Federated Transformer-Enhanced MobileNet V2for Decentralized Polyp Detection inColonoscopy Images
International Journal of Image, Graphics and Signal Processing · 08.08.2026 · 18 (4) · 121-138
DOI: 10.5815/ijigsp.2026.04.07 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Image, Graphics and Signal Processing, erschienen am 08.08.2026. Verfasst von Kumar Janardan Patra und 2 weiteren Autor:innen.
Abstract (Originalsprache)
Early polyp detection is vital in avoiding colorectal cancer, a top contributor to cancer-related deaths globally.Automated polyp detection has been greatly improved by deep learning, but extensive deployment tends to be hamperedby patient data privacy fears. For this purpose, we suggest a federated learning (FL) paradigm that enables decentralizedmodel training without sharing raw patient data while having high diagnostic accuracy. We first performed an extensiveevaluation using DL models on a polyp dataset that we gathered. MobileNetV2 was the best performing model as perimportant metrics like accuracy, precision, recall, and F1 score. In order to further expand its representational power, weincorporated a transformer module into MobileNetV2 so that the model can better capture long-range dependencies andcontext information. Our new Transformer-Enhanced MobileNetV2 model was then implemented on several simulatedclients in a federated learning scenario. This configuration enabled training over decentralized clinical data withoutviolating patient privacy. We utilized standard FL algorithms for model averaging and evaluated the system in accuracy,precision, recall, F1 score, and convergence time. The devised approach performed extremely well with an accuracy of98.37% and an F1 score of 0.971 while converging effectively in 27-33 rounds. These findings imply that a promisingpath for safe and effective medical image analysis is to combine transformer designs with lightweight models in afederated condition.
Zitieren
APA
Patra, K. J., Mishra, J., & Nayak, S. R. (2026). Federated Transformer-Enhanced MobileNet V2for Decentralized Polyp Detection inColonoscopy Images. International Journal of Image, Graphics and Signal Processing, 18(4), 121-138. https://doi.org/10.5815/ijigsp.2026.04.07
Vancouver
Patra KJ, Mishra J, Nayak SR. Federated Transformer-Enhanced MobileNet V2for Decentralized Polyp Detection inColonoscopy Images. International Journal of Image, Graphics and Signal Processing. 2026;18(4):121-138. doi:10.5815/ijigsp.2026.04.07
BibTeX
@article{Patra2026,
author = {Patra, Kumar Janardan and Mishra, Jibitesh and Nayak, Soumya Ranjan},
title = {Federated Transformer-Enhanced MobileNet V2for Decentralized Polyp Detection inColonoscopy Images},
journal = {International Journal of Image, Graphics and Signal Processing},
year = {2026},
volume = {18},
number = {4},
pages = {121--138},
doi = {10.5815/ijigsp.2026.04.07}
}
EUVIMED