Loading...
AI/under development by field
WoundScan AI
AI that quantifies plastic surgery wound treatment
We evaluate and manage wounds using computer vision and quantify the treatment results of platelet-derived regenerative medicine. The structure continues to reinforce rather than replace medical staff.
WoundScan AI
WoundScan AI is currently in the joint development stage between industry and academia (launched in June 2026).
The Problem
Wound progress is still recorded qualitatively
It is difficult to consistently compare or quantify treatment results using only photos and notes.
subjective progress judgment
Whether the wound improves depends on the individual experience of the medical staff and the visual judgment of the day. Even for the same wound, the evaluation varies depending on the medical staff treating the wound, the viewpoint, and the lighting, making it difficult to maintain consistent standards not only between institutions but also within the time course of a single patient. This variability leads to the clinical risk of late detection when it is time to redirect treatment.
Non-standardized measurements
A standard for objectively converting key indicators such as area, depth, and healing stage has not been established. It is difficult to accumulate and compare measurements based on rulers and eyeballs, and progress that does not remain as data cannot be used in decision-making for the next patient. Without quantitative indicators, there is no foundation for evidence-based improvement of treatment protocols.
Proof of regenerative medicine results
Regenerative medicine treatments, including platelet-derived components, are used in clinical practice, but there is a lack of a system to quantify and prove their effectiveness with data. If changes before and after treatment cannot be converted into objective indicators, it is difficult to convincingly present the value of new regenerative medicine standards. WoundScan AI aims to fill this very proof gap.
The Approach
AI that reads wounds with computer vision
We extend the field-specific AI patterns verified by DermatoScan AI to the area of plastic surgery wounds.
01
Computer vision-based wound assessment
Wound images are analyzed using computer vision to evaluate and track progress indicators such as area and healing stage using a consistent algorithm rather than the human eye. Since the same standards are applied to all imaging, comparable data is accumulated not only for the same patient over time but also across different institutions and medical staff. Medical staff refer to these quantitative results as the basis for decision-making, but the final decision is still made by the medical staff.
02
Quantifying regenerative medicine outcomes
Changes before and after platelet-derived component regenerative medicine treatment are converted into quantitative indicators, allowing treatment results to be proven with data rather than intuition. When objective indicators such as healing speed and change in wound area are accumulated, it is possible to determine based on evidence which treatment is effective for which wound. This is the measurement infrastructure needed to bring regenerative medicine from research to routine clinical practice.
03
Combined with horizontal infrastructure
WoundScan AI is not a single, independent app, but a field-specific AI that builds on a common foundation for all departments, including Dockie-talkie real-time interpretation and Clinical Copilot clinical assistance. Because wound assessment results share the same foundation as the interpretation and assistance layer, they create integrated value that is difficult to replicate with single-discipline AI alone. This two-tier structure is the design principle that permeates the entire AetherHeal Global platform.
Academic-Industry Collaboration
Clinical trust created through industry-academia joint development
We develop it together based on clinical plastic surgery and regenerative medicine expertise.
Industry-academia joint development partner
Ha Won, Professor of Plastic Surgery, University of Ulsan
We began joint industry-academia development of WoundScan AI in June 2026 with Professor Ha Won, CEO of PL Therapeutics. Industry-academia joint development is not simply consultation, but means combining plastic surgery wound clinical practice and platelet-derived component regenerative medicine research from the model design stage. Since wound data and treatment results that occur in actual clinical trials define the model standards, we can create AI for each field of wound evaluation and management that is actually used in the clinic, not on the desk.
Plastic surgery wound clinical trial
The clinical knowledge of the actual wound progress and treatment site is directly reflected in 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 Industry-Academic Channel
We secure a stable clinical consultation and data verification environment through university hospital industry-academia channels.
Application of AI standards by field
AI development and verification patterns for each field, clinically verified by DermatoScan AI, are applied to the wound area.
Introduction effect
Changes made by quantified wound data
This is the value expected in the medical field when WoundScan AI is clinically verified and established.
Comparable Progress Records
As wound data measured by the same standard accumulates, the patient's improvement can be objectively tracked on the time axis. Progress judgments that used to rely solely on the medical staff's memories and notes are now supported by cumulative data, making it possible to more consistently identify when to change the direction of treatment.
