Vertical back movement of cows during locomotion: detecting lameness with a simple image processing technique.

Lameness affects the sustainability of dairy farms due to the impact on animal health and production, which culminates in ethical and economic implications. Despite efforts to reduce lameness in the dairy industry, recent studies reflect that the global average prevalence still ranges from 14% to 36%. For effective management, early detection and timely treatment are crucial to mitigating the impact of lameness.

Whereas visual locomotion scoring by trained observers is the most widely used diagnostic technique for lameness, lame cows experience pain which they instinctively tend not to show, making it difficult to detect the disease before the onset of clinical signs. Also, the visual locomotion scoring method has two limitations. Firstly, detecting lame cows with minimum error in the earliest stage requires strict follow-up and continuity, which makes it a time-consuming and difficult process. In intensive dairy cattle farming, characterized by limited labour and increasingly large herd sizes, this approach becomes impractical. Furthermore, its time-intensive nature might result in an underestimation of lame cows. Secondly, the traditional method is subjective as lameness scores are highly dependent on the observers’ competence. This subjectivity has high potential for inaccuracy, especially in the early detection phases, and therefore may result in delayed treatment. Thus, methods of automatic lameness scoring are required. Research paper I cited below proposes a simple image processing technique for automatic lameness detection under farm conditions.

Apart from visual scoring, diverse efforts are being explored to develop more sensitive and objective assessments for lameness diagnosis. Several studies have focused on identifying biomarkers or sensitive diagnostic markers of lameness. Examples of blood biomarkers used as a marker of stress or acute pain in dairy cows include cortisol, nociceptive neuropeptides (i.e., norepinephrine, β-hydroxybutyrate, substance P and beta-endorphin) and acute-phase proteins (APPs) such as haptoglobin and serum amyloid A. There are several articles reporting alterations in these markers and metabolites during and after lameness diagnosis, and for elucidating the pain experienced by lame cows. Nevertheless, their relevance in detecting cows susceptible to lameness and specific claw lesions, and efficacy in assessing recovery after treatment, are not fully understood. Thus, the study reported in research paper 2 cited below, reviewed potential biomarkers for lameness reported in the literature, particularly their relevance in lameness diagnosis, identifying cows at risk of becoming lame, predicting specific claw lesions and monitoring recovery or lesion progression after treatment.

In the automatic lameness detection study (research paper 1), 75 cows were selected from a dairy farm and visually assessed for a reference/real lameness score (RLS) as they left the milking parlour, while simultaneously being video-captured. The method employed a designated walking path and video recordings processed through image analysis to derive a new computerized automatic lameness score (ALDS) based on calculated factors from back arch posture. The proposed automatic lameness detection system was calibrated using 12 cows, and the remaining 63 were used to evaluate the diagnostic characteristics of the ALDS. The agreement and correlation between ALDS and RLS were investigated.

ALDS demonstrated high diagnostic accuracy with 100% sensitivity and specificity and was found to be 100% accurate with a perfect agreement (ρc = 1) and strong correlation (r = 1, P < 0.001) for lameness detection in binary scores (lame/non-lame). Moreover, the ALDS had a strong agreement (ρc = 0.885) and was highly correlated (r = 0.840; 0.796–1.000 95% confidence interval, P < 0.001) with RLS in ordinal scores (lameness severity; LS1 to LS5). The results suggest that the proposed method has the potential to compete well with vision-based lameness detection methods in dairy cows under farm conditions.  

In the second study (research paper 2), a comprehensive literature search was performed in three databases: PubMed, Google Scholar and ScienceDirect to retrieve relevant articles published between 2010 and 2022. A total of 31 articles fulfilling the inclusion criteria were analysed. The categories of potential markers for lameness reported in the literature included acute phase proteins (APPs), nociceptive neuropeptides, stress hormones, proteomes, inflammatory cytokines and metabolites in serum, urine and milk. Cortisol, APPs (serum amyloid A and haptoglobin) and serum, urinary and milk metabolites were the most studied biomarkers.

The review showed that whereas APPs, nociceptive neuropeptides and blood cortisol analyses assisted in elucidating the pain and stress experienced by lame cows during diagnosis and after treatment, evidence-based data are lacking to support their use in identifying susceptible animals. Metabolomics techniques revealed promising results in assessing metabolic alterations occurring before, during and after lameness onset. Several metabolites in serum, urinary and milk were reported that could be used to identify susceptible cows even before the onset of clinical signs. Nevertheless, further research is required employing metabolomic techniques to advance our knowledge of claw horn lesions and the discovery of novel biomarkers for identifying susceptible cows. The applicability of these biomarkers is challenging, particularly in the field, as they often require invasive procedures.