From Global Radiomics to Parametric Maps: A Unified Workflow Fusing Radiomics and Deep Learning for PDAC Detection

TL;DR

This paper introduces a unified framework combining radiomics and deep learning at global and voxel levels for improved pancreatic cancer detection, demonstrating superior performance on multiple datasets.

Contribution

The novel approach integrates radiomics features into deep learning models at multiple levels, enhancing PDAC detection beyond existing methods.

Findings

Achieved AUC of 0.96 and AP of 0.84 on PANORAMA dataset

Outperformed baseline nnUNet on external cohort

Ranked second in PANORAMA Grand Challenge

Abstract

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