Conditional Generative Adversarial Networks Aided Motion Correction of Dynamic 18F-FDG PET Brain Studies
Por um escritor misterioso
Last updated 29 março 2025

This work set out to develop a motion-correction approach aided by conditional generative adversarial network (cGAN) methodology that allows reliable, data-driven determination of involuntary subject motion during dynamic 18F-FDG brain studies. Methods: Ten healthy volunteers (5 men/5 women; mean age ± SD, 27 ± 7 y; weight, 70 ± 10 kg) underwent a test–retest 18F-FDG PET/MRI examination of the brain ( n = 20). The imaging protocol consisted of a 60-min PET list-mode acquisition contemporaneously acquired with MRI, including MR navigators and a 3-dimensional time-of-flight MR angiography sequence. Arterial blood samples were collected as a reference standard representing the arterial input function (AIF). Training of the cGAN was performed using 70% of the total datasets ( n = 16, randomly chosen), which was corrected for motion using MR navigators. The resulting cGAN mappings (between individual frames and the reference frame [55–60 min after injection]) were then applied to the test dataset (remaining 30%, n = 6), producing artificially generated low-noise images from early high-noise PET frames. These low-noise images were then coregistered to the reference frame, yielding 3-dimensional motion vectors. Performance of cGAN-aided motion correction was assessed by comparing the image-derived input function (IDIF) extracted from a cGAN-aided motion-corrected dynamic sequence with the AIF based on the areas under the curves (AUCs). Moreover, clinical relevance was assessed through direct comparison of the average cerebral metabolic rates of glucose (CMRGlc) values in gray matter calculated using the AIF and the IDIF. Results: The absolute percentage difference between AUCs derived using the motion-corrected IDIF and the AIF was (1.2% + 0.9%). The gray matter CMRGlc values determined using these 2 input functions differed by less than 5% (2.4% + 1.7%). Conclusion: A fully automated data-driven motion-compensation approach was established and tested for 18F-FDG PET brain imaging. cGAN-aided motion correction enables the translation of noninvasive clinical absolute quantification from PET/MR to PET/CT by allowing the accurate determination of motion vectors from the PET data itself.

J. Imaging, Free Full-Text

Using domain knowledge for robust and generalizable deep learning

Fully Automated, Fast Motion Correction of Dynamic Whole-Body and

Unsupervised inter-frame motion correction for whole-body dynamic

Generative adversarial networks and its applications in the

Conditional Generative Adversarial Networks Aided Motion

Brain PET motion correction using 3D face-shape model: the first

TAI-GAN: Temporally and Anatomically Informed GAN for Early-to

The promise of artificial intelligence and deep learning in PET

Applications of Generative Adversarial Networks (GANs) in Positron

Fully Automated, Fast Motion Correction of Dynamic Whole-Body and
Recomendado para você
-
Sapatos De Segurança Antiestáticos, Sapatos De Segurança Com Biqueira De Aço Antiesmagamento/Antiperfuração, Sapatos De Trabalho Para Homens E29 março 2025
-
What The F, Aperture Photography Tank Top : Clothing, Shoes & Jewelry29 março 2025
-
36 37 38 Ford flathead V8 .020 Main Bearing set NOS 1936 1937 1938 convertible29 março 2025
-
Demonstrations of the manipulator used for 3D printing in construction.29 março 2025
-
Embraer EMB-314/A-29 Super Tucano with Armor Plate by StarEagle711 on DeviantArt29 março 2025
-
Index of property owners, real estate atlas of Cincinnati, Ohio. V.01 - Maps & Atlases - Digital Library29 março 2025
-
JCM, Free Full-Text29 março 2025
-
excel for statistics. ¿how to compute some descriptive statistics with case selection? - Microsoft Community Hub29 março 2025
-
Solved 50. EP and FP are angle bisectors of A DEF. Find29 março 2025
-
The puzzling mind of Stephen Sondheim - by David Benkof29 março 2025
você pode gostar
-
node-namegen/names.json at master · carlos8f/node-namegen · GitHub29 março 2025
-
Bestia — A friend ask me to do a 3 frame walking circle29 março 2025
-
Sonic the Hedgehog 2 (2022)29 março 2025
-
Ralph Lauren Talks Cinematic Approach to Dressing, Dream of Film Directing – The Hollywood Reporter29 março 2025
-
Demon Slayer Phone Wallpaper - EnJpg29 março 2025
-
CapCut_omori refere e doors29 março 2025
-
Pote com sorvete de biscuit Produtos Personalizados no Elo729 março 2025
-
Pool Party' Sticker29 março 2025
-
Petition · Petition to let Hogwarts Legacy join the Geforce NOW29 março 2025
-
Beneath the Tangles — First Impression: Parallel World Pharmacy29 março 2025