Learned Primal Dual Reconstruction for PET

Guazzo, Alessandro; Colarieti-Tosti, Massimiliano

doi:10.3390/jimaging7120248

Cited by 6 publications

(2 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… LPD 58 when applied to example PET phantom data. 59 Figure adapted from data courtesy Massimiliano Colarieti-Tosti. The overall processing pipeline effectively has two rails: the top rail conducts sequential processing of the sinogram data and the lower rail conducts sequential processing of the image.…”

Section: Ai Methods: From Direct To Iterativementioning

confidence: 99%

AI for PET image reconstruction

Reader

Pan

2023

The British Journal of Radiology

View full text Add to dashboard Cite

Image reconstruction for positron emission tomography (PET) has been developed over many decades, with advances coming from improved modelling of the data statistics and improved modelling of the imaging physics. However, high noise and limited spatial resolution have remained issues in PET imaging, and state-of-the-art PET reconstruction has started to exploit other medical imaging modalities (such as MRI) to assist in noise reduction and enhancement of PET’s spatial resolution. Nonetheless, there is an ongoing drive towards not only improving image quality, but also reducing the injected radiation dose and reducing scanning times. While the arrival of new PET scanners (such as total body PET) is helping, there is always a need to improve reconstructed image quality due to the time and count limited imaging conditions. Artificial intelligence (AI) methods are now at the frontier of research for PET image reconstruction. While AI can learn the imaging physics as well as the noise in the data (when given sufficient examples), one of the most common uses of AI arises from exploiting databases of high-quality reference examples, to provide advanced noise compensation and resolution recovery. There are three main AI reconstruction approaches: i) direct data-driven AI methods which rely on supervised learning from reference data, ii) iterative (unrolled) methods which combine our physics and statistical models with AI learning from data, and iii) methods which exploit AI with our known models, but crucially can offer benefits even in the absence of any example training data whatsoever. This article reviews these methods, considering opportunities and challenges of AI for PET reconstruction.

show abstract

Section: Ai Methods: From Direct To Iterativementioning

confidence: 99%

AI for PET image reconstruction

Reader

Pan

2023

The British Journal of Radiology

View full text Add to dashboard Cite

show abstract

“…The LPD was adapted by using the OSEM reconstruction as initialisation of primal channels, and by including an affine forward operator with sample-specific multiplicative and additive factors. These sample-specific factors are not included in previous LPD implementations for PET [4]. To reduce computational time a total of 3 unrolled iterations were used.…”

Section: A Deep Learning Methodsmentioning

confidence: 99%

Investigating Intensity Normalisation for PET Reconstruction with Supervised Deep Learning

Singh,

Denker,

Jin

et al. 2023

2023 IEEE Nuclear Science Symposium, Medical Imaging Conference and International Symposium on Room-Temperature Semiconductor D

View full text Add to dashboard Cite

Deep learning methods have shown great promise in the field of Positron Emission Tomography (PET) reconstruction, but the successful application of these methods depends heavily on the intensity scale of the images. Normalisation is a crucial step that aims to adjust the intensity of network inputs to make them more uniform and comparable across samples, acquisition times, and activity levels. In this work, we study the influence of different linear intensity normalisation approaches. We focus on two popular deep learning based image reconstruction methods: an unrolled algorithm (Learned Primal-Dual) and a post-processing method (OSEMConvNet). Results on the out-ofdistribution test dataset demonstrate that the choice of intensity normalisation significantly impacts on generalisability of these methods. Normalisation using the mean of acquisition data or corrected acquisition data led to improved peak-signal-to-noiseratio (PSNR) and data-consistency (KLDIV). Through evaluation of lesion-specific metrics of contrast recovery coefficients (CRC) and standard deviation (STD) an increase in CRC and STD is observed. These findings highlight the importance of carefully selecting an appropriate normalisation method for supervised deep learning-based PET reconstruction applications.

show abstract

Self-supervised and supervised deep learning for PET image reconstruction

Reader

2024

NONLINEARITY AND HEARING: ADVANCES IN THEORY AND EXPERIMENT: Proceedings of the 14th International Mechanics of Hearing Worksho

View full text Add to dashboard Cite

Learned Primal Dual Reconstruction for PET

Cited by 6 publications

References 14 publications

AI for PET image reconstruction

AI for PET image reconstruction

Investigating Intensity Normalisation for PET Reconstruction with Supervised Deep Learning

Self-supervised and supervised deep learning for PET image reconstruction

Contact Info

Product

Resources

About