OSCR

A unified FLAIR hyperintensity segmentation model for various CNS tumor types and acquisition time points.

Code ↔ Paper

2 matches between paragraphs of the paper and lines of its authors' code, computed by the harvester (lexical-v1). Click a colored paragraph or line to see its counterpart.

The 2 matches
  1. [1] § Materials and methods › Data ↔ gui/UtilsWidgets/CustomQDialog/ResearchCommunityDialog.py, lines 22–81 · score 0.70 · Olavs hospital, University Hospital, Boston, Brigham, Norway, Women
  2. [2] § Materials and methods › Evaluation metrics ↔ raidionicsval/Validation/kfold_model_validation.py, lines 49–75 · score 0.55 · ground truth volume, probability thresholds, fold, metrics, model

Paper

Loaded from Europe PMC by your browser, not stored by OSCR: doi.org · Europe PMC

The paper is loaded when this pane is shown.

The authors' code

Python · 302 lines · 16 KB · BSD-2-Clause · 1 match

  1. from PySide6.QtWidgets import QWidget, QLabel, QHBoxLayout, QVBoxLayout, QDialog, QDialogButtonBox, QScrollArea, QGridLayout
  2. from PySide6.QtCore import Qt, QSize, Signal
  3. from PySide6.QtGui import QIcon, QPixmap
  4. import os
  6. from utils.software_config import SoftwareConfigResources
  9. class ResearchCommunityDialog(QDialog):
  11. def __init__(self, parent=None):
  12. super().__init__(parent)
  13. self.setWindowTitle("Research community")
  14. self.__set_interface()
  15. self.__set_layout_dimensions()
  16. self.__set_connections()
  17. self.__set_stylesheets()
  19. def exec(self) -> int:
  20. return super().exec()
  22. def __set_interface(self):
  23. self.layout = QVBoxLayout(self)
  24. self.layout.setSpacing(5)
  25. self.layout.setContentsMargins(0, 0, 0, 0)
  27. self.main_scrollarea = QScrollArea()
  28. self.main_scrollarea.show()
  29. self.main_scrollarea_layout = QGridLayout()
  30. self.main_scrollarea.setHorizontalScrollBarPolicy(Qt.ScrollBarAsNeeded)
  31. self.main_scrollarea.setVerticalScrollBarPolicy(Qt.ScrollBarAsNeeded)
  32. self.main_scrollarea.setWidgetResizable(True)
  33. self.main_scrollarea_dummy_widget = QLabel()
  34. self.main_scrollarea_layout.setSpacing(5)
  35. self.main_scrollarea_layout.setContentsMargins(10, 0, 10, 0)
  36. self.main_scrollarea_dummy_widget.setLayout(self.main_scrollarea_layout)
  37. self.main_scrollarea.setWidget(self.main_scrollarea_dummy_widget)
  38. self.layout.addWidget(self.main_scrollarea)
  39. self.title_layout = QHBoxLayout()
  40. self.title_layout.setSpacing(0)
  41. self.title_layout.setContentsMargins(0, 0, 0, 0)
  42. self.title_label = QLabel(" The data used for training the various segmentation models was gathered from:")
  43. self.title_layout.addStretch(1)
  44. self.title_layout.addWidget(self.title_label)
  45. self.title_layout.addStretch(1)
  46. self.main_scrollarea_layout.addLayout(self.title_layout, 0, 0, 1, 4)
  48. self.st_olavs_widget = HospitalContributorWidget(self)
  49. self.st_olavs_widget.set_hospital_name("St. Olavs hospital,Trondheim\nUniversity Hospital, Trondheim, Norway")
  50. self.st_olavs_widget.set_hospital_participants("Ole Solheim, Lisa M. Sagberg, Sayed Hoseiney,\nEven H. Fyllingen, Camilla Brattbakk")
  51. self.st_olavs_widget.set_logo_icon(os.path.join(os.path.dirname(os.path.realpath(__file__)),
  52. '../../Images/stolavs-logo.png'))
  53. self.main_scrollarea_layout.addWidget(self.st_olavs_widget, 1, 0, 1, 1)
  55. self.goth_sahl_widget = HospitalContributorWidget(self)
  56. self.goth_sahl_widget.set_hospital_name("Sahlgrenska University Hospital,\nGothenburg, Sweden")
  57. self.goth_sahl_widget.set_hospital_participants("Asgeir Store Jakola")
  58. self.goth_sahl_widget.set_logo_icon(os.path.join(os.path.dirname(os.path.realpath(__file__)),
  59. '../../Images/gothenburg-hospital-icon.png'))
  60. self.main_scrollarea_layout.addWidget(self.goth_sahl_widget, 1, 1, 1, 1)
  62. self.olso_ouh_widget = HospitalContributorWidget(self)
  63. self.olso_ouh_widget.set_hospital_name("Oslo University Hospital,\nOslo, Norway")
  64. self.olso_ouh_widget.set_hospital_participants("Kyrre Eeg Emblem")
