guest ::
| Home > Publications database > GTV segmentation in MRI guided radiotherapy with promptable foundation models. > print |
| Home > Publications database > GTV segmentation in MRI guided radiotherapy with promptable foundation models. > print |
| 001 | 307471 | ||
| 005 | 20260217120817.0 | ||
| 024 | 7 | _ | |a 10.1088/1361-6560/ae2db9 |2 doi |
| 024 | 7 | _ | |a pmid:41401509 |2 pmid |
| 024 | 7 | _ | |a 0031-9155 |2 ISSN |
| 024 | 7 | _ | |a 1361-6560 |2 ISSN |
| 037 | _ | _ | |a DKFZ-2025-03070 |
| 041 | _ | _ | |a English |
| 082 | _ | _ | |a 530 |
| 100 | 1 | _ | |a Julius Blöcker, Tom |0 0009-0002-2650-4680 |b 0 |
| 245 | _ | _ | |a GTV segmentation in MRI guided radiotherapy with promptable foundation models. |
| 260 | _ | _ | |a Bristol |c 2025 |b IOP Publ. |
| 336 | 7 | _ | |a article |2 DRIVER |
| 336 | 7 | _ | |a Output Types/Journal article |2 DataCite |
| 336 | 7 | _ | |a Journal Article |b journal |m journal |0 PUB:(DE-HGF)16 |s 1767100433_1386406 |2 PUB:(DE-HGF) |
| 336 | 7 | _ | |a ARTICLE |2 BibTeX |
| 336 | 7 | _ | |a JOURNAL_ARTICLE |2 ORCID |
| 336 | 7 | _ | |a Journal Article |0 0 |2 EndNote |
| 500 | _ | _ | |a PUBLISHED29 December 2025 |
| 520 | _ | _ | |a Objective. Magnetic resonance imaging (MRI) guided radiotherapy requires the delineation of gross tumor volumes (GTV) in daily MRI from MRI-linacs. Specialized models have been developed for this task for certain tumors. This study investigated an alternative, using promptable foundation models.Approach. Promptable foundation models were prompted with six different sparse geometric prompt types (points, boxes, 2D masks) to produce GTV segmentation masks, including Segment-anything 2 (SAM2), SAM2 fine-tuned for medical imaging (MedSAM2), and nnInteractive, an nnUnet-based promptable model for medical imaging. A diverse multi-institutional dataset of clinical GTV masks from the abdomen, lung, liver, pancreas, and pelvis sites on MRI scans from MRI-linacs was used to evaluate model outputs using various metrics, including the Dice similarity coefficient (DSC).Main results. The models produced segmentation masks comparable or superior to those from domain-specific models with median DSCs of up to 0.85 (nnInteractive-mask3 prompt). Prompts with more spatial information yielded better results with lower variance, with the effect reduced for nnInteractive and MedSAM2. These produced overall better results (median DSC over all prompt types 0.75 for nnInteractive, 0.70 for MedSAM2, 0.54 for SAM2).Significance. This investigation showed that promptable foundation models can in principle be used for GTV segmentation in MRI across multiple tumor types, although more research is necessary to reduce the variance and improve model performance. |
| 536 | _ | _ | |a 899 - ohne Topic (POF4-899) |0 G:(DE-HGF)POF4-899 |c POF4-899 |f POF IV |x 0 |
| 588 | _ | _ | |a Dataset connected to CrossRef, PubMed, , Journals: inrepo02.dkfz.de |
| 650 | _ | 7 | |a GTV segmentation |2 Other |
| 650 | _ | 7 | |a MRI-linac |2 Other |
| 650 | _ | 7 | |a MRgRT |2 Other |
| 650 | _ | 7 | |a deep learning |2 Other |
| 650 | _ | 7 | |a foundation models |2 Other |
| 650 | _ | 7 | |a promptable models |2 Other |
| 650 | _ | 2 | |a Magnetic Resonance Imaging |2 MeSH |
| 650 | _ | 2 | |a Humans |2 MeSH |
| 650 | _ | 2 | |a Radiotherapy, Image-Guided: methods |2 MeSH |
| 650 | _ | 2 | |a Tumor Burden |2 MeSH |
| 650 | _ | 2 | |a Image Processing, Computer-Assisted: methods |2 MeSH |
| 650 | _ | 2 | |a Neoplasms: radiotherapy |2 MeSH |
| 650 | _ | 2 | |a Neoplasms: diagnostic imaging |2 MeSH |
| 650 | _ | 2 | |a Neoplasms: pathology |2 MeSH |
