Meeting Banner
Abstract #3512

Multi-class Deep Learning Glioma Segmentation in Hospital Data with Missing Sequences

Jiaming Wu1, Hugh G. Pemberton1,2, Ivar Kommers3, Domenique M.J. Müller3, Sjoerd B. Vos1,2, Ferran Prados1,2, Yipeng Hu1, Pierre A. Robe4, Hilko Ardon5, Lorenzo Bello6, Marco Rossi6, Tommaso Sciortino6, Marco Conti Nibali 6, Mitchel S. Berger7, Shawn L. Hervey-Jumper7, Wim Bouwknegt8, Wimar A. Van den Brink9, Julia Furtner10, Seunggu J. Han11, Albert J. S. Idema12, Barbara Kiesel13, Georg Widhalm13, Alfred Kloet14, Michiel Wagemakers15, Aeilko H. Zwinderman16, Sandro M. Krieg17,18, Emmanuel Mandonnet19, Philip de Witt Hamer3, Roelant S. Eijgelaar3, and Frederik Barkhof1,20
1Centre for Medical Image Computing (CMIC), University College London, London, United Kingdom, 2Neuroradiological Academic Unit, UCL Queen Square Institute of Neurology, University College London, London, United Kingdom, 3Neurosurgical Center Amsterdam, Amsterdam UMC, Vrije Universiteit, Amsterdam, Netherlands, 4Department of Neurology & Neurosurgery, University Medical Center Utrecht, Utrecht, Netherlands, 5Department of Neurosurgery, St. Elisabeth Hospital, Tilburg, Netherlands, 6Neurosurgical Oncology Unit, Departments of Oncology and Hemato-Oncology, Università degli Studi di Milano, Humanitas Research Hospital, IRCCS, Milan, Italy, 7Department of Neurological Surgery, University of California, San Francisco, San Francisco, CA, United States, 8Department of Neurosurgery, Medical Center Slotervaart, Amsterdam, Netherlands, 9Department of Neurosurgery, Isala Hospital, Zwolle, Netherlands, 10Department of Biomedical Imaging and Image-Guided Therapy, Medical University Vienna, Vienna, Austria, 11Department of Neurological Surgery, Oregon Health and Science University, Portland, OR, United States, 12Department of Neurosurgery, Northwest Clinics, Alkmaar, Netherlands, 13Department of Neurosurgery, Medical University Vienna, Vienna, Austria, 14Department of Neurosurgery, Medical Center Haaglanden, The Hague, Netherlands, 15Department of Neurosurgery, University of Groningen, University Medical Center Groningen, Groningen, Netherlands, 16Department of Clinical Epidemiology and Biostatistics, Academic Medical Center, Amsterdam, Netherlands, 17TUM-Neuroimaging Center, Klinikum rechts der Isar, Technische Universität München, Munich, Germany, 18Department of Neurosurgery, Klinikum rechts der Isar, Technische Universität München, Munich, Germany, 19Department of Neurosurgery, Lariboisière Hospital, APHP, Paris, France, 20Radiology & Nuclear Medicine, VU University Medical Center, Amsterdam, Netherlands

Accurate segmentation and morphological assessment of glioma can guide treatment and support follow-up. The Brain Tumour Segmentation (BraTS) challenge has been instrumental in promoting research and comparing various automated segmentation algorithms. However, models in the challenge are trained and measured on a strictly curated and high-quality dataset, which is not representative of clinically acquired MRI data. Therefore, we have tested the generalisability of three network architectures from two of the top performing BraTS challenge models. We show the utility of these models in the presence of missing sequences and different scanners in multi-centre hospital data of varying quality.

How to access this content:

For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.

After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.

After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.

Click here for more information on becoming a member.

Abstract

Keywords