E.V. Bogdanov1, M.B. Al-Kharosh2, G.A. Karkashadze3, S.I. Shchukin4

1,3 Russian Scientific Center of Surgery named after academician B.V. Petrovsky (Moscow, Russia)
1,2,4 Bauman Moscow State Technical University (Moscow, Russia)
1 Evgeniy.bogdanov95@gmail.com, 2 Alharosh@bmstu.ru, 3 karga@mail.ru, 4 schookin2200@yahoo.com

The diagnosis and monitoring of neurodegenerative changes in children with mucopolysaccharidoses (MPS) represent one of the most complex challenges in modern pediatric neuroradiology. Despite the widespread use of magnetic resonance imaging (MRI), the interpretation of images often remains subjective and depends on the specialist’s level of expertise. Existing software tools, such as FreeSurfer and SPM, do not provide sufficient accuracy in the analysis of pediatric MRI data, particularly in rare hereditary disorders accompanied by specific MRI signal abnormalities. The absence of specialized tools for quantitative assessment of morphometric changes and disease progression prediction limits the physician’s ability to objectively evaluate therapy effectiveness and plan further patient management strategies.

Objective – to develop and validate a software-algorithmic complex (SAC) for brain MRI analysis in children with mucopolysaccharidosis, enabling automated filtering, segmentation, quantitative assessment of brain structures, and disease progression forecasting, with the goal of improving diagnostic accuracy and reproducibility, as well as creating a clinical decision support tool for practical use.

A software-algorithmic complex for brain MRI analysis in children with mucopolysaccharidosis has been developed and validated. The use of a combined wavelet transform and anisotropic diffusion method significantly improved image filtering quality while preserving clear structural boundaries. The diagnostic model based on logistic regression demonstrated high classification accuracy for MPS patients, achieving an AUC of 0.95. The prognostic module enabled disease dynamics modeling using linear and exponential models, showing less than 6% deviation from actual clinical data. The exponential model most accurately described the accelerated neurodegenerative changes typical of MPS type I. Validation was performed on data from 19 patients, including 15 with genetically confirmed MPS and 4 conditionally healthy children. The results showed a 10.1% increase in segmentation accuracy compared to FreeSurfer. The complex demonstrated high reproducibility and diagnostic reliability. The obtained data confirm its effectiveness as a tool for quantitative diagnosis and disease dynamics monitoring in clinical practice.

The developed complex provides physicians with objective quantitative indicators for diagnosing and monitoring neurodegenerative changes in MPS, improving analysis reproducibility and reducing subjectivity. The software can be integrated into clinical workstations for automated MRI processing, applied in the evaluation of enzyme replacement therapy effectiveness, and used in clinical trials of new treatment methods and drug delivery approaches across the blood-brain barrier. Moreover, the proposed approach is universal and can be adapted for other neurodegenerative and metabolic diseases in children.

1. Muenzer J. Overview of the mucopolysaccharidoses. Rheumatology. 2011. V. 50. № 5. P. v4–v12.
2. Zaharova E.Yu., Voskoboeva E. Yu. Nejrodegenerativnye aspekty mukopolisaharidozov. Medicinskaya genetika. 2018. T. 17. № 2. S. 3–11 (In Russian).
3. Baranov A.A., Namazova-Baranova L.S. Klinicheskie rekomendacii po diagnostike i lecheniyu mukopolisaharidoza I tipa. M.: Pediatr". 2019. 48 s. (In Russian).
4. Fischl B. FreeSurfer. NeuroImage. 2012. V. 62. № 2. P. 774–781 (In Russian).
5. Morozov S.P., Vladzimirskij A.V., Gombolevskij V.A. Iskusstvennyj intellekt v luchevoj diagnostike: nastoyashchee i budushchee. Vestnik rentgenologii i radiologii. 2020. T. 101. № 1. S. 5–12 (In Russian).
6. Daubechies I. Orthonormal bases of compactly supported wavelets. Communications on Pure and Applied Mathematics. 1988. V. 41. № 7. P. 909–996.
7. Perona P., Malik J. Scale-space and edge detection using anisotropic diffusion. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1990. V. 12. № 7. P. 629–639.
8. Donoho D.L. De-noising by soft-thresholding. IEEE Transactions on Information Theory. 1995. V. 41. № 3. P. 613–627.
9. Gabrielli O., ClarkeL. A., Bruni M.T.D. Correlation between cerebral MRI findings, cognitive development and behaviour in patients with mucopolysaccharidosis type II. Orphanet Journal of Rare Diseases. 2010. V. 5. № 23.
10. Iozzo R.V., San Antonio J.D. The biology of perlecan: the king of syndecans. Journal of Biological Chemistry. 2012. V. 287. № 13. P. 10038–10045.
11. Manara R., Di Rocco F.S., Tomanin G.S.I. Brain imaging in mucopolysaccharidoses: a systematic review. Journal of Inherited Metabolic Disease. 2016. V. 39. № 3. P. 343–357.
12. Vedolin L., Schwartz M.G.M.S., Komlos L.S.C. MRI findings of the central nervous system in mucopolysaccharidoses: a systematic review. Journal of Neuroimaging. 2013. V. 23. № 4. P. 509–518.
13. Cabezas M., Oliver A., Lladó X. A review of atlas-based segmentation for magnetic resonance brain images. Computer Methods and Programs in Biomedicine. 2011. V. 104. № 3. P. e158–e177.
14. Gonsales R., Vuds R. Cifrovaya obrabotka izobrazhenij. M.: Tekhnosfera. 2012. 1104 s. (In Russian).
15. Ronneberger O., Fischer P., Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation. Medical Image Computing and Computer-Assisted Intervention MICCAI 2015. Springer. 2015. P. 234–241.
16. Hamano K. Pathophysiology of brain abnormalities in the mucopolysaccharidoses. Brain & Development. 2008. V. 30. № 10. P. 659–666.
17. Litjens G., Kooi T., Bejnordi B.E. A survey on deep learning in medical image analysis. Medical Image Analysis. 2017. V. 42. P. 60–88.
18. Giedd J.N., Blumenthal J., Jeffries N.O. Brain development during childhood and adolescence: a longitudinal MRI study. Nature Neuroscience. 1999. V. 2. № 10. P. 861–863.
19. Karkashadze G.A., Firumyanc A.I., SHilko N.S., Sergienko N.S., Nesterova YU.V., YAcyk L.M., Rudenko E.N., Polle M.I., Salimgareeva T.A., Gogberashvili T.YU., Sergeeva N.S., Konstantinidi T.A., Sadilloeva S.H., Kurakina M.A., D'yachenko V.V., Povalyaeva I.A., Bogdanov E.V., Rykunova A.I., Vishneva E.A., Kajtukova E.V., Efendieva K.E., Namazova-Baranova L.S. Strukturnaya morfometriya golovnogo mozga u detej s sindromom deficita vnimaniya i giperaktivnosti i komorbidnymi legkimi kognitivnymi narusheniyami. Voprosy sovremennoj pediatrii. 2024. № 23(6). S. 466–482 (In Russian).
20. Levchuk A.G. Avtomaticheskij i poluavtomaticheskij metod segmentacii postinfarktnogo kardioskleroza po MR-tomografii. Biomedicinskaya radioelektronika. 2024. T. 27. № 3. S. 13–27 (In Russian).