Optimised Deep Learning for Gastrointestinal Polyp Classification: A Controlled Benchmark of Five CNN and Transformer Architectures with Grad-CAM Interpretability
Diagnostics · 13.07.2026 · 16 (14) · 2182
DOI: 10.3390/diagnostics16142182 ↗Kurz gefasst
Fachartikel in der Zeitschrift Diagnostics, online erschienen am 13.07.2026. Verfasst von Zhengsui Gu und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, China. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Background/Objectives: Colorectal cancer (CRC) is the second leading cause of cancer-related mortality worldwide, with polyp miss rates of up to 26% reported during colonoscopy and classification accuracy remaining highly operator-dependent. Accurate multi-class polyp subtype classification is clinically critical, as it directly determines treatment decisions: adenomatous polyps require resection, whereas hyperplastic lesions may warrant only surveillance. This study aims to systematically compare five deep learning architectures for five-class gastrointestinal polyp classification and to provide clinically interpretable diagnostic insights through Grad-CAM visualisation.
Methods
ResNet50, VGG16, EfficientNet-B3, DenseNet121, and Vision Transformer (ViT-B/16) were evaluated on the Kvasir Dataset V2 (5000 images, five classes) under a unified training and evaluation protocol on common GPU hardware. All models employed ImageNet transfer learning with a redesigned multi-layer classification head. Two optimisation strategies were applied: SGD with cosine annealing for CNN architectures, and AdamW with linear warmup for ViT-B/16. Gradient-weighted Class Activation Mapping (Grad-CAM) was applied to generate spatial attention heatmaps for qualitative clinical interpretation.
Results
Under a single 80/10/10 split, ViT-B/16 attained the highest accuracy (97.2%); however, because a single split is sensitive to sampling, the evaluation was strengthened with stratified five-fold cross-validation (mean ± SD). Under cross-validation, EfficientNet-B3 achieved the highest accuracy at 95.90 ± 0.35%, followed closely by ViT-B/16 (95.12 ± 0.72%), then ResNet50 (91.74 ± 0.74%), DenseNet121 (90.32 ± 0.70%), and VGG16 (88.50 ± 1.72%); the small standard deviations indicate that all models, including ViT-B/16, were stable across folds. Pairwise McNemar tests with Holm correction found that every difference was statistically significant (p < 0.05), including the EfficientNet-B3 advantage over ViT-B/16 (p = 0.010). ViT-B/16 thus remained a strong, stable performer that significantly outperformed the three remaining CNNs, while the cross-validated ranking placed the most compact model, EfficientNet-B3, first: a Vision Transformer was highly competitive with, but not superior to, the strongest CNN. A consistent, architecture-agnostic misclassification pattern was identified between dyed-lifted polyps and dyed-resection margins across all five models, consistent with a task-level visual ambiguity that may also reflect overlapping class definitions and annotation factors, with direct clinical implications. Grad-CAM analysis, quantified by attention-entropy and concentration metrics, showed that model attention remained focused on relevant stained tissue regardless of whether predictions were correct, indicating that the dyed-class confusions reflect genuine visual ambiguity rather than a localisation failure.
Conclusions
Under cross-validation, EfficientNet-B3 achieved the highest accuracy on the Kvasir V2 five-class task, significantly outperforming all other architectures, with ViT-B/16 being a close and competitive second. The identified confusion between post-procedural chromoendoscopic classes is unlikely to be fully resolved by architectural changes alone and may require higher-resolution imaging or domain expert re-annotation. These findings contribute to the evidence base for explainable deep learning in gastrointestinal endoscopy; external, multi-centre validation remains necessary before clinical adoption.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, China.
- Department of Engineering, College of Engineering, Brunel University of London, Uxbridge UB8 3PH, UK.
Zitieren
APA
Gu, Z., Ibrahim, H. A., Balachandran, W., & Huda, M. N. (2026). Optimised Deep Learning for Gastrointestinal Polyp Classification: A Controlled Benchmark of Five CNN and Transformer Architectures with Grad-CAM Interpretability. Diagnostics, 16(14), 2182. https://doi.org/10.3390/diagnostics16142182
Vancouver
Gu Z, Ibrahim HA, Balachandran W, Huda MN. Optimised Deep Learning for Gastrointestinal Polyp Classification: A Controlled Benchmark of Five CNN and Transformer Architectures with Grad-CAM Interpretability. Diagnostics. 2026;16(14):2182. doi:10.3390/diagnostics16142182
BibTeX
@article{Gu2026,
author = {Gu, Zhengsui and Ibrahim, Hoda Anwar and Balachandran, Wamadeva and Huda, Md Nazmul},
title = {Optimised Deep Learning for Gastrointestinal Polyp Classification: A Controlled Benchmark of Five CNN and Transformer Architectures with Grad-CAM Interpretability},
journal = {Diagnostics},
year = {2026},
volume = {16},
number = {14},
pages = {2182},
doi = {10.3390/diagnostics16142182}
}
EUVIMED