Scholarlink

Oral cancer is a major public health burden with a high global prevalence. However, the early diagnosis of the oral malignancies is crucial to improve the patient outcomes, because delay in diagnosis involve aggressive treatment and also diminish the survival rate. Biopsy and clinical examination based oral cancer diagnosis. This process can be time-consuming and subject to human error. In order to tackle these issues, the evolution of deep learning methods, specifically Vision Transformers (ViT), offer a promising solution for automated image-based categorization of oral malignancy. This paper proposes a vision transformers model for image classification of oral cavity. We hope to use attention-based approaches to clearly differentiate between normal and malignant images to assist in the early diagnosis and intervention.

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

Leveraging Vision Transformers for Early Detection of Oral Cancer: A Deep Learning Approach to Medical Imaging

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Manjeet Soni,
  • Shivam Negi,
  • Sunita Varma,
  • Ashish Jain,
  • Ajay Parihar

摘要

Oral cancer is a major public health burden with a high global prevalence. However, the early diagnosis of the oral malignancies is crucial to improve the patient outcomes, because delay in diagnosis involve aggressive treatment and also diminish the survival rate. Biopsy and clinical examination based oral cancer diagnosis. This process can be time-consuming and subject to human error. In order to tackle these issues, the evolution of deep learning methods, specifically Vision Transformers (ViT), offer a promising solution for automated image-based categorization of oral malignancy. This paper proposes a vision transformers model for image classification of oral cavity. We hope to use attention-based approaches to clearly differentiate between normal and malignant images to assist in the early diagnosis and intervention.