Faithfulness of saliency explanations in a deep learning classifier for panoramic dental radiographs
SAP Artificial Intelligence in Dentistry · 29.10.2026 · 2 · 157
DOI: 10.62486/aid2026157 ↗Kurz gefasst
Fachartikel in der Zeitschrift SAP Artificial Intelligence in Dentistry, online erschienen am 29.10.2026. Verfasst von Teng He und 2 weiteren Autor:innen. Die Arbeit nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Introduction
Saliency maps are widely used to explain dental imaging classifiers, but their faithfulness has not been measured with perturbation tests.
Methods
Four saliency methods, integrated gradients, Grad-CAM, raw gradients and a random baseline, were generated for a transfer-learning classifier of four dental diagnoses in the DENTEX dataset and evaluated with deletion and insertion tests on 37 correctly classified teeth.
Results
In the insertion test Grad-CAM achieved the highest area under the curve (0.584), followed by integrated gradients (0.482) and raw gradients (0.466), all above the random baseline (0.359). The deletion test produced a different ordering, in which the random baseline showed the lowest area (0.368). Faithfulness varied across diagnosis classes.
Conclusions
Gradient-based saliency methods highlight decision-relevant regions more faithfully than a random baseline by the insertion criterion, with Grad-CAM the most faithful, but the disagreement between deletion and insertion tests warrants caution in interpreting any single saliency map.
Zitieren
APA
He, T., Long, W., & Xie, Y. (2026). Faithfulness of saliency explanations in a deep learning classifier for panoramic dental radiographs. SAP Artificial Intelligence in Dentistry, 2, 157. https://doi.org/10.62486/aid2026157
Vancouver
He T, Long W, Xie Y. Faithfulness of saliency explanations in a deep learning classifier for panoramic dental radiographs. SAP Artificial Intelligence in Dentistry. 2026;2:157. doi:10.62486/aid2026157
BibTeX
@article{He2026,
author = {He, Teng and Long, Wenya and Xie, Yingjuan},
title = {Faithfulness of saliency explanations in a deep learning classifier for panoramic dental radiographs},
journal = {SAP Artificial Intelligence in Dentistry},
year = {2026},
volume = {2},
pages = {157},
doi = {10.62486/aid2026157}
}
EUVIMED