EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Efficient Feature Learning–Driven Neuroimage Compression and High-Fidelity Reconstruction using a Lightweight Autoencoder

R. Madayanthikaa, Riya Khandelwal, Dev Tandon, Ananya R Bhat, R. Arumuga Arun, R. S. Rampriya

International Journal of Computational Intelligence Systems · 11.06.2026 · 19 (1)

DOI: 10.1007/s44196-026-01412-x ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Computational Intelligence Systems, online erschienen am 11.06.2026. Verfasst von R. Madayanthikaa und 5 weiteren Autor:innen. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Vellore Institute of Technology, Vellore.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Medical neuroimaging, and particularly MRI and CT, forms the cornerstone of current diagnosis and treatment planning owing to its accurate structural information of the brain. But the exponentially increased size and resolution of neuroimaging data significantly challenge its storage and retrieval. Traditional lossy compression schemes may affect the diagnostic features present in the medical imaging, and they rely on pre-specified transformation rather than adaptive feature learning. To address this, a lightweight SegNet and UNet++-inspired autoencoder, Medical Neuroimaging Lightweight Autoencoder (MedLiteNeuro-AE) is proposed in this research work that can compress the brain MRI and CT scan images before storing hospital environments. The proposed model compresses images into the smallest latent representation and reconstructs them by preserving diagnostically reliable fidelity. Unlike conventional codecs, the latent code layer also acts as a non-interpretable compressed representation, reducing direct visual interpretability of the original scans during storage and transmission, while clinicians interact only with the reconstructed images. Extensive evaluation proves the effectiveness of MedLiteNeuro-AE, with regeneration metrics of 3.1E-05 MSE, 5.042E-03 RMSE, 46.54 dB PSNR, 99.66% SSIM, and 99.66% MS-SSIM, along with a compression rate of 3.12% and model size of 3.87 MB. The results confirm that our model achieves a balance among the effective compression, preservation of diagnostic quality, and computational complexity, and outperforms common compression baselines while being significantly. Later, the MedLiteNeuro-AE can be decomposed into an encoder and a decoder to build a feature learning-based compressor and decompressor. These results position MedLiteNeuro-AE as a safe, lightweight, and adaptable solution for modern neuroimaging deployments.

Förderung

  • Vellore Institute of Technology, Vellore

Zitieren

APA

Madayanthikaa, R., Khandelwal, R., Tandon, D., Bhat, A. R., Arun, R. A., & Rampriya, R. S. (2026). Efficient Feature Learning–Driven Neuroimage Compression and High-Fidelity Reconstruction using a Lightweight Autoencoder. International Journal of Computational Intelligence Systems, 19(1). https://doi.org/10.1007/s44196-026-01412-x

Vancouver

Madayanthikaa R, Khandelwal R, Tandon D, Bhat AR, Arun RA, Rampriya RS. Efficient Feature Learning–Driven Neuroimage Compression and High-Fidelity Reconstruction using a Lightweight Autoencoder. International Journal of Computational Intelligence Systems. 2026;19(1). doi:10.1007/s44196-026-01412-x

BibTeX
@article{Madayanthikaa2026,
  author = {Madayanthikaa, R. and Khandelwal, Riya and Tandon, Dev and Bhat, Ananya R and Arun, R. Arumuga and Rampriya, R. S.},
  title = {Efficient Feature Learning–Driven Neuroimage Compression and High-Fidelity Reconstruction using a Lightweight Autoencoder},
  journal = {International Journal of Computational Intelligence Systems},
  year = {2026},
  volume = {19},
  number = {1},
  doi = {10.1007/s44196-026-01412-x}
}
Kostenlos starten →