Letter to the Editor: Selection of appropriate controls for studying fatal musculoskeletal injury in racehorses

Radiomics Modeling of Catastrophic Proximal Sesamoid Bone Fractures in Thoroughbred Racehorses Using μCT

Proximal sesamoid bone (PSB) fractures are the most common musculoskeletal injury in race-horses. X-ray CT imaging can detect expressed radiological features in horses that experienced catastrophic fractures. Our objective was to assess whether expressed radiomic features in the PSBs of 50 horses can be used to develop machine learning models for predicting PSB fractures. The μCTs of intact contralateral PSBs from 50 horses, 30 of which suffered catastrophic fractures, and 20 controls were studied. From the 129 intact μCT images of PSBs, 102 radiomic features were computed using a variety of voxel resampling dimensions. Decision Trees and Wrapper methods were used to identify the 20 top expressed features, and six machine learning algorithms were developed to model the risk of fracture. The accuracy of all machine learning models ranged from 0.643 to 0.903 with an average of 0.754. On average, Support Vector Machine, Random Forest (RUS Boost), and Log-regression models had higher performance than K-means Nearest Neighbor, Neural Network, and Random Forest (Bagged Trees) models. Model accuracy peaked at 0.5 mm and decreased substantially when the resampling resolution was greater than or equal to 1 mm. We find that, for this in vitro dataset, it is possible to differentiate between unfractured PSBs from case and control horses using μCT images. It may be possible to extend these findings to the assessment of fracture risk in standing horses.

Imaging and Gross Pathological Appearance of Changes in the Parasagittal Grooves of Thoroughbred Racehorses

Simple Summary

Early detection of racehorses at risk of stress fracture is key to reducing the number of horses with catastrophic fractures while racing. Bone changes are often visible in the limbs of Thoroughbred racehorses in work, particularly in the fetlock region. However, it is currently unknown whether some of these changes indicate an impending fracture or are a healthy adaptation to high-speed exercise. This study looks at imaging and gross changes in a specific area (parasagittal grooves (PSGs) of the cannon bone) and the utility of X-ray, computed tomography (CT) and magnetic resonance imaging (MRI) to detect the changes. All fetlock joints were assessed from twenty horses that died during racing or training, including horses with and without fetlock fracture. Overall, X-ray was poor for detecting PSG changes. Some PSG changes on CT and MRI were common in Thoroughbred racehorses and possibly represent normal bone adaptation when seen in clinical cases. However, certain CT and MRI findings were more prevalent in horses with a fracture, possibly indicating microdamage accumulation and increased risk of fracture. Bilateral advanced imaging is recommended in clinical cases of suspected fetlock pathology.

Abstract

(1) Background: Parasagittal groove (PSG) changes are often present on advanced imaging of racing Thoroughbred fetlocks and have been suggested to indicate increased fracture risk. Currently, there is limited evidence differentiating the imaging appearance of prodromal changes in horses at risk of fracture from horses with normal adaptive modelling in response to galloping. This study aims to investigate imaging and gross PSG findings in racing Thoroughbreds and the comparative utility of different imaging modalities to detect PSG changes. (2) Methods: Cadaver limbs were collected from twenty deceased racing/training Thoroughbreds. All fetlocks of each horse were examined with radiography, low-field magnetic resonance imaging (MRI), computed tomography (CT), contrast arthrography and gross pathology. (3) Results: Horses with fetlock fracture were more likely to have lateromedial PSG sclerosis asymmetry and/or lateral PSG lysis. PSG lysis was not readily detected using MRI. PSG subchondral bone defects were difficult to differentiate from cartilage defects on MRI and were not associated with fractures. The clinical relevance of PSG STIR hyperintensity remains unclear. Overall, radiography was poor for detecting PSG changes. (4) Conclusions: Some PSG changes in Thoroughbred racehorses are common; however, certain findings are more prevalent in horses with fractures, possibly indicating microdamage accumulation. Bilateral advanced imaging is recommended in racehorses with suspected fetlock pathology.