Detail
Článek
Článek online
FT
Medvik - BMČ
  • Je něco špatně v tomto záznamu ?

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

K. Dudasova, J. Trnka

. 2025 ; 28 (0) : 9-17. [pub] -

Jazyk angličtina Země Polsko

Typ dokumentu časopisecké články

Perzistentní odkaz   https://www.medvik.cz/link/bmc25010361

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.

Citace poskytuje Crossref.org

000      
00000naa a2200000 a 4500
001      
bmc25010361
003      
CZ-PrNML
005      
20250429135122.0
007      
ta
008      
250415s2025 pl f 000 0|eng||
009      
AR
024    7_
$a 10.5603/nmr.101316 $2 doi
035    __
$a (PubMed)40103394
040    __
$a ABA008 $b cze $d ABA008 $e AACR2
041    0_
$a eng
044    __
$a pl
100    1_
$a Dudasova, Katerina $u Czech Technical University in Prague, Faculty of Nuclear Sciences and Physical Engineering, Prague, Czech Republic. katerina.dudasova7@gmail.com $u National Radiation Protection Institute, Prague, Czech Republic. katerina.dudasova7@gmail.com $1 https://orcid.org/0009000982667442
245    10
$a Towards prediction of pseudo-normal SPECT image data using variational autoencoder / $c K. Dudasova, J. Trnka
520    9_
$a 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.
650    12
$a jednofotonová emisní výpočetní tomografie $7 D015899
650    _2
$a lidé $7 D006801
650    12
$a mozek $x diagnostické zobrazování $7 D001921
650    12
$a počítačové zpracování obrazu $7 D007091
655    _2
$a časopisecké články $7 D016428
700    1_
$a Trnka, Jiri $u Department of Medical Physics, General University Hospital in Prague, Prague, Czech Republic $1 https://orcid.org/0000000181759403 $7 xx0237908
773    0_
$w MED00156551 $t Nuclear Medicine Review $x 1644-4345 $g Roč. 28, č. 0 (2025), s. 9-17
856    41
$u https://pubmed.ncbi.nlm.nih.gov/40103394 $y Pubmed
910    __
$a ABA008 $b sig $c sign $y - $z 0
990    __
$a 20250415 $b ABA008
991    __
$a 20250429135117 $b ABA008
999    __
$a ok $b bmc $g 2311611 $s 1247442
BAS    __
$a 3
BAS    __
$a PreBMC-MEDLINE
BMC    __
$a 2025 $b 28 $c 0 $d 9-17 $e - $i 1644-4345 $m Nuclear Medicine Review $n Nucl Med Rev Cent East Eur $x MED00156551
LZP    __
$a Pubmed-20250415

Najít záznam

Citační ukazatele

Možnosti archivace