1. Glioblastoma Surgery Imaging—Reporting and Data System: Standardized Reporting of Tumor Volume, Location, and Resectability Based on Automated Segmentations
- Author
-
Lisa Millgård Sagberg, Marnix G. Witte, Domenique M J Müller, Frederik Barkhof, Marco Rossi, Wimar A. van den Brink, André Pedersen, Hilko Ardon, Pierre A. Robe, Ole Solheim, Ivar Kommers, Philip C. De Witt Hamer, Michiel Wagemakers, Georg Widhalm, Shawn L. Hervey-Jumper, Mitchel S. Berger, Aeilko H. Zwinderman, Roelant S Eijgelaar, Alfred Kloet, David Bouget, Albert J S Idema, Barbara Kiesel, Tommaso Sciortino, Even Hovig Fyllingen, Julia Furtner, Lorenzo Bello, Ingerid Reinertsen, Emmanuel Mandonnet, Marco Conti Nibali, Epidemiology and Data Science, APH - Methodology, Neurosurgery, Radiology and nuclear medicine, Amsterdam Neuroscience - Brain Imaging, Amsterdam Neuroscience - Neuroinfection & -inflammation, CCA - Imaging and biomarkers, CCA - Cancer Treatment and quality of life, and Amsterdam Neuroscience - Systems & Network Neuroscience
- Subjects
Cancer Research ,medicine.medical_specialty ,Artificial intelligence ,RESECTION ,computer-assisted image processing ,Concordance ,Article ,Neurosurgical Procedures ,030218 nuclear medicine & medical imaging ,CLINICAL TARGET VOLUME ,03 medical and health sciences ,0302 clinical medicine ,Neuroimaging ,Consistency (statistics) ,medicine ,Clinicial decision support ,magnetic resonance imaging ,DIAGNOSTIC-ACCURACY ,Equivalence (measure theory) ,RC254-282 ,Neurokirurgiske / nevrokirurgiske prosedyrer ,neuroimaging ,medicine.diagnostic_test ,business.industry ,glioblastoma ,EXTENT ,Neoplasms. Tumors. Oncology. Including cancer and carcinogens ,Magnetic resonance imaging ,CARE ,medicine.disease ,Radiology and diagnostic imaging: 763 [VDP] ,neurosurgical procedures ,Surgery ,Radiologi og bildediagnostikk: 763 [VDP] ,machine learning ,Oncology ,Kunstig intelligens ,030220 oncology & carcinogenesis ,AGREEMENT ,PATTERNS ,SURVIVAL ,Klinisk beslutningsstøtte ,GLIOMA ,Observational study ,business ,HUMAN CEREBRAL-CORTEX ,Volume (compression) ,Glioblastoma - Abstract
Simple Summary Neurosurgical decisions for patients with glioblastoma depend on tumor characteristics in the preoperative MR scan. Currently, this is based on subjective estimates or manual tumor delineation in the absence of a standard for reporting. We compared tumor features of 1596 patients from 13 institutions extracted from manual segmentations by a human rater and from automated segmentations generated by a machine learning model. The automated segmentations were in excellent agreement with manual segmentations and are practically equivalent regarding tumor features that are potentially relevant for neurosurgical purposes. Standard reports can be generated by open access software, enabling comparison between surgical cohorts, multicenter trials, and patient registries. Abstract Treatment decisions for patients with presumed glioblastoma are based on tumor characteristics available from a preoperative MR scan. Tumor characteristics, including volume, location, and resectability, are often estimated or manually delineated. This process is time consuming and subjective. Hence, comparison across cohorts, trials, or registries are subject to assessment bias. In this study, we propose a standardized Glioblastoma Surgery Imaging Reporting and Data System (GSI-RADS) based on an automated method of tumor segmentation that provides standard reports on tumor features that are potentially relevant for glioblastoma surgery. As clinical validation, we determine the agreement in extracted tumor features between the automated method and the current standard of manual segmentations from routine clinical MR scans before treatment. In an observational consecutive cohort of 1596 adult patients with a first time surgery of a glioblastoma from 13 institutions, we segmented gadolinium-enhanced tumor parts both by a human rater and by an automated algorithm. Tumor features were extracted from segmentations of both methods and compared to assess differences, concordance, and equivalence. The laterality, contralateral infiltration, and the laterality indices were in excellent agreement. The native and normalized tumor volumes had excellent agreement, consistency, and equivalence. Multifocality, but not the number of foci, had good agreement and equivalence. The location profiles of cortical and subcortical structures were in excellent agreement. The expected residual tumor volumes and resectability indices had excellent agreement, consistency, and equivalence. Tumor probability maps were in good agreement. In conclusion, automated segmentations are in excellent agreement with manual segmentations and practically equivalent regarding tumor features that are potentially relevant for neurosurgical purposes. Standard GSI-RADS reports can be generated by open access software.
- Published
- 2021