  65. self.olso_ouh_widget.set_logo_icon(os.path.join(os.path.dirname(os.path.realpath(__file__)),
  66. '../../Images/oslo_univeristy_hospital_icon.png'))
  67. self.main_scrollarea_layout.addWidget(self.olso_ouh_widget, 1, 2, 1, 1)
  69. self.brigham_boston_widget = HospitalContributorWidget(self)
  70. self.brigham_boston_widget.set_hospital_name("Brigham and Women’s Hospital,\nBoston, USA")
  71. self.brigham_boston_widget.set_hospital_participants("Timothy R. Smith,\nVasileios Kavouridis")
  72. self.brigham_boston_widget.set_logo_icon(os.path.join(os.path.dirname(os.path.realpath(__file__)),
  73. '../../Images/brigham-boston-hospital-logo.png'))
  74. self.main_scrollarea_layout.addWidget(self.brigham_boston_widget, 1, 3, 1, 1)
  76. self.amsterdam_widget = HospitalContributorWidget(self)
  77. self.amsterdam_widget.set_hospital_name("Amsterdam University Medical Centers,\nVrije Universiteit, Amsterdam, The Netherlands")
  78. self.amsterdam_widget.set_hospital_participants("Philip C. De Witt Hamer, Roelant S. Eijgelaar,\nIvar Kommers, Frederik Barkhof,\nDomenique M.J. Müller, Aeilko H. Zwinderman")
  79. self.amsterdam_widget.set_logo_icon(os.path.join(os.path.dirname(os.path.realpath(__file__)),
  80. '../../Images/amsterdam-hospital-logo.png'))
  81. self.main_scrollarea_layout.addWidget(self.amsterdam_widget, 2, 0, 1, 1)
  83. self.twee_steden_widget = HospitalContributorWidget(self)
  84. self.twee_steden_widget.set_hospital_name("Twee Steden Hospital,\nTilburg, The Netherlands")
  85. self.twee_steden_widget.set_hospital_participants("Hilko Ardon")
  86. self.twee_steden_widget.set_logo_icon(os.path.join(os.path.dirname(os.path.realpath(__file__)),
  87. '../../Images/tweesteden-hospital-logo.png'))
  88. self.main_scrollarea_layout.addWidget(self.twee_steden_widget, 2, 1, 1, 1)
  90. self.humanitas_milan_widget = HospitalContributorWidget(self)
  91. self.humanitas_milan_widget.set_hospital_name("Humanitas Research Hospital, Università\nDegli Studi di Milano, Milano, Italy")
  92. self.humanitas_milan_widget.set_hospital_participants("Lorenzo Bello, Marco Conti Nibali,\nMarco Rossi, Tommaso Sciortino")
  93. self.humanitas_milan_widget.set_logo_icon(os.path.join(os.path.dirname(os.path.realpath(__file__)),
  94. '../../Images/humanitas-milan-hospital-logo.png'))
  95. self.main_scrollarea_layout.addWidget(self.humanitas_milan_widget, 2, 2, 1, 1)
  97. self.ucsf_widget = HospitalContributorWidget(self)
  98. self.ucsf_widget.set_hospital_name("University of California San Francisco,\nSan Francisco, USA")
  99. self.ucsf_widget.set_hospital_participants("Mitchel S. Berger,\nShawn Hervey-Jumper")
  100. self.ucsf_widget.set_logo_icon(os.path.join(os.path.dirname(os.path.realpath(__file__)),
  101. '../../Images/ucsf-hospital-logo.png'))
  102. self.main_scrollarea_layout.addWidget(self.ucsf_widget, 2, 3, 1, 1)
  104. self.vienna_hospital_widget = HospitalContributorWidget(self)
  105. self.vienna_hospital_widget.set_hospital_name("Medical University Vienna,\nWien, Austria")
  106. self.vienna_hospital_widget.set_hospital_participants("Julia Furtner, Barbara Kiesel, \nGeorg Widhalm")
  107. self.vienna_hospital_widget.set_logo_icon(os.path.join(os.path.dirname(os.path.realpath(__file__)),
  108. '../../Images/vienna-hospital-logo.png'))
  109. self.main_scrollarea_layout.addWidget(self.vienna_hospital_widget, 3, 0, 1, 1)
  111. self.alkmaar_hospital_widget = HospitalContributorWidget(self)
  112. self.alkmaar_hospital_widget.set_hospital_name("Northwest Clinics, Alkmaar,\nThe Netherlands")
  113. self.alkmaar_hospital_widget.set_hospital_participants("Albert J. S. Idema")
  114. self.alkmaar_hospital_widget.set_logo_icon(os.path.join(os.path.dirname(os.path.realpath(__file__)),
  115. '../../Images/alkmaar-hospital-logo.png'))
  116. self.main_scrollarea_layout.addWidget(self.alkmaar_hospital_widget, 3, 1, 1, 1)
  118. self.hague_hospital_widget = HospitalContributorWidget(self)
  119. self.hague_hospital_widget.set_hospital_name("Haaglanden Medical Center,\nThe Hague, The Netherlands")
