Sabrina Skov Hansen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Sabrina Skov Hansen has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Karsten Thuren Key
Keydiagnostics (RealHorse®) Fredensborg Denmark
8 shared publications Katja Berg
Keydiagnostics (RealHorse®) Fredensborg Denmark
8 shared publicationsKristian Ringkjær Andresen
KeyVet Fredensborg Denmark
7 shared publicationsJakob Kirkegaard
Keydiagnostics (RealHorse®) Fredensborg Denmark
4 shared publications- Jakob Kirkegaard
Fredensborg Kommune
4 shared publications Maria Rosendahl Christensen
KeyVet Fredensborg Denmark
2 shared publications
Latest Publications
- Open Access
- 14 August 2026
- Published by Wiley in Equine Veterinary Journal
Validation of a handheld smartphone markerless method for quantifying thoracolumbar flexion–extension range of motion in horses at trot
Background: Back pain and poor performance in horses are difficult to assess objectively and thoracolumbar flexion‐extension range of motion (FE ROM ) is not reliably evaluated by subjective observation alone. A handheld, smartphone‐based markerless computer vision system (RealHorse®; RH) may enable objective clinical and field‐based FE ROM assessment but requires validation against an established optical motion capture reference system (Qualisys®; QS). Objectives: To compare the accuracy and precision of RH relative to QS for measuring FE ROM in horses trotting on a straight line and on a circle. Study Design: Cross‐sectional comparative validation study. Methods: Fifty‐nine horses were recorded trotting on a straight line; 23 of these were also recorded on a circle. Data were collected simultaneously using RH and QS, with a light source for manual frame‐level synchronisation. The validation videos of horses were not used to train the RH algorithm. Agreement between RH and QS was analysed separately for straight‐line and circular trot at stride and trial levels using mean signed error (MSE), mean absolute error (MAE), and Bland–Altman limits of agreement (LoA). Results: On the straight‐line, stride‐level MSE was −0.08°, MAE 0.96°, and LoA −2.49° to 2.32°. Trial‐level agreement was high, with MSE −0.13°, MAE 0.44°, and LoA −1.22° to 0.94°. On the circle, stride‐level MSE was −0.71°, MAE 1.14°, and LoA −3.17° to 1.74°. At the trial‐level, variability was moderate (MSE −0.62°, MAE 0.78°, LoA −2.18° to 0.93°). Overall agreement was lower on the circle than on the straight‐line and higher at trial‐level than at stride‐level. Conclusions: Clinically, RH may support objective clinic and field‐based monitoring of thoracolumbar flexion‐extension range of motion, especially for repeated within‐horse assessments, but decision thresholds remain to be established. Stride‐level agreement between RH and QS was influenced by expected stride‐to‐stride variability, whereas averaging across strides improved agreement at the trial‐level.
- 14 August 2026
- Published by Wiley in Equine Veterinary Journal
Open AccessValidation of a handheld smartphone markerless method for quantifying thoracolumbar flexion–extension range of motion in horses at trot
Background: Back pain and poor performance in horses are difficult to assess objectively and thoracolumbar flexion‐extension range of motion (FE ROM ) is not reliably evaluated by subjective observation alone. A handheld, smartphone‐based markerless computer vision system (RealHorse®; RH) may enable objective clinical and field‐based FE ROM assessment but requires validation against an established optical motion capture reference system (Qualisys®; QS). Objectives: To compare the accuracy and precision of RH relative to QS for measuring FE ROM in horses trotting on a straight line and on a circle. Study Design: Cross‐sectional comparative validation study. Methods: Fifty‐nine horses were recorded trotting on a straight line; 23 of these were also recorded on a circle. Data were collected simultaneously using RH and QS, with a light source for manual frame‐level synchronisation. The validation videos of horses were not used to train the RH algorithm. Agreement between RH and QS was analysed separately for straight‐line and circular trot at stride and trial levels using mean signed error (MSE), mean absolute error (MAE), and Bland–Altman limits of agreement (LoA). Results: On the straight‐line, stride‐level MSE was −0.08°, MAE 0.96°, and LoA −2.49° to 2.32°. Trial‐level agreement was high, with MSE −0.13°, MAE 0.44°, and LoA −1.22° to 0.94°. On the circle, stride‐level MSE was −0.71°, MAE 1.14°, and LoA −3.17° to 1.74°. At the trial‐level, variability was moderate (MSE −0.62°, MAE 0.78°, LoA −2.18° to 0.93°). Overall agreement was lower on the circle than on the straight‐line and higher at trial‐level than at stride‐level. Conclusions: Clinically, RH may support objective clinic and field‐based monitoring of thoracolumbar flexion‐extension range of motion, especially for repeated within‐horse assessments, but decision thresholds remain to be established. Stride‐level agreement between RH and QS was influenced by expected stride‐to‐stride variability, whereas averaging across strides improved agreement at the trial‐level.
