Dual-domain contrastive learning for three-dimensional multi-parametric magnetic resonance imaging to end-to-end predict kidney cancer subtypes

Prediction of subtypes is important for clinical decision-making in kidney cancer. Multi-parametric magnetic resonance imaging (mp-MRI) provides a non-invasive way to evaluate tumor characteristics. However, due to the heterogeneity of pixel, modality, and objective representation, the computer-aided diagnosis of subtypes is challenging. In this study, we propose a novel diagnosis framework for kidney cancer subtypes based on mp-MRI, dual-domain contrastive learning network (DCLNet), which has two innovations: (i) the dual-domain contrastive learning scheme based on intra-case consistency and inter-case specificity that mines the correlation and diversity of dual-domain (T1-weighted and T2-weighted) image information, and (ii) the linear diffusion augmentation strategy that enriches training data in three-dimensional image sparse representation and increases the robustness of features. In experiments, a real-world dataset from multiple centers is established for the development and validation of DCLNet. The proposed method yields multiple classification accuracy of 75.49 % for kidney cancer subtypes. The area under the curve for the aggressive malignant tumor clear cell renal cell carcinoma and the benign tumor angiomyolipoma is 89.53 % and 88.95 %, respectively. Significantly, our proposed method demonstrates significant improvement over state-of-the-art methods (p < 0.01). This study offers a reliable model for non-invasive prediction of kidney cancer subtypes. It also shows potential to overcome multi-source heterogeneity and improve performance in cancer classification. Our code is available at https://github.com/xiaojidream/DCLNet.