Deepnoid Wins Awards at Global Medical Imaging AI Competition

"Proving Generative AI Capabilities in CT Imaging"
First Place in Two Categories at the Official MICCAI Registered Challenge

Deepnoid, a leading first-generation medical artificial intelligence (AI) developer in South Korea, announced on September 29 that it achieved first place in two categories and third place in one category at the global medical imaging AI competition, the 'VLM3D Challenge'.

The 'VLM3D Challenge' is the official registered challenge of the 'International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) 2025', which was held in Daejeon on September 24. The competition utilizes 'CT-RATE', the world's largest open dataset of paired chest CT scans and radiology reports, to evaluate the innovativeness of 3D vision-language model technology. There are a total of four categories, each with its own task, and teams are ranked based on their performance in these tasks.

The 'M4CT' team, composed of Deepnoid researchers, participated in three categories using their proprietary 'M4CT' solution. Through their awards at the competition, Deepnoid demonstrated the technological excellence of their self-developed 3D vision-language model 'M4CT' on the global stage.

Among the three categories they entered, they won first place in both the self-supervised multi-abnormality localization and the multi-abnormality classification tasks. They also placed third in the automatic radiology report generation category.

Deepnoid is currently conducting multi-center clinical trials for 'M4CXR', a digital medical device that shares its technological foundation with 'M4CT'. M4CXR is a digital medical device that can interpret 41 types of lesions from chest X-ray images within seconds and automatically generate a draft radiology report. The company aims to obtain regulatory approval as early as the end of this year.

Park Jongkwon, leader of the 'M4CT' team, stated, "This achievement proves that Deepnoid's multimodal generative AI technology excels not only in 2D X-ray images but also in 3D imaging such as CT scans." He added, "We will continue to focus on research and development to commercialize 'M4CT' so that it can be effectively utilized in clinical settings in the future."