  120. self.hague_hospital_widget.set_hospital_participants("Alfred Kloet")
  121. self.hague_hospital_widget.set_logo_icon(os.path.join(os.path.dirname(os.path.realpath(__file__)),
  122. '../../Images/haaglanden-hospital-logo.png'))
  123. self.main_scrollarea_layout.addWidget(self.hague_hospital_widget, 3, 2, 1, 1)
  125. self.lariboisiere_hospital_widget = HospitalContributorWidget(self)
  126. self.lariboisiere_hospital_widget.set_hospital_name("Hôpital Lariboisière,\nParis, France")
  127. self.lariboisiere_hospital_widget.set_hospital_participants("Emmanuel Mandonnet")
  128. self.lariboisiere_hospital_widget.set_logo_icon(os.path.join(os.path.dirname(os.path.realpath(__file__)),
  129. '../../Images/lariboisiere-hospital-logo.png'))
  130. self.main_scrollarea_layout.addWidget(self.lariboisiere_hospital_widget, 3, 3, 1, 1)
  132. self.utrecht_hospital_widget = HospitalContributorWidget(self)
  133. self.utrecht_hospital_widget.set_hospital_name("University Medical Center Utrecht,\nUtrecht, The Netherlands")
  134. self.utrecht_hospital_widget.set_hospital_participants("Pierre A. Robe")
  135. self.utrecht_hospital_widget.set_logo_icon(os.path.join(os.path.dirname(os.path.realpath(__file__)),
  136. '../../Images/utrecht-hospital-logo.png'))
  137. self.main_scrollarea_layout.addWidget(self.utrecht_hospital_widget, 4, 0, 1, 1)
  139. self.isala_hospital_widget = HospitalContributorWidget(self)
  140. self.isala_hospital_widget.set_hospital_name("Isala, Zwolle, The Netherlands")
  141. self.isala_hospital_widget.set_hospital_participants("Wimar van den Brink")
  142. self.isala_hospital_widget.set_logo_icon(os.path.join(os.path.dirname(os.path.realpath(__file__)),
  143. '../../Images/isala-hospital-logo.png'))
  144. self.main_scrollarea_layout.addWidget(self.isala_hospital_widget, 4, 1, 1, 1)
  146. self.groningen_hospital_widget = HospitalContributorWidget(self)
  147. self.groningen_hospital_widget.set_hospital_name("University Medical Center Groningen,\nGroningen, The Netherlands")
  148. self.groningen_hospital_widget.set_hospital_participants("Michiel Wagemakers")
  149. self.groningen_hospital_widget.set_logo_icon(os.path.join(os.path.dirname(os.path.realpath(__file__)),
  150. '../../Images/groningen-hospital-logo.png'))
  151. self.main_scrollarea_layout.addWidget(self.groningen_hospital_widget, 4, 2, 1, 1)
  153. self.cancer_institute_ams_widget = HospitalContributorWidget(self)
  154. self.cancer_institute_ams_widget.set_hospital_name("The Netherlands Cancer Institute,\nAmsterdam, The Netherlands")
  155. self.cancer_institute_ams_widget.set_hospital_participants("Marnix G. Witte")
  156. self.cancer_institute_ams_widget.set_logo_icon(os.path.join(os.path.dirname(os.path.realpath(__file__)),
  157. '../../Images/cancer-institute-ams-logo.png'))
  158. self.main_scrollarea_layout.addWidget(self.cancer_institute_ams_widget, 4, 3, 1, 1)
  160. self.brats_widget = HospitalContributorWidget(self)
  161. self.brats_widget.set_hospital_name("The BraTS challenge 2023/2024")
  162. self.brats_widget.set_hospital_participants("""<a href="https://www.synapse.org/Synapse:syn64153130/wiki">Official website</a>""")
  163. self.brats_widget.set_logo_icon(os.path.join(os.path.dirname(os.path.realpath(__file__)),
  164. '../../Images/brats-challenge-logo.png'))
  165. self.main_scrollarea_layout.addWidget(self.brats_widget, 5, 0, 1, 1)
  167. self.main_scrollarea_layout.setRowStretch(self.main_scrollarea_layout.rowCount(), 1)
  169. # Native exit buttons
  170. self.bottom_exit_layout = QHBoxLayout()
  171. self.exit_close_pushbutton = QDialogButtonBox(QDialogButtonBox.Close)
  172. self.bottom_exit_layout.addStretch(1)
  173. self.bottom_exit_layout.addWidget(self.exit_close_pushbutton)
  174. self.layout.addLayout(self.bottom_exit_layout)
  176. def __set_layout_dimensions(self):
  177. self.setMinimumSize(QSize(600, 300))
  178. self.title_label.setFixedHeight(40)
  179. self.main_scrollarea_dummy_widget.setFixedSize(QSize(1500, 500))
  181. def __set_connections(self):
