From Global Radiomics to Parametric Maps: A Unified Workflow Fusing Radiomics and Deep Learning for PDAC Detection
This work addresses PDAC detection for medical imaging, offering a specific improvement over existing fusion methods by incorporating spatially resolved radiomic maps.
The paper tackled the problem of detecting pancreatic ductal adenocarcinoma (PDAC) by fusing radiomics and deep learning at both global and voxel levels, achieving AUCs of 0.96 and 0.95 on cross-validation and external datasets, respectively.
Radiomics and deep learning both offer powerful tools for quantitative medical imaging, but most existing fusion approaches only leverage global radiomic features and overlook the complementary value of spatially resolved radiomic parametric maps. We propose a unified framework that first selects discriminative radiomic features and then injects them into a radiomics-enhanced nnUNet at both the global and voxel levels for pancreatic ductal adenocarcinoma (PDAC) detection. On the PANORAMA dataset, our method achieved AUC = 0.96 and AP = 0.84 in cross-validation. On an external in-house cohort, it achieved AUC = 0.95 and AP = 0.78, outperforming the baseline nnUNet; it also ranked second in the PANORAMA Grand Challenge. This demonstrates that handcrafted radiomics, when injected at both global and voxel levels, provide complementary signals to deep learning models for PDAC detection. Our code can be found at https://github.com/briandzt/dl-pdac-radiomics-global-n-paramaps