A two-stage approach using YOLO for automated assessment of digital dermatitis within Dairy Cattle

Shahbaz, Ajmal; Zhang, Wenhao; Smith, Melvyn

Abstract

Digital dermatitis stands as a primary cause of lameness in dairy cows, significantly impacting various facets of productivity. This paper proposes an innovative two-stage vision system aimed at early detection of digital dermatitis (DD) lesions, ultimately preventing lameness developing in dairy cows. The first stage involves the detection of dairy cow hooves, achieved through a YOLO-based hoof detector. The detected hooves undergo a meticulous filtering process to gather high-quality data, which are free from motion blur and severe occlusions by water and mud. These selected hooves are then cropped from the original images to train a lesion detector for the second stage. The lesion detector serves to distinguish between six different DD lesion stages on the cropped sole of the hooves: lesion, M1, M2, M3, M4, and M4.1, in alignment with the gold-standard M- (Mortellaro) stages scoring system. Validated on our dataset collected from four different farms, the hoof detector has achieved precision rates above 90%, while the lesion detector maintains precision rates surpassing 70%. In addressing the critical issue of lameness, this two-stage vision system not only showcases impressive precision in hoof and lesion detection but also highlights the potential for facilitating early intervention and prevention of hoof diseases in dairy cattle. The robust performance of the detectors lays the groundwork for further advancements in proactive veterinary care within the dairy industry.

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 2024 IEEE 22nd World Symposium on Applied Machine Intelligence and Informatics (SAMI)
• Start Date: Jan 25, 2024
• End Date: Jan 27, 2024
• Acceptance Date: Dec 1, 2023
• Online Publication Date: Feb 14, 2024
• Publication Date: Feb 14, 2024
• Deposit Date: Mar 21, 2025
• Publicly Available Date: Mar 21, 2025
• Peer Reviewed: Peer Reviewed
• Series ISSN: 2767-9438
• Book Title: 2024 IEEE 22nd World Symposium on Applied Machine Intelligence and Informatics (SAMI)
• ISBN: 9798350317213
• DOI: https://doi.org/10.1109/sami60510.2024.10432745
• Public URL: https://uwe-repository.worktribe.com/output/11754771