Machine learning augmented near-infrared spectroscopy: In vivo follow-up of cartilage defects.
Abstract: To assess the potential of near-infrared spectroscopy (NIRS) for in vivo arthroscopic monitoring of cartilage defects. Sharp and blunt cartilage grooves were induced in the radiocarpal and intercarpal joints of Shetland ponies and monitored at baseline (0 weeks) and at three follow-up timepoints (11, 23, and 39 weeks) by measuring near-infrared spectra in vivo at and around the grooves. The animals were sacrificed after 39 weeks and the joints were harvested. Spectra were reacquired ex vivo to ensure reliability of in vivo measurements and for reference analyses. Additionally, cartilage thickness and instantaneous modulus were determined via computed tomography and mechanical testing, respectively. The relationship between the ex vivo spectra and cartilage reference properties was determined using convolutional neural network. In an independent test set, the trained networks yielded significant correlations for cartilage thickness (ρ = 0.473) and instantaneous modulus (ρ = 0.498). These networks were used to predict the reference properties at baseline and at follow-up time points. In the radiocarpal joint, cartilage thickness increased significantly with both groove types after baseline and remained swollen. Additionally, at 39 weeks, a significant difference was observed in cartilage thickness between controls and sharp grooves. For the instantaneous modulus, a significant decrease was observed with both groove types in the radiocarpal joint from baseline to 23 and 39 weeks. NIRS combined with machine learning enabled determination of cartilage properties in vivo, thereby providing longitudinal evaluation of post-intervention injury development. Additionally, radiocarpal joints were found more vulnerable to cartilage degeneration after damage than intercarpal joints.
Copyright © 2020 The Author(s). Published by Elsevier Ltd.. All rights reserved.
Publication Date: 2020-12-30 PubMed ID: 33359249DOI: 10.1016/j.joca.2020.12.007Google Scholar: Lookup
The Equine Research Bank provides access to a large database of publicly available scientific literature. Inclusion in the Research Bank does not imply endorsement of study methods or findings by Mad Barn.
- Journal Article
- Research Support
- Non-U.S. Gov't
Summary
This research summary has been generated with artificial intelligence and may contain errors and omissions. Refer to the original study to confirm details provided. Submit correction.
The research study explores the use of near-infrared spectroscopy (NIRS) along with machine learning in monitoring the changes in cartilage defects in Shetland ponies over time. Results indicated that this method could effectively detail the properties and deterioration of cartilage in live subjects, widening the possibility of evaluating injury progression post-treatment procedure.
Experiment Procedure
- The researchers induced cartilage grooves, both sharp and blunt, in the radiocarpal and intercarpal joints of Shetland ponies. This setup replicated the potential scenarios where such damages could occur naturally.
- They monitored these changes at four different stages, starting from the beginning (0 weeks), and at three additional timepoints (11, 23, and 39 weeks). During these periods, near-infrared spectra were acquired from the area surrounding the grooves.
- After the 39 weeks time period, the ponies were sacrificed and their joints harvested in order to acquire the spectra ex vivo, providing a reference point for the reliability of measurements taken while the animals were still alive.
- Additionally, details such as cartilage thickness and instantaneous modulus (a measure of cartilage’s resistance to deformation or strain) were determined using computed tomography and mechanical testing respectively.
Usage of Machine Learning
- Once the ex vivo spectra and cartilage properties had been collected, convolutional neural networks were used to identify the relationship between these two variables.
- This resulted in accurate predictions for factors like cartilage thickness and the instantaneous modulus, when the trained networks were tested on an independent set.
Findings
- The properties determined at different points during the experiment indicated that cartilage thickness increased significantly from baseline and remained swollen for both types of grooves introduced in the radiocarpal joint.
- At the end of the experiment (39 weeks), there was a significant difference noticed in the cartilage thickness between the controls and sharp grooves.
- On the other hand, the instantaneous modulus or elasticity of the cartilage decreased significantly from the baseline to the 23 and 39-week marks for both kinds of grooves.
- The combination of NIRS and machine learning proved successful in determining cartilage properties in a live setting, thereby allowing a thorough evaluation of how an injury progresses after a potential intervention.
- It was also noticed that the radiocarpal joints were more susceptible to cartilage degeneration after damage compared to the intercarpal joint.
Cite This Article
APA
Sarin JK, Te Moller NCR, Mohammadi A, Prakash M, Torniainen J, Brommer H, Nippolainen E, Shaikh R, Mäkelä JTA, Korhonen RK, van Weeren PR, Afara IO, Töyräs J.
(2020).
Machine learning augmented near-infrared spectroscopy: In vivo follow-up of cartilage defects.
Osteoarthritis Cartilage, 29(3), 423-432.
https://doi.org/10.1016/j.joca.2020.12.007 Publication
Researcher Affiliations
- Department of Applied Physics, University of Eastern Finland, Kuopio, Finland; Diagnostic Imaging Center, Kuopio University Hospital, Kuopio, Finland. Electronic address: jaakko.sarin@uef.fi.
- Department of Clinical Sciences, Faculty of Veterinary Medicine, Utrecht University, Utrecht, the Netherlands. Electronic address: n.c.r.temoller@uu.nl.
- Department of Applied Physics, University of Eastern Finland, Kuopio, Finland. Electronic address: ali.mohammadi@uef.fi.
- A.I. Virtanen Institute for Molecular Sciences, University of Eastern Finland, Kuopio, Finland. Electronic address: mithilesh.prakash@uef.fi.
- Department of Applied Physics, University of Eastern Finland, Kuopio, Finland; Diagnostic Imaging Center, Kuopio University Hospital, Kuopio, Finland. Electronic address: jari.torniainen@uef.fi.
- Department of Clinical Sciences, Faculty of Veterinary Medicine, Utrecht University, Utrecht, the Netherlands. Electronic address: h.brommer@uu.nl.
- Department of Applied Physics, University of Eastern Finland, Kuopio, Finland. Electronic address: ervin.nippolainen@uef.fi.
- Department of Applied Physics, University of Eastern Finland, Kuopio, Finland. Electronic address: rubina.shaikh@uef.fi.
- Department of Applied Physics, University of Eastern Finland, Kuopio, Finland. Electronic address: janne.makela@uef.fi.
- Department of Applied Physics, University of Eastern Finland, Kuopio, Finland. Electronic address: rami.korhonen@uef.fi.
- Department of Clinical Sciences, Faculty of Veterinary Medicine, Utrecht University, Utrecht, the Netherlands; Regenerative Medicine Utrecht, Utrecht, the Netherlands. Electronic address: r.vanweeren@uu.nl.
- Department of Applied Physics, University of Eastern Finland, Kuopio, Finland. Electronic address: isaac.afara@uef.fi.
- Department of Applied Physics, University of Eastern Finland, Kuopio, Finland; Diagnostic Imaging Center, Kuopio University Hospital, Kuopio, Finland; School of Information Technology and Electrical Engineering, The University of Queensland, Brisbane, Australia. Electronic address: j.toyras@uq.edu.au.
MeSH Terms
- Animals
- Arthroscopy
- Carpal Joints / diagnostic imaging
- Cartilage Diseases / diagnostic imaging
- Cartilage Diseases / pathology
- Cartilage, Articular / diagnostic imaging
- Cartilage, Articular / injuries
- Cartilage, Articular / pathology
- Horses
- Machine Learning
- Neural Networks, Computer
- Organ Size
- Spectroscopy, Near-Infrared
- Wrist Joint / diagnostic imaging
Citations
This article has been cited 7 times.- Linus A, Tanska P, Sarin JK, Nippolainen E, Tiitu V, Mäkelä JTA, Töyräs J, Korhonen RK, Mononen ME, Afara IO. Visible and Near-Infrared Spectroscopy Enables Differentiation of Normal and Early Osteoarthritic Human Knee Joint Articular Cartilage.. Ann Biomed Eng 2023 Jun 18;.
- Zhang W, Kasun LC, Wang QJ, Zheng Y, Lin Z. A Review of Machine Learning for Near-Infrared Spectroscopy.. Sensors (Basel) 2022 Dec 13;22(24).
- Sarin JK, Prakash M, Shaikh R, Torniainen J, Joukainen A, Kröger H, Afara IO, Töyräs J. Near-Infrared Spectroscopy Enables Arthroscopic Histologic Grading of Human Knee Articular Cartilage.. Arthrosc Sports Med Rehabil 2022 Oct;4(5):e1767-e1775.
- Mohammadi A, Te Moller NCR, Ebrahimi M, Plomp S, Brommer H, van Weeren PR, Mäkelä JTA, Töyräs J, Korhonen RK. Site- and Zone-Dependent Changes in Proteoglycan Content and Biomechanical Properties of Bluntly and Sharply Grooved Equine Articular Cartilage.. Ann Biomed Eng 2022 Dec;50(12):1787-1797.
- Rehman HU, Tafintseva V, Zimmermann B, Solheim JH, Virtanen V, Shaikh R, Nippolainen E, Afara I, Saarakkala S, Rieppo L, Krebs P, Fomina P, Mizaikoff B, Kohler A. Preclassification of Broadband and Sparse Infrared Data by Multiplicative Signal Correction Approach.. Molecules 2022 Apr 1;27(7).
- Honkanen MKM, Mohammadi A, Te Moller NCR, Ebrahimi M, Xu W, Plomp S, Pouran B, Lehto VP, Brommer H, van Weeren PR, Korhonen RK, Töyräs J, Mäkelä JTA. Dual-contrast micro-CT enables cartilage lesion detection and tissue condition evaluation ex vivo.. Equine Vet J 2023 Mar;55(2):315-324.
- Te Moller NCR, Mohammadi A, Plomp S, Serra Bragança FM, Beukers M, Pouran B, Afara IO, Nippolainen E, Mäkelä JTA, Korhonen RK, Töyräs J, Brommer H, van Weeren PR. Structural, compositional, and functional effects of blunt and sharp cartilage damage on the joint: A 9-month equine groove model study.. J Orthop Res 2021 Nov;39(11):2363-2375.
Use Nutrition Calculator
Check if your horse's diet meets their nutrition requirements with our easy-to-use tool Check your horse's diet with our easy-to-use tool
Talk to a Nutritionist
Discuss your horse's feeding plan with our experts over a free phone consultation Discuss your horse's diet over a phone consultation
Submit Diet Evaluation
Get a customized feeding plan for your horse formulated by our equine nutritionists Get a custom feeding plan formulated by our nutritionists
