Scale-Specific Visual Sensing for Colonoscopy Polyp Segmentation via Hybrid CNN-Transformer Attention
ICCK Transactions on Sensing, Communication, and Control · 28.06.2026 · 3 (2) · 109-123
DOI: 10.62762/tscc.2026.664028 ↗Kurz gefasst
Fachartikel in der Zeitschrift ICCK Transactions on Sensing, Communication, and Control, online erschienen am 28.06.2026. Verfasst von Ikram Majeed Khan und 1 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref).
Abstract (Originalsprache)
Precise segmentation of colorectal polyps in colonoscopy images is essential for timely cancer diagnosis and prevention. Nevertheless, current segmentation methods contend with intrinsic variability in polyp appearance, differences in size, shape, and texture, while preserving computational efficiency necessary for clinical implementation. In this paper, we present a novel segmentation architecture that integrates scale-specific attention mechanisms within a hybrid CNN-Transformer backbone to address these challenges. Our model employs Coordinate Attention for high-resolution feature maps to preserve spatial details essential for boundary delineation, and Channel Attention for deep semantic features to enhance discriminative capacity. These representations are progressively integrated through a hierarchical decoder with specialized fusion modules: Semantic Fusion for high-level features, and Detail-Preserving Fusion for low-level features. The proposed architecture achieves state-of-the-art performance across five benchmark datasets, demonstrating superior generalization and robustness in challenging clinical scenarios.
Zitieren
APA
Khan, I. M., & Khan, W. (2026). Scale-Specific Visual Sensing for Colonoscopy Polyp Segmentation via Hybrid CNN-Transformer Attention. ICCK Transactions on Sensing, Communication, and Control, 3(2), 109-123. https://doi.org/10.62762/tscc.2026.664028
Vancouver
Khan IM, Khan W. Scale-Specific Visual Sensing for Colonoscopy Polyp Segmentation via Hybrid CNN-Transformer Attention. ICCK Transactions on Sensing, Communication, and Control. 2026;3(2):109-123. doi:10.62762/tscc.2026.664028
BibTeX
@article{Khan2026,
author = {Khan, Ikram Majeed and Khan, Wisal},
title = {Scale-Specific Visual Sensing for Colonoscopy Polyp Segmentation via Hybrid CNN-Transformer Attention},
journal = {ICCK Transactions on Sensing, Communication, and Control},
year = {2026},
volume = {3},
number = {2},
pages = {109--123},
doi = {10.62762/tscc.2026.664028}
}
EUVIMED