Scholarlink

<p>Oral cancer has a high mortality rate primarily due to delayed diagnoses, highlighting the need for early detection of oral lesions. This study presents a novel deep learning framework for multi-class classification-based segmentation, enabling accurate differential diagnosis of 14 common oral lesions—benign, pre-malignant, and malignant—across various mouth locations using photographic images. A dataset of 2,072 clinical images was used to train and validate the model. The proposed framework integrates EfficientNet-B3 for classification and ResNet-101-based Mask R-CNN for segmentation, achieving a classification accuracy of 74.49% and segmentation performance with an average precision (AP50) of 72.18. The gradient-weighted class activation map technique was applied to the model outputs to enable visualization of the specific areas that were most influential for predictive decisions made by the model. This significantly improves upon the state-of-the-art, where previous models achieved lower segmentation accuracy (AP50 &lt; 50%). The framework not only classifies the lesion type but also delineates the lesion boundaries with high precision, which is critical for early detection and differential diagnosis in clinical practice.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

CLASEG: advanced multiclassification and segmentation for differential diagnosis of oral lesions using deep learning

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年7月2日

查看全文
  • Afnan Al-Ali,
  • Ali Hamdi,
  • Mohamed Elshrif,
  • Keivin Isufaj,
  • Khaled Shaban,
  • Peter Chauvin,
  • Sreenath Madathil,
  • Ammar Daer,
  • Faleh Tamimi,
  • Raidan Ba-Hattab

摘要

Oral cancer has a high mortality rate primarily due to delayed diagnoses, highlighting the need for early detection of oral lesions. This study presents a novel deep learning framework for multi-class classification-based segmentation, enabling accurate differential diagnosis of 14 common oral lesions—benign, pre-malignant, and malignant—across various mouth locations using photographic images. A dataset of 2,072 clinical images was used to train and validate the model. The proposed framework integrates EfficientNet-B3 for classification and ResNet-101-based Mask R-CNN for segmentation, achieving a classification accuracy of 74.49% and segmentation performance with an average precision (AP50) of 72.18. The gradient-weighted class activation map technique was applied to the model outputs to enable visualization of the specific areas that were most influential for predictive decisions made by the model. This significantly improves upon the state-of-the-art, where previous models achieved lower segmentation accuracy (AP50 < 50%). The framework not only classifies the lesion type but also delineates the lesion boundaries with high precision, which is critical for early detection and differential diagnosis in clinical practice.