We propose an innovative approach to low-dose computed tomography that combines a hybrid acquisition protocol with a deep convolutional neural network. Our protocol interleaves sparse, uniformly spaced high-exposure projections with dense low-exposure projections. This strategy provides object-specific training data in situ and ensures the denoising task is always a constrained interpolation between high-quality samples, which robustly prevents model-induced artifacts. The CNN then processes spatio-angular sequences of patches from these projections, explicitly leveraging angular correlation to denoise the radiographs prior to reconstruction. We validated our framework on three new, publicly available CBCT datasets. The results demonstrate a remarkable improvement in image quality at both the radiographic and volumetric levels. Even with overall exposure savings exceeding 90%, our denoised results achieve a very high similarity to the full-exposure ground truth, successfully recovering fine structural details lost in the noisy baseline data. The accompanying datasets provide a valuable resource for future research and benchmarking.
FERRETTI Riccardo;
CASADO COSCOLLA Alvaro;
CASAMICHIELA Francesco;
POLA Andrea;
VENDRELL VIDAL Eduardo;
SANCHEZ BELENGUER Carlos;
2026-10-15
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
JRC145108
2333-9403 (online),
https://publications.jrc.ec.europa.eu/repository/handle/JRC145108,
10.1109/TCI.2026.3731170 (online),
| Name | Country | City | Type |
|---|
This document is only visible at the Commission level.
You are not authorized to publish or distribute it outside the European Commission.
This is a public document. You can share this publication.
Datasets
| ID | Title | Public URL |
|---|
Dataset collections
| ID | Acronym | Title | Public URL |
|---|
Scripts / source codes
| Description | Public URL |
|---|
Additional supporting files
| File name | Description | File type |
|---|