Evidence-based protocol improvement
When quantitative indicators are accumulated, data can be used to determine which treatment was effective for which wound. This serves as a foundation for gradually improving wound management protocols based on evidence rather than rules of thumb, and is especially an asset that convincingly demonstrates the value of regenerative medicine treatments.
Platform integrated assetization
Wound data generated by WoundScan AI is accumulated as a common asset on a common basis such as dockie-talkie interpretation and clinical copilot assistance. As AI in each field increases, the value of the entire platform increases, creating a level of replication difficulty that cannot be created with a single solution.
Roadmap
From development to clinical validation and expansion
WoundScan AI is currently in the development stage, with clinical validation and expansion underway in stages.
01
ROADMAPPhase 1 · 2026
Commencement of industry-academia joint development
We are jointly developing a computer vision-based wound evaluation model with Professor Ha Won of the Department of Plastic Surgery at the University of Ulsan. The goal of this phase is to define evaluation criteria with real clinical wound data and establish an initial form of quantitative index that will quantify the results of treatment with platelet-derived components. WoundScan AI is at this stage of development and is not yet a commercial solution.
02
ROADMAPPhase 2 · 2027
Clinical validation and SaaS expansion
After the initial investment, we will begin clinical validation of WoundScan AI while launching common-based hospital services. This is a step to check with data how well the evaluation calculated by the model matches actual clinical judgment, and the scope of application is carefully expanded according to the verification results. The timing of commercial use will be determined based on the verification results.
03
ROADMAPPhase 3 · 2028~
Ecosystem/global expansion
Based on proven AI for each field, we will launch an AI ecosystem for each field of external business and expand into global markets such as Southeast Asia and the Middle East. WoundScan AI, along with DermatoScan AI, is AetherHeal Global's proven direct verification product and serves to present a standard for external entry models to follow.
Frequently Asked Questions
Frequently Asked Questions about WoundScan AI
We have summarized key questions about WoundScan AI in the industry-academia joint development stage.
no. WoundScan AI is a field-specific AI in the development stage that began joint development between industry and academia in June 2026, and is not yet a commercial solution. Currently, we are in the initial stage of establishing a computer vision-based wound assessment model and quantitative indicators, and we plan to carefully expand the scope of application after clinical verification. We do not provide definitive guidance on when to use it.
No replacement. All of AetherHeal Global's AIs are based on the principle of augmenting medical staff, but leaving the medical staff as the subject of decision-making. WoundScan AI is a tool that helps medical staff make decisions by presenting quantitative indicators such as area and healing stage on a consistent basis, and the final diagnosis and treatment decisions are always made by the medical staff.
WoundScan AI aims to analyze wound images before and after treatment using computer vision and convert them into objective indicators such as area change and healing stage. When such quantified data is accumulated, the effectiveness of regenerative medicine treatments can be proven based on evidence rather than intuition. The quantification standard itself is defined through industry-academia joint development with Professor Ha Won, CEO of PL Therapeutics.
This does not mean simply consulting, but combining clinical and research expertise from the model design stage with Professor Ha Won of the Department of Plastic Surgery at the University of Ulsan. Actual plastic surgery wound clinical knowledge and platelet-derived component regenerative medicine data define the evaluation criteria for the model, and a clinical consultation and verification environment is secured through university hospital industry-academia channels. It is a collaborative structure to create field-specific AI that is actually used in medical offices.
WoundScan AI extends the field-specific AI development and verification pattern demonstrated by DermatoScan AI, which is currently in clinical verification and operation, to the area of plastic surgery wounds. Both solutions are domain-specific AI that builds on the common foundation of dockie-talkie interpretation and clinical copilot assistance, and together they form AetherHeal Global's proven direct verification product lineup.
Organizations interested in joint development and introduction of AI in the field of plastic surgery wounds can contact us through partner inquiry. Since WoundScan AI is currently in the development stage, we will provide guidance focusing on clinical verification cooperation and future introduction discussions.
WoundScan AI Industry-Academic Partner Inquiry
If you are interested in joint development and introduction of AI in the field of plastic surgery wounds, please contact us. WoundScan AI is currently in the development stage.