1
|
Tran P, Thoprakarn U, Gourieux E, Dos Santos CL, Cavedo E, Guizard N, Cotton F, Krolak-Salmon P, Delmaire C, Heidelberg D, Pyatigorskaya N, Ströer S, Dormont D, Martini JB, Chupin M. Automatic segmentation of white matter hyperintensities: validation and comparison with state-of-the-art methods on both Multiple Sclerosis and elderly subjects. Neuroimage Clin 2022; 33:102940. [PMID: 35051744 PMCID: PMC8896108 DOI: 10.1016/j.nicl.2022.102940] [Citation(s) in RCA: 11] [Impact Index Per Article: 5.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/28/2021] [Revised: 12/15/2021] [Accepted: 01/06/2022] [Indexed: 11/27/2022]
Abstract
Automatic segmentation of MS lesions and age-related WMH from 3D T1 and T2-FLAIR. Comparison to consensus show improved performance of WHASA-3D compared to WHASA. WHASA-3D outperforms available state-of-the-art methods with their default settings. WHASA-3D could be a useful tool for clinical practice and clinical trials.
Different types of white matter hyperintensities (WMH) can be observed through MRI in the brain and spinal cord, especially Multiple Sclerosis (MS) lesions for patients suffering from MS and age-related WMH for subjects with cognitive disorders and/or elderly people. To better diagnose and monitor the disease progression, the quantitative evaluation of WMH load has proven to be useful for clinical routine and trials. Since manual delineation for WMH segmentation is highly time-consuming and suffers from intra and inter observer variability, several methods have been proposed to automatically segment either MS lesions or age-related WMH, but none is validated on both WMH types. Here, we aim at proposing the White matter Hyperintensities Automatic Segmentation Algorithm adapted to 3D T2-FLAIR datasets (WHASA-3D), a fast and robust automatic segmentation tool designed to be implemented in clinical practice for the detection of both MS lesions and age-related WMH in the brain, using both 3D T1-weighted and T2-FLAIR images. In order to increase its robustness for MS lesions, WHASA-3D expands the original WHASA method, which relies on the coupling of non-linear diffusion framework and watershed parcellation, where regions considered as WMH are selected based on intensity and location characteristics, and finally refined with geodesic dilation. The previous validation was performed on 2D T2-FLAIR and subjects with cognitive disorders and elderly subjects. 60 subjects from a heterogeneous database of dementia patients, multiple sclerosis patients and elderly subjects with multiple MRI scanners and a wide range of lesion loads were used to evaluate WHASA and WHASA-3D through volume and spatial agreement in comparison with consensus reference segmentations. In addition, a direct comparison on the MS database with six available supervised and unsupervised state-of-the-art WMH segmentation methods (LST-LGA and LPA, Lesion-TOADS, lesionBrain, BIANCA and nicMSlesions) with default and optimised settings (when feasible) was conducted. WHASA-3D confirmed an improved performance with respect to WHASA, achieving a better spatial overlap (Dice) (0.67 vs 0.63), a reduced absolute volume error (AVE) (3.11 vs 6.2 mL) and an increased volume agreement (intraclass correlation coefficient, ICC) (0.96 vs 0.78). Compared to available state-of-the-art algorithms on the MS database, WHASA-3D outperformed both unsupervised and supervised methods when used with their default settings, showing the highest volume agreement (ICC = 0.95) as well as the highest average Dice (0.58). Optimising and/or retraining LST-LGA, BIANCA and nicMSlesions, using a subset of the MS database as training set, resulted in improved performances on the remaining testing set (average Dice: LST-LGA default/optimized = 0.41/0.51, BIANCA default/optimized = 0.22/0.39, nicMSlesions default/optimized = 0.17/0.63, WHASA-3D = 0.58). Evaluation and comparison results suggest that WHASA-3D is a reliable and easy-to-use method for the automated segmentation of white matter hyperintensities, for both MS lesions and age-related WMH. Further validation on larger datasets would be useful to confirm these first findings.