| 700 | 1 | _ | |a Delopoulos, Nikolaos |b 1 |
| 700 | 1 | _ | |a Palacios, Miguel A |b 2 |
| 700 | 1 | _ | |a Klüter, Sebastian |0 0000-0003-3139-3444 |b 3 |
| 700 | 1 | _ | |a Hörner-Rieber, Juliane |b 4 |
| 700 | 1 | _ | |a Rippke, Carolin |b 5 |
| 700 | 1 | _ | |a Placidi, Lorenzo |b 6 |
| 700 | 1 | _ | |a Boldrini, Luca |b 7 |
| 700 | 1 | _ | |a Frascino, Vincenzo |b 8 |
| 700 | 1 | _ | |a Andratschke, Nicolaus |b 9 |
| 700 | 1 | _ | |a Baumgartl, Michael |b 10 |
| 700 | 1 | _ | |a Dal Bello, Riccardo |b 11 |
| 700 | 1 | _ | |a Marschner, Sebastian N |b 12 |
| 700 | 1 | _ | |a Belka, Claus |0 P:(DE-HGF)0 |b 13 |
| 700 | 1 | _ | |a Corradini, Stefanie |b 14 |
| 700 | 1 | _ | |a Dudas, Denis |0 0000-0003-0667-3727 |b 15 |
| 700 | 1 | _ | |a Riboldi, Marco |0 0000-0002-2431-4966 |b 16 |
| 700 | 1 | _ | |a Kurz, Christopher |b 17 |
| 700 | 1 | _ | |a Landry, Guillaume |0 0000-0003-1707-4068 |b 18 |
| 773 | _ | _ | |a 10.1088/1361-6560/ae2db9 |g Vol. 71, no. 1, p. 015006 - |0 PERI:(DE-600)1473501-5 |n 1 |p 015006 |t Physics in medicine and biology |v 71 |y 2025 |x 0031-9155 |
| 856 | 4 | _ | |y OpenAccess |u https://inrepo02.dkfz.de/record/307471/files/Julius_Bl%C3%B6cker_2026_Phys._Med._Biol._71_015006.pdf |
| 856 | 4 | _ | |y OpenAccess |x pdfa |u https://inrepo02.dkfz.de/record/307471/files/Julius_Bl%C3%B6cker_2026_Phys._Med._Biol._71_015006.pdf?subformat=pdfa |
| 909 | C | O | |o oai:inrepo02.dkfz.de:307471 |p openaire |p open_access |p VDB |p driver |p dnbdelivery |
| 910 | 1 | _ | |a Deutsches Krebsforschungszentrum |0 I:(DE-588b)2036810-0 |k DKFZ |b 13 |6 P:(DE-HGF)0 |
| 913 | 1 | _ | |a DE-HGF |b Programmungebundene Forschung |l ohne Programm |1 G:(DE-HGF)POF4-890 |0 G:(DE-HGF)POF4-899 |3 G:(DE-HGF)POF4 |2 G:(DE-HGF)POF4-800 |4 G:(DE-HGF)POF |v ohne Topic |x 0 |
| 914 | 1 | _ | |y 2025 |
| 915 | _ | _ | |a DBCoverage |0 StatID:(DE-HGF)0200 |2 StatID |b SCOPUS |d 2024-12-27 |
| 915 | _ | _ | |a DBCoverage |0 StatID:(DE-HGF)0300 |2 StatID |b Medline |d 2024-12-27 |
| 915 | _ | _ | |a DBCoverage |0 StatID:(DE-HGF)1050 |2 StatID |b BIOSIS Previews |d 2024-12-27 |
| 915 | _ | _ | |a DBCoverage |0 StatID:(DE-HGF)1190 |2 StatID |b Biological Abstracts |d 2024-12-27 |
| 915 | _ | _ | |a DBCoverage |0 StatID:(DE-HGF)0600 |2 StatID |b Ebsco Academic Search |d 2024-12-27 |
| 915 | _ | _ | |a JCR |0 StatID:(DE-HGF)0100 |2 StatID |b PHYS MED BIOL : 2022 |d 2024-12-27 |
| 915 | _ | _ | |a DBCoverage |0 StatID:(DE-HGF)1030 |2 StatID |b Current Contents - Life Sciences |d 2024-12-27 |
| 915 | _ | _ | |a WoS |0 StatID:(DE-HGF)0113 |2 StatID |b Science Citation Index Expanded |d 2024-12-27 |
| 915 | _ | _ | |a DBCoverage |0 StatID:(DE-HGF)0150 |2 StatID |b Web of Science Core Collection |d 2024-12-27 |
| 915 | _ | _ | |a IF < 5 |0 StatID:(DE-HGF)9900 |2 StatID |d 2024-12-27 |
| 915 | _ | _ | |a OpenAccess |0 StatID:(DE-HGF)0510 |2 StatID |
| 915 | _ | _ | |a Peer Review |0 StatID:(DE-HGF)0030 |2 StatID |b ASC |d 2024-12-27 |
| 915 | _ | _ | |a National-Konsortium |0 StatID:(DE-HGF)0430 |2 StatID |d 2024-12-27 |w ger |
| 915 | _ | _ | |a DBCoverage |0 StatID:(DE-HGF)0160 |2 StatID |b Essential Science Indicators |d 2024-12-27 |
| 915 | _ | _ | |a DBCoverage |0 StatID:(DE-HGF)0199 |2 StatID |b Clarivate Analytics Master Journal List |d 2024-12-27 |
| 920 | 1 | _ | |0 I:(DE-He78)MU01-20160331 |k MU01 |l DKTK Koordinierungsstelle München |x 0 |
| 980 | _ | _ | |a journal |
| 980 | _ | _ | |a VDB |
| 980 | _ | _ | |a UNRESTRICTED |
| 980 | _ | _ | |a I:(DE-He78)MU01-20160331 |
| 980 | 1 | _ | |a FullTexts |
| Library | Collection | CLSMajor | CLSMinor | Language | Author |
|---|