EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

PhysioSpeck-Net: Physics-Guided Feature Separation for Parameter-Efficient and Uncertainty-Aware Retinal OCT Classification Under Cross-Dataset Shift

Tahasin Ahmed Fahim, Fatema Binte Alam, Md Shamim Ahmed, Yu Jia

Computers · 19.09.2026 · 15 (9) · 630

DOI: 10.3390/computers15090630 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computers, online erschienen am 19.09.2026. Verfasst von Tahasin Ahmed Fahim und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: UK Engineering and Physical Sciences Research Council.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep networks for optical coherence tomography (OCT) classification usually learn directly from image appearance, which leaves coherent speckle, depth-dependent attenuation, point-spread-function blur, and refractive distortion entangled with pathology inside a single feature representation. This work asks whether making that separation architecturally explicit is a useful inductive bias, rather than whether it raises benchmark accuracy. PhysioSpeck-Net routes a shared stem representation through four branches aligned one-to-one with distinct OCT image-formation effects, recombines them through cross-branch attention and a physics-guided gate, and constrains them with auxiliary objectives derived from a seven-layer retinal simulator. The framework is evaluated on a 1000-image balanced test set and, without fine-tuning, on 1400 images from a second OCT source. Under a common training protocol, the model is competitive with substantially larger convolutional and transformer baselines while using 8.80 million parameters, but the more informative results concern reliability: predictive entropy separates errors from correct predictions with error-detection AUCs of 0.9847 and 0.9688, expected calibration error remains near 4–5% on both sets, and Grad-CAM++ perturbation analysis shows that attribution faithfulness is class-dependent rather than uniformly high. Distributional analysis further shows a residual gap between simulated and clinical images. Leave-one-branch-out and loss ablations produced consistent performance reductions, paired significance testing confirmed gains over most conventional baselines, and duplicate-control analysis found no exact or confirmed near-duplicate images across the evaluated datasets. These findings support physics-guided feature separation as a compact and uncertainty-aware strategy for retinal OCT classification under dataset shift.

Förderung

  • UK Engineering and Physical Sciences Research Council

Zitieren

APA

Fahim, T. A., Alam, F. B., Ahmed, M. S., & Jia, Y. (2026). PhysioSpeck-Net: Physics-Guided Feature Separation for Parameter-Efficient and Uncertainty-Aware Retinal OCT Classification Under Cross-Dataset Shift. Computers, 15(9), 630. https://doi.org/10.3390/computers15090630

Vancouver

Fahim TA, Alam FB, Ahmed MS, Jia Y. PhysioSpeck-Net: Physics-Guided Feature Separation for Parameter-Efficient and Uncertainty-Aware Retinal OCT Classification Under Cross-Dataset Shift. Computers. 2026;15(9):630. doi:10.3390/computers15090630

BibTeX
@article{Fahim2026,
  author = {Fahim, Tahasin Ahmed and Alam, Fatema Binte and Ahmed, Md Shamim and Jia, Yu},
  title = {PhysioSpeck-Net: Physics-Guided Feature Separation for Parameter-Efficient and Uncertainty-Aware Retinal OCT Classification Under Cross-Dataset Shift},
  journal = {Computers},
  year = {2026},
  volume = {15},
  number = {9},
  pages = {630},
  doi = {10.3390/computers15090630}
}
Kostenlos starten →