Generative adversarial network-created brain SPECTs of cerebral ischemia are indistinguishable to scans from real patients
Abstract Deep convolutional generative adversarial networks (GAN) allow for creating images from existing databases. We applied a modified light-weight GAN (FastGAN) algorithm to cerebral blood flow SPECTs and aimed to evaluate whether this technology can generate created images close to real patien...
Main Authors: | Rudolf A. Werner, Takahiro Higuchi, Naoko Nose, Fujio Toriumi, Yohji Matsusaka, Ichiei Kuji, Koshino Kazuhiro |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2022-11-01
|
Series: | Scientific Reports |
Online Access: | https://doi.org/10.1038/s41598-022-23325-3 |
Similar Items
-
Performance Evaluation of a Preclinical SPECT Scanner with a Collimator Designed for Medium-Sized Animals
by: Yohji Matsusaka, et al.
Published: (2022-01-01) -
Quantification of bone metabolic activity in the natural course of fractural lesions measured by quantitative SPECT/CT
by: Tomohiko Yamane, et al.
Published: (2023-01-01) -
Diffuse FDG uptake in the bilateral lungs: hypersensitivity pneumonitis supported by low-dose CT findings
by: Shun Goto, et al.
Published: (2022-01-01) -
In Vivo Functional Assessment of Sodium-Glucose Cotransporters (SGLTs) Using [18F]Me4FDG PET in Rats
by: Yohji Matsusaka, et al.
Published: (2022-01-01) -
Rationalizing the Binding Modes of PET Radiotracers Targeting the Norepinephrine Transporter
by: Anna Tutov, et al.
Published: (2023-02-01)