- Open Access
- 31 January 2026
- Published by Wiley
Validation of a handheld smartphone markerless method for quantifying thoracolumbar flexion--extension range of motion in horses at trot
Background: Thoracolumbar flexion–extension range of motion (FE ROM ) in horses is difficult to assess reliably using subjective evaluation. A handheld, smartphone-based markerless computer vision system (Anonymised, RH) may enable objective field-based assessment but requires validation against an established optical motion capture reference system (Qualisys®; QS). Objectives: To compare the accuracy and precision of RH relative to QS for measuring FE ROM in horses trotting on a straight-line and on a circle. Study Design: Cross-sectional comparative validation study of a markerless computer vision algorithm. Methods: Fifty-nine horses were recorded trotting on a straight-line; 23 of these were also recorded on a circle. Data were collected simultaneously using RH and QS, with a marker light used for temporal synchronisation. Anatomical landmarks at the withers, mid-back, and croup were used to calculate the flexion–extension angle at the mid-back. FE ROM was derived at the stride-level as the difference between stride-specific maxima and minima. Agreement between RH and QS was analysed separately for straight-line and circular trot at stride- and trial-levels using mean signed error (MSE), mean absolute error (MAE), and Bland–Altman limits of agreement (LoA). Results: On the straight-line, stride-level MSE was −0.08°, MAE 0.96°, and LoA −2.49° to 2.32°. Trial-level agreement improved, with MSE −0.13°, MAE 0.44°, and LoA −1.22° to 0.94°. On the circle, stride-level MSE was −0.71°, MAE 1.14°, and LoA −3.17° to 1.74°. At the trial-level, variability was reduced (MSE −0.62°, MAE 0.78°, LoA −2.18° to 0.93°). Overall agreement was lower on the circle than on the straight-line. Conclusions: Stride-level agreement between RH and QS was influenced by expected stride-to-stride variability, particularly during circular exercise, while trial-level agreement was improved. RH enables objective assessment of FE ROM under field conditions.
- 31 January 2026
- Published by Wiley
Open AccessValidation of a handheld smartphone markerless method for quantifying thoracolumbar flexion--extension range of motion in horses at trot
Background: Thoracolumbar flexion–extension range of motion (FE ROM ) in horses is difficult to assess reliably using subjective evaluation. A handheld, smartphone-based markerless computer vision system (Anonymised, RH) may enable objective field-based assessment but requires validation against an established optical motion capture reference system (Qualisys®; QS). Objectives: To compare the accuracy and precision of RH relative to QS for measuring FE ROM in horses trotting on a straight-line and on a circle. Study Design: Cross-sectional comparative validation study of a markerless computer vision algorithm. Methods: Fifty-nine horses were recorded trotting on a straight-line; 23 of these were also recorded on a circle. Data were collected simultaneously using RH and QS, with a marker light used for temporal synchronisation. Anatomical landmarks at the withers, mid-back, and croup were used to calculate the flexion–extension angle at the mid-back. FE ROM was derived at the stride-level as the difference between stride-specific maxima and minima. Agreement between RH and QS was analysed separately for straight-line and circular trot at stride- and trial-levels using mean signed error (MSE), mean absolute error (MAE), and Bland–Altman limits of agreement (LoA). Results: On the straight-line, stride-level MSE was −0.08°, MAE 0.96°, and LoA −2.49° to 2.32°. Trial-level agreement improved, with MSE −0.13°, MAE 0.44°, and LoA −1.22° to 0.94°. On the circle, stride-level MSE was −0.71°, MAE 1.14°, and LoA −3.17° to 1.74°. At the trial-level, variability was reduced (MSE −0.62°, MAE 0.78°, LoA −2.18° to 0.93°). Overall agreement was lower on the circle than on the straight-line. Conclusions: Stride-level agreement between RH and QS was influenced by expected stride-to-stride variability, particularly during circular exercise, while trial-level agreement was improved. RH enables objective assessment of FE ROM under field conditions.
