Hybrid DCN_DNN

Using Artificial Intelligence (AI) to Identify Wound Etiology – 
A Preliminary Study

Innovations in Wound Healing Annual Conference. Dec, 2018.

“The proposed hybrid model achieves an accuracy of 94 % in differentiating burn, pressure injury, venous ulcer, and diabetic wound. This early application of artificial intelligence on etiology identification demonstrates the potential of AI in wound care. Future work will focus on improving the robustness and generalizability of the DCN/DNN hybrid model with more images and data augmentation, including the use of infrared image, depth map, and other clinical input.”


Burns logo

3-D Wound Scanner: A Novel, Effective, Reliable, and Convenient Tool for Measuring Scar Area

Burns Journal. Oct, 25, 2018 (epub ahead of print).

•Innovative use of portable 3D wound scanners to measure scar area;.
•Questioned the gold standard of the measurement of scar area, profile method, and showed this method is not suitable for measurement of hypertrophic scar area;
•Traditional methods are adequate for flat areas, however, errors are large in radial and angled areas. Scar was divided into three categories, flat, radial (cylindrical), and angled such as joints…

Read More

IWH 2017

Alternative 3D Wound Measurement Device for Monitoring Wound Area

Innovations in Wound Healing Annual Conference. Dec, 2017.

“The area measurements of the eKare device appear to be comparable to laser-­assisted wound measurement devices, making it an option for clinicians and researchers interested in monitoring wound progression. Clinical experience indicates the eKare device has a friendly user interface, a convenient portable design, and can take quick wound-­area measurements.”



The reliability of a novel mobile 3-Dimensional wound measurement device

Wounds. Nov, 2016.

“The 3D-WM was found to be highly reliable for measuring wound areas for a range of wound sizes and types as compared to manual measurement and scaled photography. The depth and therefore volume measurement using the 3D-WM was found to have a lower ICC, but volume ICC alone was moderate. Overall this device offers an affordable mobile option for objective wound measurement in the clinical setting.”
Note: The study involves shallow diabetic foot ulcers with average depth of approx. 1mm and may not be appropriate to evaluate depth measurement. See “Discussion” on page 5.



Pilot study to evaluate a novel three-dimensional wound measurement device

International Wound Journal. Dec, 2016.

This study aims to determine the accuracy of a new 3-dimensional wound measurement (3DWM) device against laser-assisted wound measurement (LAWM) devices and traditional methods of wound measurement. … (D)ata demonstrate that the 3DWM device provides an accurate and reproducible method for measuring changes in wound healing similar to other available technologies. Further, the use of the 3DWM device provides a faster and more consistent measurement, which is critical for clinical application and use.

Read More


Feasibility of 3D Stucture Sensing for accurate assessment of chronic wound dimensions

Computer Assisted Radiology and Surgery Annual Congress. June, 2015.

Ruler-based assessments can overestimate wound area by up to 44%. Tracing wounds using planimetry can give a better estimate of size but is time consuming and still highly variable between operators. Simple point-of-care solution that enables comprehensive 3D wound assessment on a mobile device would significantly improve the care and outcome. For this purpose we determine the feasibility of the current prototype and the implemented algorithms on phantom measurements with well know geometry in this research.

Download PDF


Mobile Wound Assessment Using Novel Computer Vision Methods

American College of Surgeons Clinical Congress. Oct, 2014.

Chronic wounds affect 6.5 million patients in the US, incurring $25 billion healthcare expenditure annually. Despite the significant clinical burden, wound care is plagued by a general lack of objective evidence to guide management. The problem stems from deficiencies in wound assessment that still relies on crude visual observation. We introduce novel computer vision techniques that will pave way towards an accurate and consistent wound assessment solution.

Download PDF