DAEJEON, July 28 (Korea Bizwire) — The Korea Advanced Institute of Science and Technology (KAIST) said on Wednesday that it has developed new artificial intelligence (AI) technology that can automatically decode chest X-ray images, identifying diseases such as tuberculosis, pneumothorax and COVID-19.
In collaboration with a national hospital, the research team developed a new AI algorithm with self-supervised and self-trained learning (DISTL).
The algorithm involves self-learning and teacher-student knowledge transfer techniques to mimic the process in which radiologists learn to read images in hospitals.
If the initial model is trained with only a small amount of label data, the model can improve its performance on its own with only unlabeled data that accumulates over time.
The research team said it is novel technology to be able to use countless chest X-ray images collected during annual health checkups.
Most of the currently used medical AI techniques are based on the supervised learning method, which has been a stumbling block preventing the development of medical AI due to the problem of continuously obtaining expert data labels which takes a lot of time and money.
M. H. Lee ([email protected])