Computer analysis of thermal back images shine light on saddle’s influence

Share
Samples of thermographic images of the thoracolumbar region of the same horse taken on two consecutive days: A shows the before image and B the after result under a low bodyweight rider. C shows the before image and D the result after being ridden by the higher bodyweight rider. Images: https://doi.org/10.1186/s12917-021-02803-2

Computer-driven analysis of thermographic images of a horse’s back shows promise in assessing what is going on beneath the saddle, the findings of fresh research suggest.

The backs of horses are particularly exposed to overload and injuries because of the direct contact with the saddle and the influence of the rider’s body weight.

The maximal load for a horse’s back during riding has been suggested not to exceed 20% of the animal’s body weight.

The prevalence of back problems in riding horses prompted the use of thermography of the thoracolumbar region — the area of the back affected by the saddle.

However, the analysis methods used so far do not distinguish loaded horses with body weights varying between 10% and 20%.

Malgorzata Masko and her colleagues at the Warsaw University of Life Sciences in Poland, writing in the journal BMV Veterinary Research, described their study involving six Polish warmbloods, all owned by the university.

The superficial body temperature of the saddle region was imaged using a non-contact thermographic camera before and after riding using riders with a low body weight (10% of the animal’s weight) and a higher weight (15% of the animal’s weight).

The six riders used in the study were all women with four to five years of riding experience who were considered of comparable skills.

During the experiment, each horse was worked by each rider for about 50 minutes, which allowed 36 combinations.

Images were analyzed using six methods, five of which had already been described in previous studies, and a sixth computer-aided one involving a novel approach based on what is known as Gray Level Co-Occurrence Matrix (GLCM) and Gray Level Run Length Matrix (GLRLM).

The previously used methods included looking for thermographically portrayed “hot spots” or “cold regions”, analyzing the range of temperatures for the back measured along three horizontal lines, and comparing the average temperatures measured in three areas.

However, as the authors noted, since the thermogram is an image, computer-aided analysis can be used — in this case GLCM and GLRLM.

The temperatures of each horse’s thoracolumbar region were predictably higher after the training rides.

However, none of the first five analysis methods described in previously published research could distinguish between the rider’s body weight. But effort-dependent differences were noted for six features of GLCM and GLRLM analysis, with the values differing between the low body weight and high body weight groups.

The study team said the GLCM and GLRLM analyses allowed the differentiation of horses subjected to a load of 10% and 15% of their body weights while horseback riding, in contrast to the previously used analysis methods.

The new analysis methods seem to be promising tools in considering the quantitative assessment of thermographic images of horses’ thoracolumbar region, they said.

The study team comprised Masko, Malgorzata Domino, Tomasz Jasinski, Lukasz Zdrojkowski and Zdzislaw Gajewski, all with the Warsaw University of Life Sciences; and Marta Borowska, with the Białystok University of Technology.

Masko, M., Borowska, M., Domino, M. et al. A novel approach to thermographic images analysis of equine thoracolumbar region: the effect of effort and rider’s body weight on structural image complexity. BMC Vet Res 17, 99 (2021). https://doi.org/10.1186/s12917-021-02803-2

The study, published under a Creative Commons License, can be read here

 

Leave a Reply

Your email address will not be published. Required fields are marked *