Biologically Inspired Selective Attention for Prostate MRI: A Segmentation-Guided Vision Transformer Framework for Computer-Aided Diagnosis
Biomimetics · 11.11.2026 · 11 (11) · 824
DOI: 10.3390/biomimetics11110824 ↗Kurz gefasst
Fachartikel in der Zeitschrift Biomimetics, online erschienen am 11.11.2026. Verfasst von Saqib Iqbal und 6 weiteren Autor:innen. Die Arbeit nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Umm AL-Qura University.
Abstract (Originalsprache)
Prostate cancer is the second most commonly diagnosed malignancy in men, yet interpretation of multiparametric MRI (mpMRI) suffers from substantial inter-observer variability and depends on scarce expert radiologists. Expert readers follow a hierarchical, coarse-to-fine visual strategy: they first localize the prostate gland and then direct focused attention to tissue within it. Inspired by this biological selective-attention mechanism, we propose a segmentation-guided framework in which a modality-aware 3D Vision Transformer (ViT) first delineates the prostate gland from T2-weighted, ADC, and DWI volumes, and the resulting anatomical mask then constrains downstream cancer detection. Global self-attention models long-range anatomical context, analogous to the integration of peripheral and foveal information in human vision. Detection was evaluated through two pathways: gray-level co-occurrence matrix (GLCM) texture features with classical classifiers, and a ViT classifier. On 200 patients from the public PROSTATEx cohort, the proposed segmentation model achieved a Dice Similarity Coefficient of [0.903 ± 0.033] versus [0.898 ± 0.034] for an optimized U-Net. Ablation experiments confirmed that anatomical guidance improved both pathways. These results show that emulating expert visual search strategies yields accurate and interpretable computer-aided prostate cancer diagnosis.
Förderung
- Umm AL-Qura University
Zitieren
APA
Iqbal, S., Raza, A., Nawaz, S., Bilal, M., Jaffar, A. Y., Alharbi, A., & Iqbal, M. Z. (2026). Biologically Inspired Selective Attention for Prostate MRI: A Segmentation-Guided Vision Transformer Framework for Computer-Aided Diagnosis. Biomimetics, 11(11), 824. https://doi.org/10.3390/biomimetics11110824
Vancouver
Iqbal S, Raza A, Nawaz S, Bilal M, Jaffar AY, Alharbi A, et al. Biologically Inspired Selective Attention for Prostate MRI: A Segmentation-Guided Vision Transformer Framework for Computer-Aided Diagnosis. Biomimetics. 2026;11(11):824. doi:10.3390/biomimetics11110824
BibTeX
@article{Iqbal2026,
author = {Iqbal, Saqib and Raza, Ali and Nawaz, Sameen and Bilal, Muhammad and Jaffar, Amar Y. and Alharbi, Ayman and Iqbal, Muhammad Zafar},
title = {Biologically Inspired Selective Attention for Prostate MRI: A Segmentation-Guided Vision Transformer Framework for Computer-Aided Diagnosis},
journal = {Biomimetics},
year = {2026},
volume = {11},
number = {11},
pages = {824},
doi = {10.3390/biomimetics11110824}
}
EUVIMED