Open Access
Subscription Access
A review on machine learning approaches on automated multiple sclerosis brain atrophy detection and volume quantification using MR images
Abstract
Multiple sclerosis (MS) is a progressive autoimmune illness that affects the brain and results in abnormalities in the central nervous system that impair mobility, sensation, and vision. Even though there are several diagnostic techniques for determining brain atrophy or tissue degeneration in multiple sclerosis (MS), magnetic resonance imaging (MRI) draws signifi- cant attention from the medical world. MRI modalities meet the necessity for doctors to have a basic understanding of brain anatomy and physiology in order to diagnose brain atrophy quickly. Nevertheless, brain atrophy diagnosis with MRI is a labor-intensive and human error-prone procedure. The use of deep learning and typical machine learning approaches in the study of computer-assisted diagnostic systems (CADS) for the identification and measurement of brain atrophy is reviewed in this paper. It also explores the challenges and areas requiring additional study in the field of automated brain atrophy assess- ment.
References
J. A. Matias-Guiu, A. Corte´s-Mart´ınez, P. Montero, V. Pytel, T. Moreno- Ramos, M. Jorquera, M. Yus, J. Arrazola, and J. Mat´ıas-Guiu, “Struc-
tural mri correlates of pasat performance in multiple sclerosis,” BMC neurology, vol. 18, no. 1, pp. 1–8, 2018.
J. Mottershead, K. Schmierer, M. Clemence, J. Thornton, F. Scaravilli,
G. Barker, P. Tofts, J. Newcombe, M. Cuzner, R. Ordidge et al., “High field mri correlates of myelin content and axonal density in multiple sclerosis: a post-mortem study of the spinal cord,” Journal of neurology, vol. 250, pp. 1293–1301, 2003.
S. P. Zelilidou, E. E. Tripoliti, K. I. Vlachos, S. Konitsiotis, and D. I. Fo- tiadis, “Clustering based segmentation of mr images for the delineation and monitoring of multiple sclerosis progression,” in 2021 IEEE 21st International Conference on Bioinformatics and Bioengineering (BIBE). IEEE, 2021, pp. 1–4.
——, “Segmentation and volume quantification of mr images for the detection and monitoring multiple sclerosis progression,” in 2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). IEEE, 2022, pp. 4745–4748.
N. M. El Garhy, M. M. El Toukhy, and M. M. Fatouh, “Mr volumetry in detection of brain atrophic changes in ms patients and its implication on disease prognosis: retrospective study,” Egyptian Journal of Radiology and Nuclear Medicine, vol. 53, no. 1, p. 78, 2022.
E. Ghione, N. Bergsland, M. Dwyer, J. Hagemeier, D. Jakimovski,
D. Ramasamy, D. Hojnacki, A. Lizarraga, C. Kolb, S. Eckert et al., “Dis- ability improvement is associated with less brain atrophy development in multiple sclerosis,” American Journal of Neuroradiology, vol. 41, no. 9,
pp. 1577–1583, 2020.
A. L. Kaipainen, J. Pitka¨nen, F. Haapalinna, O. Ja¨a¨skela¨inen, H. Jokinen,
S. Melkas, T. Erkinjuntti, R. Vanninen, A. M. Koivisto, J. Lo¨tjo¨nen et al., “A novel ct-based automated analysis method provides comparable results with mri in measuring brain atrophy and white matter lesions,” Neuroradiology, vol. 63, pp. 2035–2046, 2021.
K. Ha¨nninen, M. Viitala, T. Paavilainen, J. O. Karhu, J. Rinne,
J. Koikkalainen, J. Lo¨tjo¨nen, and M. Soilu-Ha¨nninen, “Thalamic atrophy predicts 5-year disability progression in multiple sclerosis,” Frontiers in Neurology, vol. 11, p. 606, 2020.
E. E. Carvajal-Camelo, J. Bernal, A. Oliver, X. Llado´, M. Trujillo, and
A. D. N. Initiative, “Evaluating the effect of intensity standardisation on longitudinal whole brain atrophy quantification in brain magnetic resonance imaging,” Applied Sciences, vol. 11, no. 4, p. 1773, 2021.
S. Noteboom, D. van Nederpelt, A. Bajrami, B. Moraal, M. Caan,
F. Barkhof, M. Calabrese, H. Vrenken, E. Strijbis, M. Steenwijk et al., “Feasibility of detecting atrophy relevant for disability and cognition in multiple sclerosis using 3d-flair,” Journal of neurology, pp. 1–10, 2023.
Refbacks
- There are currently no refbacks.