How Artificial Intelligence and Machine Learning Is Assisting Us to Extract Meaning from Data on Bone Mechanics?

Dramatic advancements in interdisciplinary research with the fourth paradigm of science, especially the implementation of computer science, nourish the potential for artificial intelligence (AI), machine learning (ML), and artificial neural network (ANN) algorithms to be applied to studies concerning mechanics of bones. Despite recent enormous advancement in techniques, gaining deep knowledge to find correlations between bone shape, material, mechanical, and physical responses as well as properties is a daunting task. This is due to both complexity of the material itself and the convoluted shapes that this complex material forms. Moreover, many uncertainties and ambiguities exist concerning the use of traditional computational techniques that hinders gaining a full comprehension of this advanced biological material. This book chapter offers a review of literature on the use of AI, ML, and ANN in the study of bone mechanics research. A main question as to why to implement AI and ML in the mechanics of bones is fully addressed and explained. This chapter also introduces AI and ML and elaborates on the main features of ML algorithms such as learning paradigms, subtypes, main ideas with examples, performance metrics, training algorithms, and training datasets. As a frequently employed ML algorithm in bone mechanics, feedforward ANNs are discussed to make their taxonomy and working principles more readily comprehensible to researchers. A summary as well as detailed review of papers that employed ANNs to learn from collected data on bone mechanics are presented. Reviewing literature on the use of these data-driven tools is essential since their wider application has the potential to: improve clinical assessments enabling real-time simulations; avoid and/or minimize injuries; and, encourage early detection of such injuries in the first place.

Investigating canine elbow joint stabilisation through mechanical constraints of the deep fascia and other soft tissues.

The objective of this research was to investigate how the range of flexion and extension of the canine elbow joint is constrained by the mechanical connections and attachments of soft tissue structures. The skin, a section of deep fascia and several muscles from both forelimbs from six adult greyhounds and seven other breeds were sequentially transected or removed, over 13 steps. During each step, repeated measurements of elbow flexion and extension were recorded using a goniometer. Only marginally significant changes to the range of flexion occurred in any of the 13 steps or overall for the greyhounds. Clearly significant changes to extension occurred in several dissection steps. Removing the skin resulted in a significant increase in elbow extension of 1.7° ± 0.3 (P < 0.001) in the greyhounds and 1.6° ± 0.3 (P < 0.001) in the other breeds. Severing the deep fascia from the humerus and its connections across the elbow joint resulted in the largest significant change in elbow extension of 9.9° ± 0.3 (P < 0.001) in the greyhounds and 6.9° ± 0.7 (P < 0.001) in the other breeds. Transecting the biceps brachii m. close to the elbow resulted in an increase of 2.8° ± 0.3 (P < 0.001) in the greyhounds but a non-significant change in the other breeds. Transecting the extensor carpi radialis m. from its origin resulted in an increase of 5.5° ± 0.4 (P < 0.001) in the greyhounds and 3.9° ± 0.7 (P < 0.001) in the other breeds. These results suggest that the collagenous framework and attachments of the skin, deep fascia, and extensor carpi radialis m., play a significant role in the function of the canine elbow by restricting it from overextension and hence stabilising it during periods of loading, in a variety of different canine breeds, and that these structures are functionally integrated into the way the forelimb supports the bodyweight separately from any involvement of muscle tone or muscle movements. Observations on the anatomical connections of the deep fascia between the cranial distal humerus and the antebrachial fascia highlighted its probable importance in relating movements between the shoulder and the carpus.

Techniques for thoracic duct cannulation without thoracotomy in piglets.

