Work

Imaging-molecular integration in veterinary oncology: a perspective on evidence standards, validation, and translational readiness

Year: 2026
Type: article
Abstract: Veterinary oncology increasingly generates imaging, pathology, and molecular data, but these layers are often interpreted in parallel rather than linked within clinically testable models. Radiogenomics is used here as a focused form of imaging-molecular integration, whereas multimodal artificial intelligence refers more broadly to models combining imaging, pathology, molecular, biomarker, and clinical variables. Quantitative imaging, radiomics, and pathomics can describe tumour morphology and spatial heterogeneity, whereas molecular biomarkers may provide biological context relevant to prognosis and treatment response. The key challenge is not to add more artificial intelligence to veterinary cancer diagnostics, but to determine when integration adds value beyond clinical, imaging-only, and molecular-only baselines. This Perspective proposes minimum evidence standards for veterinary oncologic radiogenomics and multimodal artificial intelligence, covering animal- and lesion-level linkage, preprocessing, data-leakage control, justified multimodal fusion design, clinically meaningful comparators, calibration, external validation, cautious interpretation of explainability outputs, and transparent reporting. Imaging-molecular artificial intelligence should be treated as a translational research programme, not an immediately deployable diagnostic product.
Language: English
Field: Medicine
Open Access status: hybrid
Estimated APC paid: $2,490
OpenAlex ID: W7233620007
FWCI:
Cites: 28
Cited by:
Related to: