Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Imaging Studies II: Positron Emission Tomography and Scintigraphy01:25

Imaging Studies II: Positron Emission Tomography and Scintigraphy

275
Positron Emission Tomography (PET) is a medical imaging technique that provides crucial insights into the body's physiological functions at a molecular level. It is an indispensable resource for diagnosing, staging, and monitoring various illnesses, notably cancer, neurological disorders, and cardiovascular conditions.
Fundamental Principles of PET
275
Positron Emission Tomography01:29

Positron Emission Tomography

6.3K
Positron emission tomography (PET) is a medical imaging technique involving radiopharmaceuticals — substances that emit short-lived radiation. Although the first PET scanner was introduced in 1961, it took 15 more years before radiopharmaceuticals were combined with the technique and revolutionized its potential.
One of the main requirements of a PET scan is a positron-emitting radioisotope, which is produced in a cyclotron and then attached to a substance used by the part of the body...
6.3K
Imaging Studies III: Computed Tomography01:27

Imaging Studies III: Computed Tomography

95
DefinitionComputed Tomography (CT) of the genitourinary (GU) tract is a non-invasive imaging modality that utilizes X-rays and computer processing to generate detailed cross-sectional images of the urinary system, encompassing the kidneys, ureters, bladder, and adjacent structures such as the adrenal glands.PurposeCT scans of the GU tract serve several diagnostic and therapeutic purposes, including:Diagnosis of Urinary Tract Diseases: Detects kidney stones, tumors, cysts, and congenital...
95

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Age and sex-dependent alteration in AMPA receptor density in living human brain.

European journal of nuclear medicine and molecular imaging·2026
Same author

Non-Enzymatic Formation of Chaxines and Natural Steroidal Derivatives via Ergosterol Air Oxidation.

The Journal of organic chemistry·2026
Same author

Clinical benefit of paclitaxel/carboplatin plus bevacizumab with zoledronic acid in pulmonary epithelioid hemangioendothelioma complicated by hypertrophic pulmonary osteoarthropathy and cardiac tamponade: a case report.

Frontiers in oncology·2026
Same author

ADAMTS1 Is Required for Ventral Abdominal Wall Closure.

The journal of histochemistry and cytochemistry : official journal of the Histochemistry Society·2026
Same author

Effective elimination of respiratory misregistration-induced attenuation correction errors in PET/CT via deep learning trained on data-driven gated PET from strictly respiratory-phase-matched PET/CT cases.

EJNMMI physics·2026
Same author

Early administration of renin-angiotensin system inhibitors improves survival and cardiac remodeling in heart failure with preserved ejection fraction.

PloS one·2026

Related Experiment Video

Updated: Oct 25, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.1K

Generative image transformer (GIT): unsupervised continuous image generative and transformable model for [123I]FP-CIT

Shogo Watanabe1, Tomohiro Ueno2, Yuichi Kimura3

  • 1Human Health Sciences, Graduate School of Medicine, Kyoto University, 53 Shogoin-Kawaharacho, Sakyo-ku, Kyoto City, Kyoto, Japan. wshogo1993@gmail.com.

Annals of Nuclear Medicine
|August 4, 2021
PubMed
Summary

A novel transformer-based generative model can create and alter SPECT images, showing potential for Parkinson's disease diagnosis. This approach successfully generates patient-specific brain scans and transforms healthy scans into Parkinson's-like images.

Keywords:
Generative modelParkinson’s diseaseTransformerUnsupervised learning[123I]FP-CIT SPECT

More Related Videos

Radiotracer Administration for High Temporal Resolution Positron Emission Tomography of the Human Brain: Application to FDG-fPET
09:03

Radiotracer Administration for High Temporal Resolution Positron Emission Tomography of the Human Brain: Application to FDG-fPET

Published on: October 22, 2019

10.4K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

584

Related Experiment Videos

Last Updated: Oct 25, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.1K
Radiotracer Administration for High Temporal Resolution Positron Emission Tomography of the Human Brain: Application to FDG-fPET
09:03

Radiotracer Administration for High Temporal Resolution Positron Emission Tomography of the Human Brain: Application to FDG-fPET

Published on: October 22, 2019

10.4K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

584

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Neuroscience

Background:

  • Generative adversarial networks (GANs) are increasingly used in medical imaging to enhance diagnostic accuracy through data augmentation.
  • Existing generative models face challenges in accurately representing complex medical image characteristics.
  • Parkinson's disease diagnosis relies on identifying subtle changes in neuroimaging, such as in SPECT scans.

Purpose of the Study:

  • To introduce a new generative model for medical imaging based on transformer decoder blocks.
  • To evaluate the model's capability in generating and transforming Single-Photon Emission Computed Tomography (SPECT) images, specifically for Parkinson's disease (PD) characteristics.
  • To demonstrate the model's potential as an alternative to GANs in medical image generation.

Main Methods:

  • A novel architecture utilizing transformer decoder blocks was developed to sequentially generate inferior image slices from superior ones.
  • The model was trained on [123I]FP-CIT SPECT images from the Parkinson's Progression Marker Initiative database, normalizing pixel values by the specific/nonspecific binding ratio (SNBR).
  • Generated images were assessed visually and quantitatively using mean absolute value and asymmetric index; transformation of healthy control SPECT images into PD-like images was also performed.

Main Results:

  • The transformer-based model successfully generated and transformed SPECT images into PD-like representations.
  • The mean absolute SNBR remained mostly below 0.15, indicating successful normalization and generation.
  • Analysis of the asymmetric index confirmed the successful variation introduced in the generated dataset images.

Conclusions:

  • The proposed generative approach based on transformers demonstrates significant potential for SPECT image generation and transformation.
  • A single transformer-based model achieved both the generation of new SPECT images and the transformation of existing ones into PD-like images.
  • This study highlights a promising new direction for AI-driven medical image analysis in neurodegenerative diseases.