AIToday
AI in HealthcareNikkei AI StocksPublished: Aug 28, 2026, 19:01 JST2 min read

Osaka University's AI detects oral cancer in 30 seconds

Osaka University's AI detects oral cancer in 30 seconds

Key takeaway

  • Japan's health ministry approved an AI system that detects suspected oral cancer in 30 seconds.

  • Developed by Osaka University with Nvidia's help, it helps dentists decide referrals.

  • The device is called Mucosight AI.

3 Key Points

  1. What happened

    Osaka University and colleagues received regulatory approval from Japan's health ministry for an AI diagnostic support system that detects suspected oral cancer in about 30 seconds. The AI model was developed with support from Nvidia, and Morita Tokyo Manufacturing handles manufacturing and sales.

  2. Why it matters

    Oral cancer affects about 10,000 new patients annually in Japan, and early lesions can be mistaken for mouth sores, delaying detection. The AI analyzes oral images to identify precancerous lesions, mouth sores, and benign tumors, helping dentists decide whether to refer patients to specialists.

  3. What to watch

    The system, named Mucosight AI, is now approved as a 'program medical device.' Development began in 2017, with 40,000 oral images from seven hospitals used to train the AI. The university team aims to connect local dental clinics with advanced medical institutions for early detection.

Ask the AI about this article →

Context & Analysis

The approval marks a milestone in applying AI to cancer screening in Japan. The system addresses a real clinical challenge: early oral cancer looks similar to common mouth sores, often leading to delayed diagnosis. By providing a quick, objective analysis, it could help dentists in community clinics decide when to refer patients to higher-level hospitals, potentially improving early detection rates. The collaboration with Nvidia highlights the role of computing power in medical AI development. The project's scale—40,000 images from seven institutions—underscores the importance of high-quality training data. However, the article does not specify the system's sensitivity or specificity, so the actual clinical benefit remains to be seen in practice. The device's approval as a 'program medical device' indicates it meets regulatory standards for safety and effectiveness, but its real-world impact will depend on adoption and integration into routine dental care.

FAQ

How accurate is the AI system?
The article does not provide accuracy statistics. It states that the AI analyzes oral images to identify features of precancerous lesions, mouth sores, and benign tumors in about 30 seconds.
Who is the manufacturer and seller of the device?
Morita Tokyo Manufacturing, based in Saitama Prefecture, is responsible for manufacturing and sales of the system.
When did development begin and how was the AI trained?
Development started in 2017. The AI was trained on 40,000 oral images from seven medical institutions, with evaluations by specialists at Osaka University. Nvidia provided technical support since 2018.
Nikkei AI StocksRead Original Article

Get the latest AI in Healthcare news every morning

For example, today's edition would include:

  • Huawei healthcare chief signals more AI pharma tie-upsTop Companies AI · 15h ago
  • Oral Cancer AI 'Mucosight AI' Gets ApprovalITmedia AI+ · 1d ago
  • Astellas adopts Boltz-2 NIM to speed up drug discoveryTop Companies AI · 1d ago

AI-summarized, only the topics you pick — one digest a day via Email, Slack, or Discord.

Free · takes 30 seconds · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. Q&As are published on this page for other readers too.

Related Articles

Next articleNvidia forms PAC to expand Washington lobbying