Robustness of Single- and Dual-Energy Deep-Learning-Based Scatter Correction Models on Simulated and Real Chest X-rays
Open Access
- 12 December 2023
- journal article
- research article
- Published by MDPI AG in Algorithms
- Vol. 16 (12) , 565
Abstract
Chest X-rays (CXRs) represent the first tool globally employed to detect cardiopulmonary pathologies. These acquisitions are highly affected by scattered photons due to the large field of view required. Scatter in CXRs introduces background in the images, which reduces their contrast. We developed three deep-learning-based models to estimate and correct scatter contribution to CXRs. We used a Monte Carlo (MC) ray-tracing model to simulate CXRs from human models obtained from CT scans using different configurations (depending on the availability of dual-energy acquisitions). The simulated CXRs contained the separated contribution of direct and scattered X-rays in the detector. These simulated datasets were then used as the reference for the supervised training of several NNs. Three NN models (single and dual energy) were trained with the MultiResUNet architecture. The performance of the NN models was evaluated on CXRs obtained, with an MC code, from chest CT scans of patients affected by COVID-19. The results show that the NN models were able to estimate and correct the scatter contribution to CXRs with an error of <5%, being robust to variations in the simulation setup and improving contrast in soft tissue. The single-energy model was tested on real CXRs, providing robust estimations of the scatter-corrected CXRs.Keywords
All Related Versions
Funding Information
- Spanish Ministry of Science and Innovation (PID2021-126998OB-I00, RTC2019-007112-1 XPHASE-LASER, PDC2022-133057-I00/AEI/10.13039/501100011033, CT82/20-CT83/20)
- Unión Europea NextGenerationEU/PRTR (PID2021-126998OB-I00, RTC2019-007112-1 XPHASE-LASER, PDC2022-133057-I00/AEI/10.13039/501100011033, CT82/20-CT83/20)
- University Complutense of Madrid and Banco Santander predoctoral fellowship (PID2021-126998OB-I00, RTC2019-007112-1 XPHASE-LASER, PDC2022-133057-I00/AEI/10.13039/501100011033, CT82/20-CT83/20)
This publication has 50 references indexed in Scilit:
- Effects of tube potential and scatter rejection on image quality and effective dose in digital chest X-ray examination: An anthropomorphic phantom studyRadiography, 2013
- Use of a digitally reconstructed radiograph-based computer simulation for the optimisation of chest radiographic techniques for computed radiography imaging systemsBritish Journal of Radiology, 2012
- Exact global histogram specification optimized for structural similarityOptical Review, 2009
- Dual energy subtraction: Principles and clinical applicationsEuropean Journal of Radiology, 2009
- Optimisation of imaging technique used in direct digital radiographyJournal of Radiological Protection, 2006
- A novel technique to suppress grid line artifactsMedical Physics, 2006
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004
- The calibration of CT Hounsfield units for radiotherapy treatment planningPhysics in Medicine & Biology, 1996
- Energy-selective reconstructions in X-ray computerised tomographyPhysics in Medicine & Biology, 1976
- The Beer-Lambert LawJournal of Chemical Education, 1962