- Open Access
- 16 January 2026
- Published by Wiley in Equine Veterinary Journal
- Vol. 58 (5) , 1493-1504
Validation of a handheld smartphone markerless gait‐analysis tool using an estimated groundline in horses
Background: A handheld smartphone‐based computer vision algorithm (RealHorse® [RH]) offers accessible alternatives for equine gait analysis but requires validation against a gold‐standard three‐dimensional multicamera optical motion capture system (Qualisys® [QS]). Objectives: To evaluate the accuracy and precision of RH in measuring vertical displacement signals (VDS) at the eye, withers, back and croup in horses trotting on a straight line and on a circle. Study Design: Cross‐sectional comparative validation study of a markerless computer vision algorithm. Methods: Fifty‐nine horses were recorded while trotting on a straight line and 24 were lunged on a circle. RH detected two‐dimensional anatomical keypoints on each frame, which were used to estimate a dynamic groundline and compute ground relative VDS with stride‐based difference in maxima (Maxdiff) and minima (Mindiff). QS provided synchronous ground‐relative VDS reference values. Agreement was evaluated using mean signed error, mean absolute error and Bland–Altman analysis. Results: On the straight line ( n = 2620 strides), the pooled stride‐level MAE for Maxdiff and Mindiff was 3.8 mm. Keypoint‐specific errors were 5.1 mm (eye), 4.3 mm (withers) and 3.0 mm (croup). On the circle ( n = 2419 strides), pooled stride‐level error increased to 5.5 mm. Trial‐level analysis ( n = 58 trials) showed much lower errors: 1.4 mm for both eye and withers and 1.1 mm for croup. On the circle ( n = 24 trials), trial‐level errors were higher, with 2.8 mm for the eye, 1.8 mm for the withers and 3.3 mm for the croup. The back keypoint consistently showed the lowest errors across both stride and trial levels. Main Limitations: RH measurements of the croup Mindiff during circling resulted in higher values and showed the largest error. Conclusions: RH measured vertical displacement of all keypoints with high accuracy and precision (trial‐level MAE 1.1–1.4 mm straight, 1.8–3.3 mm circle), supporting its use for equine gait analysis.
- 16 January 2026
- Published by Wiley in Equine Veterinary Journal
- Vol. 58 (5) , 1493-1504
Open AccessValidation of a handheld smartphone markerless gait‐analysis tool using an estimated groundline in horses
Background: A handheld smartphone‐based computer vision algorithm (RealHorse® [RH]) offers accessible alternatives for equine gait analysis but requires validation against a gold‐standard three‐dimensional multicamera optical motion capture system (Qualisys® [QS]). Objectives: To evaluate the accuracy and precision of RH in measuring vertical displacement signals (VDS) at the eye, withers, back and croup in horses trotting on a straight line and on a circle. Study Design: Cross‐sectional comparative validation study of a markerless computer vision algorithm. Methods: Fifty‐nine horses were recorded while trotting on a straight line and 24 were lunged on a circle. RH detected two‐dimensional anatomical keypoints on each frame, which were used to estimate a dynamic groundline and compute ground relative VDS with stride‐based difference in maxima (Maxdiff) and minima (Mindiff). QS provided synchronous ground‐relative VDS reference values. Agreement was evaluated using mean signed error, mean absolute error and Bland–Altman analysis. Results: On the straight line ( n = 2620 strides), the pooled stride‐level MAE for Maxdiff and Mindiff was 3.8 mm. Keypoint‐specific errors were 5.1 mm (eye), 4.3 mm (withers) and 3.0 mm (croup). On the circle ( n = 2419 strides), pooled stride‐level error increased to 5.5 mm. Trial‐level analysis ( n = 58 trials) showed much lower errors: 1.4 mm for both eye and withers and 1.1 mm for croup. On the circle ( n = 24 trials), trial‐level errors were higher, with 2.8 mm for the eye, 1.8 mm for the withers and 3.3 mm for the croup. The back keypoint consistently showed the lowest errors across both stride and trial levels. Main Limitations: RH measurements of the croup Mindiff during circling resulted in higher values and showed the largest error. Conclusions: RH measured vertical displacement of all keypoints with high accuracy and precision (trial‐level MAE 1.1–1.4 mm straight, 1.8–3.3 mm circle), supporting its use for equine gait analysis.
- Open Access
- 30 December 2025
- Published by Wiley in Veterinary Medicine and Science
- Vol. 12 (1) , e70739
Evaluating the Accuracy of a Vision‐Based Algorithm for Groundline Estimation in Trotting Horses Using Multiple Camera Angles
Background: Equine lameness diagnosis largely relies on subjective visual assessments, which can be biased. Although marker‐based methods, force plates and inertial measurement units (IMUs) provide objective measurements, they require specialized setups. Vision‐based algorithms offer a portable, markerless alternative, but their accuracy needs thorough testing. Objectives: To evaluate a custom vision‐based algorithm for estimating the groundline across multiple camera angles, including handheld use in horses trotting on a treadmill. Study design: Experimental comparative study. Methods: Eight Standardbred trotter mares were recorded trotting on a high‐speed treadmill using seven iPhones positioned at various heights and angles, including a handheld device. A trained deep neural network algorithm placed 2D keypoints on each video frame. Vertical Displacement Signals (VDS) for the eye, withers and croup (tuber sacrale) were computed relative to either an algorithm‐estimated or a fixed treadmill groundline. Maximum (Maxdiff) and minimum (Mindiff) stride values were compared using Bland–Altman analysis, scatter plots and histograms. The effect of handheld use on variability and accuracy was assessed by comparing results from a handheld camera to those from a static camera. Results: Groundline estimation closely matched the fixed reference, exhibiting near‐zero mean angle error and low mean average error (MAE = 0.45°; n = 242.192). Maxdiff and Mindiff stride‐level ( n = 36.981) MAE were 0.5 mm, with clinically acceptable additional variability introduced by handheld use at the trial level (Maxdiff and Mindiff MAE < 1.8 mm; n = 357). Main limitations: Treadmill‐based data and a single breed/coat colour may limit generalizability to other settings. Conclusions: The vision‐based algorithm accurately estimates the groundline and stride VDS parameters from various camera setups, including handheld. Further validation in diverse environments and against other objective gait analysis systems is recommended.