BACKGROUND: Pigs are the natural hosts of many zoonotic pathogens such as influenza viruses and Staphylococcus aureus and thus have advantages over non-natural hosts when studying these zoonotic diseases. In addition, pulmonary infections are a key issue in the pig industry, for example: porcine reproductive and respiratory syndrome virus infection. Exploration of the pathogenesis of swine pulmonary infections, in particular at the onset of disease, will provide valuable information for the development of vaccines against these diseases. Therefore, there is need to develop a methodology that allows for in vivo sampling of efferent pulmonary lymph with minimum damage to the target tissues for studying the pathogenesis of swine pulmonary infections. RESULTS: We introduce the surgical procedures for cannulating the thoracic duct at its point of entry into the external jugular vein cranial to the first rib on the left in pigs. Using this methodology, we monitored the amounts of triglyceride and cholesterol in the lymph collected from the thoracic duct following 30 h fasting and at multiple time points after meals. It was found that the levels of triglyceride rather than cholesterol corresponded to the milky appearance of the lymph samples. CONCLUSIONS: Our techniques provide a strategy for collecting lymph including pulmonary lymph from the thoracic duct without thoracotomy. A pig model for collecting in vivo, in situ efferent lymph draining the lower respiratory tract and its local lymph nodes in real-time with minimal tissue damage to the target tissues opens a new door for studying disease processes in pulmonary infections. Techniques described here are the key to this door.

Anatomical basis for the development of a thoracic duct cannulation model without thoracotomy in Large White pigs.

BACKGROUND: To collect lymph draining the lungs provides a useful strategy for tracing pulmonary microvascular fluid and protein biology. A methodology that allows for in vivo sampling of efferent pulmonary lymph in real-time in sheep by cannulating the thoracic duct without entering the thoracic cavity was previously established. To develop a similar thoracic duct cannulation model without thoracotomy in pigs, we investigated the anatomy of the left cervico-thoracic regions of 15 Large White (Yorkshire or Yorkshire-dominated) piglets (aged 4-7 weeks). RESULTS: The thoracic duct, together with the left tracheal trunk, joined the cardiovascular system (the ampulla of the thoracic duct) at a site located craniomedial to the first rib on the left in 80 % (12/15) of the piglets. CONCLUSIONS: As the location of the ampulla of the thoracic duct was consistent in most of the piglets, Large White piglets appear to be suitable for the development of a thoracic duct cannulation model without thoracotomy. The anatomical findings in this study will enable the development of further surgical procedures for cannulating the thoracic duct without thoracotomy, with minimal damage to local tissue, and without transecting any major blood vessels, nerves or muscle bellies. The establishment of a thoracic duct cannulation model for collecting in vivo, in situ efferent lymph, including pulmonary lymph, in pigs without entering the thoracic cavity would be invaluable for many immunological studies, studies on pulmonary immune responses in particular.

Distal forelimb radiographic bone morphology in Thoroughbred foals during the first 10 months post-partum. Part 1: Carpus.

BACKGROUND: The risk of carpal injury in racehorses may be related to the morphology, yet whether carpal morphologies are set from birth or change through growth remains unclear. OBJECTIVE: To quantify carpal bone changes through growth. METHOD: Twenty privately owned Thoroughbred foals born between January 2022 and May 2023 were radiographed bimonthly from birth to 10 months of age. Imprint training was used to take radiographs safely without chemical restraints. Fifteen individual and 11 relative angular carpal parameters were measured using ImageJ on dorsopalmar radiographs of the carpus at zero degrees of vertical and horizontal rotation. Associations with age (growth), sex and the differences between left and right limbs were analysed separately using a linear mixed effects model. RESULTS: Six individual carpal parameters changed with age (radial carpal joint [RCJ], Prx.dor. radial carpal [Cr], Prx.Cu, Dis.dor. third carpal [C3], Dis.pal.C3 and Dis.pal. intermediate carpal), and one was influenced by side, that is higher in the left carpus (Dis.pal.Cr). Seven relative parameters changed with age, and one relative parameter was influenced by side, that is higher in the left (Ra.met-RCJ). The proximo-dorsal bone surface angle of Cr and disto-dorsal bone surface angle of C3 became flatter over time, which may be associated with the re-direction of the load towards the sagittal carpal plane. Sex did not influence any of the carpal parameters, nor did the combined effect of age, side of the limb and sex. CONCLUSION: Specific individual and relative angular carpal parameters changed significantly over time and some differed between the left and right limb, whereas other parameters did not change. The steeper carpal bone angles achieved proximally with the parameters that did change may improve stability by redirecting the load more medially through the carpus and the proximal and distal bones.

