High resolution micro-CT images are often corrupted by ring artefacts, prohibiting quantitative analysis and hampering post processing. Removing or at least significantly reducing such artefacts is indispensable. However, since micro-CT systems are pushed to the extremes in the quest for the ultimate spatial resolution, ring artefacts can hardly be avoided. Moreover, as opposed to clinical CT systems, conventional correction schemes such as flat-field correction do not lead to satisfactory results. Therefore, in this note a simple but efficient and fast post processing method is proposed that effectively reduces ring artefacts in reconstructed micro-CT images.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1088/0031-9155/49/14/n06 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Syn2Real: synthesis of CT image ring artifacts for deep learning-based correction.
Phys Med Biol
January 2025
Center for Biotechnology and Interdisciplinary Studies, Rensselaer Polytechnic Institute, Room 3209, CBIS/BME, 110 8th Street, Troy, NY 12180, USA, Troy, 12180, UNITED STATES.
We strive to overcome the challenges posed by ring artifacts in X-ray computed tomography (CT) by developing a novel approach for generating training data for deep learning-based methods. Training such networks require large, high quality, datasets that are often generated in the data domain, time-consuming and expensive. Our objective is to develop a technique for synthesizing realistic ring artifacts directly in the image domain, enabling scalable production of training data without relying on specific imaging system physics.
View Article and Find Full Text PDFUltra-sparse reconstruction for photoacoustic tomography: Sinogram domain prior-guided method exploiting enhanced score-based diffusion model.
Photoacoustics
February 2025
School of Information Engineering, Nanchang University, Nanchang 330031, China.
Photoacoustic tomography, a novel non-invasive imaging modality, combines the principles of optical and acoustic imaging for use in biomedical applications. In scenarios where photoacoustic signal acquisition is insufficient due to sparse-view sampling, conventional direct reconstruction methods significantly degrade image resolution and generate numerous artifacts. To mitigate these constraints, a novel sinogram-domain priors guided extremely sparse-view reconstruction method for photoacoustic tomography boosted by enhanced diffusion model is proposed.
View Article and Find Full Text PDFUnsupervised Deep Learning for Synthetic CT Generation from CBCT Images for Proton and Carbon Ion Therapy for Paediatric Patients.
Sensors (Basel)
November 2024
Bioengineering Unit, Clinical Department, CNAO National Centre for Oncological Hadrontherapy, 27100 Pavia, Italy.
Article Synopsis
- Image-guided treatment adaptation using CycleGAN for synthetic CT generation is a significant advancement in particle therapy for young cancer patients.
- The study involved processing CBCT scans from 15 pelvic patients to create synthetic CT images, which were evaluated against verification CT scans for quality.
- Results showed that despite some limitations, the CycleGAN method produced satisfactory synthetic CT images that could improve treatment efficacy in pediatric oncology.
Development of a low-dose strategy for propagation-based imaging helical computed tomography (PBI-HCT): high image quality and reduced radiation dose.
Biomed Phys Eng Express
December 2024
Division of Biomedical Engineering, College of Engineering, University of Saskatchewan, Saskatoon, SK S7N 5A9, Canada.
Article Synopsis
- Propagation-based imaging computed tomography (PBI-CT) is gaining popularity for visualizing low-density materials thanks to its high resolution and image contrast, but it poses radiation risks in live animal imaging due to high doses.
- This study integrates a deep learning method called Sparse2Noise with PBI-CT to significantly reduce radiation exposure (up to 90%) while preserving image quality, showing improved results over traditional low-dose imaging methods.
- The findings indicate that Sparse2Noise provides a better signal-to-noise ratio compared to two other advanced low-dose algorithms, enhancing the effectiveness of PBI-CT for biomedical applications.
Based on the generative adversarial network (GAN), we present a multifunctional X-ray tomographic protocol for artifact correction, noise suppression, and super-resolution of reconstruction. The protocol mainly consists of a data preprocessing module and multifunctional GAN-based loss function simultaneously dealing with ring artifacts and super-resolution. The experimental protocol removes ring artifacts and improves the contrast-to-noise ratio (CNR) and spatial resolution (SR) of reconstructed images successfully, which shows the capability to adaptively rectify ring artifacts with varying intensities and types while achieving super-resolution.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!