{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T21:59:25Z","timestamp":1780696765837,"version":"3.54.1"},"reference-count":20,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"3","content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":[],"abstract":"<jats:sec>\n                    <jats:title>Objectives:<\/jats:title>\n                    <jats:p>Automated segmentation of 3D pelvic topography using deep learning networks has the potential to improve the accuracy of preoperative planning and surgical navigation. However, anisotropic MRI scans\u2014often used in clinical practice\u2014present a major limitation due to their uneven resolution across anatomical planes. We compared the performance of a model trained on anisotropic versus isotropic MRI reconstructions for the segmentation of pelvic muscle and nerve tissue.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods:<\/jats:title>\n                    <jats:p>A total of 35 rectal cancer patients were included, each with axial, sagittal, and coronal T2-weighted MRI scans. Isotropic volumes were reconstructed from anisotropic scans. Two nnU-Net models were trained: one on anisotropic data and the other on isotropic reconstructions. Both models were evaluated for their segmentation of the sacral nerves, obturator nerve, and piriformis muscle. Dice Similarity Coefficient (DSC), Intersection over Union (IoU), precision, and recall were calculated to assess model performance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results:<\/jats:title>\n                    <jats:p>The performance of the model trained on isotropic images had better segmentation performance, with particularly noticeable improvement for the obturator nerve (DSC: 0.76 vs. 0.71). Both models achieved high DSC scores for the piriformis muscle (&gt;0.95) and good performance for the sacral nerves (&gt;0.86). Qualitative evaluation showed smoother and more natural anatomical representations in isotropic models, while anisotropic models displayed rougher, discontinuous surfaces.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions:<\/jats:title>\n                    <jats:p>Isotropic MRI reconstructions yielded slightly better segmentation results and provided more anatomically accurate 3D models. This suggests that isotropic reconstruction should be favored in clinical workflows to improve segmentation accuracy and efficiency in pelvic MRI images for accurate preoperative planning and surgical navigation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1097\/rct.0000000000001828","type":"journal-article","created":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T18:00:06Z","timestamp":1771351206000},"page":"339-345","update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":0,"title":["Deep Learning Segmentation of Pelvic Soft Tissue in Isotropic and Anisotropic MRI Using Routine T2 Scans"],"prefix":"10.1097","volume":"50","author":[{"given":"Renske","family":"Schram","sequence":"first","affiliation":[{"name":"Department of Surgery"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3426-4710","authenticated-orcid":false,"given":"Reinier S.A.","family":"ten Brink","sequence":"additional","affiliation":[{"name":"Department of Surgery"},{"name":"3D Lab, University Medical Center Groningen, Groningen"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manon A.G.","family":"Bakker","sequence":"additional","affiliation":[{"name":"Department of Surgery"},{"name":"3D Lab, University Medical Center Groningen, Groningen"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Can O.","family":"Tan","sequence":"additional","affiliation":[{"name":"University of Twente; Enschede"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joep","family":"Kraeima","sequence":"additional","affiliation":[{"name":"3D Lab, University Medical Center Groningen, Groningen"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jean-Paul P.M.","family":"de Vries","sequence":"additional","affiliation":[{"name":"Department of Surgery"},{"name":"University of Groningen, Groningen, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arthur R.","family":"Wijsmuller","sequence":"additional","affiliation":[{"name":"Department of Surgery"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","published-online":{"date-parts":[[2026,5]]},"reference":[{"key":"R1-20260605","doi-asserted-by":"crossref","first-page":"645","DOI":"10.3390\/life12050645","article-title":"Use of image-guided surgical navigation during resection of locally recurrent rectal cancer","volume":"12","author":"Groen","year":"2022","journal-title":"Life"},{"key":"R2-20260605","doi-asserted-by":"crossref","first-page":"e208522","DOI":"10.1001\/jamanetworkopen.2020.8522","article-title":"Association of image-guided navigation with complete resection rate in patients with locally advanced primary and recurrent rectal cancer: a nonrandomized controlled trial","volume":"3","author":"Kok","year":"2020","journal-title":"JAMA Network Open"},{"key":"R4-20260605","doi-asserted-by":"crossref","first-page":"7602","DOI":"10.1245\/s10434-023-13964-9","article-title":"Navigation-assisted surgery for locally advanced primary and recurrent rectal cancer","volume":"30","author":"Solbakken","year":"2023","journal-title":"Ann Surg Oncol"},{"key":"R5-20260605","doi-asserted-by":"crossref","first-page":"788","DOI":"10.1002\/ags3.12574","article-title":"Artificial