Experimental Study on Wound Area Measurement with Mobile Devices

Abstract

Healthcare treatments might benefit from advances in artificial intelligence and technological equipment such as smartphones and smartwatches. The presence of cameras in these devices with increasingly robust and precise pattern recognition techniques can facilitate the estimation of the wound area and other telemedicine measurements. Currently, telemedicine is vital to the maintenance of the quality of the treatments remotely. This study proposes a method for measuring the wound area with mobile devices. The proposed approach relies on a multi-step process consisting of image capture, conversion to grayscale, blurring, application of a threshold with segmentation, identification of the wound part, dilation and erosion of the detected wound section, identification of accurate data related to the image, and measurement of the wound area. The proposed method was implemented with the OpenCV framework. Thus, it is a solution for healthcare systems by which to investigate and treat people with skin-related diseases. The proof-of-concept was performed with a static dataset of camera images on a desktop computer. After we validated the approach’s feasibility, we implemented the method in a mobile application that allows for communication between patients, caregivers, and healthcare professionals.

Mobile Application and Advanced Analytics in Wound Care: Variable Predictors of Wound Evolution in a Public Intermediate Hospital

“…This increase in productivity and decision-making accuracy will undoubtedly improve patient care quality. In terms of efficiency, tools like Clinicgram®, or others [18,19,20,21,22,23] provides capabilities for the practical analysis of the cost-effectiveness of different treatments, as well as the generation of ratios that can reveal the real use of these treatments and their related costs.…”

A novel tension relief technique to aid the primary closure of traumatic equine wounds under excessive tension

“…The main limitations of this study are related to its retrospective nature, the possibility of selection bias and the subjective assessment of the outcome. Many approaches have been proposed to assess wound healing, varying from a simple measurement with tape or calliper to more complex methods using digital cameras or a three‐dimensional measurement device 21–23 . However, these latter methods are expensive and not validated for primary closure.…”

A time motion study of manual versus artificial intelligence methods for wound assessment

“…Our findings showed that clinicians successfully captured quality images of the wounds on the first attempt, 16.5% more often with Swift than manual methods. Evidence shows that quality images are essential to accurately measuring the wound area and tracking wound progress [ 7 ], an attribute that can support successful pre-authorization claims [ 32 ].…”

“…Our findings showed that clinicians successfully captured quality images of the wounds on the first attempt, 16.5% more often with Swift than manual methods. Evidence shows that quality images are essential to accurately measuring the wound area and tracking wound progress [7], an attribute that can support successful pre-authorization claims [32]. Unlike Swift's application, using standard digital cameras to capture wound images can present challenges in capturing quality images due to a lack of image calibration that accounts for variable lighting conditions, skin tones and distance the picture is taken from the wound.…”

“…Wound assessment largely depends on evaluating the visual elements of the wound, such as the amount of surrounding erythema, the presence and color of granulation tissue, wound drainage, and accurately measuring the key dimensions of the wound to calculate the wound area and volume. These processes are typically accomplished by traditional methods, such as a photographic image of the wound using a digital camera, a paper-ruler, and a depth probe to determine the key measurements of the wounds [ 7 ]. However, using these traditional methods in daily practices is not ideal [ 8 ], especially when measuring irregular wound boundaries [ 9 , 10 ], or unequal distances from the edge of the wound [ 11 ].…”