KTransNet: A Hybrid Transformer-CNN Framework for Early-Stage Chronic Kidney Disease Detection Using Multi-Modal Renal Imaging
International Journal of Innovative Science and Research Technology · 11.05.2026 · 37
DOI: 10.38124/ijisrt/26may250 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Innovative Science and Research Technology, online erschienen am 11.05.2026. Verfasst von Ravirajsinh Vaghela und 1 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben.
Abstract (Originalsprache)
Chronic Kidney Disease (CKD) often progresses silently until advanced stages, making early detection crucial for timely intervention. This paper introduces KTransNet, a novel hybrid deep learning model that combines Transformerbased encoders with CNN layers and integrates a YOLOv8 detection head for efficient early-stage CKD diagnosis from medical imaging. The model employs a patch-based token embedding strategy with custom positional encoding and dense blocks for feature reuse, enabling robust local and global feature extraction.
Zitieren
APA
Vaghela, R., & Thacker, S. (2026). KTransNet: A Hybrid Transformer-CNN Framework for Early-Stage Chronic Kidney Disease Detection Using Multi-Modal Renal Imaging. International Journal of Innovative Science and Research Technology, 37. https://doi.org/10.38124/ijisrt/26may250
Vancouver
Vaghela R, Thacker S. KTransNet: A Hybrid Transformer-CNN Framework for Early-Stage Chronic Kidney Disease Detection Using Multi-Modal Renal Imaging. International Journal of Innovative Science and Research Technology. 2026:37. doi:10.38124/ijisrt/26may250
BibTeX
@article{Vaghela2026,
author = {Vaghela, Ravirajsinh and Thacker, Smit},
title = {KTransNet: A Hybrid Transformer-CNN Framework for Early-Stage Chronic Kidney Disease Detection Using Multi-Modal Renal Imaging},
journal = {International Journal of Innovative Science and Research Technology},
year = {2026},
pages = {37},
doi = {10.38124/ijisrt/26may250}
}
EUVIMED