EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Variational autoencoders can detect coronary artery disease in myocardial perfusion SPECT images

Koichi Okuda, Kenichi Nakajima, Takeshi Hara, Hiroto Yoneyama, Seigo Kinuya

European Journal of Nuclear Medicine and Molecular Imaging · 2026-11 · 53 (13) · 8014-8022

DOI: 10.1007/s00259-026-08161-1 ↗

Kurz gefasst

Fachartikel in der Zeitschrift European Journal of Nuclear Medicine and Molecular Imaging, online erschienen am 29.08.2026. Verfasst von Koichi Okuda und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiation Science, Hirosaki University Graduate School of Health Sciences, 66-1 Hon-cho, Hirosaki-shi, Aomori, 036-8564, Japan. okuda1@…. Hauptthemen laut MEDLINE: Autoencoder, Myocardial Perfusion Imaging, Coronary Artery Disease, Tomography, Emission-Computed, Single-Photon. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Kanazawa University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

Variational autoencoders (VAEs) can detect unsupervised anomalies in medical images. We aimed to determine whether a VAE could automatically detect anomalies in myocardial perfusion SPECT (MPS) images. We then interpreted the training and generative processes of the VAE.

Methods

We trained a VAE on polar maps to learn the variability of normal myocardial perfusion profiles in latent space. The training dataset comprised 3,432 polar map images (49% male) without coronary artery disease (CAD) and the validation set contained 111 polar map images (59% male), among whom, (43% had obstructive CAD). This latent representation allowed the VAE to reconstruct synthetic normal images that served as references to detect anomalies. Abnormal myocardial perfusion was automatically identified by measuring differences between generated and original images using cosine similarity. We also summed stress scores (SSS) using sex-segregated normal databases.

Results

The trained VAE generated reference normal polar maps, regardless of normal and defect profiles and sex differences. The areas under the receiver-operating characteristics curve to detect CAD were 0.89 ± 0.041 for cosine similarity and 0.81 ± 0.030 for SSS ( p = 0.047). The VAE learned the characteristics of normal male and female myocardial perfusion distributions in the latent space.

Conclusion

This VAE-based approach improved CAD detection in MPS images and eliminated the need to determine sex-specific myocardial perfusion characteristics.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AutoencoderMyocardial Perfusion ImagingCoronary Artery DiseaseTomography, Emission-Computed, Single-PhotonImage Processing, Computer-AssistedHumansMaleFemale

Stichwörter der Autor:innen

Anomaly detectionImagingMyocardial perfusionVariational autoencoder

Autor:innen und Institutionen

  • Department of Radiation Science, Hirosaki University Graduate School of Health Sciences, 66-1 Hon-cho, Hirosaki-shi, Aomori, 036-8564, Japan. okuda1@hirosaki-u.ac.jp.
  • Department of Nuclear Medicine, Kanazawa University Graduate School of Medical Sciences, Kanazawa, Japan.
  • Department of Electrical, Electronic and Computer Engineering, Gifu University, Gifu, Japan.
  • Center for One Medicine Innovative Translational Research, Gifu University, Gifu, Japan.
  • Department of Radiological Technology, Kanazawa University Hospital, Kanazawa, Japan.

Förderung

  • Kanazawa University

Zitieren

APA

Okuda, K., Nakajima, K., Hara, T., Yoneyama, H., & Kinuya, S. (2026). Variational autoencoders can detect coronary artery disease in myocardial perfusion SPECT images. European Journal of Nuclear Medicine and Molecular Imaging, 53(13), 8014-8022. https://doi.org/10.1007/s00259-026-08161-1

Vancouver

Okuda K, Nakajima K, Hara T, Yoneyama H, Kinuya S. Variational autoencoders can detect coronary artery disease in myocardial perfusion SPECT images. European Journal of Nuclear Medicine and Molecular Imaging. 2026;53(13):8014-8022. doi:10.1007/s00259-026-08161-1

BibTeX
@article{Okuda2026,
  author = {Okuda, Koichi and Nakajima, Kenichi and Hara, Takeshi and Yoneyama, Hiroto and Kinuya, Seigo},
  title = {Variational autoencoders can detect coronary artery disease in myocardial perfusion SPECT images},
  journal = {European Journal of Nuclear Medicine and Molecular Imaging},
  year = {2026},
  volume = {53},
  number = {13},
  pages = {8014--8022},
  doi = {10.1007/s00259-026-08161-1}
}
Kostenlos starten →