FigureAsia 35 Under 35 · Healthcare
Seokhwan Oh
Age 28 · Ultrasound artificial intelligence · Seoul, South Korea
Cofounder and coauthor of an accepted 2026 model trained on 5.2 million ultrasound images across breast, thyroid, cardiac, gallbladder and pulmonary tasks.
- Approximate age at 31 December 2025
- 28
- Field
- Healthcare
- Country or region
- Seoul, South Korea
- FigureAsia U35 Assessment
- 80.7 / 100
Profile
Career and documented record
Ultrasound is widely available, operator-dependent and visually different from the image modalities on which many general models are trained. Seokhwan Oh's 2026 work approached the problem with anatomy-aware pretraining on 5.2 million ultrasound images. The accepted conference paper evaluated the model across breast, thyroid, cardiac, gallbladder and COVID-19-related tasks.
The breadth is the point: a representation that understands common ultrasonic structure may reduce the data required to build each downstream tool. Oh's company has also pursued earlier clinical pilots and regulatory work in South Korea, connecting the research to actual imaging workflow rather than a benchmark alone. His contribution is collaborative — he is a coauthor and cofounder, not the sole creator of the model.
Company claims of a 15% diagnostic improvement and financing totals are not treated as independent evidence. The 5.2-million-image training corpus is substantial, but dataset size does not guarantee demographic coverage, device generalization or patient benefit. Oh's inclusion recognizes an Asia-based effort to build ultrasound-specific foundations with a visible route toward clinical testing.
FigureAsia selection
Why Seokhwan Oh is on the list
FigureAsia selected Oh because his team is addressing a modality that matters disproportionately in settings with limited imaging infrastructure. The 2026 work combines scale with cross-anatomy evaluation, and earlier pilot activity creates a plausible translational path. The score remains conservative because clinical outcome, regulator and independent validation evidence is still limited.
Verified work
The 2025–26 record
Principal milestone
5.2 million ultrasound images used for training
Evidence record
Five broad anatomy or disease task groups evaluated
Scale or implementation
Accepted for ICLR 2026
Field context
The work in its field
Within ultrasound artificial intelligence, the relevant test is whether a result can survive scrutiny of maturity, attribution, validity and practical fit. That distinction matters: completed evidence is not projected benefit, and individual responsibility is not interchangeable with the wider team’s achievement.
FigureAsia U35 Assessment
Assessment breakdown
80.7out of 100
Substantive 2025–2026 contribution
18 / 20
The score reflects completed 2025–26 work in ultrasound artificial intelligence, assessed at the documented maturity of research validation with earlier clinical pilots.
Verified impact
10.5 / 15
Impact credit is limited to the measured study, regulatory, implementation or operating record stated in the profile; unsupported patient benefit is excluded.
Originality and distinction
9 / 10
The work creates or materially advances a distinctive capability within ultrasound artificial intelligence rather than relying on title or institutional association.
Field and industry influence
7 / 10
The assessment recognises demonstrated effects on research, product development, care delivery or professional practice, with publicity alone carrying no weight.
Individual agency
8 / 10
Named authorship and the documented role of Cofounder establish individual responsibility while preserving credit for collaborators.
Durability and trajectory
4 / 5
The cited work forms part of a continuing programme, platform or research trajectory rather than a single uncompleted announcement.
Asian significance and global relevance
5 / 5
The Asian connection is material to the person's identity, operating base or populations served: South Korean engineer and founder based in Seoul.
Clinical and scientific validity
5.6 / 7
Clinical and scientific validity is calibrated to research validation with earlier clinical pilots, with the profile retaining the evidence boundary attached to the result.
Safety, quality and responsible governance
4.9 / 7
Safety and governance credit reflects accurate regulatory language, study limitations, data stewardship and the refusal to turn early evidence into clinical certainty.
Translation and care-pathway fit
4.2 / 6
The work is scored for its demonstrated fit with a laboratory, regulatory, clinical, operational or public-health pathway, not for projected future adoption.
Access, equity and resource stewardship
4.5 / 5
Access credit reflects documented reach, capacity, affordability or inclusion while distinguishing service volume from proven clinical outcome.