  182. self.exit_close_pushbutton.clicked.connect(self.accept)
  184. def __set_stylesheets(self):
  185. software_ss = SoftwareConfigResources.getInstance().stylesheet_components
  186. font_color = software_ss["Color7"]
  187. background_color = software_ss["Color2"]
  189. self.setStyleSheet("""
  190. QDialog{
  191. background-color: """ + background_color + """;
  192. }
  193. """)
  195. self.main_scrollarea.setStyleSheet("""
  196. QScrollArea{
  197. background-color: """ + background_color + """;
  198. }
  199. """)
  201. self.main_scrollarea_dummy_widget.setStyleSheet("""
  202. QWidget{
  203. background-color: """ + background_color + """;
  204. }
  205. """)
  207. self.title_label.setStyleSheet("""
  208. QLabel{
  209. color: """ + font_color + """;
  210. background-color: """ + background_color + """;
  211. font: 18px;
  212. }""")
  215. class HospitalContributorWidget(QWidget):
  217. def __init__(self, parent=None):
  218. super().__init__(parent)
  219. self.__set_interface()
  220. self.__set_layout_dimensions()
  221. self.__set_connections()
  222. self.__set_stylesheets()
  224. def __set_interface(self):
  225. self.setAttribute(Qt.WA_StyledBackground, True) # Enables to set e.g. background-color for the QWidget
  226. self.layout = QHBoxLayout(self)
  227. self.layout.setSpacing(0)
  228. self.layout.setContentsMargins(5, 5, 5, 5)
  230. self.hospital_logo_layout = QVBoxLayout()
  231. self.hospital_logo_layout.setSpacing(0)
  232. self.hospital_logo_layout.setContentsMargins(0, 0, 0, 0)
  233. self.hospital_logo_label = QLabel()
  234. self.hospital_logo_layout.addStretch(1)
  235. self.hospital_logo_layout.addWidget(self.hospital_logo_label)
  236. self.hospital_logo_layout.addStretch(1)
  237. self.hospital_name_label = QLabel()
  238. self.hospital_name_label.setTextInteractionFlags(Qt.TextSelectableByMouse)
  239. self.hospital_participants_label = QLabel()
  240. self.hospital_participants_label.setTextInteractionFlags(Qt.TextSelectableByMouse | Qt.TextBrowserInteraction)
  241. self.hospital_participants_label.setOpenExternalLinks(True)
  243. self.hospital_location_layout = QVBoxLayout()
  244. self.hospital_location_layout.setSpacing(0)
  245. self.hospital_location_layout.setContentsMargins(0, 0, 0, 0)
  246. self.hospital_location_layout.addWidget(self.hospital_name_label)
  247. self.hospital_location_layout.addWidget(self.hospital_participants_label)
  248. self.hospital_location_layout.addStretch(1)
  250. self.layout.addWidget(self.hospital_logo_label)
  251. self.layout.addLayout(self.hospital_location_layout)
  253. def __set_layout_dimensions(self):
  254. self.setFixedSize(QSize(350, 100))
  255. self.hospital_logo_label.setFixedSize(QSize(50, 50))
  256. self.hospital_name_label.setFixedSize(QSize(270, 40))
  257. self.hospital_participants_label.setFixedSize(QSize(270, 50))
  259. def __set_connections(self):
  260. pass
  262. def __set_stylesheets(self):
  263. software_ss = SoftwareConfigResources.getInstance().stylesheet_components
  264. font_color = software_ss["Color7"]
  265. background_color = software_ss["Color2"]
  267. self.setStyleSheet("""
  268. QWidget{
  269. background-color: """ + background_color + """;
  270. border: 2px solid black;
  271. }
  272. """)
  274. self.hospital_logo_label.setStyleSheet("""
  275. QLabel{
  276. border: none;
  277. }""")
  279. self.hospital_name_label.setStyleSheet("""
  280. QLabel{
  281. color: """ + font_color + """;
  282. font-size: 13px;
  283. border: none;
  284. }
  285. """)
  287. self.hospital_participants_label.setStyleSheet("""
  288. QLabel{
  289. color: """ + font_color + """;
  290. font-size: 13px;
  291. border: none;
  292. }
  293. """)
  295. def set_logo_icon(self, filename: str) -> None:
  296. self.hospital_logo_label.setPixmap(QPixmap(filename).scaled(QSize(50, 50)))
  298. def set_hospital_name(self, name: str) -> None:
  299. self.hospital_name_label.setText(name)
  301. def set_hospital_participants(self, participants: str) -> None:
  302. self.hospital_participants_label.setText(participants)

