Machine Learning-Assisted SHG Morphometry Reveals Distinct Collagen Microarchitectures of Trabecular Bone and Fibrosis in Bone Marrow Biopsies
International Journal of Molecular Sciences · 2026
DOI: 10.3390/ijms27177685 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Molecular Sciences, 2026. Verfasst von Zakhar P Asaulenko und 16 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Computational Mathematics and Information Technologies, Kazan Federal University, Kremlyovskaya 35, 420008 Kazan, Russia. Hauptthemen laut MEDLINE: Machine Learning, Collagen, Cancellous Bone, Primary Myelofibrosis. Die Arbeit nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Government of Russia, Kazan Federal University.
Abstract (Originalsprache)
Collagen microarchitecture in bone marrow biopsies represents a largely underexplored source of candidate quantitative biomarkers for histopathological diagnostics and analysis of tissue remodeling. While second harmonic generation (SHG) microscopy has been increasingly applied to fibrosis assessment, the collagen organization of trabecular bone in bone marrow trephine biopsies remains poorly characterized. Here, we combined high-resolution SHG microscopy with shallow machine learning-assisted morphometry to compare collagen architecture in structured trabecular bone, unstructured trabecular bone, and fibrosis in bone marrow biopsies from patients with primary myelofibrosis. SHG image segmentation was performed using the LabKit plugin in Fiji. Several annotation strategies were evaluated to identify classifier configurations that preserved fibrillar structures. Quantitative morphometric analysis revealed marked differences in collagen organization between tissue types. Per-patient analysis consistently demonstrated thinner collagen fibers and reduced branching complexity in fibrosis than in structured trabecular bone. In contrast, unstructured trabecular bone showed extensive network branching accompanied by shorter skeleton branch length, consistent with remodeling-associated alterations of trabecular collagen architecture. Our results further demonstrate that annotation strategy substantially influences segmentation outcome and downstream morphometric measurements in SHG-based collagen analysis. Overall, this descriptive proof-of-concept study establishes a reproducible workflow for machine learning-assisted SHG morphometry that may prove useful for quantitative assessment of fibrosis, bone remodeling, and extracellular matrix organization in bone marrow pathology.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Institute of Computational Mathematics and Information Technologies, Kazan Federal University, Kremlyovskaya 35, 420008 Kazan, Russia.
- Pathological Anatomy Department, Federal Scientific and Clinical Center of Infectious Diseases of the Federal Medical and Biological Agency, 197022 St. Petersburg, Russia.
- Pathological Anatomy Department of Clinical Molecular Morphology, E.E. Eichwald Clinic, North-Western State Medical University Named After I.I. Mechnikov, 195067 St. Petersburg, Russia.
- Department of Medical Biology and Genetics, Kazan State Medical University, Butlerova 49, 420012 Kazan, Russia.
- Kazan Institute of Biochemistry and Biophysics, FRC Kazan Scientific Center, Russian Academy of Sciences, Lobachevskogo 2/31, 420111 Kazan, Russia.
- Institute of Physics, Kazan Federal University, Kremlyovskaya 16a, 420008 Kazan, Russia.
ORCID-Profile: Dmitry A Peshekhonov, Leniz F Nurullin, Daria S Vedischeva, Nikita S Gladyshev, Maxim E Fedchenko, Dmitry V Samigullin, Mikhail Paveliev
Förderung
- Government of Russia
- Kazan Federal University
Zitieren
APA
Asaulenko, Z. P., Egorchev, A. A., Peshekhonov, D. A., Nurullin, L. F., Melnikova, A. A., Rosin, A. A., Vedischeva, D. S., Shaidullin, S. M., Vafin, I. I., Buchaka, A. S., Gladyshev, N. S., Fedchenko, M. E., Chickrin, D. E., Krivolapov, Y. A., Samigullin, D. V., Aganov, A. V., & Paveliev, M. (2026). Machine Learning-Assisted SHG Morphometry Reveals Distinct Collagen Microarchitectures of Trabecular Bone and Fibrosis in Bone Marrow Biopsies. International Journal of Molecular Sciences. https://doi.org/10.3390/ijms27177685
Vancouver
Asaulenko ZP, Egorchev AA, Peshekhonov DA, Nurullin LF, Melnikova AA, Rosin AA, et al. Machine Learning-Assisted SHG Morphometry Reveals Distinct Collagen Microarchitectures of Trabecular Bone and Fibrosis in Bone Marrow Biopsies. International Journal of Molecular Sciences. 2026. doi:10.3390/ijms27177685
BibTeX
@article{Asaulenko2026,
author = {Asaulenko, Zakhar P and Egorchev, Anton A and Peshekhonov, Dmitry A and Nurullin, Leniz F and Melnikova, Anastasiia A and Rosin, Alexander A and Vedischeva, Daria S and Shaidullin, Samat M and Vafin, Ilsaf I and Buchaka, Anton S and Gladyshev, Nikita S and Fedchenko, Maxim E and Chickrin, Dmitry E and Krivolapov, Yuriy A and Samigullin, Dmitry V and Aganov, Albert V and Paveliev, Mikhail},
title = {Machine Learning-Assisted SHG Morphometry Reveals Distinct Collagen Microarchitectures of Trabecular Bone and Fibrosis in Bone Marrow Biopsies},
journal = {International Journal of Molecular Sciences},
year = {2026},
doi = {10.3390/ijms27177685}
}
EUVIMED