Loading...
Specialty AI · in development
WoundScan AI
Computer vision that makes wound progress measurable
WoundScan AI is being designed to assess wound images consistently and quantify changes following platelet-derived regenerative treatments. It supports clinicians without replacing their judgment.
WoundScan AI
WoundScan AI entered academic-industry co-development in June 2026 and is not yet commercially available.
The Problem
Wound progress is still documented largely in qualitative terms
Photos and narrative notes alone make treatment outcomes difficult to measure and compare consistently.
Subjective assessment of progress
Assessments can vary with the clinician, camera angle, and lighting—even for the same wound. That variability makes it difficult to apply a consistent standard across institutions or across one patient’s recovery and may delay recognition that the treatment plan needs to change.
Nonstandard measurements
Key indicators such as wound area, depth, and healing stage are not always captured in a standardized way. Measurements based on rulers and visual estimates are hard to compare over time. Without structured quantitative data, improving protocols on evidence is difficult.
Measuring regenerative-treatment outcomes
Platelet-derived regenerative treatments are used in practice, but their outcomes are difficult to evaluate without consistent measures. Converting changes before and after treatment into objective indicators can strengthen the evidence base. WoundScan AI is being developed to support that measurement.
The Approach
A consistent view of wounds through computer vision
We are extending the specialty-AI development and validation pattern established with DermatoScan AI into plastic-surgery wound care.
01
Computer vision-based wound assessment
Computer vision analyzes wound images and tracks indicators such as area and healing stage using a consistent method. Applying the same measurement framework can produce comparable data across visits, clinicians, and institutions. Clinicians may use these measurements as supporting evidence, but they retain final judgment.
02
Quantifying regenerative medicine outcomes
Changes following platelet-derived regenerative treatment are converted into quantitative indicators. Over time, measures such as healing rate and change in wound area can help teams evaluate which approaches work for which wounds. This measurement infrastructure can support the transition from research to routine clinical use.
03
Combined with horizontal infrastructure
WoundScan AI is a specialty module built on shared infrastructure that includes Dockie-talkie interpretation and Clinical Copilot. Wound assessments can therefore remain connected to the same conversation, documentation, and review context used across the clinic.
Academic-Industry Collaboration
Clinical rigor through academic-industry co-development
The project combines expertise in plastic-surgery wound care, regenerative medicine, and product development.
Academic-industry co-development partner
Professor Won Ha · Plastic Surgery, University of Ulsan
We began co-developing WoundScan AI in June 2026 with Professor Won Ha, CEO of PL Therapeutics. This is more than an advisory relationship: clinical wound-care and platelet-derived regenerative-medicine expertise informs the model from the design stage. The goal is a specialty AI system grounded in real clinical requirements rather than a laboratory-only prototype.
Plastic-surgery wound expertise
Clinical knowledge of wound progression and treatment settings directly informs the model design and evaluation criteria.
Regenerative medicine expertise
Together, we define the criteria for quantifying the results of regenerative medicine treatments based on platelet-derived components.
University of Ulsan academic channel
The academic partnership supports clinical consultation and a structured environment for data validation.
A reusable specialty-AI standard
The development and validation pattern established with DermatoScan AI is being adapted for wound care.
Expected impact
What quantified wound data can change
The clinical value we expect to test as WoundScan AI moves through validation.
Comparable progress records
When wound data is measured consistently, clinicians can track change over time against a common baseline. Cumulative data can supplement memory and narrative notes and help teams recognize when a treatment plan may need review.
Evidence-based protocol improvement
Accumulated quantitative indicators can help teams assess which approaches work for which wounds. That evidence can support gradual improvement of wound-management protocols and more rigorous evaluation of regenerative treatments.
A platform-wide data asset
WoundScan data can remain connected to the shared context created by Dockie-talkie and Clinical Copilot. As additional specialty modules join the same foundation, the platform becomes more useful across workflows.
Roadmap
From development to clinical validation
WoundScan AI is in development, with validation and expansion planned in stages.
01
ROADMAPPhase 1 · 2026
Academic-industry co-development begins
We are developing a computer-vision wound-assessment model with Professor Won Ha of the University of Ulsan. This phase focuses on defining evaluation criteria using clinical wound data and establishing initial quantitative measures for outcomes following platelet-derived treatment. WoundScan AI is not yet a commercial solution.
02
ROADMAPPhase 2 · 2027
Clinical validation and SaaS expansion
We plan to begin clinical validation while launching shared hospital services. This phase will measure how closely model-generated assessments align with clinical judgment and will expand scope only as the evidence supports it. Commercial timing will depend on the validation results.
03
ROADMAPPhase 3 · 2028~
Ecosystem and global expansion
After validating our specialty AI, we plan to open the platform to third-party modules and pursue expansion into markets such as Southeast Asia and the Middle East. WoundScan AI and DermatoScan AI are intended to establish the validation standard that future integrations must follow.
Frequently Asked Questions
Frequently Asked Questions about WoundScan AI
Key questions about WoundScan AI at its current co-development stage.
No. WoundScan AI entered academic-industry co-development in June 2026 and is not yet commercially available. We are establishing the initial computer-vision assessment model and quantitative indicators. Any expansion in scope will follow clinical validation, and we are not yet announcing a launch date.
No. WoundScan AI is designed to present consistent measures such as wound area and healing stage as decision-support information. Licensed clinicians retain responsibility for diagnosis and treatment decisions.
WoundScan AI is being designed to analyze images over time and convert visible changes into indicators such as wound-area change and healing stage. Accumulated measurements can support evidence-based evaluation of regenerative treatments. The measurement framework is being defined with Professor Won Ha, CEO of PL Therapeutics.
This is not a one-time advisory arrangement. Clinical and research expertise from Professor Won Ha and his team informs the model from the design stage, including evaluation criteria for wound care and platelet-derived regenerative treatment. The partnership also supports a structured clinical consultation and validation environment.
WoundScan AI extends the development and validation pattern established with DermatoScan AI into plastic-surgery wound care. Both are specialty modules built on the shared Dockie-talkie and Clinical Copilot foundation.
Organizations interested in plastic-surgery wound AI can contact us through the partner inquiry channel. Because WoundScan AI is still in development, current discussions focus on clinical-validation collaboration and potential future adoption.
Discuss a WoundScan AI partnership
Contact us to discuss clinical validation, co-development, or future adoption in plastic-surgery wound care. WoundScan AI is currently in development.