Automated nonlinear registration of coronary PET to CT angiography using pseudo-CT generated from PET with generative adversarial networks

Singh, Ananya; Kwieciński, Jacek; Cadet, Sebastien; Killekar, Aditya; Tzolos, Evangelos; Williams, Michelle C.; Dweck, Marc R; Newby, David E.; Dey, Damini; Slomka, Piotr J.

doi:10.1007/s12350-022-03010-8

Cited by 15 publications

(6 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[128] [131] Size Adjustment Size Adjustment involves changing the dimensions or resolution of an image to fit a specific requirement, such as resizing it for display or analysis.…”

Section: ] [123] [124]mentioning

confidence: 99%

Generative Adversarial Networks (GANs) in Medical Imaging: Advancements, Applications, and Challenges

Islam,

Aziz,

Nabil

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Generative Adversarial Networks are a class of artificial intelligence algorithms that consist of a generator and a discriminator trained simultaneously through adversarial training. GANs have found crucial applications in various fields, including medical imaging. In healthcare, GANs contribute by generating synthetic medical images, enhancing data quality, and aiding in image segmentation, disease detection, and medical image synthesis. Their importance lies in their ability to generate realistic images, facilitating improved diagnostics, research, and training for medical professionals. Understanding its applications, algorithms, current advancements, and challenges is imperative for further advancement in the medical imaging domain. However, no study explores the recent state-of-the-art development of GANs in medical imaging. To overcome this research gap, in this extensive study, we began by exploring the vast array of applications of GANs in medical imaging, scrutinizing them within recent research. We then dive into the prevalent datasets and pre-processing techniques to enhance comprehension. Subsequently, an in-depth discussion of the GAN algorithms, elucidating their respective strengths and limitations, is provided. After that, we meticulously analyzed the results and experimental details of some recent cutting-edge research to obtain a more comprehensive understanding of the current development of GANs in medical imaging. Lastly, we discussed the diverse challenges encountered and future research directions to mitigate these concerns. This systematic review offers a complete overview of GANs in medical imaging, encompassing their application domains, models, state-of-the-art results analysis, challenges, and research directions, serving as a valuable resource for multidisciplinary studies.

show abstract

“…[128] [131] Size Adjustment Size Adjustment involves changing the dimensions or resolution of an image to fit a specific requirement, such as resizing it for display or analysis.…”

Section: ] [123] [124]mentioning

confidence: 99%

Generative Adversarial Networks (GANs) in Medical Imaging: Advancements, Applications, and Challenges

Islam,

Aziz,

Nabil

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Further gains in image quality can be achieved by performing image acquisitions at a longer (3 h) delay from tracer injection [ 40 ]. Recently, to streamline image analysis, artificial intelligence approaches have been harnessed to facilitate co-registration of CT and PET images [ 41 ]. Given the aforementioned advances, along with dedicated software for analysis and imaging protocols which have been validated extensively, 18 F-NaF coronary PET is now becoming a technology which can be easily implemented across PET labs [ 42 , 43 , 44 , 45 , 46 ].…”

Section: 18 F-sodium Fluoride Coronary Pet Imagingmentioning

confidence: 99%

Advances in the Assessment of Coronary Artery Disease Activity with PET/CT and CTA

et al. 2023

Self Cite

View full text Add to dashboard Cite

Non-invasive testing plays a pivotal role in the diagnosis, assessment of progression, response to therapy, and risk stratification of coronary artery disease. Although anatomical plaque imaging by computed tomography angiography (CTA) and ischemia detection with myocardial perfusion imaging studies are current standards of care, there is a growing body of evidence that imaging of the processes which drive atherosclerotic plaque progression and rupture has the potential to further enhance risk stratification. In particular, non-invasive imaging of coronary plaque inflammation and active calcification has shown promise in this regard. Positron emission tomography (PET) with newly-adopted radiotracers provides unique insights into atheroma activity acting as a powerful independent predictor of myocardial infarctions. Similarly, by providing a quantitative measure of coronary inflammation, the pericoronary adipose tissue density (PCAT) derived from standard coronary CTA enhances cardiac risk prediction and allows re-stratification over and above current state-of-the-art assessments. In this review, we shall discuss the recent advances in the non-invasive methods of assessment of disease activity by PET and CTA, highlighting how these methods could improve risk stratification and ultimately benefit patients with coronary artery disease.

show abstract

“…Dedicated reconstruction parameters along with a pancoronary uptake measure (the coronary microcalficiation activity) provide an opportunity for a patient-level assessment which is more closely associated with outcomes than single-pixel uptake values and has improved reproducibility [86][87][88][89][90]. Most recently, dedicated software and artificial intelligence tools have been shown to further streamline the analysis [91,92].…”

Section: Atherosclerotic Plaque Imagingmentioning

confidence: 99%

The Role of Positron Emission Tomography in Advancing the Understanding of the Pathogenesis of Heart and Vascular Diseases

Błach

Kwieciński

2023

Diagnostics

Self Cite

View full text Add to dashboard Cite

Cardiovascular disease remains the leading cause of morbidity and mortality worldwide. For developing new therapies, a better understanding of the underlying pathology is required. Historically, such insights have been primarily derived from pathological studies. In the 21st century, thanks to the advent of cardiovascular positron emission tomography (PET), which depicts the presence and activity of pathophysiological processes, it is now feasible to assess disease activity in vivo. By targeting distinct biological pathways, PET elucidates the activity of the processes which drive disease progression, adverse outcomes or, on the contrary, those that can be considered as a healing response. Given the insights provided by PET, this non-invasive imaging technology lends itself to the development of new therapies, providing a hope for the emergence of strategies that could have a profound impact on patient outcomes. In this narrative review, we discuss recent advances in cardiovascular PET imaging which have greatly advanced our understanding of atherosclerosis, ischemia, infection, adverse myocardial remodeling and degenerative valvular heart disease.

show abstract

Automated nonlinear registration of coronary PET to CT angiography using pseudo-CT generated from PET with generative adversarial networks

Cited by 15 publications

References 36 publications

Generative Adversarial Networks (GANs) in Medical Imaging: Advancements, Applications, and Challenges

Generative Adversarial Networks (GANs) in Medical Imaging: Advancements, Applications, and Challenges

Advances in the Assessment of Coronary Artery Disease Activity with PET/CT and CTA

The Role of Positron Emission Tomography in Advancing the Understanding of the Pathogenesis of Heart and Vascular Diseases

Contact Info

Product

Resources

About