Monitoring Wound Healing With Contactless Measurements and Augmented Reality

Mamone, Virginia; Fonzo, Miriam Di; Esposito, Nicola; Ferrari, Mauro; Ferrari, Vincenzo

doi:10.1109/jtehm.2020.2983156

Cited by 26 publications

(28 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…AI is playing an increasingly large role in optimizing diagnostic and therapeutic workflows and is starting to affect the area of wound care. 18 , 19 , 27 , 28 , 29 , 30 Ongoing research and development in wound assessment devices and software aims to improve technologies and standardize practices. The eTable in the Supplement summarizes the potential advantages and disadvantages of AI-based digital wound assessment tools, which will be important to consider as these technologies become more prevalent across diverse wound care settings.…”

Section: Discussionmentioning

confidence: 99%

Development of a Method for Clinical Evaluation of Artificial Intelligence–Based Digital Wound Assessment Tools

et al. 2021

View full text Add to dashboard Cite

IMPORTANCE Accurate assessment of wound area and percentage of granulation tissue (PGT) are important for optimizing wound care and healing outcomes. Artificial intelligence (AI)-based wound assessment tools have the potential to improve the accuracy and consistency of wound area and PGT measurement, while improving efficiency of wound care workflows.OBJECTIVE To develop a quantitative and qualitative method to evaluate AI-based wound assessment tools compared with expert human assessments. DESIGN, SETTING, AND PARTICIPANTSThis diagnostic study was performed across 2 independent wound centers using deidentified wound photographs collected for routine care (site 1, 110 photographs taken between May 1 and 31, 2018; site 2, 89 photographs taken between January 1 and December 31, 2019). Digital wound photographs of patients were selected chronologically from the electronic medical records from the general population of patients visiting the wound centers.For inclusion in the study, the complete wound edge and a ruler were required to be visible; circumferential ulcers were specifically excluded. Four wound specialists (2 per site) and an AI-based wound assessment service independently traced wound area and granulation tissue. MAIN OUTCOMES AND MEASURESThe quantitative performance of AI tracings was evaluated by statistically comparing error measure distributions between test AI traces and reference human traces (AI vs human) with error distributions between independent traces by 2 humans (human vs human). Quantitative outcomes included statistically significant differences in error measures of false-negative area (FNA), false-positive area (FPA), and absolute relative error (ARE) between AI vs human and human vs human comparisons of wound area and granulation tissue tracings. Six masked attending physician reviewers (3 per site) viewed randomized area tracings for AI and human annotators and qualitatively assessed them. Qualitative outcomes included statistically significant difference in the absolute difference between AI-based PGT measurements and mean reviewer visual PGT estimates compared with PGT estimate variability measures (ie, range, standard deviation) across reviewers. RESULTS A total of 199 photographs were selected for the study across both sites; mean (SD) patient age was 64 (18) years (range, 17-95 years) and 127 (63.8%) were women. The comparisons of AI vs human with human vs human for FPA and ARE were not statistically significant. AI vs human FNA was slightly elevated compared with human vs human FNA (median [IQR], 7.7% [2.7%-21.2%] vs 5.7% [1.6%-14.9%]; P < .001), indicating that AI traces tended to slightly underestimate the human reference wound boundaries compared with human test traces. Two of 6 reviewers had a statistically higher frequency in agreement that human tracings met the standard area definition, but overall agreement was moderate (352 yes responses of 583 total responses [60.4%] for AI and 793 yes responses of 1166 total responses [68.0%] for human tracings). AI PGT measurements fel...

show abstract

Section: Discussionmentioning

confidence: 99%

Development of a Method for Clinical Evaluation of Artificial Intelligence–Based Digital Wound Assessment Tools

et al. 2021

View full text Add to dashboard Cite

show abstract

“…It is important to perform the risk analysis of such a common and serious health problem, which can bring morbidity and mortality, and to correctly determine the staging and appropriate nursing interventions when it occurs. Nurses are the entities responsible for determining the stage of the injury and for providing appropriate care for the stage [8,9,12,36,37]. Studies focusing on the prevention, detection, and treatment of pressure injuries have shown that innovative approaches such as mobile applications, biosensors, augmented reality, and artificial intelligence are currently being applied [35,36,[38][39][40][41][42].…”

