1
|
Ntiri EE, Holmes MF, Forooshani PM, Ramirez J, Gao F, Ozzoude M, Adamo S, Scott CJM, Dowlatshahi D, Lawrence-Dewar JM, Kwan D, Lang AE, Symons S, Bartha R, Strother S, Tardif JC, Masellis M, Swartz RH, Moody A, Black SE, Goubran M. Improved Segmentation of the Intracranial and Ventricular Volumes in Populations with Cerebrovascular Lesions and Atrophy Using 3D CNNs. Neuroinformatics 2021; 19:597-618. [PMID: 33527307 DOI: 10.1007/s12021-021-09510-1] [Citation(s) in RCA: 10] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 01/01/2021] [Indexed: 11/30/2022]
Abstract
Successful segmentation of the total intracranial vault (ICV) and ventricles is of critical importance when studying neurodegeneration through neuroimaging. We present iCVMapper and VentMapper, robust algorithms that use a convolutional neural network (CNN) to segment the ICV and ventricles from both single and multi-contrast MRI data. Our models were trained on a large dataset from two multi-site studies (N = 528 subjects for ICV, N = 501 for ventricular segmentation) consisting of older adults with varying degrees of cerebrovascular lesions and atrophy, which pose significant challenges for most segmentation approaches. The models were tested on 238 participants, including subjects with vascular cognitive impairment and high white matter hyperintensity burden. Two of the three test sets came from studies not used in the training dataset. We assessed our algorithms relative to four state-of-the-art ICV extraction methods (MONSTR, BET, Deep Extraction, FreeSurfer, DeepMedic), as well as two ventricular segmentation tools (FreeSurfer, DeepMedic). Our multi-contrast models outperformed other methods across many of the evaluation metrics, with average Dice coefficients of 0.98 and 0.96 for ICV and ventricular segmentation respectively. Both models were also the most time efficient, segmenting the structures in orders of magnitude faster than some of the other available methods. Our networks showed an increased accuracy with the use of a conditional random field (CRF) as a post-processing step. We further validated both segmentation models, highlighting their robustness to images with lower resolution and signal-to-noise ratio, compared to tested techniques. The pipeline and models are available at: https://icvmapp3r.readthedocs.io and https://ventmapp3r.readthedocs.io to enable further investigation of the roles of ICV and ventricles in relation to normal aging and neurodegeneration in large multi-site studies.
Collapse
Affiliation(s)
- Emmanuel E Ntiri
- Hurvitz Brain Sciences Program, Sunnybrook Research Institute, University of Toronto, Toronto, Canada
| | - Melissa F Holmes
- Hurvitz Brain Sciences Program, Sunnybrook Research Institute, University of Toronto, Toronto, Canada
| | - Parisa M Forooshani
- Hurvitz Brain Sciences Program, Sunnybrook Research Institute, University of Toronto, Toronto, Canada
| | - Joel Ramirez
- Hurvitz Brain Sciences Program, Sunnybrook Research Institute, University of Toronto, Toronto, Canada
| | - Fuqiang Gao
- Hurvitz Brain Sciences Program, Sunnybrook Research Institute, University of Toronto, Toronto, Canada
| | - Miracle Ozzoude
- Hurvitz Brain Sciences Program, Sunnybrook Research Institute, University of Toronto, Toronto, Canada
| | - Sabrina Adamo
- Hurvitz Brain Sciences Program, Sunnybrook Research Institute, University of Toronto, Toronto, Canada
| | - Christopher J M Scott
- Hurvitz Brain Sciences Program, Sunnybrook Research Institute, University of Toronto, Toronto, Canada
| | - Dar Dowlatshahi
- Department of Medicine, The Ottawa Hospital, Faculty of Medicine, University of Ottawa, Ottawa, Canada
| | | | - Donna Kwan
- Department of Psychology, Faculty of Health, York University, Toronto, Canada
| | - Anthony E Lang
- The Edmond J. Safra Program in Parkinson's Disease and Morton and Gloria Shulman Movement Disorders Clinic, Toronto Western Hospital, Toronto, Canada.,Department of Medicine (Neurology division), University of Toronto, Toronto, Canada
| | - Sean Symons
- Department of Medical Imaging, University of Toronto, Toronto, Canada
| | - Robert Bartha
- Department of Medical Biophysics, Schulich School of Medicine and Dentistry, Robarts Research Institute, University of Western Ontario, London, Canada
| | - Stephen Strother
- Department of Medical Biophysics, University of Toronto, Toronto, Canada
| | | | - Mario Masellis
- Hurvitz Brain Sciences Program, Sunnybrook Research Institute, University of Toronto, Toronto, Canada.,Department of Medicine (Neurology division), University of Toronto, Toronto, Canada.,Canadian Partnership for Stroke Recovery, Heart and Stroke Foundation, Toronto, Canada
| | - Richard H Swartz
- Hurvitz Brain Sciences Program, Sunnybrook Research Institute, University of Toronto, Toronto, Canada.,Department of Medicine (Neurology division), University of Toronto, Toronto, Canada.,Canadian Partnership for Stroke Recovery, Heart and Stroke Foundation, Toronto, Canada
| | - Alan Moody
- Hurvitz Brain Sciences Program, Sunnybrook Research Institute, University of Toronto, Toronto, Canada.,Department of Medical Imaging, University of Toronto, Toronto, Canada
| | - Sandra E Black
- Hurvitz Brain Sciences Program, Sunnybrook Research Institute, University of Toronto, Toronto, Canada.,Department of Medicine (Neurology division), University of Toronto, Toronto, Canada.,Canadian Partnership for Stroke Recovery, Heart and Stroke Foundation, Toronto, Canada
| | - Maged Goubran
- Hurvitz Brain Sciences Program, Sunnybrook Research Institute, University of Toronto, Toronto, Canada. .,Department of Medical Biophysics, University of Toronto, Toronto, Canada. .,Canadian Partnership for Stroke Recovery, Heart and Stroke Foundation, Toronto, Canada.
| |
Collapse
|