Ovine pulmonary adenocarcinoma (OPA) is a contagious lung tumour caused by the Jaagsiekte Sheep Retrovirus (JSRV). Histopathological diagnosis is the gold standard for OPA diagnosis. However, interpretation of traditional pathology images is complex and operator dependent. The mask regional convolutional neural network (Mask R-CNN) has emerged as a valuable tool in pathological diagnosis. This study utilized 54 typical OPA whole slide images (WSI) to extract 7167 typical lesion images containing OPA to construct a Common Objects in Context (COCO) dataset for OPA pathological images. The dataset was categorized into training and test sets (8:2 ratio) for model training and validation. Mean average specificity (mASp) and average sensitivity (ASe) were used to evaluate model performance. Six WSI-level pathological images (three OPA and three non-OPA images), not included in the dataset, were used for anti-peeking model validation. A random selection of 500 images, not included in the dataset establishment, was used to compare the performance of the model with assessment by pathologists. Accuracy, sensitivity, specificity, and concordance rate were evaluated. The model achieved a mASp of 0.573 and an ASe of 0.745, demonstrating effective lesion detection and alignment with expert annotation. In Anti-Peeking verification, the model showed good performance in locating OPA lesions and distinguished OPA from non-OPA pathological images. In the random 500-image diagnosis, the model achieved 92.8% accuracy, 100% sensitivity, and 88% specificity. The agreement rates between junior and senior pathologists were 100% and 96.5%, respectively. In conclusion, the Mask R-CNN-based OPA diagnostic model developed for OPA facilitates rapid and accurate diagnosis in practical applications.

Ovine pulmonary adenocarcinoma (OPA), caused by the exogenous Jaagsiekte sheep retrovirus (JSRV), shares several pathological and molecular features with human lung adenocarcinoma, providing an important model for comparative oncology. JSRV pathogenesis is mostly studied at the transcriptome level, with systematic proteomic and metabolomic studies remaining insufficient. Therefore, this study aimed to systematically characterise the molecular alterations associated with JSRV-induced OPA by integrating direct data-independent acquisition proteomics and untargeted metabolomics. We established an OPA model by infecting lambs with JSRV and performed multi-omics analyses on the lesion and control lung tissues (n = 3 per group for both proteomic and metabolomic analyses). In total, 1631 differentially expressed proteins and 748 differential metabolites were identified, and the two omics datasets exhibited highly coordinated variations. Integrated analyses suggested that adhesion remodelling (with downregulated LIMCH1), endoplasmic reticulum stress (with upregulated HYOU1), and metabolic and immune-related alterations (accompanied by elevated GFPT1 and PTGS2) represent major biological processes associated with JSRV infection. Western blot analysis confirmed the expression changes in these proteins. Overall, this study provides a multidimensional molecular landscape of OPA and expands current understanding of the molecular alterations associated with JSRV infection. These findings provide candidate pathways and molecular targets for future mechanistic studies and comparative investigations of lung adenocarcinoma.