intelligence-based technology to make a three-dimensional pelvic model for preoperative simulation of rectal cancer surgery using MRI","volume":"6","author":"Hamabe","year":"2022","journal-title":"Ann Gastroenterol Surg"},{"key":"R6-20260605","doi-asserted-by":"crossref","first-page":"805","DOI":"10.1109\/TMI.2020.3037187","article-title":"SMORE: a self-supervised anti-aliasing and super-resolution algorithm for MRI using deep learning","volume":"40","author":"Zhao","year":"2021","journal-title":"IEEE Trans Med Imaging"},{"key":"R7-20260605","doi-asserted-by":"crossref","first-page":"e0316611","DOI":"10.1371\/journal.pone.0316611","article-title":"Analysis of the sample size used in clinical MRI studies","volume":"20","author":"B\u00f6gerl","year":"2025","journal-title":"PLoS ONE"},{"key":"R8-20260605","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":"R9-20260605","doi-asserted-by":"crossref","first-page":"116324","DOI":"10.1016\/j.neuroimage.2019.116324","article-title":"An automated framework for localization, segmentation and super-resolution reconstruction of fetal brain MRI","volume":"206","author":"Ebner","year":"2020","journal-title":"Neuroimage"},{"key":"R10-20260605","first-page":"517","article-title":"A two-dimensional interpolation function for irregularly-spaced data","author":"Shepard","year":"1968","journal-title":"Acm\u201868"},{"key":"R11-20260605","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1016\/0165-1684(95)00020-E","article-title":"Recursive implementation of the Gaussian filter","volume":"44","author":"Young","year":"1995","journal-title":"Signal Processing"},{"key":"R12-20260605","doi-asserted-by":"crossref","first-page":"1739","DOI":"10.1109\/TMI.2010.2051680","article-title":"Robust super-resolution volume reconstruction from slice acquisitions: application to fetal brain MRI","volume":"29","author":"Gholipour","year":"2010","journal-title":"IEEE Trans Med Imaging"},{"key":"R13-20260605","doi-asserted-by":"crossref","first-page":"1323","DOI":"10.1016\/j.mri.2012.05.001","article-title":"3D Slicer as an image computing platform for the Quantitative Imaging Network","volume":"30","author":"Fedorov","year":"2012","journal-title":"Magn Reson Imaging"},{"key":"R14-20260605","doi-asserted-by":"crossref","first-page":"3582","DOI":"10.1007\/s00464-018-6086-3","article-title":"A step towards stereotactic navigation during pelvic surgery: 3D nerve topography","volume":"32","author":"Wijsmuller","year":"2018","journal-title":"Surg Endosc"},{"key":"R15-20260605","doi-asserted-by":"crossref","first-page":"5479","DOI":"10.1002\/mp.16378","article-title":"Automatic segmentation of neurovascular bundle on mri using deep learning based topological modulated network","volume":"50","author":"Lei","year":"2023","journal-title":"Med Phys"},{"key":"R16-20260605","doi-asserted-by":"crossref","first-page":"431","DOI":"10.1002\/mrm.28939","article-title":"Scale- and Slice-aware Net (S2aNet) for 3D segmentation of organs and musculoskeletal structures in pelvic MRI","volume":"87","author":"Yan","year":"2022","journal-title":"Magn Reson Med"},{"key":"R17-20260605","doi-asserted-by":"crossref","first-page":"11735","DOI":"10.1038\/s41598-024-61798-6","article-title":"A deep learning model for brain segmentation across pediatric and adult populations","volume":"14","author":"Simarro","year":"2024","journal-title":"Sci Rep"},{"key":"R18-20260605","doi-asserted-by":"crossref","first-page":"1616293","DOI":"10.3389\/fradi.2025.1616293","article-title":"Brain tumor segmentation using deep learning: high performance with minimized MRI data","volume":"5","author":"Huang","year":"2025","journal-title":"Front Radiol"},{"key":"R19-20260605","doi-asserted-by":"crossref","first-page":"296","DOI":"10.3390\/jimaging10120296","article-title":"Evaluating brain tumor detection with deep learning convolutional neural networks across multiple MRI modalities","volume":"10","author":"Stathopoulos","year":"2024","journal-title":"J Imaging"},{"key":"R20-20260605","doi-asserted-by":"crossref","first-page":"542","DOI":"10.1016\/j.procs.2023.01.036","article-title":"3D MRI segmentation using U-Net architecture for the detection of brain tumor","volume":"218","author":"Sangui","year":"2023","journal-title":"Procedia Comput Sci"},{"key":"R21-20260605","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1016\/j.nic.2013.03.026","article-title":"Magnetic resonance neurography of the pelvis and lumbosacral plexus","volume":"24","author":"Delaney","year":"2014","journal-title":"Neuroimaging Clin N Am"}],"container-title":["Journal of Computer Assisted Tomography"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.lww.com\/10.1097\/RCT.0000000000001828","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T21:00:17Z","timestamp":1780693217000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.lww.com\/10.1097\/RCT.0000000000001828"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,24]]},"references-count":20,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026]]}},"URL":"https:\/\/doi.org\/10.1097\/rct.0000000000001828","relation":{},"ISSN":["1532-3145"],"issn-type":[{"value":"1532-3145","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,24]]},"assertion":[{"value":"2025-06-11","name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-18","name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}}]}}