Intracortical remodelling increases in highly loaded bone after exercise cessation.

Resorption within cortices of long bones removes excess mass and damaged tissue and increases during periods of reduced mechanical loading. Returning to high-intensity exercise may place bones at risk of failure due to increased porosity caused by bone resorption. We used point-projection X-ray microscopy images of bone slices from highly loaded (metacarpal, tibia) and minimally loaded (rib) bones from 12 racehorses, 6 that died during a period of high-intensity exercise and 6 that had a period of intense exercise followed by at least 35 days of rest prior to death, and measured intracortical canal cross-sectional area (Ca.Ar) and number (N.Ca) to infer remodelling activity across sites and exercise groups. Large canals that are the consequence of bone resorption (Ca.Ar >0.04 mm2 ) were 1.4× to 18.7× greater in number and area in the third metacarpal bone from rested than exercised animals (p = 0.005-0.008), but were similar in number and area in ribs from rested and exercised animals (p = 0.575-0.688). An intermediate relationship was present in the tibia, and when large canals and smaller canals that result from partial bony infilling (Ca.Ar >0.002 mm2 ) were considered together. The mechanostat may override targeted remodelling during periods of high mechanical load by enhancing bone formation, reducing resorption and suppressing turnover. Both systems may work synergistically in rest periods to remove excess and damaged tissue.

Classification of racehorse limb radiographs using deep convolutional neural networks.

Purpose: To assess the capability of deep convolutional neural networks to classify anatomical location and projection from a series of 48 standard views of racehorse limbs. Materials and methods: Radiographs (N = 9504) of horse limbs from image sets made for veterinary inspections by 10 independent veterinary clinics were used to train, validate and test (116, 40 and 42 radiographs, respectively) six deep learning architectures available as part of the open source machine learning framework PyTorch. The deep learning architectures with the best top-1 accuracy had the batch size further investigated. Results: Top-1 accuracy of six deep learning architectures ranged from 0.737 to 0.841. Top-1 accuracy of the best deep learning architecture (ResNet-34) ranged from 0.809 to 0.878, depending on batch size. ResNet-34 (batch size = 8) achieved the highest top-1 accuracy (0.878) and the majority (91.8%) of misclassification was due to laterality error. Class activation maps indicated that joint morphology, not side markers or other non-anatomical image regions, drove the model decision. Conclusions: Deep convolutional neural networks can classify equine pre-import radiographs into the 48 standard views including moderate discrimination of laterality, independent of side marker presence.