FREE SHIPPING over $40
OVER 9000 FIVE-STAR REVIEWS
5% OFF ALL SUBSCRIPTIONS
100% HAPPINESS GUARANTEE
Analyze Diet
0
Home / Equine Research Bank / Vet Radiol Ultrasound / Leveraging MRI characterization of longitudinal tears of the...
Veterinary radiology & ultrasound : the official journal of the American College of Veterinary Radiology and the International Veterinary Radiology Association2022; 63(5); 580-592; doi: 10.1111/vru.13090

Leveraging MRI characterization of longitudinal tears of the deep digital flexor tendon in horses using machine learning.

Abstract: While MRI is the modality of choice for the diagnosis of longitudinal tears (LTs) of the deep digital flexor tendon (DDFT) of horses, differentiating between various grades of tears based on imaging characteristics is challenging due to overlapping imaging features. In this retrospective, exploratory, diagnostic accuracy study, a machine learning (ML) scheme was applied to link quantitative features and qualitative descriptors to leverage MRI characteristics of different grades of tearing of the DDFT of horses. A qualitative MRI characteristic scheme, combining tendon morphologic features, altered signal intensity, and synovial sheath distention, was used for LT classification with an excellent diagnostic accuracy of the high-grade tears but more limited accuracy for the detection of low-grade tears. A quantitative ML approach was followed to measure the contribution of 30 quantitative phenotypic features for characterizing and classifying tendinous tears. Among the 30 imaging features, boundary curvature represented by the standard deviation and maximum had the most significant discriminatory power (P < 0.05) between normal and abnormal tendons and could be used as an aid for classifying the different grades of LTs of DDFTs. Imaging analysis-based 3D interactive surface plot supports qualitative characterization of different grades of LTs of the DDFT through clearer visualization of the tendon in three dimensions and simple integration of two perspectives features (i.e., margin/distribution and intensity/distribution). A systematic approach combining quantitative features with qualitative analyses using ML was diagnostically beneficial in MRI characterization and in discriminating between different grades of LTs of the DDFT of horses.
© 2022 American College of Veterinary Radiology.
Get Full Text
Publication Date: 2022-04-12 PubMed ID: 35415959DOI: 10.1111/vru.13090Google 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.
LinkedInCopy
  • Journal Article

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 paper discusses a machine learning approach to enhance Magnetic Resonance Imaging (MRI) analyses in identifying various grades of longitudinal tears in the deep digital flexor tendon (DDFT) of horses.

Background

  • The deep digital flexor tendon in horses can often suffer from longitudinal tears (LTs). Diagnostic imaging such as MRI is commonly used to detect these tears. However, differentiating differing grades of tears can be challenging due to overlapping imaging characteristics.
  • This paper focuses on an exploratory diagnostic accuracy study that employs a machine learning scheme to improve on these shortfalls.

Methodology

  • The researchers used a combined scheme of morphological features, signal intensity, and synovial sheath distension to classify longitudinal tears.
  • This approach was particularly successful in diagnosing high-grade tears, though somewhat less successful for low-grade tears.
  • Subsequently, a quantitative machine learning method was employed, involving 30 quantitative phenotypic features to characterize and differentiate tendon tears.
  • Among these 30 features, the boundary curvature represented by the standard deviation and maximum showed the most significant discriminatory power.

Results

  • The boundary curvature could potentially be employed as a classification aid for varying grades of tendon tears.
  • The scientists also made use of 3D imaging analyses, which provided clearer visualization of the tendon and simple integration of two important features: margin/distribution and intensity/distribution.

Conclusion

  • A combined approach using quantitative features with qualitative analyses through machine learning showed promise in improving the diagnostic process.
  • It enhanced MRI characterization by distinguishing different grades of longitudinal tears in the deep digital flexor tendon of horses more accurately.

Cite This Article

APA
ELKhamary AN, Keenihan EK, Schnabel LV, Redding WR, Schumacher J. (2022). Leveraging MRI characterization of longitudinal tears of the deep digital flexor tendon in horses using machine learning. Vet Radiol Ultrasound, 63(5), 580-592. https://doi.org/10.1111/vru.13090

Publication

Veterinary radiology & ultrasound : the official journal of the American College of Veterinary Radiology and the International Veterinary Radiology Association
ISSN: 1740-8261
NlmUniqueID: 9209635
Country: England
Language: English
Volume: 63
Issue: 5
Pages: 580-592

Researcher Affiliations

ELKhamary, Ahmed N
  • Department of Surgery, Radiology and Anesthesiology, Faculty of Veterinary Medicine, Damanhour University, Damanhour, Behera, Egypt.
Keenihan, Erin K
  • Department of Molecular and Biomedical Sciences, College of Veterinary Medicine, North Carolina State University, Raleigh, North Carolina, USA.
Schnabel, Lauren V
  • Department of Clinical Sciences, North Carolina State University, Raleigh, North Carolina, USA.
Redding, William R
  • Department of Clinical Sciences, North Carolina State University, Raleigh, North Carolina, USA.
Schumacher, Jim
  • Large Animal Clinical Sciences, University of Tennessee College of Veterinary Medicine, Knoxville, Tennessee, USA.

MeSH Terms

  • Animals
  • Horse Diseases / diagnosis
  • Horses
  • Machine Learning
  • Magnetic Resonance Imaging / veterinary
  • Retrospective Studies
  • Tendons / diagnostic imaging

References

This article includes 40 references
  1. Arensburg L, Wilderjans H, Simon O, Dewulf J, Boussauw B. Nonseptic tenosynovitis of the digital flexor tendon sheath caused by longitudinal tears in the digital flexor tendons: a retrospective study of 135 tenoscopic procedures.. Equine Vet J 2011;43:660-668.
  2. Smith MRW, Wright IM. Noninfected tenosynovitis of the digital flexor tendon sheath: a retrospective analysis of 76 cases.. Equine Vet J 2006;38:134-141.
  3. Wilderjans H, Boussauw B, Madder K, Simon O. Tenosynovitis of the digital flexor tendon sheath and annular ligament constriction syndrome caused by longitudinal tears in the deep digital flexor tendon: a clinical and surgical report of 17 cases in Warmblood horses.. Equine Vet J 2003;35:270-275.
  4. Wright IM, McMahon PJ. Tenosynovitis associated with longitudinal tears of the digital flexor tendons in horses: a report of 20 cases.. Equine Vet J 1999;31:12-18.
  5. Daniel AJ, Leise BS, Selberg KT, Barrett MF. Enhanced ultrasonographic imaging of the equine distal limb using saline injection of the digital flexor tendon sheath: a cadaver study.. Vet J 2019;26-31.
  6. Fiske-Jackson AR, Barker WHJ, Eliashar E, Foy K, Smith RKW. The use of intrathecal analgesia and contrast radiography as preoperative diagnostic methods for digital flexor tendon sheath pathology.. Equine Vet J 2013;45:36-40.
  7. Bertuglia A, Mollo G, Bullone M, Riccio B. Identification of surgically induced longitudinal lesions of the equine deep digital flexor tendon in the digital flexor tendon sheath using contrast-enhanced ultrasonography: an ex-vivo pilot study.. Acta Vet Scand 2014;56:1-8.
  8. Cillán-García E, Milner PI, Talbot A. Deep digital flexor tendon injury within the hoof capsule;does lesion type or location predict prognosis?. Vet Rec 2013;173:70-70.
  9. Vanel M, Olive J, Gold S, Mitchell RD, Walker L. Clinical significance and prognosis of deep digital flexor tendinopathy assessed over time using MRI.. Vet Radiol Ultrasound 2012;53:621-627.
  10. Gonzalez LM, Schramme MC, Robertson ID, Thrall DE, Redding RW. MRI features of metacarpo (tarso) phalangeal region lameness in 40 horses.. Vet Radiol Ultrasound 2010;51:404-414.
  11. King JN, Zubrod CJ, Schneider RK, Sampson SN, Roberts G. MRI findings in 232 horses with lameness localized to the metacarpo (tarso) phalangeal region and without a radiographic diagnosis.. Vet Radiol Ultrasound 2013;54:36-47.
  12. Lutter JD, Schneider RK, Sampson SN, Cary JA, Roberts GD, Vahl CI. Medical treatment of horses with deep digital flexor tendon injuries diagnosed with high-field-strength magnetic resonance imaging: 118 cases (2000-2010).. J Am Vet Med Assoc 2015;247:1309-1318.
  13. Hosny A, Parmar C, Quackenbush J, Schwartz LH, Aerts HJ. Artificial intelligence in radiology.. Nat Rev Cancer 2018;18:500-510.
  14. Shen D, Wu G, Suk H-I. Deep learning in medical image analysis.. Annu Rev Biomed Eng 2017;19:221-248.
  15. Zhou M, Scott J, Chaudhury B. Radiomics in brain tumor: image assessment, quantitative feature descriptors, and machine-learning approaches.. Am J Neuroradiol 2018;39:208-216.
  16. Mongan J, Moy L Jr, Kahn CE. Checklist for artificial intelligence in medical imaging (CLAIM): A guide for authors and reviewers.. Radiological Society of North America 2020.
  17. Snyder SJ, Pachelli AF, Del Pizzo W, Friedman MJ, Ferkel RD, Pattee G. Partial thickness rotator cuff tears: results of arthroscopic treatment.. Arthrosc J Arthrosc Relat Surg 1991;1-7.
  18. Blunden A, Murray R, Dyson S. Lesions of the deep digital flexor tendon in the digit: a correlative MRI and post mortem study in control and lame horses.. Equine Vet J 2009;41:25-33.
  19. Murray RC, Roberts BL, Schramme MC, Dyson SJ, Branch M. Quantitative evaluation of equine deep digital flexor tendon morphology using magnetic resonance imaging.. Vet Radiol Ultrasound 2004;45:103-111.
  20. Dyson S. Proximal injuries of the accessory ligament of the deep digital flexor tendon in forelimbs and hindlimbs: 12 horses (2006-2010).. Equine Vet Educ 2012;134-142.
  21. Hawass NE. Comparing the sensitivities and specificities of two diagnostic procedures performed on the same group of patients.. Br J Radiol 1997;70:360-366.
  22. Zewei Z, Tianyue W, Li G, Tingting W, Lu X. An interactive method based on the live wire for segmentation of the breast in mammography images.. Comput Math Methods Med 2014.
  23. Dijkstra EW. A note on two problems in connexion with graphs.. Numer Math 1959;1:269-271.
  24. Wagenknecht G, Belitz H, Wolff R, Castellanos J. Segmentation of ROIs/VOIs from small animal images for functional analysis.. Nucl Instrum Methods Phys Res Sect Accel Spectrometers Detect Assoc Equip 2006;481-487.
  25. Sadro C, Dalinka M. Magnetic resonance imaging of the tendons of the ankle and foot.. UPOJ 2000;13:1-19.
  26. Okoroha KR, Mehran N, Duncan J. Characterization of rotator cuff tears: ultrasound versus magnetic resonance imaging.. Orthopedics 2017;40:e124.
  27. Blockeel H, Struyf J. Efficient algorithms for decision tree cross-validation.. J Mach Learn Res 2002;3:621-650.
  28. Arlot S, Celisse A. A survey of cross-validation procedures for model selection.. Stat Surv 2010;4:40-79.
  29. Diekstall M, Rijkenhuizen ABM, Gudehus T. Tenoscopic resection of the manica flexoria in 21 horses using a two-portal unilateral technique.. Equine Vet Educ 2020;66-71.
  30. Barrett MF, Frisbie DD, King MR, Werpy NM, Kawcak CE. A review of how magnetic resonance imaging can aid in case management of common pathological conditions of the equine foot.. Equine Vet Educ 2017;683-693.
  31. Werpy NM, Ho CP, Kawcak CE. Magic angle effect in normal collateral ligaments of the distal interphalangeal joint in horses imaged with a high-field magnetic resonance imaging system.. Vet Radiol Ultrasound 2010;2-10.
  32. Smith RK. Tendon and ligament injury.. Proc 54th Annu Conv Am Assoc Equine Pract 2008 San Diego Calif;475-501.
  33. Ganal E, Ho CP, Wilson KJ. Quantitative MRI characterization of arthroscopically verified supraspinatus pathology: comparison of tendon tears, tendinosis and asymptomatic supraspinatus tendons with T2 mapping.. Knee Surg Sports Traumatol Arthrosc 2016;2216-2224.
  34. Kim JY, Rhee S-M, Rhee YG. Accuracy of MRI in diagnosing intra-articular pathology of the long head of the biceps tendon: results with a large cohort of patients.. BMC Musculoskelet Disord 2019;1-9.
  35. Chang PD, Wong TT, Rasiej MJ. Deep learning for detection of complete anterior cruciate ligament tear.. J Digit Imaging 2019;980-986.
  36. Payabvash S, Aboian M, Tihan T, Cha S. Machine Learning Decision Tree Models for Differentiation of Posterior Fossa Tumors Using Diffusion Histogram Analysis and Structural MRI Findings.. Front Oncol 2020 Feb 7;10:71.
    doi: 10.3389/fonc.2020.00071google scholar: lookup
  37. Refaeilzadeh P, Tang L, Liu H. Cross-validation.. Encycl Database Syst 2009;5:532-538.
  38. Driscoll MK, Fourkas JT, Losert W. Local and global measures of shape dynamics.. Phys Biol 2011;8:055001.
  39. Driscoll MK, Losert W, Jacobson K, Kapustina M. Spatiotemporal relationships between the cell shape and the actomyosin cortex of periodically protruding cells.. Cytoskeleton 2015;268-281.
  40. Driscoll M, McCann C, Kopace R. Cell Shape Dynamics: from Waves to Migration.. APS March Meet Abstr 2011;V39-007.

Citations

This article has been cited 0 times.
Subscribe to our newsletter
Join 99,344 horse owners like you who receive our email updates on horse health and nutrition.