- 30 December 2025
- Published by Wiley in Veterinary Medicine and Science
- Vol. 12 (1) , e70739
Open AccessEvaluating the Accuracy of a Vision‐Based Algorithm for Groundline Estimation in Trotting Horses Using Multiple Camera Angles
Background: Equine lameness diagnosis largely relies on subjective visual assessments, which can be biased. Although marker‐based methods, force plates and inertial measurement units (IMUs) provide objective measurements, they require specialized setups. Vision‐based algorithms offer a portable, markerless alternative, but their accuracy needs thorough testing. Objectives: To evaluate a custom vision‐based algorithm for estimating the groundline across multiple camera angles, including handheld use in horses trotting on a treadmill. Study design: Experimental comparative study. Methods: Eight Standardbred trotter mares were recorded trotting on a high‐speed treadmill using seven iPhones positioned at various heights and angles, including a handheld device. A trained deep neural network algorithm placed 2D keypoints on each video frame. Vertical Displacement Signals (VDS) for the eye, withers and croup (tuber sacrale) were computed relative to either an algorithm‐estimated or a fixed treadmill groundline. Maximum (Maxdiff) and minimum (Mindiff) stride values were compared using Bland–Altman analysis, scatter plots and histograms. The effect of handheld use on variability and accuracy was assessed by comparing results from a handheld camera to those from a static camera. Results: Groundline estimation closely matched the fixed reference, exhibiting near‐zero mean angle error and low mean average error (MAE = 0.45°; n = 242.192). Maxdiff and Mindiff stride‐level ( n = 36.981) MAE were 0.5 mm, with clinically acceptable additional variability introduced by handheld use at the trial level (Maxdiff and Mindiff MAE < 1.8 mm; n = 357). Main limitations: Treadmill‐based data and a single breed/coat colour may limit generalizability to other settings. Conclusions: The vision‐based algorithm accurately estimates the groundline and stride VDS parameters from various camera setups, including handheld. Further validation in diverse environments and against other objective gait analysis systems is recommended.
- Open Access
- 4 November 2025
- Published by Wiley in Equine Veterinary Journal
- Vol. 58 (5) , 1467-1481
Reliability, agreement and variability of a markerless computer vision algorithm for equine gait analysis under field conditions
Background: Computer vision‐based algorithms offer accessible alternatives for equine gait analysis but require thorough assessment under diverse conditions. Objectives: To evaluate a proprietary vision‐based algorithm's reliability in measuring vertical displacement signals (VDS) at the eye, withers and croup, alongside groundline estimation, for horses trotting on straight lines and circles under field conditions. Study Design: Cross‐sectional comparative study evaluating agreement, variability and reliability of a markerless computer vision algorithm. Methods: We obtained 67 handheld iPhone recordings from 37 horses. A vision‐based algorithm and independent manual annotation produced 2D anatomical keypoints on all frames of the recordings, which were processed to estimate a groundline and compute VDS and stride‐based maxima (Maxdiff) and minima (Mindiff) vertical differences. Mean signed error (MSE), mean absolute error (MAE) and Bland–Altman plots were used to compare detected and annotated data. Results: The frame level vertical keypoint accuracy was 4.5 mm (eye), 5.5 mm (croup) and 11.8 mm (withers), and the manual annotation error was averaged at 2.7 mm. At the stride level ( n = 1556), the overall mean absolute errors (MAEs) for both Maxdiff and Mindiff were 4.3 mm. The eye keypoint exhibited the lowest errors (2.9 mm Maxdiff, 3.0 mm Mindiff), while the withers error was 5.5 mm for both Maxdiff and Mindiff, and the croup showed 4.3 mm (Maxdiff) and 4.4 mm (Mindiff). Trial‐level ( n = 67) analysis, with below optimal number of strides per trial in this study, revealed lower overall absolute differences (Eye: 2.3 mm, Withers: 3.7 mm, Croup: 2.7 mm), indicating consistent performance across multiple strides. Subjective lameness scoring aligned with objective measures with some variation. Main Limitations: Groundline estimation accuracy was stress‐tested on treadmill data in another study. Further clinical comparison with established gait analysis systems is recommended. Conclusions: The algorithm robustly measured vertical displacements under varied conditions.
