EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Explainable AI for Oral Cancer Diagnosis: Multiclass Classification of Histopathology Images and Grad-CAM Visualization

Jelena Štifanić iD, Daniel Štifanić iD, Nikola Anđelić iD, Zlatan Car

Biology · 22.07.2025 · 14 (8) · 909

DOI: 10.3390/biology14080909 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biology, online erschienen am 22.07.2025. Verfasst von Jelena Štifanić und 3 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Engineering, University of Rijeka, Vukovarska 58, 51000 Rijeka, Croatia. Die Arbeit wurde bisher 27-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Oral cancer is typically diagnosed through histological examination; however, the primary issue with this type of procedure is tumor heterogeneity, where a subjective aspect of the examination may have a direct effect on the treatment plan for a patient. To reduce inter- and intra-observer variability, artificial intelligence algorithms are often used as computational aids in tumor classification and diagnosis. This research proposes a two-step approach for automatic multiclass grading using oral histopathology images (the first step) and Grad-CAM visualization (the second step) to assist clinicians in diagnosing oral squamous cell carcinoma. The Xception architecture achieved the highest classification values of 0.929 (±σ = 0.087) AUCmacro and 0.942 (±σ = 0.074) AUCmicro. Additionally, Grad-CAM provided visual explanations of the model’s predictions by highlighting the precise areas of histopathology images that influenced the model’s decision. These results emphasize the potential of integrated AI algorithms in medical diagnostics, offering a more precise, dependable, and effective method for disease analysis.

Schlagwörter

Stichwörter der Autor:innen

GRAD-Camartificial intelligenceexplainable deep learninghistopathology imagesoral squamous cell carcinoma

Autor:innen und Institutionen

  • Faculty of Engineering, University of Rijeka, Vukovarska 58, 51000 Rijeka, Croatia.
  • Faculty of Engineering, Catholic University of Croatia, Ilica 244, 10000 Zagreb, Croatia.

ORCID-Profile: Jelena Štifanić, Daniel Štifanić, Nikola Anđelić

Zitieren

APA

Štifanić, J., Štifanić, D., Anđelić, N., & Car, Z. (2025). Explainable AI for Oral Cancer Diagnosis: Multiclass Classification of Histopathology Images and Grad-CAM Visualization. Biology, 14(8), 909. https://doi.org/10.3390/biology14080909

Vancouver

Štifanić J, Štifanić D, Anđelić N, Car Z. Explainable AI for Oral Cancer Diagnosis: Multiclass Classification of Histopathology Images and Grad-CAM Visualization. Biology. 2025;14(8):909. doi:10.3390/biology14080909

BibTeX
@article{tifani2025,
  author = {Štifanić, Jelena and Štifanić, Daniel and Anđelić, Nikola and Car, Zlatan},
  title = {Explainable AI for Oral Cancer Diagnosis: Multiclass Classification of Histopathology Images and Grad-CAM Visualization},
  journal = {Biology},
  year = {2025},
  volume = {14},
  number = {8},
  pages = {909},
  doi = {10.3390/biology14080909}
}
Kostenlos starten →