Asosiy kontentga oʻtish
Maqola

Preoperative Brain Tumor Imaging: Models and Software for Segmentation and Standardized Reporting

David BougetDepartment of Health Research, SINTEF Digital, Trondheim, NorwayAndré PedersenDepartment of Clinical and Molecular Medicine, Norwegian University of Science and Technology, Trondheim, NorwayAsgeir Store JakolaDepartment of Neurosurgery, Sahlgrenska University Hospital, Gothenburg, SwedenVasileios K. KavouridisDepartment of Neurosurgery, St. Olavs Hospital, Trondheim University Hospital, Trondheim, NorwayKyrre E. EmblemDivision of Radiology and Nuclear Medicine, Department of Physics and Computational Radiology, Oslo University Hospital, Oslo, NorwayRoelant S. EijgelaarDepartment of Neurosurgery, Amsterdam University Medical Centers, Vrije Universiteit, Amsterdam, NetherlandsIvar KommersDepartment of Neurosurgery, Amsterdam University Medical Centers, Vrije Universiteit, Amsterdam, NetherlandsHilko ArdonDepartment of Neurosurgery, Twee Steden Hospital, Tilburg, NetherlandsFrederik BarkhofVrije Universiteit AmsterdamLorenzo BelloNeurosurgical Oncology Unit, Department of Oncology and Hemato-Oncology, Humanitas Research Hospital, Università degli Studi di Milano, Milan, ItalyMitchel S. BergerDepartment of Neurological Surgery, University of California, San Francisco, San Francisco, CA, United StatesMarco Conti NibaliNeurosurgical Oncology Unit, Department of Oncology and Hemato-Oncology, Humanitas Research Hospital, Università degli Studi di Milano, Milan, ItalyJulia FurtnerDepartment of Biomedical Imaging and Image-Guided Therapy, Medical University Vienna, Wien, AustriaShawn L. Hervey‐JumperNeurological SurgeryAlbert J. S. IdemaBarbara KieselDepartment of Neurosurgery, Medical University Vienna, Wien, AustriaAlfred KloetDepartment of Neurosurgery, Haaglanden Medical Center, The Hague, NetherlandsEmmanuel MandonnetDepartment of Neurological Surgery, Hôpital Lariboisière, Paris, FranceDomenique M. J. MüllerCancer Center Amsterdam, Brain Tumor Center, Amsterdam University Medical Centers, Amsterdam, NetherlandsPierre A. RobeDepartment of Neurology and Neurosurgery, University Medical Center Utrecht, Utrecht, NetherlandsMarco RossiNeurosurgical Oncology Unit, Department of Oncology and Hemato-Oncology, Humanitas Research Hospital, Università degli Studi di Milano, Milan, ItalyTommaso SciortinoNeurosurgical Oncology Unit, Department of Oncology and Hemato-Oncology, Humanitas Research Hospital, Università degli Studi di Milano, Milan, ItalyWimar A. van den BrinkDepartment of Neurosurgery, Isala, Zwolle, NetherlandsMichiel WagemakersDepartment of Neurosurgery, University Medical Center Groningen, University of Groningen, Groningen, NetherlandsGeorg WidhalmDepartment of Neurosurgery, Medical University Vienna, Wien, AustriaMarnix G. WitteDepartment of Radiation Oncology, Netherlands Cancer Institute, Amsterdam, NetherlandsAeilko H. ZwindermanUniversity of AmsterdamPhilip C. De Witt HamerCancer Center Amsterdam, Brain Tumor Center, Amsterdam University Medical Centers, Amsterdam, NetherlandsOle SolheimDepartment of Neurosurgery, St. Olavs Hospital, Trondheim University Hospital, Trondheim, NorwayIngerid ReinertsenDepartment of Health Research, SINTEF Digital, Trondheim, Norway
2022en
Ochiq kirishOltin

Litsenziya: cc-by

ABI

Annotatsiya

For patients suffering from brain tumor, prognosis estimation and treatment decisions are made by a multidisciplinary team based on a set of preoperative MR scans. Currently, the lack of standardized and automatic methods for tumor detection and generation of clinical reports, incorporating a wide range of tumor characteristics, represents a major hurdle. In this study, we investigate the most occurring brain tumor types: glioblastomas, lower grade gliomas, meningiomas, and metastases, through four cohorts of up to 4,000 patients. Tumor segmentation models were trained using the AGU-Net architecture with different preprocessing steps and protocols. Segmentation performances were assessed in-depth using a wide-range of voxel and patient-wise metrics covering volume, distance, and probabilistic aspects. Finally, two software solutions have been developed, enabling an easy use of the trained models and standardized generation of clinical reports: Raidionics and Raidionics-Slicer. Segmentation performances were quite homogeneous across the four different brain tumor types, with an average true positive Dice ranging between 80 and 90%, patient-wise recall between 88 and 98%, and patient-wise precision around 95%. In conjunction to Dice, the identified most relevant other metrics were the relative absolute volume difference, the variation of information, and the Hausdorff, Mahalanobis, and object average symmetric surface distances. With our Raidionics software, running on a desktop computer with CPU support, tumor segmentation can be performed in 16-54 s depending on the dimensions of the MRI volume. For the generation of a standardized clinical report, including the tumor segmentation and features computation, 5-15 min are necessary. All trained models have been made open-access together with the source code for both software solutions and validation metrics computation. In the future, a method to convert results from a set of metrics into a final single score would be highly desirable for easier ranking across trained models. In addition, an automatic classification of the brain tumor type would be necessary to replace manual user input. Finally, the inclusion of post-operative segmentation in both software solutions will be key for generating complete post-operative standardized clinical reports.

Hali tarjima qilinmagan

Identifikatorlar

Iqtiboslar va manbalar

2 ta iqtibos0 ta foydalanilgan manba