- 4 November 2025
- Published by Wiley in Equine Veterinary Journal
- Vol. 58 (5) , 1467-1481
Open AccessReliability, agreement and variability of a markerless computer vision algorithm for equine gait analysis under field conditions
Background: Computer vision‐based algorithms offer accessible alternatives for equine gait analysis but require thorough assessment under diverse conditions. Objectives: To evaluate a proprietary vision‐based algorithm's reliability in measuring vertical displacement signals (VDS) at the eye, withers and croup, alongside groundline estimation, for horses trotting on straight lines and circles under field conditions. Study Design: Cross‐sectional comparative study evaluating agreement, variability and reliability of a markerless computer vision algorithm. Methods: We obtained 67 handheld iPhone recordings from 37 horses. A vision‐based algorithm and independent manual annotation produced 2D anatomical keypoints on all frames of the recordings, which were processed to estimate a groundline and compute VDS and stride‐based maxima (Maxdiff) and minima (Mindiff) vertical differences. Mean signed error (MSE), mean absolute error (MAE) and Bland–Altman plots were used to compare detected and annotated data. Results: The frame level vertical keypoint accuracy was 4.5 mm (eye), 5.5 mm (croup) and 11.8 mm (withers), and the manual annotation error was averaged at 2.7 mm. At the stride level ( n = 1556), the overall mean absolute errors (MAEs) for both Maxdiff and Mindiff were 4.3 mm. The eye keypoint exhibited the lowest errors (2.9 mm Maxdiff, 3.0 mm Mindiff), while the withers error was 5.5 mm for both Maxdiff and Mindiff, and the croup showed 4.3 mm (Maxdiff) and 4.4 mm (Mindiff). Trial‐level ( n = 67) analysis, with below optimal number of strides per trial in this study, revealed lower overall absolute differences (Eye: 2.3 mm, Withers: 3.7 mm, Croup: 2.7 mm), indicating consistent performance across multiple strides. Subjective lameness scoring aligned with objective measures with some variation. Main Limitations: Groundline estimation accuracy was stress‐tested on treadmill data in another study. Further clinical comparison with established gait analysis systems is recommended. Conclusions: The algorithm robustly measured vertical displacements under varied conditions.
- Open Access
- 15 October 2025
- Published by Wiley
Validation of a handheld smartphone-based markerless computer vision algorithm with estimated groundline for equine gait analysis
Background: A handheld smartphone-based computer vision algorithm (Anonymised (RH)) offers accessible alternatives for equine gait analysis but requires validation against a gold-standard multicamera optical motion capture system (Qualisys® (QS)). Objectives: To evaluate the accuracy and precision of RH in measuring vertical displacement signals (VDS) at the eye, withers, back, and croup in horses trotting on a straight line and on a circle. Study Design: Cross-sectional comparative validation study of a markerless computer vision algorithm. Methods: Fifty-nine horses were recorded while trotting on a straight line and 24 were lunged on a circle. RH detected two-dimensional anatomical keypoints on each frame, which were used to estimate a dynamic groundline and compute ground relative VDS with stride-based difference in maxima (Maxdiff) and minima (Mindiff). QS provided synchronous true VDS reference values. Agreement was evaluated using mean signed error (MSE), mean absolute error (MAE), and Bland-Altman analysis. Results: On the straight line (n = 2620 strides), the pooled stride-level MAE for Maxdiff and Mindiff was 3.8 mm. Keypoint-specific errors were 5.1 mm (eye), 4.3 mm (withers), and 3.0 mm (croup). On the circle (n = 2419 strides), pooled stride-level error increased to 5.5 mm. Trial-level analysis (n = 58 straight trials) showed much lower errors: 1.4 mm for both eye and withers and 1.1 mm for croup. On the circle (n = 24 trials), trial-level errors were higher, with 2.8 mm for the eye, 1.8 mm for the withers, and 3.3 mm for the croup. The back keypoint consistently showed the lowest errors across both stride- and trial-levels. Main Limitations: Croup Mindiff detection during circle trials had the highest error and bias. Conclusions: RH measured vertical displacement of the eye, withers, back, and croup with higher accuracy and precision than any previously reported markerless systems, supporting its use for equine gait analysis.
