DeepPolyp: an artificial intelligence framework for polyp detection and segmentation
Exploration of Digital Health Technologies · 2025
DOI: 10.37349/edht.2025.101158 ↗Kurz gefasst
Fachartikel in der Zeitschrift Exploration of Digital Health Technologies, 2025. Verfasst von Marco Mameli und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Aim
Colorectal cancer is a leading cause of cancer-related mortality, emphasising the need for accurate polyp segmentation during colonoscopy for early detection. Existing methods often struggle to generalize effectively across diverse clinical scenarios. This study introduces DeepPolyp, an artificial intelligence framework designed for comprehensive benchmarking and real-time clinical deployment of polyp segmentation models.
Methods
Transformer-based segmentation models, SegFormer and SSFormer, were trained from scratch using an extensive dataset comprising public collections (CVC-ClinicDB, ETIS-LaribPolypDB, Kvasir) and recently augmented datasets (PolypDataset-TCNoEndo, PolypGen). Training involved standardized data augmentation, learning rate schedules, and early stopping. Models were evaluated using Dice and Intersection over Union (IoU) metrics. Real-time inference performance was assessed on an NVIDIA Jetson Orin device with ONNX and TensorRT optimizations.
Results
SegFormer-B4 achieved the highest accuracy (Dice: 0.9843, IoU: 0.9694), but was not selected for clinical deployment due to computational constraints. SegFormer-B2 provided comparable accuracy (Dice: 0.9787, IoU: 0.9588) with significantly faster inference (94 ms per frame), offering an optimal balance suitable for real-time clinical use. SSFormer showed lower accuracy and slower inference, limiting its practical deployment.
Conclusions
DeepPolyp enables systematic evaluation of polyp segmentation models, assisting in selecting models based on both performance and computational efficiency. Despite superior accuracy from SegFormer-B4, SegFormer-B2 was selected for clinical deployment due to its advantageous balance between accuracy and real-time execution efficiency.
Zitieren
APA
Mameli, M., Shiralizadeh, S., Papi, M., & Coltea, I. G. (2025). DeepPolyp: an artificial intelligence framework for polyp detection and segmentation. Exploration of Digital Health Technologies. https://doi.org/10.37349/edht.2025.101158
Vancouver
Mameli M, Shiralizadeh S, Papi M, Coltea IG. DeepPolyp: an artificial intelligence framework for polyp detection and segmentation. Exploration of Digital Health Technologies. 2025. doi:10.37349/edht.2025.101158
BibTeX
@article{Mameli2025,
author = {Mameli, Marco and Shiralizadeh, Sepideh and Papi, Massimiliano and Coltea, Iulian Gabriel},
title = {DeepPolyp: an artificial intelligence framework for polyp detection and segmentation},
journal = {Exploration of Digital Health Technologies},
year = {2025},
doi = {10.37349/edht.2025.101158}
}
EUVIMED