Collapse
Affiliation(s)
- Philippe Tran
- Qynapse, Paris, France; Equipe-projet ARAMIS, ICM, CNRS UMR 7225, Inserm U1117, Sorbonne Université UMR_S 1127, Centre Inria de Paris, Groupe Hospitalier Pitié-Salpêtrière Charles Foix, Faculté de Médecine Sorbonne Université, Paris, France.
| | | | - Emmanuelle Gourieux
- CATI, ICM, CNRS UMR 7225, Inserm U1117, Sorbonne Université UMR_S 1127, Paris, France; NeuroSpin, CEA, Saclay, France
| | | | | | | | - François Cotton
- Service de Radiologie, Centre Hospitalier Lyon-Sud, Hospices Civils de Lyon, Pierre-Bénite, France; Univ Lyon, INSA-Lyon, Université Claude Bernard Lyon 1, UJM-Saint Etienne, CNRS, Inserm, CREATIS UMR 5220, U1206, F-69495, Pierre-Bénite, France
| | - Pierre Krolak-Salmon
- Univ Lyon, INSA-Lyon, Université Claude Bernard Lyon 1, UJM-Saint Etienne, CNRS, Inserm, CREATIS UMR 5220, U1206, F-69495, Pierre-Bénite, France; Clinical and Research Memory Centre of Lyon, Hospices Civils de Lyon, Lyon, France; INSERM, U1028, UMR CNRS 5292, Lyon Neuroscience Research Center, Lyon, France
| | | | - Damien Heidelberg
- Service de Radiologie, Centre Hospitalier Lyon-Sud, Hospices Civils de Lyon, Pierre-Bénite, France
| | - Nadya Pyatigorskaya
- Department of Neuroradiology, Groupe Hospitalier Pitié-Salpêtrière, AP-HP, Sorbonne Université UMR_S 1127, Paris, France
| | - Sébastian Ströer
- Department of Neuroradiology, Groupe Hospitalier Pitié-Salpêtrière, AP-HP, Sorbonne Université UMR_S 1127, Paris, France
| | - Didier Dormont
- Equipe-projet ARAMIS, ICM, CNRS UMR 7225, Inserm U1117, Sorbonne Université UMR_S 1127, Centre Inria de Paris, Groupe Hospitalier Pitié-Salpêtrière Charles Foix, Faculté de Médecine Sorbonne Université, Paris, France; Department of Neuroradiology, Groupe Hospitalier Pitié-Salpêtrière, AP-HP, Sorbonne Université UMR_S 1127, Paris, France
| | | | - Marie Chupin
- CATI, ICM, CNRS UMR 7225, Inserm U1117, Sorbonne Université UMR_S 1127, Paris, France
| | | |
Collapse
|
2
|
Homos MD. Can white matter lesion burden predict involvement of normal appearing thalami in multiple sclerosis? Study using 3D FLAIR and DTI. THE EGYPTIAN JOURNAL OF RADIOLOGY AND NUCLEAR MEDICINE 2021. [DOI: 10.1186/s43055-021-00406-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/10/2022] Open
Abstract
Abstract
Background
Multiple sclerosis is a chronic demyelinating disease that affects the white and grey matter. The thalamus is responsible for many neurological functions, and it is liable to damage in multiple sclerosis in the absence of MRI-detectable thalamic lesions. Standardized imaging protocol for multiple sclerosis includes 3D FLAIR sequence that is highly sensitive in detecting white matter lesions. Owing to the thalamic functional importance, we aim in this study to show to what extent the standardized imaging protocol (3D FLAIR) can predict microscopic damage of normal appearing thalami, depending on DTI metrics (ADC and FA) as indicators of the microscopic damage.
Results
We examined 42 multiple sclerosis patients, 16 males and 26 females, with mean age 29 ± 6 years using 3D FLAIR sequence to delineate the white matter lesions and calculate their total areas and using DTI to calculate the average ADC and FA values of the thalami. Spearman’s correlation coefficient (r) was used to correlate between the white matter lesion burden and the thalamic diffusivity (ADC and FA).
Moderate correlation was found between average ADC values of the thalami and the total white matter lesion areas (r = 0.5, p = 0.03).
Very weak correlation was found between average FA values of the thalami and the total white matter lesion areas (r = − 0.1, p = 0.6)
Conclusion
White matter lesion burden detected using the highly sensitive 3D FLAIR sequence does not always correlate with the microstructural damage in normal appearing thalami. DTI needs to be added to the examination protocol if damage of normal appearing thalami is of concern.
Collapse
|