EUVIMEDObjevte EUVIMED
Crossref

Towards prediction of pseudo-normal SPECT image data using variational autoencoder

Katerina Dudasova iD, Jiri Trnka iD

Nuclear Medicine Review · 2025

DOI: 10.5603/nmr.101316 ↗

At a glance

Journal article in Nuclear Medicine Review, 2025. Written by Katerina Dudasova and 1 co-authors. Institution: Czech Technical University in Prague, Faculty of Nuclear Sciences and Physical Engineering, Prague, Czech Republic. katerina.dudasova7@gmail.com. Major MEDLINE topics: Autoencoder, Image Processing, Computer-Assisted, Tomography, Emission-Computed, Single-Photon.

AbstraktSubjectsBibliografické údajeCiteRelated studies

Abstract (original language)

Background

This study aims to evaluate the feasibility of generating pseudo-normal single photon emission computed tomography (SPECT) data from potentially abnormal images. These pseudo-normal images are primarily intended for use in an on-the-fly data harmonization technique. Material and methods: The methodology was tested on brain SPECT with [123I]Ioflupane. The proposed model for generating a pseudo-normal image was based on a variational autoencoder (VAE) designed to process 2D sinograms of the brain [123I]-FP-CIT SPECT, potentially exhibiting abnormal uptake. The model aimed to predict SPECT sinograms with corresponding normal uptake. Training, validation, and testing datasets were created by SPECT simulator from 45 brain masks segmented from real patient’s magnetic resonance (MR) scans, using various uptake levels. The training and validation datasets each comprised 612 and 360 samples, respectively, drawn from 36 brain masks. The testing dataset contained 153 samples based on 9 brain masks. VAE performance was evaluated through brain dimensions, Dice similarity coefficient (DSC) and specific binding ratio.

Results

Mean DSC was 80% for left basal ganglia and 84% for right basal ganglia. The proposed VAE demonstrated excellent consistency in predicting basal ganglia shape, with a coefficient of variation of DSC being less than 1.1%.

Conclusions

The study demonstrates that VAE can effectively estimate an individualized pseudo-normal distribution of the radiotracer [123I]-FP-CIT SPECT from abnormal SPECT images. The main limitations of this preliminary research are the limited availability of real brain MR data, used as input for the SPECT data simulator, and the simplified simulation setup employed to create the synthetic dataset.

Subjects

MeSH terms (MEDLINE)

AutoencoderImage Processing, Computer-AssistedTomography, Emission-Computed, Single-PhotonHumansBrainTropanes

Author keywords

SPECT[123I]-FP-CITharmonizationvariational autoencoder

Substances

2-carbomethoxy-8-(3-fluoropropyl)-3-(4-iodophenyl)tropaneTropanes

Authors and institutions

  • Czech Technical University in Prague, Faculty of Nuclear Sciences and Physical Engineering, Prague, Czech Republic. katerina.dudasova7@gmail.com.
  • National Radiation Protection Institute, Prague, Czech Republic. katerina.dudasova7@gmail.com.
  • Department of Medical Physics, General University Hospital in Prague, Prague, Czech Republic.

ORCID profiles: Katerina Dudasova, Jiri Trnka

Cite

APA

Dudasova, K., & Trnka, J. (2025). Towards prediction of pseudo-normal SPECT image data using variational autoencoder. Nuclear Medicine Review. https://doi.org/10.5603/nmr.101316

Vancouver

Dudasova K, Trnka J. Towards prediction of pseudo-normal SPECT image data using variational autoencoder. Nuclear Medicine Review. 2025. doi:10.5603/nmr.101316

BibTeX
@article{Dudasova2025,
  author = {Dudasova, Katerina and Trnka, Jiri},
  title = {Towards prediction of pseudo-normal SPECT image data using variational autoencoder},
  journal = {Nuclear Medicine Review},
  year = {2025},
  doi = {10.5603/nmr.101316}
}
Start for free →