AI-Based Wound Monitoring: Automated Wound Progression Assessment Via Marker-Free Image Sequence

NCT07619430 | Not Yet Recruiting

• 1 other identifier: 202603061RINB
• Study Type: observational
• Target: 1,000
• Locations: 1 country
• Sites: 1

Brief Summary

This study aims to develop a low-cost, marker-free intelligent wound assessment system that can analyze wound photos taken with a standard smartphone. By comparing wound images over time, the system will generate a quantifiable Wound Progression Index (WPI) to provide objective feedback on whether a wound is improving, stable, or worsening. The long-term goal is to support early detection of wound deterioration and improve wound care in both clinical and home settings.

Conditions

Hard-to-heal Wounds; AI (Artificial Intelligence); Wound Care; Pressure Injuries

Keywords

chronic wounds; wound assessment; medical AI; semantic segmentation; longitudinal image registration; marker-free; wound progression index; home-based care; telemedicine; clinical validation

Outcome Measures

Primary Outcomes (1)

• Agreement between marker-free and marker-based wound progression indices

  To evaluate the agreement between the Marker-Free Wound Progression Index (WPI\_MF) and the gold-standard marker-based Wound Progression Index (WPI\_GS) derived from longitudinal wound photographs.

  Up to 6 months

Secondary Outcomes (1)

• Minimum image overlap threshold for reliable analysis

  Up to 6 months

Study Arms (1)

patients with hard-to-heal wounds

patients with hard-to-heal wounds

Other: Marker-free wound image registration technology

Interventions

Marker-free wound image registration technology OTHER

Marker-free longitudinal wound image registration and wound progression assessment using serial wound photographs.

patients with hard-to-heal wounds

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

Adult patients with hard-to-heal wounds located on body sites that can be fully captured within a single standardized image.

You may qualify if:

• (1) Presence of a hard-to-heal wound that has remained unhealed for more than one month. (2)The wound can be photographed according to the standardized imaging protocol. (3)The participant was aged 18 years or older and provided informed consent personally or via a legally authorized representative, with a signed informed consent form.

You may not qualify if:

• Wounds whose margins could not be fully included within the imaging field.

Sponsors & Collaborators

• National Taiwan University Hospital: lead
• Industrial Technology Research Institute, Taiwan: collaborator

Study Sites (1)

National Taiwan University Hospital Yunlin branch

Douliu, Yunlin, 640, Taiwan

Location

Related Publications (9)

• Liu TJ, Wang H, Christian M, Chang CW, Lai F, Tai HC. Automatic segmentation and measurement of pressure injuries using deep learning models and a LiDAR camera. Sci Rep. 2023 Jan 13;13(1):680. doi: 10.1038/s41598-022-26812-9.

  PMID: 36639395 BACKGROUND

• Bowling FL, King L, Paterson JA, Hu J, Lipsky BA, Matthews DR, Boulton AJ. Remote assessment of diabetic foot ulcers using a novel wound imaging system. Wound Repair Regen. 2011 Jan-Feb;19(1):25-30. doi: 10.1111/j.1524-475X.2010.00645.x. Epub 2010 Dec 6.

  PMID: 21134035 BACKGROUND

• Anisuzzaman DM, Wang C, Rostami B, Gopalakrishnan S, Niezgoda J, Yu Z. Image-Based Artificial Intelligence in Wound Assessment: A Systematic Review. Adv Wound Care (New Rochelle). 2022 Dec;11(12):687-709. doi: 10.1089/wound.2021.0091. Epub 2021 Dec 20.

  PMID: 34544270 BACKGROUND

• Foltynski P. Ways to increase precision and accuracy of wound area measurement using smart devices: Advanced app Planimator. PLoS One. 2018 Mar 5;13(3):e0192485. doi: 10.1371/journal.pone.0192485. eCollection 2018.

  PMID: 29505569 BACKGROUND

• Isensee F, Jaeger PF, Kohl SAA, Petersen J, Maier-Hein KH. nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat Methods. 2021 Feb;18(2):203-211. doi: 10.1038/s41592-020-01008-z. Epub 2020 Dec 7.

  PMID: 33288961 BACKGROUND

• Hallett CE, Austin L, Caress A, Luker KA. Wound care in the community setting: clinical decision making in context. J Adv Nurs. 2000 Apr;31(4):783-93. doi: 10.1046/j.1365-2648.2000.01348.x.

  PMID: 10759974 BACKGROUND

• Chen L, Cheng L, Gao W, Chen D, Wang C, Ran X. Telemedicine in Chronic Wound Management: Systematic Review And Meta-Analysis. JMIR Mhealth Uhealth. 2020 Jun 25;8(6):e15574. doi: 10.2196/15574.

  PMID: 32584259 BACKGROUND

• Bloemen MC, van Zuijlen PP, Middelkoop E. Reliability of subjective wound assessment. Burns. 2011 Jun;37(4):566-71. doi: 10.1016/j.burns.2011.02.004. Epub 2011 Mar 8.

  PMID: 21388743 BACKGROUND

• Olsson M, Jarbrink K, Divakar U, Bajpai R, Upton Z, Schmidtchen A, Car J. The humanistic and economic burden of chronic wounds: A systematic review. Wound Repair Regen. 2019 Jan;27(1):114-125. doi: 10.1111/wrr.12683. Epub 2018 Dec 2.

  PMID: 30362646 BACKGROUND

MeSH Terms

Conditions

Pressure Ulcer

Condition Hierarchy (Ancestors)

Skin Ulcer; Skin Diseases; Skin and Connective Tissue Diseases

Central Study Contacts

Hui-Hsiu Chang

CONTACT

886-972655406; huihsiu@gmail.com

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: PROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: May 27, 2026
• First Posted: June 2, 2026
• Study Start: June 8, 2026
• Primary Completion (Estimated): December 31, 2027
• Study Completion (Estimated): December 31, 2027
• Last Updated: June 2, 2026

Record last verified: 2026-05

Data Sharing

• IPD Sharing: Will share
• Shared Documents: STUDY PROTOCOL
• Time Frame: starting 6 months after publication
• Access Criteria: Requests must include a structured research proposal specifying the objectives, analysis plan, and data required. All requests will be reviewed by the corresponding investigator and the study's principal research team to ensure scientific validity, ethical compliance, and protection of participant confidentiality. Additional approval from an institutional review board or ethics committee may be required depending on the nature of the proposed analysis.

Locations

TW (1)