and Information Engineering, Polytechnic University of Bari, Via Giuseppe Re David 4, 70126 Bari, Italy; nicola.altini@poliba.it (N.A.); e.lasaracina@studenti.poliba.it (E.L.); f.galeone2@studenti.poliba.it (F.G.); m.prunella@phd.poliba.it (M.P.); vladimiro.suglia@poliba.it (V.S.); leonarda.carnimeo@poliba.it (L.C.) | |
| 700 | 1 | |a Triggiani Vito |u Masmec Biomed SpA, Via delle Violette 14, 70026 Bari, Italy; daniele.ranieri@masmec.com (D.R.); gioacchino.brunetti@masmecbiomed.com (G.B.) | |
| 700 | 1 | |a Ranieri Daniele |u Masmec Biomed SpA, Via delle Violette 14, 70026 Bari, Italy; daniele.ranieri@masmec.com (D.R.); gioacchino.brunetti@masmecbiomed.com (G.B.) | |
| 700 | 1 | |a Brunetti Gioacchino |u Masmec Biomed SpA, Via delle Violette 14, 70026 Bari, Italy; daniele.ranieri@masmec.com (D.R.); gioacchino.brunetti@masmecbiomed.com (G.B.) | |
| 700 | 1 | |a Bevilacqua Vitoantonio |u Department of Electrical and Information Engineering, Polytechnic University of Bari, Via Giuseppe Re David 4, 70126 Bari, Italy; nicola.altini@poliba.it (N.A.); e.lasaracina@studenti.poliba.it (E.L.); f.galeone2@studenti.poliba.it (F.G.); m.prunella@phd.poliba.it (M.P.); vladimiro.suglia@poliba.it (V.S.); leonarda.carnimeo@poliba.it (L.C.) | |
| 773 | 0 | |t Machine Learning and Knowledge Extraction |g vol. 7, no. 3 (2025), p. 84-108 | |
| 786 | 0 | |d ProQuest |t Advanced Technologies & Aerospace Database | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/3254583170/abstract/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text + Graphics |u https://www.proquest.com/docview/3254583170/fulltextwithgraphics/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text - PDF |u https://www.proquest.com/docview/3254583170/fulltextPDF/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch |