A radiomics platform for computing imaging features from µCT images of Thoroughbred racehorse proximal sesamoid bones: Benchmark performance and evaluation.
CT imaging
density
epidemiology
exercise
horse
morphology
Journal
Equine veterinary journal
ISSN: 2042-3306
Titre abrégé: Equine Vet J
Pays: United States
ID NLM: 0173320
Informations de publication
Date de publication:
Mar 2021
Mar 2021
Historique:
received:
18
03
2020
revised:
08
06
2020
accepted:
02
07
2020
pubmed:
13
7
2020
medline:
10
2
2021
entrez:
13
7
2020
Statut:
ppublish
Résumé
Proximal sesamoid bone (PSB) fractures are the most common fatal musculoskeletal injury in North American racehorses. Computed tomography has the potential to detect morphological changes in bone structure but can be challenging to analyse reliably and quantitatively. To develop a radiomics platform that allows the comparison of features from micro-CTs (µCT) of PSBs in horses that sustained catastrophic fractures with horses that did not. To compare features calculated with a radiomics approach with features calculated from a previously published study that used quantitative µCT in the same specimens. Retrospective study of cadaver specimens of µCT images of PSBs using prospectively applied radiomics. Radiomics features were computed on standardised CT datasets to benchmark the software. Features from µCT images of PSBs from eight horses that sustained PSB fracture and eight controls were computed using the contralateral, intact forelimb from horses sustaining PSB fracture (cases, n = 19) and all available forelimbs for controls (n = 30). Two-hundred and fifteen radiomic features were calculated, and similar or comparable features were compared with those reported in a previous study that used the same specimens. Morphologic features computed with the radiomics approach, such as volume, minor axis dimensions and anisotropy were highly correlated with previously published data. A high number of imperceptible radiomic features, such as entropy, coarseness and histogram features were also found to be significantly different (P < .01). The extent of the differences in image features for the cases and controls PSBs depends on radiomic calculation settings. Only datasets obtained from cadaver specimens were included in the study. A radiomics approach for analysing µCT images of PSBs was able to identify and reproduce differences in image features in cases and controls. Furthermore, radiomics revealed many more imperceptible image features between cases and control PSBs.
Sections du résumé
BACKGROUND
BACKGROUND
Proximal sesamoid bone (PSB) fractures are the most common fatal musculoskeletal injury in North American racehorses. Computed tomography has the potential to detect morphological changes in bone structure but can be challenging to analyse reliably and quantitatively.
OBJECTIVES
OBJECTIVE
To develop a radiomics platform that allows the comparison of features from micro-CTs (µCT) of PSBs in horses that sustained catastrophic fractures with horses that did not. To compare features calculated with a radiomics approach with features calculated from a previously published study that used quantitative µCT in the same specimens.
STUDY DESIGN
METHODS
Retrospective study of cadaver specimens of µCT images of PSBs using prospectively applied radiomics.
METHODS
METHODS
Radiomics features were computed on standardised CT datasets to benchmark the software. Features from µCT images of PSBs from eight horses that sustained PSB fracture and eight controls were computed using the contralateral, intact forelimb from horses sustaining PSB fracture (cases, n = 19) and all available forelimbs for controls (n = 30). Two-hundred and fifteen radiomic features were calculated, and similar or comparable features were compared with those reported in a previous study that used the same specimens.
RESULTS
RESULTS
Morphologic features computed with the radiomics approach, such as volume, minor axis dimensions and anisotropy were highly correlated with previously published data. A high number of imperceptible radiomic features, such as entropy, coarseness and histogram features were also found to be significantly different (P < .01). The extent of the differences in image features for the cases and controls PSBs depends on radiomic calculation settings.
MAIN LIMITATIONS
CONCLUSIONS
Only datasets obtained from cadaver specimens were included in the study.
CONCLUSIONS
CONCLUSIONS
A radiomics approach for analysing µCT images of PSBs was able to identify and reproduce differences in image features in cases and controls. Furthermore, radiomics revealed many more imperceptible image features between cases and control PSBs.
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
277-286Subventions
Organisme : Harry M. Zweig Memorial Fund for Equine Research
Informations de copyright
© 2020 EVJ Ltd.
Références
Spargo KE, Rubio-Martinez LM, Wheeler DP, Fletcher L, Carstens A. Catastrophic musculoskeletal injuries in Thoroughbred racehorses on racetracks in Gauteng, South Africa. J S Afr Vet Assoc. 2019;90:e1-e5.
Palmer SE, McDonough SP, Mohammed HO. Reduction of Thoroughbred racing fatalities at New York Racing Association racetracks using a multi-disciplinary mortality review process. J Vet Diagn Invest. 2017;29:465-75.
Stover SM, Murray A. The California Postmortem Program: leading the way. Vet Clin North Am Equine Pract. 2008;24:21-36.
Hernandez J, Hawkins DL, Scollay MC. Race-start characteristics and risk of catastrophic musculoskeletal injury in Thoroughbred racehorses. J Am Vet Med Assoc. 2001;218:83-6.
Hitchens PL, Morrice-West AV, Stevenson MA, Whitton RC. Meta-analysis of risk factors for racehorse catastrophic musculoskeletal injury in flat racing. Vet J. 2019;245:29-40.
Anthenill LA, Stover SM, Gardner IA, Hill AE. Risk factors for proximal sesamoid bone fractures associated with exercise history and horseshoe characteristics in Thoroughbred racehorses. Am J Vet Res. 2007;68:760-71.
Shi L, Wang D, Riggs CM, Qin L, Griffith JF. Statistical analysis of bone mineral density using voxel-based morphometry-an application on proximal sesamoid bones in racehorses. J Orthop Res. 2011;29:1230-6.
Wang D, Shi L, Griffith JF, Qin L, Yew DTW, Riggs CM. Comprehensive surface-based morphometry reveals the association of fracture risk and bone geometry. J Orthop Res. 2012;30:1277-84.
Trope GD, Ghasem-Zadeh A, Anderson GA, Mackie EJ, Whitton RC. Can high-resolution peripheral quantitative computed tomography imaging of subchondral and cortical bone predict condylar fracture in Thoroughbred racehorses? Equine Vet J. 2015;47:428-32.
Cresswell EN, McDonough SP, Palmer SE, Hernandez CJ, Reesink HL. Can quantitative computed tomography detect bone morphological changes associated with catastrophic proximal sesamoid bone fracture in Thoroughbred racehorses? Equine Vet J. 2019;51:123-30.
Erickson BJ, Korfiatis P, Akkus Z, Kline TL. Machine learning for medical imaging. Radiographics. 2017;37:505-15.
Lambin P, Leijenaar RTH, Deist TM, Peerlings J, de Jong EEC, van Timmeren J, et al. Radiomics: the bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol. 2017;14:749-62.
Lubner MG, Smith AD, Sandrasegaran K, Sahani DV, Pickhardt PJ. CT texture analysis: definitions, applications, biologic correlates, and challenges. Radiographics. 2017;37:1483-503.
Jacobs C, van Ginneken B. AI: a promising tool that needs further validation. Nat Rev Clin Oncol. 2019;16:532-3.
Wang J, Shen L, Zhong H, Zhou Z, Hu P, Gan J, et al. Radiomics features on radiotherapy treatment planning CT can predict patient survival in locally advanced rectal cancer patients. Sci Rep. 2019;9:1-9.
Lee SE, Han K, Kwak JY, Lee E, Kim E-K. Radiomics of US texture features in differential diagnosis between triple-negative breast cancer and fibroadenoma. Sci Rep. 2018;2018(8):13546.
Gatenby RA, Grove O, Gillies RJ. Quantitative imaging in cancer evolution and ecology. Radiology. 2013;269:8-14.
McEvoy FJ, Amigo JM. Using machine learning to classify image features from canine pelvic radiographs: evaluation of partial least squares discriminant analysis and artificial neural network models. Vet Radiol Ultrasound. 2013;54:122-6.
Banzato T, Bernardini M, Cherubini GB, Zotti A. A methodological approach for deep learning to distinguish between meningiomas and gliomas on canine MR-images. BMC Vet Res. 2018;14:317.
Rastegar S, Vaziri M, Qasempour Y, Akhash MR, Abdalvand N, Shiri I, et al. Radiomics for classification of bone mineral loss: a machine learning study. Diagn Interv Imag. In Press; 2020. https://doi.org/10.1016/j.diii.2020.01.008
Acar E, Leblebici A, Ellidokuz BE, Başbınar Y, Kaya GÇ. Machine learning for differentiating metastatic and completely responded sclerotic bone lesion in prostate cancer: a retrospective radiomics study. Br J Radiol. 2019;92:20190286.
Budán F, Szigeti K, Weszl M, Horváth I, Balogh E, Kanaan R, et al. Novel radiomics evaluation of bone formation utilizing multimodal (SPECT/X-ray CT) in vivo imaging. PLoS One. 2018;13(9):e0204423.
Saeedi E, Dezhkam A, Beigi J, Rastegar S, Yousefi Z, Mehdipour LA, et al. Radiomic feature robustness and reproducibility in quantitative bone radiography: a study on radiologic parameter changes. J Clin Densitom. 2019;22:203-13.
Ger RB, Craft DF, Mackin DS, Zhou S, Layman RR, Jones AK, et al. Practical guidelines for handling head and neck computed tomography artifacts for quantitative image analysis. Comput Med Imaging Graph. 2018;69:134-9.
Zwanenburg A, Leger S, Vallières M, Löck S. Image biomarker standardisation initiative. arXiv:1612.07003[cs, eess]. 2019. Accessed February 20, 2020.
Vallières M. mvallieres/radiomics-develop [WWW document]. 2020. https://github.com/mvallieres/radiomics-develop. Accessed June 5, 2020.
Ashrafinia S. ashrafinia/SERA. [WWW document]. 2020. https://github.com/ashrafinia/SERA. Accessed June 5, 2020.
Basran P. pbasran/EquineRadiomics. 2020. [WWW document]. https://github.com/pbasran/EquineRadiomics. Accessed June 5, 2020.
Morin O, Vallières M, Jochems A, Woodruff HC, Valdes G, Braunstein SE, et al. A deep look into the future of quantitative imaging in oncology: a statement of working principles and proposal for change. Int J Rad Oncol Biol Phys. 2018;102:1074-82.
Daniel. Region Growing (2D/3D grayscale) [WWW document]. 2020. https://www.mathworks.com/matlabcentral/fileexchange/32532-region-growing-2d-3d-grayscale, MATLAB Central File Exchange. Accessed March 17, 2020.
Loughridge AB, Hess AM, Parkin TD, Kawcak CE. Qualitative assessment of bone density at the distal articulating surface of the third metacarpal in Thoroughbred racehorses with and without condylar fracture. Equine Vet J. 2017;49:172-7.
Rubio-Martínez LM, Cruz AM, Gordon K, Hurtig MB. Structural characterization of subchondral bone in the distal aspect of third metacarpal bones from Thoroughbred racehorses via micro-computed tomography. Am J Vet Res. 2008;69:1413-22.
Davis AM, Fan X, Shen L, Robinson P, Riggs CM. Improved radiological diagnosis of palmar osteochondral disease in the Thoroughbred racehorse. Equine Vet J. 2017;49:454-60.
Anthenill LA, Gardner IA, Pool RR, Garcia TC, Stover SM. Comparison of macrostructural and microstructural bone features in Thoroughbred racehorses with and without midbody fracture of the proximal sesamoid bone. Am J Vet Res. 2010;71:755-65.
Firth EC, Rogers CW, Doube M, Jopson NB. Musculoskeletal responses of 2-year-old Thoroughbred horses to early training. 6. Bone parameters in the third metacarpal and third metatarsal bones. N Z Vet J. 2005;53:101-12.
Boyde A, Firth EC. Musculoskeletal responses of 2-year-old Thoroughbred horses to early training. 8. Quantitative back-scattered electron scanning electron microscopy and confocal fluorescence microscopy of the epiphysis of the third metacarpal bone. N Z Vet J. 2005;53:123-32.
Duron L, Balvay D, Vande Perre S, Bouchouicha A, Savatovsky J, Sadik J-C, et al. Gray-level discretization impacts reproducible MRI radiomics texture features. PLoS One. 2019;14(3):e0213459.
Spriet M, Espinosa-Mur P, Cissell DD, Phillips KL, Arino-Estrada G, Beylin D, et al. 18F-sodium fluoride positron emission tomography of the racing Thoroughbred fetlock: validation and comparison with other imaging modalities in nine horses. Equine Vet J. 2019;51:375-83.
Ger RB, Zhou S, Chi P-CM, Lee HJ, Layman RR, Jones AK, et al. Comprehensive investigation on controlling for CT Imaging Variabilities In Radiomics Studies. Sci Rep. 2018;8:1-14.