EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Syncretic Grad-CAM Integrated ViT-CNN Hybrids with Inherent Explainability for Early Thyroid Cancer Diagnosis from Ultrasound

Ahmed Y Alhafdhi, Gibrael Abosamra iD, Abdulrhman M Alshareef iD

Diagnostics · 26.03.2026 · 16 (7) · 999

DOI: 10.3390/diagnostics16070999 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Diagnostics, online erschienen am 26.03.2026. Verfasst von Ahmed Y Alhafdhi und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Information Systems, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah 21589, Saudi Arabia. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: KAU Endowment (WAQF) at King Abdulaziz University, Jeddah.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background/Objectives: Accurate detection of thyroid cancer using ultrasound remains a challenge, as malignant nodules can be microscopic and heterogeneous, easily confused with point clusters and borderline-featured tissues. Current studies in deep learning demonstrate good performance with convolutional neural networks (CNNs) and clustering; however, many approaches focus on local tissue and provide limited, non-quantitative interpretation, reducing clinical confidence. This study proposes an integrated framework combining enhanced convolutional feature encoders (DenseNet169 and VGG19) with an enhanced vision transformer (ViT-E) to integrate local feature and global relational context during learning, rather than delayed integration.

Methods

The proposed framework integrates enhanced convolutional feature encoders (DenseNet169 and VGG19) with an enhanced vision transformer (ViT-E), enabling simultaneous learning of local feature representations and global relational context. This design allows feature fusion during the learning stage instead of delayed integration, aiming to improve diagnostic performance and interpretability in thyroid ultrasound image analysis.

Results

The best-performing model, ViT-E–DenseNet169, achieved 98.5% accuracy, 98.9% sensitivity, 99.15% specificity, and 97.35% AUC, surpassing the robust basic hybrid model (CNN–XGBoost/ANN) and existing systems. A second contribution is improved interpretability, moving from mere illustration to validation. Gradient-weighted class activation mapping (Grad-CAM) maps demonstrated distinct and clinically understandable concentration patterns across various thyroid cancers: precise intralesional concentration for high-confidence malignancies (PTC = 0.968), edge/interface concentration for capsule risk patterns (PTC = 0.957), and broader-field activation consistent with infiltration concerns (PTC = 0.984), while benign scans showed low and diffuse activation (PTC = 0.002). Spatial audits reinforced this behavior (IoU/PAP: 0.72/91%, 0.65/78%, 0.58/62%).

Conclusions

The integrated ViT-E–DenseNet169 framework provides highly accurate thyroid cancer detection while offering clinically meaningful interpretability through Grad-CAM-based spatial validation, supporting improved confidence in AI-assisted ultrasound diagnosis.

Schlagwörter

Stichwörter der Autor:innen

ANNCNNGrad-CAMViT-EXGBoostfusion featuresthyroid cancer

Autor:innen und Institutionen

  • Department of Information Systems, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah 21589, Saudi Arabia.

ORCID-Profile: Gibrael Abosamra, Abdulrhman M Alshareef

Förderung

  • KAU Endowment (WAQF) at King Abdulaziz University, Jeddah

Zitieren

APA

Alhafdhi, A. Y., Abosamra, G., & Alshareef, A. M. (2026). Syncretic Grad-CAM Integrated ViT-CNN Hybrids with Inherent Explainability for Early Thyroid Cancer Diagnosis from Ultrasound. Diagnostics, 16(7), 999. https://doi.org/10.3390/diagnostics16070999

Vancouver

Alhafdhi AY, Abosamra G, Alshareef AM. Syncretic Grad-CAM Integrated ViT-CNN Hybrids with Inherent Explainability for Early Thyroid Cancer Diagnosis from Ultrasound. Diagnostics. 2026;16(7):999. doi:10.3390/diagnostics16070999

BibTeX
@article{Alhafdhi2026,
  author = {Alhafdhi, Ahmed Y and Abosamra, Gibrael and Alshareef, Abdulrhman M},
  title = {Syncretic Grad-CAM Integrated ViT-CNN Hybrids with Inherent Explainability for Early Thyroid Cancer Diagnosis from Ultrasound},
  journal = {Diagnostics},
  year = {2026},
  volume = {16},
  number = {7},
  pages = {999},
  doi = {10.3390/diagnostics16070999}
}
Kostenlos starten →