Automatic segmentation of demyelination lesions in multiple sclerosis
- Authors: Zakharov A.V.1, Shirolapov I.V.1, Khivintseva E.V.1, Sergeeva M.S.1, Romanchuk N.P.1, Dedyk D.A.1, Melnikova D.D.1, Andreev A.M.1, Mavletova A.I.1, Shchepetov A.O.1, Hemanth J.2
-
Affiliations:
- Samara State Medical University
- Karunya Institute of Technology and Sciences
- Issue: Vol 9, No 4 (2024)
- Pages: 284-290
- Section: Medical Informatics
- URL: https://journals.rcsi.science/2500-1388/article/view/277327
- DOI: https://doi.org/10.35693/SIM636947
- ID: 277327
Cite item
Abstract
Aim – to evaluate the effectiveness of the YOLOv8 algorithm for automatic segmentation of demyelination lesions in various locations in patients with multiple sclerosis.
Material and methods. The study included 120 patients with a clinically confirmed diagnosis of multiple sclerosis who underwent contrast-enhanced MRI. The MRI data from patients with different types of disease progression were analyzed. T1-weighted, T2-weighted, and FLAIR sequences were used for the analysis. The YOLOv8 algorithm was adapted for medical imaging and trained on manually annotated MRI scans. Model performance was evaluated using precision, recall, and F1-Score metrics.
Results. The YOLOv8 model demonstrated high segmentation performance with a precision of 0.79, recall of 00.73, and F1-Score of 0.65. The model effectively identified demyelination lesions in various locations typical for multiple sclerosis. However, there remains a need to improve recall to minimize the missed lesions. Testing on independent data confirmed the stability of the results of the model.
Conclusion. The YOLOv8 algorithm shows significant potential for automatic segmentation of demyelination lesions in multiple sclerosis patients. This method could be successfully implemented in clinical practice, enabling faster diagnosis and improved monitoring of disease progression. Further optimization of the model, through data augmentation techniques and hybrid architectures, may enhance both segmentation accuracy and recall.
Full Text
##article.viewOnOriginalSite##About the authors
Alexander V. Zakharov
Samara State Medical University
Author for correspondence.
Email: zakharov1977@mail.ru
ORCID iD: 0000-0003-1709-6195
PhD, Associate professor, Head of the Neurosciences Research Institute
Russian Federation, SamaraIgor V. Shirolapov
Samara State Medical University
Email: ishirolapov@mail.ru
ORCID iD: 0000-0002-7670-6566
PhD, Associate professor, Head of laboratory
Russian Federation, SamaraElena V. Khivintseva
Samara State Medical University
Email: e.v.hivinceva@samsmu.ru
ORCID iD: 0000-0002-1878-7951
PhD, Associate professor of the Department of Neurology and Neurosurgery
Russian Federation, SamaraMariya S. Sergeeva
Samara State Medical University
Email: m.s.sergeeva@samsmu.ru
ORCID iD: 0000-0002-0926-8551
PhD, Associate professor
Russian Federation, SamaraNatalya P. Romanchuk
Samara State Medical University
Email: n.p.romanchuk@samsmu.ru
ORCID iD: 0000-0003-3522-6803
PhD, MD, Associate professor, Head of the laboratory of neuromorphic systems, research institute of neurosciences
Russian Federation, SamaraDmitry A. Dedyk
Samara State Medical University
Email: d.a.dedyk@samsmu.ru
ORCID iD: 0009-0000-7902-6964
engineer of the advanced engineering school
Russian Federation, SamaraDarya D. Melnikova
Samara State Medical University
Email: Daha442242@gmail.com
ORCID iD: 0009-0000-6516-8216
engineer of the advanced engineering school
Russian Federation, SamaraArseniy M. Andreev
Samara State Medical University
Email: 2001qwert2001@gmail.com
ORCID iD: 0009-0002-0292-930X
engineer of the advanced engineering school
Russian Federation, SamaraAlexandra I. Mavletova
Samara State Medical University
Email: alexamavletova@gmail.com
ORCID iD: 0009-0007-4429-7554
engineer of the advanced engineering school
