Determining the Presence and Size of Shoulder Lesions in Sows Using Computer Vision

Authors

Shubham Bery, University of Nebraska-LincolnFollow
Tami M. Brown-Brandl, USDA-ARS Meat Animal Research CenterFollow
Bradley T. Jones, USDA-ARS Meat Animal Research Center
Gary A. Rohrer, USDA-ARS Meat Animal Research CenterFollow
Sudhendu Raj Sharma, University of Nebraska-LincolnFollow

ORCID IDs

Bery 0009-0006-8516-8583

Brown-Brandl 0000-0002-0874-8035

Rohrer 0000-0002-8252-9308

Sharma 0000-0003-1996-673X

Document Type

Article

Date of this Version

12-2023

Citation

MDPI Animals (December 2024) 14: 131

doi: 10.3390/ani14010131

Comments

Open access

License: CC BY 4.0

Abstract

Shoulder sores predominantly arise in breeding sows and often result in untimely culling. Reported prevalence rates vary significantly, spanning between 5% and 50% depending upon the type of crate flooring inside a farm, the animal’s body condition, or an existing injury that causes lameness. These lesions represent not only a welfare concern but also have an economic impact due to the labor needed for treatment and medication. The objective of this study was to evaluate the use of computer vision techniques in detecting and determining the size of shoulder lesions. A Microsoft Kinect V2 camera captured the top-down depth and RGB images of sows in farrowing crates. The RGB images were collected at a resolution of 1,920 × 1,080. To ensure the best view of the lesions, images were selected with sows lying on their right and left sides with all legs extended. A total of 824 RGB images from 70 sows with lesions at various stages of development were identified and annotated. Three deep learning-based object detection models, YOLOv5, YOLOv8, and Faster-RCNN, pre-trained with the COCO and ImageNet datasets, were implemented to localize the lesion area. YOLOv5 was the best predictor as it was able to detect lesions with an mAP@0.5 of 0.92. To estimate the lesion area, lesion pixel segmentation was carried out on the localized region using traditional image processing techniques like Otsu’s binarization and adaptive thresholding alongside DL-based segmentation models based on U-Net architecture. In conclusion, this study demonstrates the potential of computer vision techniques in effectively detecting and assessing the size of shoulder lesions in breeding sows, providing a promising avenue for improving sow welfare and reducing economic losses.