- 15 October 2025
- Published by Wiley
Open AccessValidation of a handheld smartphone-based markerless computer vision algorithm with estimated groundline for equine gait analysis
Background: A handheld smartphone-based computer vision algorithm (Anonymised (RH)) offers accessible alternatives for equine gait analysis but requires validation against a gold-standard multicamera optical motion capture system (Qualisys® (QS)). Objectives: To evaluate the accuracy and precision of RH in measuring vertical displacement signals (VDS) at the eye, withers, back, and croup in horses trotting on a straight line and on a circle. Study Design: Cross-sectional comparative validation study of a markerless computer vision algorithm. Methods: Fifty-nine horses were recorded while trotting on a straight line and 24 were lunged on a circle. RH detected two-dimensional anatomical keypoints on each frame, which were used to estimate a dynamic groundline and compute ground relative VDS with stride-based difference in maxima (Maxdiff) and minima (Mindiff). QS provided synchronous true VDS reference values. Agreement was evaluated using mean signed error (MSE), mean absolute error (MAE), and Bland-Altman analysis. Results: On the straight line (n = 2620 strides), the pooled stride-level MAE for Maxdiff and Mindiff was 3.8 mm. Keypoint-specific errors were 5.1 mm (eye), 4.3 mm (withers), and 3.0 mm (croup). On the circle (n = 2419 strides), pooled stride-level error increased to 5.5 mm. Trial-level analysis (n = 58 straight trials) showed much lower errors: 1.4 mm for both eye and withers and 1.1 mm for croup. On the circle (n = 24 trials), trial-level errors were higher, with 2.8 mm for the eye, 1.8 mm for the withers, and 3.3 mm for the croup. The back keypoint consistently showed the lowest errors across both stride- and trial-levels. Main Limitations: Croup Mindiff detection during circle trials had the highest error and bias. Conclusions: RH measured vertical displacement of the eye, withers, back, and croup with higher accuracy and precision than any previously reported markerless systems, supporting its use for equine gait analysis.
- Open Access
- 13 February 2025
- Published by Wiley
Accuracy of a Markerless Computer Vision-Based Algorithm for Equine Gait Analysis: Stride- and Trial-Level Comparisons of Gait Asymmetry Metrics from Manually Annotated Versus Algorithm-Detected Keypoints
Background: Objective gait analysis is valuable in diagnosing and managing equine lameness. Computer vision-based algorithms offer accessible alternatives for equine gait analysis but require thorough accuracy and precision assessment under diverse conditions. Objectives: To evaluate a proprietary vision-based algorithm’s accuracy and precision in measuring vertical displacement signals (VDS) at the eye, withers, and croup, alongside groundline estimation, for horses trotting on straight lines and circles under field conditions. Study Design: Experimental comparative study against manually annotated references. Methods: We obtained 67 recordings from 37 horses. A vision-based algorithm and independently manual annotation produced 2D anatomical keypoints on all frames of the recordings, which were processed to estimate a groundline and compute VDS and stride-based maxima (Maxdiff) and minima (Mindiff) vertical differences. No stride exclusions were applied. Mean signed error (MSE), mean absolute error (MAE) and Bland-Altman plots were used to compare detected and annotated data. Results: At the stride level (n = 1556), the overall mean absolute errors (MAEs) for both Maxdiff and Mindiff were 4.3 mm. The eye keypoint exhibited the lowest errors (2.9 mm Maxdiff, 3.0 mm Mindiff), while the withers error was 5.5 mm for both Maxdiff and Mindiff, and the croup showed 4.3 mm (Maxdiff) and 4.4 mm (Mindiff). Trial-level (n=67) analysis, with below optimal number of strides per trial in this study, revealed lower overall absolute differences (Eye: 2.3 mm, Withers: 3.7 mm, Croup: 2.7 mm) indicating consistent performance across multiple strides. Eye keypoint accuracy was higher on circles than on straight lines, whereas the withers and croup performed comparably under both conditions. Main Limitations: Groundline estimation accuracy was stress-tested on treadmill data in another study. Further clinical comparison with established gait analysis systems is recommended. Conclusions: The algorithm robustly measured vertical displacements under varied conditions, supporting a clinical and field-based utility.