ResearchCommunityDialog.py at commit fcb5d92, under BSD-2-Clause · at the source

Overview

Authors: Mathilde Gajda Faanes1, David Bouget1, Asgeir S Jakola2,3, Timothy R Smith4, Vasileios K Kavouridis4, Francesco Latini5, Margret Jensdottir6, Peter Milos7, Henrietta Nittby Redebrandt8, Rickard L Sjöberg9, Rupavathana Mahesparan10, Lars Kjelsberg Pedersen11, Ole Solheim12,13, Ingerid Reinertsen1,14
ORCID iDs: Margret Jensdottir, Rickard L Sjöberg, Ole Solheim
14 affiliations
  1. Department of Health Research, SINTEF Digital, Trondheim, Norway
  2. Department of Clinical Neuroscience, Institute of Neuroscience and Physiology, University of Gothenburg, Gothenburg, Sweden
  3. Department of Neurosurgery, Sahlgrenska University Hospital, Region Västragötaland, Gothenburg, Sweden
  4. Department of Neurosurgery, Brigham and Women’s Hospital, Harvard Medical School, Boston, MA USA
  5. Department Medical Sciences, Section of Neurosurgery, Uppsala University Hospital, Uppsala, Sweden
  6. Department of Neurosurgery, Karolinska University Hospital, Stockholm, Sweden
  7. Department of Neurosurgery, Linköping University Hospital, Linköping, Sweden
  8. Department of Neurosurgery, Skåne University Hospital, Lund, Sweden
  9. Department of Clinical Science, Umeå University, Umeå, Sweden
  10. Department of Neurosurgery, Haukeland University Hospital, Bergen, Norway
  11. Department of Neurosurgery, University Hospital of North Norway, Tromsø, Norway
  12. Department of Neuromedicine and Movement Science, Norwegian University of Science and Technology, Trondheim, Norway
  13. Department of Neurosurgery, St. Olavs hospital, Trondheim University Hospital, Trondheim, Norway
  14. Department of Circulation and Medical Imaging, Norwegian University of Science and Technology, Trondheim, Norway
Institutions: SINTEF Digital; SINTEF (Norway); Sahlgrenska University Hospital (Sweden); University of Gothenburg (Sweden); Brigham and Women's Hospital (United States); Harvard University (United States); Uppsala University Hospital (Sweden); Karolinska University Hospital (Sweden); Linköping University Hospital (Sweden); Skåne University Hospital (Sweden); Umeå University (Sweden); Haukeland University Hospital (Norway); University Hospital of North Norway (Norway); Norwegian University of Science and Technology (Norway); St Olav's University Hospital (Norway)
Journal: Scientific reports, volume 16, issue 1, article 19707
Dates: received 16 January 2026; accepted 8 April 2026; published online 24 April 2026
Type: Research article · Language: English
License: CC BY
Identifiers: DOI 10.1038/s41598-026-48496-1 · PMID 42031792 · PMCID PMC13315698 · OpenAlex W7155561789
Open access: gold, a free copy (OpenAlex)
Status: code verified
Categories: structural MRI / diffusion (modality), human (organism), other condition (population), methods / tools (subfield)
Methods: Connectivity, Machine learning
Keywords: Cancer, Computational biology and bioinformatics, Medical research, Oncology
MeSH: Brain Neoplasms*, Central Nervous System Neoplasms*, Image Processing, Computer-Assisted*, Magnetic Resonance Imaging*, Female, Glioma, Humans (* major topic)
Topic: Brain Tumor Detection and Classification (Neurology, Neuroscience), according to OpenAlex
Funding: NTNU Norwegian University of Science and Technology
Citations: not cited yet (Europe PMC); 37 references in the paper

