Cross-species application of the lumbar intervertebral disc radiomics model in humans and cynomolgus monkeys

Abstract Nonhuman primates are ideal animal models for studying intervertebral disc degeneration. Radiomics technology could be used to accurately evaluate intervertebral disc degeneration, which is the basis for disc-related studies. In the study of nonhuman primates, the number of precious animals is limited, which cannot meet the sample size requirements of radiomics for study subjects, while these radiomics models could be obtained more easily in humans. Therefore, it is possible to construct radiomics models based on human intervertebral disc data, and then apply the models to nonhuman primates. However, cross-species application of the radiomics models has not previously been well established in the literature. Here we show that a total of 12.30% (438/3562) of radiomics features are reproducible between humans and cynomolgus monkeys. Furthermore, the human dataset is used as the training set to construct radiomics models, and the cynomolgus monkey’s dataset is used as the testing set to verify the inter species universality of the radiomics models. We found that the radiomics models constructed using human datasets as training sets still has good performance in cynomolgus monkeys. This study provides a theoretical basis for the cross-species application of radiomics model.