From Global Radiomics to Parametric Maps: A Unified Workflow Fusing Radiomics and Deep Learning for PDAC Detection
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917283952066560 |
|---|---|
| author | Deng, Zengtian He, Yimeng Shi, Yu Wang, Lixia Qureshi, Touseef Ahmad Huang, Xiuzhen Li, Debiao |
| author_facet | Deng, Zengtian He, Yimeng Shi, Yu Wang, Lixia Qureshi, Touseef Ahmad Huang, Xiuzhen Li, Debiao |
| contents | 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 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_17986 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | From Global Radiomics to Parametric Maps: A Unified Workflow Fusing Radiomics and Deep Learning for PDAC Detection Deng, Zengtian He, Yimeng Shi, Yu Wang, Lixia Qureshi, Touseef Ahmad Huang, Xiuzhen Li, Debiao Image and Video Processing Computer Vision and Pattern Recognition 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 |
| title | From Global Radiomics to Parametric Maps: A Unified Workflow Fusing Radiomics and Deep Learning for PDAC Detection |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.17986 |