Abstract

Fluid-attenuated inversion recovery (FLAIR) magnetic resonance imaging (MRI) scans are important for diagnosis, treatment planning, and monitoring of various brain tumors. Depending on the tumor type, the FLAIR hyperintensity volume is an important measure to assess the tumor volume, surrounding vasogenic edema, or treatment induced changes, such as gliosis. Automatic segmentation would therefore be valuable in the clinic and in clinical trials. In this study, around 5000 FLAIR images of various brain tumors types and acquisition time points, from different neurosurgical centers, were used to train a unified FLAIR hyperintensity segmentation model using an Attention U-Net architecture. The performance was compared against dataset-specific models and was validated on different tumor types, acquisition time points, and against BraTS. The unified model achieved an average Dice score of 88.65% for pre-operative meningiomas, 80.08% for pre-operative metastases, 90.92% for pre-operative and 84.60% for post-operative gliomas from BraTS, and 84.47% for pre-operative and 61.27% for post-operative lower grade gliomas. In addition, the results showed that the unified model achieved comparable segmentation performance to the dataset-specific models on their respective datasets. The documented generalization across tumor types and acquisition time points is a strong indicator for efficient deployment in a clinical setting. The model has been integrated into Raidionics, an open-source software for CNS tumor analysis.

Reproduced under the paper's license (CC BY), from the paper cited above.

Repositories

Its files are read in the Code ↔ Paper reader above, with 2 matches between paragraphs and lines of code.

raidionics/raidionics-models

License: BSD-2-Clause
State: the link answers, verified on 30 September 2026
Evidence: files inventoried
Commit: 78a810e490412614dc554158236ee9930a8193f1, 14 December 2023
Size: 2 files, 0 scripts
Software Heritage: not archived
Found in: “Data and code availability”
Holds: README, license file
Not found: CITATION.cff, environment file, tests, continuous integration, documentation
Availability: 1 check, the latest on 30 September 2026: the link answers
  • 30 September 2026: the link answers
2 files
At the source: github.com/raidionics/Raidionics-models/releases/tag/v1.3.0-rc

raidionics/Raidionics

License: BSD-2-Clause
State: the link answers, verified on 30 September 2026
Evidence: files inventoried
Commit: fcb5d92f9ab8150336cd4ba23968823cc49f4aa2, 15 January 2026
Languages: Python (126)
Size: 241 files, 126 scripts
Software Heritage: not archived
Found in: “Data and code availability”
Holds: README, license file, environment (assets/requirements.txt), tests, continuous integration
Not found: CITATION.cff, documentation
Tools: NumPy (15 files), NiBabel (6 files), pandas (6 files), SimpleITK (3 files), Plotly (1 file), SciPy (1 file)
Availability: 1 check, the latest on 30 September 2026: the link answers
  • 30 September 2026: the link answers
128 files
At the source: github.com/raidionics/Raidionics

dbouget/validation_metrics_computation

License: BSD-2-Clause
State: the link answers, verified on 30 September 2026
Evidence: files inventoried
Commit: 22448bb0352984bfc04289954d0f175135e61267, 31 July 2026
Languages: Python (41), Jupyter (2)
Size: 56 files, 43 scripts
Software Heritage: archived
Found in: “Data and code availability”
Holds: README, license file, CITATION.cff, environment (Dockerfile, pyproject.toml), tests, continuous integration, documentation, 2 notebooks
Tools: NumPy (17 files), pandas (15 files), Matplotlib (8 files), NiBabel (3 files), scikit-learn (2 files), SciPy (2 files), seaborn (2 files), h5py (1 file), Pillow (1 file), scikit-image (1 file), SimpleITK (1 file), statsmodels (1 file)
Availability: 1 check, the latest on 30 September 2026: the link answers
  • 30 September 2026: the link answers
45 files
At the source: github.com/dbouget/validation_metrics_computation

The paper's code and data availability statement is in the Data section.

Tracing map

Proposed by the machine: these links were found in the paper and verified at the source, without human review. The map will receive a Zenodo DOI once one of the paper's authors has validated it with their ORCID.

What the map holds:

  • 3 repositories of the authors' code, each at its verified commit, with its license and how the link was found in the paper;
  • 169 scripts, each with its path and the digest of its content;
  • 2 matches between paragraphs of the paper and lines of the code (method lexical-v1);
  • neither the text of the paper nor the code itself.

Its JSON (tracing-map.json) is deposited on Zenodo with its DOI once the map is validated.

Data

Datasets cited

Data and code availability

The data analyzed in this study is subject to the following licenses/restrictions: patient data are protected under GDPR and cannot be publicly distributed. Requests to access these datasets should be directed to David Bouget for consideration. The BraTS Challenge datasets are available at the following URL: https://www.synapse.org/Synapse:syn53708126/wiki/626320. The Raidionics environment with all related information is available at https://github.com/raidionics. More specifically, all trained models can be accessed at https://github.com/raidionics/Raidionics-models/releases/tag/v1.3.0-rc, the Raidionics software can be found at https://github.com/raidionics/Raidionics. Finally, the source code used to compute the validation metrics is available at https://github.com/dbouget/validation_metrics_computation.

Reproduced under the paper's license (CC BY), from the paper cited above.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 1, 30 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 14 authors, 4 keywords, 7 MeSH terms, 1 funder, 34 references.

Cite

This paper

Faanes, M. G., Bouget, D., Jakola, A. S., Smith, T. R., Kavouridis, V. K., Latini, F., Jensdottir, M., Milos, P., Redebrandt, H. N., Sjöberg, R. L., Mahesparan, R., Pedersen, L. K., Solheim, O., & Reinertsen, I. (2026). A unified FLAIR hyperintensity segmentation model for various CNS tumor types and acquisition time points. Scientific reports, 16(1), 19707. https://doi.org/10.1038/s41598-026-48496-1

BibTeX

@article{faanes2026unified,
author = {Faanes, Mathilde Gajda and Bouget, David and Jakola, Asgeir S and Smith, Timothy R and Kavouridis, Vasileios K and Latini, Francesco and Jensdottir, Margret and Milos, Peter and Redebrandt, Henrietta Nittby and Sjöberg, Rickard L and Mahesparan, Rupavathana and Pedersen, Lars Kjelsberg and Solheim, Ole and Reinertsen, Ingerid},
title = {{A unified FLAIR hyperintensity segmentation model for various CNS tumor types and acquisition time points}},
journal = {Scientific reports},
year = {2026},
month = apr,
volume = {16},
number = {1},
pages = {19707},
publisher = {Nature Publishing Group},
issn = {2045-2322},
doi = {10.1038/s41598-026-48496-1},
url = {https://doi.org/10.1038/s41598-026-48496-1},
pmid = {42031792},
pmcid = {PMC13315698}
}

RIS

TY - JOUR
AU - Faanes, Mathilde Gajda
AU - Bouget, David
AU - Jakola, Asgeir S
AU - Smith, Timothy R
AU - Kavouridis, Vasileios K
AU - Latini, Francesco
AU - Jensdottir, Margret
AU - Milos, Peter
AU - Redebrandt, Henrietta Nittby
AU - Sjöberg, Rickard L
AU - Mahesparan, Rupavathana
AU - Pedersen, Lars Kjelsberg
AU - Solheim, Ole
AU - Reinertsen, Ingerid
TI - A unified FLAIR hyperintensity segmentation model for various CNS tumor types and acquisition time points
T2 - Scientific reports
J2 - Sci Rep
PY - 2026
DA - 2026/04/24
VL - 16
IS - 1
SP - 19707
SN - 2045-2322
PB - Nature Publishing Group
DO - 10.1038/s41598-026-48496-1
UR - https://doi.org/10.1038/s41598-026-48496-1
LA - en
ER -

