Automatic and standardized reporting of perioperative MRIs in patients with central nervous system tumors

David Bouget^1*Mathilde Gajda Faanes¹Asgeir S Jakola^2,3Frederik Barkhof^4,5Hilko Ardon⁶Lorenzo Bello⁷Mitchel S. Berger⁸Shawn L. Hervey-Jumper⁸Julia Furtner^10,9Albert J.S Idema¹¹Barbara Kiesel⁹Georg Widhalm⁹Rishi Nandoe Tewarie¹²Emmanuel Mandonnet¹³Pierre A. Robe¹⁴Michiel Wagemakers¹⁵Vasileios Kavouridis^16,17Timothy R. Smith^16,17Philip C. De Witt Hamer^18,19Ole Solheim^20,21Ingerid Reinertsen^1,20

• ¹SINTEF Digital, Trondheim, Norway
• ²Goteborgs universitet, Gothenburg, Sweden
• ³Sahlgrenska universitetssjukhuset, Gothenburg, Sweden
• ⁴Vrije Universiteit Amsterdam, Amsterdam, Netherlands
• ⁵University College London, London, United Kingdom
• ⁶Elisabeth-TweeSteden Ziekenhuis, Tilburg, Netherlands
• ⁷IRCCS Humanitas Research Hospital, Rozzano, Italy
• ⁸University of California, San Francisco, United States
• ⁹Medizinische Universitat Wien, Vienna, Austria
• ¹⁰Donau-Universitat Krems Fakultat fur Gesundheit und Medizin, Krems an der Donau, Austria
• ¹¹Noordwest Ziekenhuisgroep Radiologie, Alkmaar, Netherlands
• ¹²Medisch Centrum Haaglanden, The Hague, Netherlands
• ¹³Hopital Lariboisiere Service de Neurochirurgie, Paris, France
• ¹⁴Universitair Medisch Centrum Utrecht Afdeling Neurologie en Neurochirurgie, Utrecht, Netherlands
• ¹⁵University Medical Ccenter Groningen Department of Neurosurgery, Groningen, Netherlands
• ¹⁶Brigham and Women's Hospital Department of Neurosurgery, Boston, United States
• ¹⁷Harvard Medical School, Boston, United States
• ¹⁸Amsterdam University Medical Centers Department of Neurosurgery, Amsterdam, Netherlands
• ¹⁹Amsterdam University Medical Centers Cancer Center Amsterdam, Amsterdam, Netherlands
• ²⁰Norges teknisk-naturvitenskapelige universitet, Trondheim, Norway
• ²¹St Olavs Hospital Universitetssykehuset i Trondheim avdeling Nevrokirurgi, Trondheim, Norway

Magnetic resonance (MR) imaging is essential for diagnosing central nervous system (CNS) tumors, guiding surgical planning, treatment decisions, and assessing postoperative outcomes and complications. While recent work has advanced automated tumor segmentation and report generation, most efforts have focused on preoperative data, with limited attention to postoperative imaging analysis. This study introduces a comprehensive pipeline for standardized postsurgical reporting in CNS tumors. Using the Attention U-Net architecture, segmentation models were trained, independently targeting the preoperative tumor core, non-enhancing tumor core, postoperative contrast-enhancing residual tumor, and resection cavity. In the process, the influence of varying MR sequence combinations was assessed. Additionally, MR sequence classification and tumor type identification for contrast-enhancing lesions were explored using the DenseNet architecture. The models were integrated seamlessly into an automated and standardized reporting pipeline, following the RANO 2.0 guidelines. Training was conducted on multicentric datasets comprising 2 000 to 7 000 patients, incorporating both private and public data, using a 5-fold cross-validation. Evaluation included patient-, voxel-, and object-wise metrics, with benchmarking against the latest BraTS challenge results. The segmentation models achieved average voxel-wise Dice scores of 87%, 66%, 70%, and 77% for the tumor core, non-enhancing tumor core, contrast-enhancing residual tumor, and resection cavity, respectively. Classification models reached 99.5% balanced accuracy in MR sequence classification and 80% in tumor type classification. The pipeline presented in this study enables robust, automated segmentation, MR sequence classification, and standardized report generation aligned with RANO 2.0 guidelines, enhancing postoperative evaluation and clinical decision-making. The proposed models and methods were integrated into Raidionics, open-source software platform for CNS tumor analysis, now including a dedicated module for postsurgical analysis.