Passive Dynamics of the Head, Neck and Forelimb in Equine Foetuses-An Observational Study.

Passive dynamics is an aspect of locomotion which is entirely dependent on the mechanical configuration and linkages of adjacent body segments. Tension distribution along mechanical linkages enables the execution of movement patterns with reduced need for complex neurological pathways and may play a role in reestablishing postural stability following external disturbances. Here we demonstrate a uni-directional mechanical relationship between the equine forelimb, head and neck, which may have implications for balance and forelimb loading in the horse. These observations suggest that forelimb, head and neck movement coordination (observed in the horse during unrestrained locomotion) is significantly influenced by the mechanical linkages between body segments, rather than being entirely dependent on neurological input as previously thought. This highlights the potential significance of research directed at investigating passively induced movements in understanding common locomotory patterns. Additionally, it suggests a mode of postural control which may provide instantaneous adjustments to postural disturbances, thus promoting rapid and efficient locomotion.

The influence of equine hoof conformation on the initiation and progression of laminitis.

BACKGROUND: The health and performance of horses are significantly affected by diseases associated with the hoof. Laminitis is a critical hoof disease that causes pain and, potentially, severe hoof and bone pathology. OBJECTIVE: To generate an equine hoof finite element (FE) model to investigate the impact of normal and toe-in hoof conformations on the degeneration (decrease in elastic modulus) of the laminar junction (LJ), as occurs in chronic laminitis. STUDY DESIGN: Computer software modelling. METHODS: A hoof FE model was generated to investigate the biomechanics of hoof laminitis. A 3D model, consisting of nine components, was constructed from computed tomography scans of an equine left forelimb hoof. The model was loaded with 100 cycles of trotting. Two different centres of pressure (COP) paths representing normal and toe-in conformations were assigned to the model. LJ injury was modelled by degenerating the tissue's elastic modulus in the presence of excessive maximum principal stresses. RESULTS: FE models successfully showed findings similar to clinical observations, confirming third phalanx (P3) dorsal rotation, a symmetric distal displacement of the P3 (2 mm at the lateral and medial sides) in the normal model, and an asymmetric distal displacement of the P3 (4 mm at the lateral and 1.5 mm at the medial side) in the toe-in model. The proximal distance between P3 and the ground after LJ degeneration in the current model was significantly different from experimental measurements from healthy hooves (P < 0.01). MAIN LIMITATIONS: The inability to account for variations in population geometry and approximation of boundary conditions and system relations were the limitations of the current study. CONCLUSIONS: The distribution of LJ tissue degeneration was symmetric at the quarters in the normal hoof and in comparison, there was a lateral concentration of degeneration in the toe-in model.

HISTORIAL: La salud y el desempeño atlético de los caballos son afectados por patologías asociadas al casco. La laminitis es una enfermedad critica del casco que causa dolor y, potencialmente, patología severa del casco y ósea. OBJETIVO: Generar un modelo finito del casco equino para investigar el impacto de la conformación normal y del dedo-hacia-adentro sobre la degeneración (reducción del módulo elástico) de la unión laminar (UL), como ocurre en la laminitis crónica. DISEÑO DEL ESTUDIO: Modelado por computadora. MÉTODOS: Un modelo de elemento finito (EF) de casco fue generado para investigar la biomecánica de la laminitis en el casco. Un modelo 3D, que consistía de nueve componentes, fue construido a partir de imágenes de tomografía computarizada de un casco equino izquierdo. El modelo fue cargado con 100 ciclos de trote. Dos vías con centros de presión (VCP) distintos representando la conformación normal y dedo-hacia-adentro fueron asignadas al modelo. La lesión de la UL fue modelada degenerando el modelo elástico del tejido en la presencia de estrés principales excesivos máximos. RESULTADOS: Los modelos EF mostraron exitosamente hallazgos similares a las observaciones clínicas, confirmando que la rotación dorsal de la tercera falange (F3), con un desplazamiento distal simétrico de F3 (2 mm por medial y lateral) en el modelo normal, y un desplazamiento distal asimétrico de F3 (4 mm por lateral y 1.5 mm por medial) en el modelo dedo-hacia-adentro. La distancia proximal entre F3 y el suelo después de la degeneración de la UL en el modelo actual fue significativamente diferente de las mediciones experimentales de casco saludables (P < 0.01). LIMITACIONES DEL ESTUDIO: La inhabilidad de tomar en cuenta las variaciones en la geometría de la población y la aproximación de condiciones marginales, y relaciones de sistemas fueron las limitantes de este estudio. CONCLUSIONES: La distribución de la degeneración del tejido de la UL fue simétrico en los cuartos en el casco normal, hubo una concentración lateral de la degeneración en el modelo dedo-hacia-adentro. PALABRAS CLAVE: laminitis, conformación del casco del caballo, centro de presión, método de elemento finito, modelo hiperelástico.