- 13 February 2025
- Published by Wiley
Open AccessAccuracy of a Markerless Computer Vision-Based Algorithm for Equine Gait Analysis: Stride- and Trial-Level Comparisons of Gait Asymmetry Metrics from Manually Annotated Versus Algorithm-Detected Keypoints
Background: Objective gait analysis is valuable in diagnosing and managing equine lameness. Computer vision-based algorithms offer accessible alternatives for equine gait analysis but require thorough accuracy and precision assessment under diverse conditions. Objectives: To evaluate a proprietary vision-based algorithm’s accuracy and precision in measuring vertical displacement signals (VDS) at the eye, withers, and croup, alongside groundline estimation, for horses trotting on straight lines and circles under field conditions. Study Design: Experimental comparative study against manually annotated references. Methods: We obtained 67 recordings from 37 horses. A vision-based algorithm and independently manual annotation produced 2D anatomical keypoints on all frames of the recordings, which were processed to estimate a groundline and compute VDS and stride-based maxima (Maxdiff) and minima (Mindiff) vertical differences. No stride exclusions were applied. Mean signed error (MSE), mean absolute error (MAE) and Bland-Altman plots were used to compare detected and annotated data. Results: At the stride level (n = 1556), the overall mean absolute errors (MAEs) for both Maxdiff and Mindiff were 4.3 mm. The eye keypoint exhibited the lowest errors (2.9 mm Maxdiff, 3.0 mm Mindiff), while the withers error was 5.5 mm for both Maxdiff and Mindiff, and the croup showed 4.3 mm (Maxdiff) and 4.4 mm (Mindiff). Trial-level (n=67) analysis, with below optimal number of strides per trial in this study, revealed lower overall absolute differences (Eye: 2.3 mm, Withers: 3.7 mm, Croup: 2.7 mm) indicating consistent performance across multiple strides. Eye keypoint accuracy was higher on circles than on straight lines, whereas the withers and croup performed comparably under both conditions. Main Limitations: Groundline estimation accuracy was stress-tested on treadmill data in another study. Further clinical comparison with established gait analysis systems is recommended. Conclusions: The algorithm robustly measured vertical displacements under varied conditions, supporting a clinical and field-based utility.
- Open Access
- 13 February 2025
- Published by Wiley
Evaluating the accuracy of a Vision-Based Algorithm for Groundline Estimation in Trotting Horses Using Multiple Camera Angles
Background: Equine lameness diagnosis largely relies on subjective visual assessments, which can be biased. Although marker-based methods, force plates, and inertial measurement units (IMUs) provide objective measurements, they require specialized setups. Vision-based algorithms offer a portable, markerless alternative, but their accuracy needs thorough testing. Objectives: To evaluate a custom vision-based algorithm for estimating the groundline across multiple camera angles, including handheld use in horses trotting on a treadmill. Study design: Experimental comparative study. Methods: Eight Standardbred trotter mares were recorded trotting on a high-speed treadmill using seven iPhones positioned at various heights and angles, including a handheld device. A trained deep neural network algorithm placed 2D keypoints on each video frame. Vertical Displacement Signals (VDS) for the eye, withers, and croup were computed relative to either an algorithm-estimated or a fixed treadmill groundline. Maximum (Maxdiff) and minimum (Mindiff) stride values were compared using Bland-Altman analysis, scatter plots, and histograms. The effect of handheld use on variability and accuracy was assessed by comparing results from a handheld camera to those from a static camera. Results: Groundline estimation closely matched the fixed reference, exhibiting near-zero mean angle error and low mean average error (MAE = 0.45°; n = 242.192). Maxdiff and Mindiff stride-level (n = 36.981) MAE were 0.5 mm, with clinically acceptable additional variability introduced by handheld use at the trial level (Maxdiff and Mindiff MAE < 1.8 mm; n = 357). Main limitations: Treadmill-based data and a single breed/coat colour may limit generalizability to other settings. Conclusions: The vision-based algorithm accurately estimates the groundline and stride VDS parameters from various camera setups, including handheld. Further validation in diverse environments and against other objective gait analysis systems is recommended.
- 13 February 2025
- Published by Wiley
Open AccessEvaluating the accuracy of a Vision-Based Algorithm for Groundline Estimation in Trotting Horses Using Multiple Camera Angles
Background: Equine lameness diagnosis largely relies on subjective visual assessments, which can be biased. Although marker-based methods, force plates, and inertial measurement units (IMUs) provide objective measurements, they require specialized setups. Vision-based algorithms offer a portable, markerless alternative, but their accuracy needs thorough testing. Objectives: To evaluate a custom vision-based algorithm for estimating the groundline across multiple camera angles, including handheld use in horses trotting on a treadmill. Study design: Experimental comparative study. Methods: Eight Standardbred trotter mares were recorded trotting on a high-speed treadmill using seven iPhones positioned at various heights and angles, including a handheld device. A trained deep neural network algorithm placed 2D keypoints on each video frame. Vertical Displacement Signals (VDS) for the eye, withers, and croup were computed relative to either an algorithm-estimated or a fixed treadmill groundline. Maximum (Maxdiff) and minimum (Mindiff) stride values were compared using Bland-Altman analysis, scatter plots, and histograms. The effect of handheld use on variability and accuracy was assessed by comparing results from a handheld camera to those from a static camera. Results: Groundline estimation closely matched the fixed reference, exhibiting near-zero mean angle error and low mean average error (MAE = 0.45°; n = 242.192). Maxdiff and Mindiff stride-level (n = 36.981) MAE were 0.5 mm, with clinically acceptable additional variability introduced by handheld use at the trial level (Maxdiff and Mindiff MAE < 1.8 mm; n = 357). Main limitations: Treadmill-based data and a single breed/coat colour may limit generalizability to other settings. Conclusions: The vision-based algorithm accurately estimates the groundline and stride VDS parameters from various camera setups, including handheld. Further validation in diverse environments and against other objective gait analysis systems is recommended.
