Precise Identification of Oral Cancer Lesions Using Artificial Intelligence

Area of Science:

• Medical Imaging
• Artificial Intelligence in Healthcare
• Oral Pathology

Background:

• Dentists, particularly in rural areas, require AI tools for accurate oral cancer screening using smartphone images.
• Limited research exists on AI models for oral lesion segmentation in smartphone imagery.

Purpose of the Study:

• To develop a deep learning-based AI system for simultaneous identification and segmentation of oral cancer lesions in smartphone images.
• To address the need for accessible oral cancer screening tools for general dentists.

Main Methods:

• Utilized a deep learning approach for image analysis.
• The AI model was trained to detect oral lesions, classify lesion types (oral potentially malignant disorders and oral squamous cell carcinoma), and precisely outline lesion boundaries.

Main Results:

• The AI model successfully detected the presence of oral lesions in images.
• The system accurately determined the types of oral lesions.
• Precise segmentation of oral lesion boundaries was achieved.

Conclusions:

• This AI system offers a novel solution for early detection and diagnosis of oral cancer and potentially malignant disorders.
• The technology has the potential to improve patient outcomes through timely intervention and treatment.
• Further development can enhance accessibility of advanced diagnostic capabilities for dentists in underserved regions.