PulseExploreJournal ClubTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
May 14, 2026Scientific ReportsOpen Access

Efficient deep learning models for oral squamous cell carcinoma classification in histopathological images

View Full Paper
Ask AI
Bookmark
Share

Authors

JKJ S Ananda KumarMKM Surendra KumarMJMani Jindal

Discussion

Loading...

Member takes

Overview

Randomized trial demonstrates high accuracy in classifying oral squamous cell carcinoma using deep learning models, suggesting enhanced diagnostic capabilities.

Key Points

  • The aim is to evaluate the effectiveness of deep learning models in classifying histopathological images of oral squamous cell carcinoma.
  • Evaluated four deep learning convolutional neural network models: ResNet50, DenseNet201, EfficientNetB0, and ConvNeXt_Tiny.
  • Performed binary classification of 10,000 histopathological images (benign vs. carcinoma).
  • Analyzed model performance using accuracy and ROC-AUC scores.
  • EfficientNetB0 achieved an accuracy of 97.6% and ROC-AUC of 0.9963.
  • ConvNeXt_Tiny yielded an accuracy of 95.92%.
  • DenseNet201 achieved 86.08% accuracy, while ResNet50 had the lowest at 71.52%.

Cite This Study

Kumar et al. (2026) studied this question.

synapsesocial.com/papers/6a0567a8a550a87e60a1fd26https://doi.org/10.1038/s41598-026-44424-5
View Full Paper
Ask AI
Bookmark
Share