cs.CVNov 6, 2026

Dual-Region Slice Aggregation for CT-Based Renal Tumor Classification

Authors: Yuan Liang, Sourav Bhattacharjee, Abraham Campbell

Organizations: Research Ireland Centre for Research Training in Machine Learning · School of Computer Science, University College Dublin, Dublin, Ireland · School of Veterinary Medicine, University College Dublin, Dublin, Ireland

Abstract

Clear cell renal cell carcinoma (ccRCC) is the most common kidney cancer in adults. We present a region-aware architecture for CT-based ccRCC classification. Tumor and 0--10 mm peritumoral context are pooled separately from shared frozen DINOv3 feature maps. A shared position-aware slice aggregator precedes fixed training-only principal component analysis (PCA). The resulting representations are fused with radiomics using two scalar feature gates. Evaluation on KiTS23 and 111 external cases yields internal test and external AUCs of 0.8078\pm0.0154 and 0.9094\pm0.0015. Compared with matched single-tumor readout, mean AUC increases by 1.50 and 2.34 percentage points, respectively. Early-PCA and reconstruction controls yield lower internal mean AUCs, while external AUC is similar for early and late PCA. These findings highlight the joint role of regional readout and slice aggregation in adapting frozen visual features to renal CT.

Figures & tables

Explore similar work

CardsList
  1. MSR-ABC: Complementary Feature Fusion for Clear Cell Renal Cell Carcinoma Classification

    Nov 6, 2026Yuan Liang, Sourav Bhattacharjee, Abraham CampbellCancer Subtype ClassificationMulti-View Feature Fusion

  2. Complementary Roles of Radiomics and Foundation Representations in Renal Cell Carcinoma Classification: A Comparative Study of 2D and 3D CT Encodings

    Sep 22, 2026Yuan Liang, Sourav Bhattacharjee, Abraham CampbellMedical Imaging Foundation ModelsOncology

  3. Radiomics--Foundation Fusion for Interpretable RCC Classification: Internal Benchmarking and Exploratory External Transfer

    Sep 22, 2026Yuan Liang, Fangyijie Wang, Kathleen M. Curran +3Medical Image AnalysisRadiomics