- Open Access
- 3 February 2025
- Published by Wiley in Equine Veterinary Education
- Vol. 37 (11)
Mesenteric rents in the ascending mesocolon as a cause of colic — A retrospective case series
Summary: The ventral and dorsal components of the ascending colon are adjoined by the ascending mesocolon, and few case reports have described congenital or acquired malformations of this structure. This case series reports the occurrence of large mesenteric rents of the ascending mesocolon (Hernia mesocolica coli ascendentis) in six adult horses diagnosed during exploratory laparotomy. Based on the history of the patients, the rents were most likely acquired. The rents were mainly located directly adjacent to the left dorsal colon, and without affecting the intestinal blood supply. The size of the defect varied between 20 and 80 cm, and in 5/6 cases it was a subacute or chronic rupture with rounded edges. Two different types of intestinal displacements in relation to the rent were found, with either a localised torsion of the dorsal colon or incarceration of the pelvic flexure in the rent. In all cases, the intestine could be repositioned, and the rent was sutured. Despite some minor postoperative complications, the short‐ and long‐term outcomes were excellent. It was hypothesised that trauma elicited by an intrauterine foal or recurrent colon displacements may have been the cause of the rent in some of the cases.
- 3 February 2025
- Published by Wiley in Equine Veterinary Education
- Vol. 37 (11)
Open AccessMesenteric rents in the ascending mesocolon as a cause of colic — A retrospective case series
Summary: The ventral and dorsal components of the ascending colon are adjoined by the ascending mesocolon, and few case reports have described congenital or acquired malformations of this structure. This case series reports the occurrence of large mesenteric rents of the ascending mesocolon (Hernia mesocolica coli ascendentis) in six adult horses diagnosed during exploratory laparotomy. Based on the history of the patients, the rents were most likely acquired. The rents were mainly located directly adjacent to the left dorsal colon, and without affecting the intestinal blood supply. The size of the defect varied between 20 and 80 cm, and in 5/6 cases it was a subacute or chronic rupture with rounded edges. Two different types of intestinal displacements in relation to the rent were found, with either a localised torsion of the dorsal colon or incarceration of the pelvic flexure in the rent. In all cases, the intestine could be repositioned, and the rent was sutured. Despite some minor postoperative complications, the short‐ and long‐term outcomes were excellent. It was hypothesised that trauma elicited by an intrauterine foal or recurrent colon displacements may have been the cause of the rent in some of the cases.
- Open Access
- 1 September 2024
- Published by Wiley
Mesenteric rents in the ascending mesocolon as cause of colic -- a retrospective case series
The ventral and dorsal components of the ascending colon are adjoined by the ascending mesocolon, and few case reports have described congenital or acquired malformations of this structure. This case series reports the occurrence of large mesenteric rents of the ascending mesocolon ( Hernia mesocolica coli ascendentis ) in 6 adult horses diagnosed during exploratory laparotomy. Based on the history of the patients, the rents were most likely acquired. The rents were mainly located directly adjacent to the left dorsal colon, and without affecting the intestinal blood supply. The size of the defect varied between 20 and 80 cm, and in 5/6 cases it was a subacute or chronic rupture with rounded edges. Two different types of intestinal displacements in relation to the rent were found, with either a localized torsion of the dorsal colon or herniation of the pelvic flexure through the rent. In all cases, the intestine could be repositioned, and the rent was sutured. Despite some minor postoperative complications, the short- and long-term outcome was excellent. It was hypothesised that recurrent colon displacements or trauma elicited by an intrauterine foal may have been the cause of the rent in some of the cases.
- 1 September 2024
- Published by Wiley
Open AccessMesenteric rents in the ascending mesocolon as cause of colic -- a retrospective case series
The ventral and dorsal components of the ascending colon are adjoined by the ascending mesocolon, and few case reports have described congenital or acquired malformations of this structure. This case series reports the occurrence of large mesenteric rents of the ascending mesocolon ( Hernia mesocolica coli ascendentis ) in 6 adult horses diagnosed during exploratory laparotomy. Based on the history of the patients, the rents were most likely acquired. The rents were mainly located directly adjacent to the left dorsal colon, and without affecting the intestinal blood supply. The size of the defect varied between 20 and 80 cm, and in 5/6 cases it was a subacute or chronic rupture with rounded edges. Two different types of intestinal displacements in relation to the rent were found, with either a localized torsion of the dorsal colon or herniation of the pelvic flexure through the rent. In all cases, the intestine could be repositioned, and the rent was sutured. Despite some minor postoperative complications, the short- and long-term outcome was excellent. It was hypothesised that recurrent colon displacements or trauma elicited by an intrauterine foal may have been the cause of the rent in some of the cases.