Variation in palmaromedial articulations of carpometacarpal joints in Thoroughbred and Standardbred racehorses.

Background: Carpal conformation is an important factor in relation to joint soundness. The equine carpometacarpal joint (CMCJ) was reported to have variations in its three palmaromedial articulations. Lacking one or more of these articulations has not been radiographically evaluated in Thoroughbred (TB) and Standardbred (SB) racehorses. Aim: The study aimed to identify the prevalence of the variation in the palmaromedial articulation of the carpometacarpal joint (PM-CMCJ) in TB and SB horses. Additionally, to detect the probability of having each of the three articulations within and between the breeds. Finally, to establish an anatomical description for the different patterns of the articulations in these horses. Methods: 313 dorsopalmar radiographs from 174 horses (117 TB and 57 SB) were used. Three articulations at PM-CMCJ were evaluated based on their presence or absence: the articulations between the second and third carpal bones (C2-C3), the second carpal-second metacarpal (C2-Mc2), and the second and third metacarpal (Mc2-Mc3) bones. The probability of each articulation was determined in the breeds. Depending on the presence/absence of one or more of these articulations in each horse, each group of horses that had the same patterns of articulation was gathered into one category. Results: Prevalence of variation in articulations of PM-CMCJ was identified in about 28% of the horses. SB showed a higher variation than TB throughout the comparisons. C2-C3 articulation was significantly the most common articulation, especially in TB (98%). The most common pattern of articulations (73%) was found in category I, which had three articulations whereas three horses grouped in category VI had no palmaromedial articulations. Conclusion: The variations in the articulations of PM-CMCJ in TB and SB racehorse might show a breed association. C2-C3 articulation was considerably the most frequent feature and category I was the common pattern of articulations in PM-CMCJ. The potential clinical effects of the varied patterns of the articulations require investigation.

An Investigation Into Different Measurement Techniques to Assess Equine Proximal Hoof Circumference.

Equine hoof conformation is integral to equine performance and soundness. Consequently, it is a major area of interest within the field of equine health. Researchers have measured several hoof shape parameters to study the hoof conformation. Proximal hoof circumference (PHC) is a primary hoof shape parameter, and its assessment may help to recognize the early stages of the development of changes in hoof morphology or poor hoof shape. Previous studies have mainly used a measuring tape to measure PHC. However, some doubts still exist regarding the reliability, repeatability and accuracy of measuring tape in this context. The current study conducted a technical comparison between the measuring tape and two alternative methods of 3D scanning and photogrammetry to measure PHC. Five equine limbs were collected from five adult horses, and the PHC of the limbs was measured using these three methods. The 3D scanner method was considered to be the highest accuracy and the reference for method comparisons. Pairwise correlations between the 3D scanner and the other two methods were conducted using a linear mixed model. The measuring tape and photogrammetry tended to overestimate the mean PHC compared to the 3D scanner by 0.96 mm (P > .05) and 2.2 mm (P < .05), respectively. In addition, an excellent interrater and intrarater correlation coefficient index was reported for the reliability of the tape measurements. The variation of the tape measurements was ±2 mm, which justified the use of measuring tape for PHC measurements in various clinical and horse management applications.

Feedforward backpropagation artificial neural networks for predicting mechanical responses in complex nonlinear structures: A study on a long bone.

Feedforward backpropagation artificial neural networks (ANNs) have been increasingly employed in many engineering practices concerning materials modeling. Despite their extensive applications, how to achieve successfully trained ANNs is not thoroughly explained in the literature, nor are there lucid discussions to delineate influential parameters obtained from analyses. Long bones are composite materials possessing nonhomogeneous and anisotropic properties, and their mechanical responses exhibit dependency on numerous variables. Material complexity hinders researchers from arriving at a consensus in implementing an optimal constitutive model or encourages them to adopt a simple constitutive model including many simplifying assumptions. However, such exceptional features and engineering challenges make long bones materials worth investigating, enriching our comprehension of complex engineering structures using novel techniques where traditional methods may present limitations. This paper reports on the prediction of loading, displacement, load and displacement simultaneously, and strains using feedforward backpropagation ANNs trained with experimental recordings. The technique was used to find optimum network structures (architectures) that encompass the best prediction ability. To enhance predictions, the influence of several elements such as a network training algorithm, injecting noise to datasets prior to training, the level of injected noise which directly affects model fitting and regularization, and data normalization prior to training were investigated and discussed. Essential parameters influencing decision making in identifying well-trained and well-generalized ANNs were elaborated. A considerable emphasis in this study was placed on examining the generalization ability of the already trained and tested ANNs, thus guaranteeing unbiased models that avoided overfitting. Gaining favorable outcomes in this study required three years of performing experiments and data collection before establishing the networks. The subsequent training, testing, and determination of the generalization of more than 60,000 ANNs are promising and will assist researchers in comprehending mechanical responses of complicated engineering structures that exhibit peculiar nonlinear properties.

Observations of different types of sacra in Greyhounds based on the occurrence of sacrocaudal fusion.

Little attention has been paid to the normal fusion of the vertebrae of greyhounds despite the common occurrence of sacrocaudal fusion. The current study aimed to investigate and provide data on the morphology of different types of fused sacra (B, C and D) in greyhounds and also to determine the potential association between the sex, body mass and morphology of fused sacra (S. Weight, S. Length and S. Width) in greyhounds. The sacra were collected from 171 greyhounds from Melbourne, Australia. After classifying the sacra based on the occurrence and types of the sacrocaudal fusion, they were measured for weight of the sacrum, length of sacrum and the width of sacrum. Multiple linear regression analyses were used to quantify the association between weight of the sacrum (as the outcome variable) type of sacrum (A, B, C and D), body mass and sex (as explanatory variables). The results proved that there are measurable differences between each type of fused sacra (B, C and D) and the standard sacra (A). In addition, this study showed that sex or body mass do not influence the occurrence of different types of fusion. The results of this study showed that the occurrence of sacrocaudal fusions was independent of body size in this population of greyhounds. Sacrocaudal fusion might affect the biomechanics in greyhounds independently of effects of body size.

Morphometrics of nuchal ligament in greyhound in different neck and body positions.

