EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Explainable CNN–Radiomics Fusion and Ensemble Learning for Multimodal Lesion Classification in Dental Radiographs

Zuhal Can iD, Emre Aydin iD

Diagnostics · 09.08.2025 · 15 (16) · 1997

DOI: 10.3390/diagnostics15161997 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Diagnostics, online erschienen am 09.08.2025. Verfasst von Zuhal Can und 1 weiteren Autor:innen. Beteiligte Einrichtung: Computer Engineering Department, Engineering and Architecture Faculty, Eskisehir Osmangazi University, Eskisehir 26040, Türkiye. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background/Objectives: Clinicians routinely rely on periapical radiographs to identify root-end disease, but interpretation errors and inconsistent readings compromise diagnostic accuracy. We, therefore, developed an explainable, multimodal AI framework that (i) fuses two data modalities, deep CNN embeddings and radiomic texture descriptors that are extracted only from lesion-relevant pixels selected by Grad-CAM, and (ii) makes every prediction transparent through dual-layer explainability (pixel-level Grad-CAM heatmaps + feature-level SHAP values).

Methods

A dataset of 2285 periapical radiographs was processed using six CNN architectures (EfficientNet-B1/B4/V2M/V2S, ResNet-50, Xception). For each image, a Grad-CAM heatmap generated from the penultimate layer of the CNN was thresholded to create a binary mask that delineated the region most responsible for the network’s decision. Radiomic features (first-order, GLCM, GLRLM, GLDM, NGTDM, and shape2D) were then computed only within that mask, ensuring that handcrafted descriptors and learned embeddings referred to the same anatomic focus. The two feature streams were concatenated, optionally reduced by principal component analysis or SelectKBest, and fed to random forest or XGBoost classifiers; five-view test-time augmentation (TTA) was applied at inference. Pixel-level interpretability was provided by the original Grad-CAM, while SHAP quantified the contribution of each radiomic and deep feature to the final vote.

Results

Raw CNNs achieved a ca. 52% accuracy and AUC values near 0.60. The multimodal fusion raised performance dramatically; the Xception + radiomics + random forest model achieved a 95.4% accuracy and an AUC of 0.9867, and adding TTA increased these to 96.3% and 0.9917, respectively. The top ensemble, Xception and EfficientNet-V2S fusion vectors classified with XGBoost under five-view TTA, reached a 97.16% accuracy and an AUC of 0.9914, with false-positive and false-negative rates of 4.6% and 0.9%, respectively. Grad-CAM heatmaps consistently highlighted periapical regions, while SHAP plots revealed that radiomic texture heterogeneity and high-level CNN features jointly contributed to correct classifications.

Conclusions

By tightly integrating CNN embeddings, mask-targeted radiomics, and a two-tiered explainability stack (Grad-CAM + SHAP), the proposed system delivers state-of-the-art lesion detection and a transparent technique, addressing both accuracy and trust.

Schlagwörter

Stichwörter der Autor:innen

CNN-radiomic fusionSHAPdeep learningdental radiographsdimensionality reductionexplainabilityperiapical lesion detectionradiomicstest-time augmentation

Autor:innen und Institutionen

  • Computer Engineering Department, Engineering and Architecture Faculty, Eskisehir Osmangazi University, Eskisehir 26040, Türkiye.

ORCID-Profile: Zuhal Can, Emre Aydin

Zitieren

APA

Can, Z., & Aydin, E. (2025). Explainable CNN–Radiomics Fusion and Ensemble Learning for Multimodal Lesion Classification in Dental Radiographs. Diagnostics, 15(16), 1997. https://doi.org/10.3390/diagnostics15161997

Vancouver

Can Z, Aydin E. Explainable CNN–Radiomics Fusion and Ensemble Learning for Multimodal Lesion Classification in Dental Radiographs. Diagnostics. 2025;15(16):1997. doi:10.3390/diagnostics15161997

BibTeX
@article{Can2025,
  author = {Can, Zuhal and Aydin, Emre},
  title = {Explainable CNN–Radiomics Fusion and Ensemble Learning for Multimodal Lesion Classification in Dental Radiographs},
  journal = {Diagnostics},
  year = {2025},
  volume = {15},
  number = {16},
  pages = {1997},
  doi = {10.3390/diagnostics15161997}
}
Kostenlos starten →