Home > Press Releases
JST Press Release

Aug. 29, 2012

Japan Science and Technology Agency (JST)
5-3, Yonbancho, Chiyoda-ku, Tokyo 102-8666

CARTA, Clustering-Aided Rapid Training Agent,
universal and self-learning bioimage classification software;
applicable to high-speed diagnostic imaging

Diverse imaging technologies are widely used from basic research to clinical diagnostic imaging. Analyzing huge number of images requires a lot of time and skills and limits the diagnostic effectiveness. Matsunaga and his colleagues have successfully developed CARTA (Clustering-Aided Rapid Training Agent), which is an active learning software to classify a large number of images. Several biological and medical image datasets were successfully classified by CARTA. These results demonstrate CARTA's potential impact to realize powerful diagnostic imaging.

Research Information

JST-SENTAN (Development of Advanced Measurement and Analysis Systems), Technology Development Type, “Development of customized classifying software for bioimaging”

Article Information

Natsumaro Kutsuna, Takumi Higaki, Sachihiro Matsunaga, Tomoshi Otsuki, Masayuki Yamaguchi, Hirofumi Fujii and Seiichiro Hasezawa. “Active learning framework with iterative clustering for bioimage classification.” Nature Communications, 2012.
doi: 10.1038/ncomms2030


About Research :

Sachihiro MATSUNAGA, Ph.D.
Associate Professor,
Department of Applied Biological Science, Faculty of Science and Technology,
Tokyo University of Science

About Program :

Akira KUBO
Department of Industry-Academic Alliance, in charge of Advanced Measuring Technology,
Japan Science and Technology Agency


JST, an integrated organization of science and technology in Japan, establishes an infrastructure for the entire process from the creation of knowledge to the return to the society. For more information, visit http://www.jst.go.jp/EN/