This study was conducted to describe the morphometrics of nuchal ligament and investigate the effects of different neck and body positions on the nuchal ligament in greyhounds. Nine adult greyhounds cadavers without any locomotion abnormalities were dissected through the neck musculature on the left side to expose the nuchal ligament. Three pins were placed to mark regions of interest on the nuchal ligament: at one cm cranial to the site of origin (the most dorsal point of the spinous process of the first thoracic vertebra), at the midpoint of the nuchal ligament and one cm caudal to the nuchal ligament site of insertion (close to the caudal aspect of the spinous process of the axis). Each cadaver was positioned on a masonite board and placed on a table on the floor in their lateral recumbency and seven different standardized body positions; P1-P7 were mimicked using goniometers and metal wires. Photographs were taken by positioning and fixing the camera above the nuchal ligament region. The length and widths (W1, W2 and W3) of nuchal ligament were measured using Image Pro software (Image-Pro Express version 5.0) on standardized photographs of each of seven different body and neck positions. The length of nuchal ligament in relation to the neutral position (P1) was less (- 7%, p > 0·05) in P6 (neck elevated) and increased in all other positions (+1%, p > 0·05 for P2, +19%, p < 0·05 for P3, +37%, p < 0·05 for P4, +1%, p > 0·05 for P5, +40%, p < 0·05 for P7). Nuchal ligament width at the middle (W2) decreased significantly with P4 (- 26%, p < 0·05), and P7 (- 32%, p < 0·05). Also, nuchal ligament width at the site of origin (W3) decreased significantly with P4 (- 24%, p < 0·05) and P7 (-35%, p < 0·05). These findings reflect the need for clinical and biomechanical studies to describe in-depth the gross anatomy of the nuchal ligament in greyhounds. They suggest that different neck and body positions change the shape, and hence, the function of the nuchal ligament during movement.

Radiographic assessment of carpal conformation in the horse, part 2: Finding acceptable limits to postural and rotational variations during radiography.

Finding an appropriate location for perpendicular positioning of the X-ray machine to produce zero lateromedial (ZLM) and zero dorsopalmar (ZDP) carpal images (views) and finding an acceptable range of rotational variations for measurement of carpal conformational parameters were two major challenges identified during field radiography of equine forelimbs. 16 cadaver forelimbs transacted at antebrachial midshaft from 10 horses (aged 9.13 ± 4.59 years) were axially mounted into a custom-built frame, and the radiographic machine and plate were perpendicularly aligned with the limb. Each limb was then radiographed at 2.5° interval of vertical rotation of the machine until ZLM and ZDP images were acquired, and at 24 other postural and rotational positions from ZLM and ZDP at 5° interval for comparison of measurements with the standardized ZLM and ZDP images. ZLM radiographs were produced at a mean vertical projection angle (VPA) of 9.84 ± 3.47° palmarolateral-dorsomedial oblique (PaL-DMO), while ZDP was acquired at VPA of 6.41 ± 2.73° dorsolateral-palmaromedial oblique (DL-PaMO). Changes in limbs' postural tilts, vertical plate rotations (VPR) and horizontal beam rotations (HBR) had no effect on the quality of the radiographs and on carpal measurements, while vertical beam rotation (VBR) of X-ray beam produced significant changes on the quality of radiographs and on measurements of carpal parameters. It is recommended that field radiographs of equine forelimbs intended for carpal measurement be obtained within a proposed range of VPA of 2.5° to 12.5° PaL-DMO for ZLM and 2.5° to 10° DL-PaMO for ZDP in order to minimize potential errors attributable to vertical rotational movements.

Morphometric analysis of the intercarpal ligaments of the equine proximal carpal bones during simulated flexion and extension of cadaver limbs.

Despite many reported cases of carpal lameness associated with intercarpal ligament injuries in horses, the morphometry, movement pattern and general intrinsic biomechanics of the carpus are largely unknown. Using osteoligamentous preparation of the carpus prepared from 14 equine cadaver forelimbs (aged 9.62 ± 4.25 years), locomotory simulations of flexion and extension movements of the carpal joint were carried out to observed carpal biomechanics and, thereafter, the limbs were further dissected to obtain morphometric measurements of the medial and lateral collateral ligaments (MLC and LCL); medial and lateral palmar intercarpal ligaments (MPICL and LPICL); intercarpal ligaments between radial (Cr) and intermediate (Ci) carpal bones (Cr-Ci ICL); and intercarpal ligaments between Ci and ulnar (Cu) carpal bones (Ci-Cu ICL). The Cr, Ci, Cu and Ca are held together by a series of intercarpal ligaments and move in unison lateropalmarly during flexion, and mediodorsally during extension with a distinguishable proximo-distal sliding movement (gliding) of Cr and Ci against each other during movement. The mean length of MCL (108.82 ± 9.64 mm) was significantly longer (p = 0.042) than LCL (104.43 ± 7.65 mm). The Cr-Ci ICL has a dorsopalmar depth of 37.58 ± 4.14 mm and a midpoint width of 12.05 ± 3.09 mm and its fibres ran diagonally from the medial side of the Ci in a proximo-palmar disto-dorsal direction (i.e. palmarodistally) to the lateral side of the Cr. The specialized movement of the Cr-Ci ICL, which appeared to be further facilitated by a longer MCL suggest a biomechanical function by which carpal damage may be minimized in the equine carpus.