Russian Federation, SamaraAnton O. Shchepetov
Samara State Medical University
Email: antonshepetov1@gmail.com
ORCID iD: 0009-0009-5925-6426
engineer of the advanced engineering school
Russian Federation, SamaraJude Hemanth
Karunya Institute of Technology and Sciences
Email: judehemanth@karunya.edu
ORCID iD: 0000-0002-6091-1880
PhD, Professor
India, CoimbatoreReferences
- Jakimovski D, Bittner S, Zivadinov R, et al. Multiple sclerosis. The Lancet. 2024;403(10422):183-202. DOI: https://doi.org/10.1016/S0140-6736(23)01473-3
- Kaisey M, Solomon AJ. Multiple Sclerosis Diagnostic Delay and Misdiagnosis. Neurologic Clinics. 2024;42(1):1-13. DOI: https://doi.org/10.1016/j.ncl.2023.07.001
- Giovannoni G, Butzkueven H, Dhib-Jalbut S, et al. Brain health: time matters in multiple sclerosis. Multiple Sclerosis and Related Disorders. 2016;9:5-48. DOI: https://doi.org/10.1016/j.msard.2016.07.003
- Thompson AJ, Banwell BL, Barkhof F, et al. Diagnosis of multiple sclerosis: 2017 revisions of the McDonald criteria. The Lancet Neurology. 2018;17(2):162-173. DOI: https://doi.org/10.1016/S1474-4422(17)30470-2
- Wattjes MP, Ciccarelli O, Reich DS, et al. 2021 MAGNIMS–CMSC–NAIMS consensus recommendations on the use of MRI in patients with multiple sclerosis. The Lancet Neurology. 2021;20(8):653-670. DOI: https://doi.org/10.1016/S1474-4422(21)00095-8
- Egger C, Opfer R, Wang C, et al. MRI FLAIR lesion segmentation in multiple sclerosis: Does automated segmentation hold up with manual annotation? NeuroImage: Clinical. 2017;13:264-270. DOI: https://doi.org/10.1016/j.nicl.2016.11.020
- Diaz-Hurtado M, Martínez-Heras E, Solana E, et al. Recent advances in the longitudinal segmentation of multiple sclerosis lesions on magnetic resonance imaging: a review. Neuroradiology. 2022;64(11):2103-2117. DOI: https://doi.org/10.1007/s00234-022-03019-3
- Commowick O, Combès B, Cervenansky F, Dojat M. Editorial: Automatic methods for multiple sclerosis new lesions detection and segmentation. Front Neurosci. 2023;17:1176625. DOI: https://doi.org/10.3389/fnins.2023.1176625
- Fartaria MJ, Bonnier G, Roche A, et al. Automated detection of white matter and cortical lesions in early stages of multiple sclerosis. Magnetic Resonance Imaging. 2016;43(6):1445-1454. DOI: https://doi.org/10.1002/jmri.25095
- Todea AR, Melie‐Garcia L, Barakovic M, et al. A Multicenter Longitudinal MRI Study Assessing LeMan‐PV Software Accuracy in the Detection of White Matter Lesions in Multiple Sclerosis Patients. Magnetic Resonance Imaging. 2023;58(3):864-876. DOI: https://doi.org/10.1002/jmri.28618
- A. Abdullah B. Multi-Sectional Views Textural Based SVM for MS Lesion Segmentation in Multi-Channels MRIs. TOBEJ. 2012;6(1):56-72. DOI: https://doi.org/10.2174/1874230001206010056
- ElSebely R, Yousef AH, Salem AA, Abdullah B. Automatic Segmentation of Multiple Sclerosis Lesions in Brain MR Images Using Ensemble Machine Learning. In: 2021 International Mobile, Intelligent, and Ubiquitous Computing Conference (MIUCC). IEEE; 2021:28-33. DOI: https://doi.org/1 0.1109/MIUCC52538.2021.9447657
- HosseiniPanah S, Zamani A, Emadi F, HamtaeiPour F. Multiple Sclerosis Lesions Segmentation in Magnetic Resonance Imaging using Ensemble Support Vector Machine (ESVM). J Biomed Phys Eng. 2019;9(6):699-710. DOI: https://doi.org/10.31661/jbpe.v0i0.986
- Schmidt P, Gaser C, Arsic M, et al. An automated tool for detection of FLAIR-hyperintense white-matter lesions in Multiple Sclerosis. NeuroImage. 2012;59(4):3774-3783. DOI: https://doi.org/10.1016/j.neuroimage.2011.11.032
- Galimzianova A, Lesjak Ž, Rubin DL, et al. Locally adaptive magnetic resonance intensity models for unsupervised segmentation of multiple sclerosis lesions. J Med Imag. 2017;5(1):011007. DOI: https://doi.org/10.1117/1.JMI.5.1.011007
