Deep learning based landmark detection for measuring hock and knee angles in sows.

This paper presents a visual deep learning approach to automatically determine hock and knee angles from sow images. Lameness is the second largest reason for culling of breeding herd females and relies on human observers to provide visual scoring for detection which can be slow, subjective, and inconsistent. A deep learning model classified and detected ten and two key body landmarks from the side and rear profile images, respectively (mean average precision = 0.

Quantitation of Gait and Stance Alterations Due to Monosodium Iodoacetate-induced Knee Osteoarthritis in Yucatan Swine.

Knee osteoarthritis is one of the most common causes of chronic pain worldwide, and several animal models have been developed to investigate disease mechanisms and treatments to combat associated morbidities. Here we describe a novel method for assessment of locomotor pain behavior in Yucatan swine. We used monosodium iodoacetate (MIA) to induce osteoarthritis in the hindlimb knee, and then conducted live observation, quantitative gait analysis, and quantitative weight-bearing stance analysis.

Objective evaluation of female feet and leg joint conformation at time of selection and post first parity in swine1.

Feet and legs of replacement females were objectively evaluated at selection, i.e., approximately 150 d of age (n = 319) and post first parity, i.