What can artificial intelligence and machine learning tell us? A review of applications to equine biomechanical research.

Artificial intelligence (AI) and machine learning (ML) are fascinating interdisciplinary scientific domains where machines are provided with an approximation of human intelligence. The conjecture is that machines are able to learn from existing examples, and employ this accumulated knowledge to fulfil challenging tasks such as regression analysis, pattern classification, and prediction. The horse biomechanical models have been identified as an alternative tool to investigate the effects of mechanical loading and induced deformations on the tissues and structures in humans. Many reported investigations into bone fatigue, subchondral bone damage in the joints of both humans and animals, and identification of vital parameters responsible for retaining integrity of anatomical regions during normal activities in all species are heavily reliant on equine biomechanical research. Horse racing is a lucrative industry and injury prevention in expensive thoroughbreds has encouraged the implementation of various measurement techniques, which results in massive data generation. ML substantially accelerates analysis and interpretation of data and provides considerable advantages over traditional statistical tools historically adopted in biomechanical research. This paper provides the reader with: a brief introduction to AI, taxonomy and several types of ML algorithms, working principle of a feedforward artificial neural network (ANN), and, a detailed review of the applications of AI, ML, and ANN in equine biomechanical research (i.e. locomotory system function, gait analysis, joint and bone mechanics, and hoof function). Reviewing literature on the use of these data-driven tools is essential since their wider application has the potential to: improve clinical assessments enabling real-time simulations, avoid and/or minimize injuries, and encourage early detection of such injuries in the first place.

Radiographic assessment of carpal conformation in the horse: Technique development and validation of the consistency of measurements.

Carpal conformation is often considered as a contributory factor to performance and lameness in the horse; however, few attempts have been made to objectively measure radiographic variations of carpal conformation in horses due to insufficient measurable carpal parameters. This pilot study used carpal radiographic images acquired from 10 cadaveric equine forelimbs transected at the antebrachial midshaft from 7 adult horses (7.2 ± 2.6 years), positioned at 'zero lateromedial' (ZLM) and 'zero dorsopalmar' (ZDP) views, to investigate the anatomy of the equine carpus and develop parameters that could be objectively used to assess carpal conformation in horses. Dorsal carpal angle (DCA: 176.61 ± 0.66º), distal radial slope carpal angle (DRSCA: 145.59 ± 2.19º), intermediate carpal bone proximal tuberosity-radial angle (CiPxTRA: 115.69 ± 3.15º) and third carpal bone palmar facet angle (C3PalFCA: 84.43 ± 1.13º) were all developed from the ZLM view while medial carpal angle (MCA: 183.34 ± 1.02º), disto-dorsal slope angle of the third carpal bone (C3DDSA: 8.27 ± 0.92º) and width ratio of distal radius to proximal metacarpus (WDR:WPM = 1.13±0.03) were 3 of the 10 parameters developed from the ZDP view. Easy to identify and measurable parameters will help to provide quantitative assessment of carpal conformation in the horse with potential of eliminating subjective observational variation errors between clinicians. These newly developed parameters will be useful in further studies to measure variations in the conformation of the equine carpus in live horses and comparison between subjective visual assessment and objective radiographic evaluation methods.

Structural anatomy and morphometric analyses of sacra in greyhounds.

