Multiscale Cross-Modal Mapping of Molecular, Pathologic, and Radiologic Phenotypes in Lipid-Deficient Clear Cell Renal CellCarcinoma

2025-12-13

AI Summary

Clear cell renal cell carcinoma (ccRCC) exhibits substantial intratumoral heterogeneity, particularly in the lipid-deficient dedifferentiated ccRCC (DCCD-ccRCC) subtype—associated with poor prognosis and challenging preoperative identification—thereby limiting the clinical utility of TNM staging. Method: We propose the first hierarchical, multi-scale, cross-modal mapping framework, comprising two complementary models: PathoDCCD (a computational pathology model integrating microscopic-to-regional features) and RadioDCCD (a radiomics model fusing whole-tumor, tumor microenvironment, and 2D spatial heterogeneity features). Leveraging cross-modal representation transfer and hierarchical modeling, both models jointly reconstruct molecular subtypes from routine histopathology and MRI/CT images. Results: Validated across five independent cohorts (n = 1,659), our framework achieves accurate molecular subtype recapitulation and noninvasive preoperative prediction, consistently identifying the poorest-prognosis DCCD-ccRCC subgroup—establishing, for the first time, a supervised bridge linking molecular phenotypes to histopathological and radiological features.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Computer Vision: Multi-modal Vision
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Clear cell renal cell carcinoma (ccRCC) exhibits extensive intratumoral heterogeneity on multiple biological scales, contributing to variable clinical outcomes and limiting the effectiveness of conventional TNM staging, which highlights the urgent need for multiscale integrative analytic frameworks. The lipid-deficient de-clear cell differentiated (DCCD) ccRCC subtype, defined by multi-omics analyses, is associated with adverse outcomes even in early-stage disease. Here, we establish a hierarchical cross-scale framework for the preoperative identification of DCCD-ccRCC. At the highest layer, cross-modal mapping transferred molecular signatures to histological and CT phenotypes, establishing a molecular-to-pathology-to-radiology supervisory bridge. Within this framework, each modality-specific model is designed to mirror the inherent hierarchical structure of tumor biology. PathoDCCD captured multi-scale microscopic features, from cellular morphology and tissue architecture to meso-regional organization. RadioDCCD integrated complementary macroscopic information by combining whole-tumor and its habitat-subregions radiomics with a 2D maximal-section heterogeneity metric. These nested models enabled integrated molecular subtype prediction and clinical risk stratification. Across five cohorts totaling 1,659 patients, PathoDCCD reliably recapitulated molecular subtypes, while RadioDCCD provided reliable preoperative prediction. The consistent predictions identified patients with the poorest clinical outcomes. This cross-scale paradigm unifies molecular biology, computational pathology, and quantitative radiology into a biologically grounded strategy for preoperative noninvasive molecular phenotyping of ccRCC.

Problem

• Develops a multiscale framework for preoperative identification of lipid-deficient ccRCC
• Integrates molecular, pathological, and radiological data to predict aggressive cancer subtypes
• Enables noninvasive clinical risk stratification to improve patient outcome predictions

Innovation

• Hierarchical cross-scale framework for preoperative identification
• Cross-modal mapping transfers molecular signatures to histology and CT
• Nested models integrate molecular subtype prediction and risk stratification