Advances in MRI optic nerve segmentation.
Authors
Affiliations (5)
Affiliations (5)
- e-Health Center, Universitat Oberta de Catalunya, Barcelona, Spain. Electronic address: [email protected].
- Queen Square MS Centre, Department of Neuroinflammation, UCL Institute of Neurology, Faculty of Brain Sciences, University College London, London, United Kingdom.
- Queen Square MS Centre, Department of Neuroinflammation, UCL Institute of Neurology, Faculty of Brain Sciences, University College London, London, United Kingdom; National Institute for Health Research (NIHR) University College London Hospitals (UCLH) Biomedical Research Centre, United Kingdom.
- Neuroimmunology and Multiple Sclerosis Unit, Hospital Clínic de Barcelona, Institut d'Investigacions Biomèdiques August Pi i Sunyer (IDIBAPS) and Universitat de Barcelona, Barcelona, Spain.
- e-Health Center, Universitat Oberta de Catalunya, Barcelona, Spain; Queen Square MS Centre, Department of Neuroinflammation, UCL Institute of Neurology, Faculty of Brain Sciences, University College London, London, United Kingdom; Centre for Medical Image Computing, Department of Medical Physics and Biomedical Engineering, University College London, London, United Kingdom.
Abstract
Understanding optic nerve structure and monitoring changes within it can provide insights into neurodegenerative diseases like multiple sclerosis, in which optic nerves are often damaged by inflammatory episodes of optic neuritis. Over the past decades, interest in the optic nerve has increased, particularly with advances in magnetic resonance technology and the advent of deep learning solutions. These advances have significantly improved the visualisation and analysis of optic nerves, making it possible to detect subtle changes that aid the early diagnosis and treatment of optic nerve-related diseases, and for planning radiotherapy interventions. Effective segmentation techniques, therefore, are crucial for enhancing the accuracy of predictive models, planning interventions and treatment strategies. This comprehensive review, which includes 27 peer-reviewed articles published between 2007 and 2024, examines and highlights the evolution of optic nerve magnetic resonance imaging segmentation over the past decade, tracing the development from intensity-based methods to the latest deep learning algorithms, including multi-atlas solutions using single or multiple image modalities.