This study was conducted to provide structural and morphological data on the sacra of greyhounds. Descriptive quantitative investigation was carried out on 171 sacra of greyhound`s cadavers and then classified into standard and fused sacra based on the number of fused sacral vertebrae. The weight, length and width of sacrum of sacra were measured. Both standard (59%) and fused sacra (41%) were identified. The average length and width of the standard sacrum were found to be 46.14 ± 2.53 mm and 57.89 ± 3.54 mm, respectively. The sacral length was 1.61-mm longer in males (p < .01), and the sacral width was 0.46-mm shorter in males but not significant (p = .51). The average weight of a standard sacrum was 26.54 ± 4.55 g and was 1.18 g heavier in males but not statistically significant (p = .24). Results showed that one-kilogram increase in the body mass was associated with a 0.3 mm (p < .001) increase in sacral length, and a 0.54 mm (p < .001) increase in sacral width, respectively. The morphological data of the standard and fused sacra provided in this study might help the veterinary community to improve treatment and rehabilitation and help the trainer to design the right training protocol for racing greyhounds. In addition, the results of this study are a step to understand the sacrum's functions and how the greyhound's body functions and future studies are required to investigate the biological importance of these findings.

Variation in the seventh lumbar vertebra and the lumbosacral junction morphometry associated with the sacrocaudal fusion in greyhounds.

The lumbosacral joint is where the 7th lumbar vertebra (L.7) articulates within the sacrum. It is a clinically important area in the dog because of its relatively large range of motion. The current study aims to determine the possible differences in the length of the L.7 vertebra and the angle of the lumbosacral junction among greyhounds of standard and those of fused sacra, and to determine the potential association of sex, body mass and type of fused sacrum (standard and fused) on the morphology of the L.7 vertebra and the angle of the lumbosacral junction. Radiographs of 55 greyhound cadavers were used for radiographing; all radiographic images were stored and measured using X-ray acquisition software, and then analysed using descriptive statistics, multiple linear regression and logistic regression. The results of this study showed a significant increase (p < .008) in the length of the L.7 vertebra and the angle of the lumbosacral junction (p < .028) in greyhounds with fused sacra comparing with those of standard sacra, but the L.6 length was not significant (p = .431). Differences have been found in the length of L.7 vertebra and the angle of the lumbosacral junction in greyhounds. It was found that in greyhounds, any variation in the sacrum's anatomical features may alter the structure of the surrounding anatomical structures such as the L.7 vertebra and lumbosacral junction.

Transmucosal healing around peri-implant defects: crestal and subcrestal implant placement in dogs.

OBJECTIVE: This study was designed to evaluate the transmucosal healing response of implants placed with the junction of the smooth surfaces, either crestal or subcrestal, into simulated extraction defects after healing periods of 1 and 3 months. MATERIALS AND METHODS: A total of 23 Straumann SP v3.3 mm NN, SLA 10 mm implants were placed in the mandibular premolar regions of three greyhound dogs 3 months after the teeth were removed. Five control implants were placed at the crestal bone level, and test implants with surgically created peri-implant defects of 1.25 mm wide x 5 mm depth were placed either at the crestal (nine implants) or at the 2 mm subcrestal (nine implants) bone level. Implants on the right side were placed 1 month before the dogs were sacrificed, and implants on the left side were placed 3 months before sacrifice. All dogs had daily plaque control following surgery and were sacrificed 3 months after implant placement for histological and histometric analyses. RESULTS: Mesial-distal ground sections of the control and test implant specimens showed a greater %BIC in the coronal defect region after 3 months of healing. This healing response was incomplete for the test implants compared with the control implants after a 1-month healing period. The histometric measurements for test implants placed at the crestal bone level or 2 mm subcrestal with surgically created peri-implant defects were more coronal or closer to the implant margin compared with the control implants. Additionally, the degree of osseointegration between the newly formed bone and the implant surface was similar between the test implants. CONCLUSION: Peri-implant defects of 1.25 mm width healed with spontaneous bone regeneration around implants placed transmucosally at crestal or 2 mm subcrestal with a high degree of osseointegration after a 3-month healing period.