Automatic identification, segmentation, and percentage calculation of healthy and unhealthy bovine lung tissue using machine learning algorithms

• Alfredo Emanuel Pavón-Pérez ^[1] ; Luis Felipe Marín-Urias ^[1] ; Alejandro José Linares-Díaz ^[2] ; Carlos Morales-Morales ^[1] ; Vaniareli Ascenez Fernández-Villa ^[1] ; Pedro Javier García-Ramírez ^[1] ; Manuel Barrientos-Morales ^[1] ; Belisario Domínguez-Mancera ^[1] ; Rogelio de Jesús Portillo-Vélez ^[1]
  1. [1] Universidad Veracruzana

     Universidad Veracruzana

     México

     
  2. [2] Universidad de San Carlos de Guatemala

     Universidad de San Carlos de Guatemala

     Guatemala

     
• Localización: Austral journal of veterinary sciences, ISSN 0719-8000, ISSN-e 0719-8132, Vol. 58, Nº. 1, 2026, págs. 74-90
• Idioma: inglés
• Enlaces
  • Texto completo
• Resumen

  • Respiratory syndromes are a major cause of morbidity and mortality in the feedlot industry, making the accurate identification of lung lesions essential for effective health management. This study proposes an auto-mated approach for identifying and segmenting pulmonary structures and lesions using a visual machine learning model trained on a limited dataset of post-mortem images captured at a slaughterhouse. The implementation was performed using Python 3.12 with computer vision libraries and the Ultralytics framework employing YOLO11n-seg. Training incorporated both dorsal and ventral views to identify lungs, trachea and extra tissues, and lesions (desig-nated as “findings”). Data augmentation and k-fold cross-validation were applied to address the data limitations. In addition, we developed an automated algorithm that quantifies lung health by calculating the proportion of affected versus healthy tissue through a pixel overlap comparison between segmented lung regions and detected lesions. The proposed method enables objective and reproducible assessments of pulmonary conditions from different anatomi-cal perspectives. The results demonstrate strong performance in both anatomical segmentation and lesion detection, while also highlighting the challenges inherent in data-constrained conditions. These findings contribute to the de-velopment of computer-aided tools for veterinary diagnostics