Skip to main content
See every side of every news story
Published loading...Updated

Scientist turns people’s mental images into text using ‘mind-captioning’ technology

The AI-driven method decodes brain activity into detailed text with about 50% accuracy in identifying viewed or imagined videos among 100 candidates, advancing communication aid research.

  • On November 25, 2025, Tomoyasu Horikawa published in Science Advances a method converting mental images into descriptive sentences using brain activity at NTT's Communication Science Laboratories.
  • The research sought to bridge nonverbal mental representations and language by addressing limits of prior decoding methods reliant on verbal activity, aiming to help aphasia and other conditions limiting access to language.
  • In the experiment, six adult participants underwent fMRI while viewing 2,180 silent videos and recalling 72 test videos repeated five times; researchers used DeBERTa, linear decoders, and RoBERTa with 100 optimization iterations.
  • The method generated coherent descriptions without relying on the brain's traditional language regions, suggesting it could help people with aphasia or amyotrophic lateral sclerosis communicate.
  • Ethicists such as Marcello Ienca and Aukasz Szoszkiewicz warned about mental-privacy risks and urged strict consent and regulation as study participants provided about 17 hours of data each.
Insights by Ground AI

14 Articles

Center

A scientist in Japan developed a technique that uses brain scanners and artificial intelligence to convert a person’s mental images into descriptive and precise sentences. While there have been advances in the use of brain activity scanners to translate the words we think into text, converting our complex mental images into language has proved to be a challenge, according to Tomoyasu Horikawa, author of a study published on November 5 in Science…

CNNCNN
+9 Reposted by 9 other sources
Lean Left

Scientist turns people’s mental images into text using ‘mind-captioning’ technology

A scientist in Japan has developed a technique that uses brain scans and artificial intelligence to turn a person’s mental images into descriptive sentences.

·Atlanta, United States
Read Full Article
Think freely.Subscribe and get full access to Ground NewsSubscriptions start at $9.99/yearSubscribe

Bias Distribution

  • 91% of the sources are Center
91% Center

Factuality Info Icon

To view factuality data please Upgrade to Premium

Ownership

Info Icon

To view ownership data please Upgrade to Vantage

PsyPost broke the news in on Monday, November 10, 2025.
Too Big Arrow Icon
Sources are mostly out of (0)

Similar News Topics

News
Feed Dots Icon
For You
Search Icon
Search
Blindspot LogoBlindspotLocal