CSL-JSON

{
"id": "10.1038/s41598-026-48496-1",
"type": "article-journal",
"title": "A unified FLAIR hyperintensity segmentation model for various CNS tumor types and acquisition time points",
"container-title": "Scientific reports",
"author": [
{
"family": "Faanes",
"given": "Mathilde Gajda"
},
{
"family": "Bouget",
"given": "David"
},
{
"family": "Jakola",
"given": "Asgeir S"
},
{
"family": "Smith",
"given": "Timothy R"
},
{
"family": "Kavouridis",
"given": "Vasileios K"
},
{
"family": "Latini",
"given": "Francesco"
},
{
"family": "Jensdottir",
"given": "Margret"
},
{
"family": "Milos",
"given": "Peter"
},
{
"family": "Redebrandt",
"given": "Henrietta Nittby"
},
{
"family": "Sjöberg",
"given": "Rickard L"
},
{
"family": "Mahesparan",
"given": "Rupavathana"
},
{
"family": "Pedersen",
"given": "Lars Kjelsberg"
},
{
"family": "Solheim",
"given": "Ole"
},
{
"family": "Reinertsen",
"given": "Ingerid"
}
],
"container-title-short": "Sci Rep",
"volume": "16",
"issue": "1",
"page": "19707",
"DOI": "10.1038/s41598-026-48496-1",
"PMID": "42031792",
"PMCID": "PMC13315698",
"ISSN": "2045-2322",
"publisher": "Nature Publishing Group",
"URL": "https://doi.org/10.1038/s41598-026-48496-1",
"language": "en",
"issued": {
"date-parts": [
[
2026,
4,
24
]
]
}
}

The tracing map gets a citation of its own once an author has validated it and it has a DOI.

Similar papers

The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.

[1] doi:10.1016/j.phro.2026.101056 [code]
Toward uncertainty-aware manual delineation of brain tumours using eye-tracking and image-derived features.
Journal: Physics and imaging in radiation oncology
In common: scikit-image, Pillow, NiBabel, 6 other tools, synapse.org/synapse:syn51156910, other condition, 2 references
[2] doi:10.21037/qims-2026-0792 [code]
An nnU-Net-based framework with adaptive feature representation for 3D brain tumor segmentation.
Journal: Quantitative imaging in medicine and surgery
In common: SimpleITK, scikit-image, NiBabel, 6 other tools, methods / tools, structural MRI / diffusion, other condition, 4 references
[3] doi:10.1002/alz.71649 [code]
Postmortem brain MRI reveals differential associations of subcortical and limbic volumes with cortical thinning and neurodegenerative pathologies.
Journal: Alzheimer's & dementia : the journal of the Alzheimer's Association
In common: SimpleITK, Plotly, scikit-image, 9 other tools, structural MRI / diffusion, other condition
[4] doi:10.3389/fnins.2026.1870124 [code]
An end-to-end pipeline for automated fetal brain segmentation and biometry from 3D SSFP MRI.
Journal: Frontiers in neuroscience
In common: SimpleITK, scikit-image, NiBabel, 6 other tools, structural MRI / diffusion, 3 references
[5] doi:10.3389/frai.2026.1771088 [code]
Few-shot deployment of pretrained MRI transformers in brain imaging tasks.
Journal: Frontiers in artificial intelligence
In common: SimpleITK, scikit-image, h5py, 8 other tools, methods / tools, structural MRI / diffusion
[6] doi:10.1038/s41598-026-57519-w [code]
Automated segmentation of neurons and spinal cord structures in immunofluorescence images using SpineDL.
Journal: Scientific reports
In common: Plotly, scikit-image, h5py, 7 other tools, methods / tools, other condition, 1 reference
[7] doi:10.1038/s41467-026-72437-1 [code]
High-speed whole-brain imaging in Drosophila.
Journal: Nature communications
In common: SimpleITK, Plotly, scikit-image, 8 other tools
[8] doi:10.1016/j.patter.2026.101538 [code]
A multi-modal foundation model for brain disease diagnosis and medical imaging.
Journal: Patterns (New York, N.Y.)
In common: scikit-image, h5py, Pillow, 6 other tools, 2 references
[9] doi:10.1186/s12880-026-02481-2 [code]
Deep learning-based neuroanatomical profiling reveals population-specific brain changes in multiple sclerosis: a large-scale Middle Eastern study.
Journal: BMC medical imaging
In common: Plotly, scikit-image, Pillow, 7 other tools, structural MRI / diffusion, 1 reference
[10] doi:10.1016/j.xcrm.2026.102766 [code]
A longitudinal single-cell and spatial multiomic atlas of pediatric high-grade glioma.
Journal: Cell reports. Medicine
In common: Plotly, scikit-image, h5py, 7 other tools, other condition, 1 reference

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Sign in with ORCID to claim this paper as one of its authors, correct its record or validate its tracing map: when the paper's metadata lists your ORCID iD, you are recognized at once. Maintainers of its code: sign in with GitHub, then claim the repository on your account page.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion, reproductions, activity

Discussion: questions and error reports about this paper and its code, from signed-in readers and its authors. It opens with sign-in.

Reproductions: reports from readers who ran the authors' code: what they reproduced, with which environment, commit and data. It opens with sign-in.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.