- Geremia E, Clatz O, Menze BH, et al. Spatial decision forests for MS lesion segmentation in multi-channel magnetic resonance images. NeuroImage. 2011;57(2):378-390. DOI: https://doi.org/10.1016/j.neuroimage.2011.03.080
- Dwyer MG, Bergsland N, Ramasamy DP, et al. Salient Central Lesion Volume: A Standardized Novel Fully Automated Proxy for Brain FLAIR Lesion Volume in Multiple Sclerosis. Journal of Neuroimaging. 2019;29(5):615-623. DOI: https://doi.org/10.1111/jon.12650
- Tran P, Thoprakarn U, Gourieux E, et al. Automatic segmentation of white matter hyperintensities: validation and comparison with state-of-the-art methods on both Multiple Sclerosis and elderly subjects. NeuroImage: Clinical. 2022;33:102940. DOI: https://doi.org/10.1016/j.nicl.2022.102940
- Cavedo E, Tran P, Thoprakarn U, et al. Validation of an automatic tool for the rapid measurement of brain atrophy and white matter hyperintensity: QyScore®. Eur Radiol. 2022;32(5):2949-2961. DOI: https://doi.org/10.1007/s00330-021-08385-9
- Brune S, Høgestøl EA, Cengija V, et al. LesionQuant for Assessment of MRI in Multiple Sclerosis – A Promising Supplement to the Visual Scan Inspection. Front Neurol. 2020;11:546744. DOI: https://doi.org/10.3389/fneur.2020.546744
- Valcarcel AM, Muschelli J, Pham DL, et al. TAPAS: A Thresholding Approach for Probability Map Automatic Segmentation in Multiple Sclerosis. NeuroImage: Clinical. 2020;27:102256. DOI: https://doi.org/10.1016/j.nicl.2020.102256
- Basaran BD, Matthews PM, Bai W. New lesion segmentation for multiple sclerosis brain images with imaging and lesion-aware augmentation. Front Neurosci. 2022;16:1007453. DOI: https://doi.org/10.3389/fnins.2022.1007453
- Isensee F, Jaeger PF, Kohl SAA, et al. nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat Methods. 2021;18(2):203-211. DOI: https://doi.org/10.1038/s41592-020-01008-z
- Ronneberger O, Fischer P, Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation. In: Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015. Vol. 9351. Lecture Notes in Computer Science. Springer International Publishing. 2015:234-241. DOI: https://doi.org/10.1007/978-3-319-24574-4_28
- Hitziger S, Ling WX, Fritz T, et al. Triplanar U-Net with lesion-wise voting for the segmentation of new lesions on longitudinal MRI studies. Front Neurosci. 2022;16:964250. DOI: https://doi.org/10.3389/fnins.2022.964250
- Andresen J, Uzunova H, Ehrhardt J, et al. Image registration and appearance adaptation in non-correspondent image regions for new MS lesions detection. Front Neurosci. 2022;16:981523. DOI: https://doi.org/10.3389/fnins.2022.981523
- Kamraoui RA, Mansencal B, Manjon JV, Coupé P. Longitudinal detection of new MS lesions using deep learning. Front Neuroimaging. 2022;1:948235. DOI: https://doi.org/10.3389/fnimg.2022.948235
- Salem M, Ryan MA, Oliver A, et al. Improving the detection of new lesions in multiple sclerosis with a cascaded 3D fully convolutional neural network approach. Front Neurosci. 2022;16:1007619. DOI: https://doi.org/10.3389/fnins.2022.1007619
- Kurtzke JF. Rating neurologic impairment in multiple sclerosis: An expanded disability status scale (EDSS). Neurology. 1983;33(11):1444-1444. DOI: https://doi.org/10.1212/WNL.33.11.1444
- Kurtzke JF. Clinical definition for multiple sclerosis treatment trials. Ann Neurol. 1994;36(1):73-79. DOI: https://doi.org/10.1002/ana.410360717
- Kurtzke JF. On the origin of EDSS. Multiple Sclerosis and Related Disorders. 2015;4(2):95-103. DOI: https://doi.org/10.1016/j.msard.2015.02.003
- Wang CY, Mark Liao HY, Wu YH, et al. CSPNet: A New Backbone that can Enhance Learning Capability of CNN. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). IEEE; 2020:1571-1580. DOI: https://doi.org/10.1109/CVPRW50498.2020.00203
- Bochkovskiy A, Wang CY, Liao HYM. YOLOv4: Optimal Speed and Accuracy of Object Detection. Published online 2020. DOI: https://doi.org/10.48550/ARXIV.2004.10934
Supplementary files