Section: The Innovative Approaches Used In the Detection And Classification Of Pressure Injuries In The World And Turkeymentioning

confidence: 99%

“…Nurses are the entities responsible for determining the stage of the injury and for providing appropriate care for the stage [8,9,12,36,37]. Studies focusing on the prevention, detection, and treatment of pressure injuries have shown that innovative approaches such as mobile applications, biosensors, augmented reality, and artificial intelligence are currently being applied [35,36,[38][39][40][41][42].…”

Section: The Innovative Approaches Used In the Detection And Classification Of Pressure Injuries In The World And Turkeymentioning

confidence: 99%

“…Fraiwan et al [32] developed a mobile application that detects body temperature and analyzes the risk of pressure injury. Tibes et al [36] stated that the error rate in staging and risk calculation of the Braden scale decreased with the use of mobile application developed for the prevention and classification of pressure injury. Poon et al [37] developed a mobile application that allows for the color and size of the pressure injury to be accurately determined.…”

Section: The Innovative Approaches Used In the Detection And Classification Of Pressure Injuries In The World And Turkeymentioning

confidence: 99%

See 1 more Smart Citation

Prediction and classification of pressure injuries by deep learning

Yilmaz¹,

Kızıl²,

Kaya³

et al. 2021

hpc

View full text Add to dashboard Cite

Authors' contributionWkład autorów: A. Study design/planning zaplanowanie badań B. Data collection/entry zebranie danych C. Data analysis/statistics dane -analiza i statystyki D. Data interpretation interpretacja danych E. Preparation of manuscript przygotowanie artykułu F. Literature analysis/search wyszukiwanie i analiza literatury G. Funds collection zebranie funduszy SummaryPressure injuries are a serious medical problem that both negatively affects the patient's quality of life and results in significant healthcare costs. In cases where a patient doesn't receive appropriate treatment and care, death may result. Nurses play critical roles in the prevention, care, and treatment of pressure injuries as members of the healthcare team who closely monitor the health status of the patient. Today, the use of artificial intelligence is becoming more prevalent in healthcare, as in many other areas. Artificial intelligence is a method that aims to solve complex problems by using computers to mathematically simulate the way the brain works. In this article, we compile and share information about a deep learning model developed for the detection and classification of pressure injuries. Deep learning can operate on many types of data. Convolutional Neural Networks (CNN) prefer images because they can handle 2D arrays. In this case, the images, annotated according to the National Pressure Injury Advisory Panel pressure injury classification system, have been fed into a deep learning model using CNN. The developed CNN model has a 97% success in detecting and classifying pressure injuries, and as more images are collected and fed into the CNN, the prediction accuracy will increase. This deep learning model allows for the automatic detection and classification of pressure injuries, an indicator of health outcomes, at an early stage and for quick and accurate intervention. In this context, it is expected that the quality of nursing care will increase, the prevalence of pressure injury will decrease, and the economic burden of this health problem will decrease.

show abstract

“…Recently, technological development led to a high brightness even from small LED sources and to increasing miniaturization of micro-lenses, thus resulting in lightweight and handy projectors. This paved the way for new biomedical applications: a mini projector in combination with a laparoscopic ultrasound has been proposed to improve efficacy and safety in laparoscopic partial nephrectomy [15]; in [16], the authors developed a portable system for monitoring skin ulcers through projected AR; in [17], the authors presented a mini projector for guided neurosurgery that allows the regions of interest to be visualized directly on the patient's head, skull, or brain. Projected AR relies on a different paradigm than egocentric AR based on HMDs and has the potential to overcome the limitations that prevent AR from routinely entering the operating room.…”

Section: Introductionmentioning

confidence: 99%

Projected Augmented Reality to Drive Osteotomy Surgery: Implementation and Comparison With Video See-Through Technology

et al. 2020

Self Cite

View full text Add to dashboard Cite

In recent years, the spreading of visual augmented reality as an effective tool in image-guided surgery, has stimulated the research community to investigate the use of commercial augmented reality headsets a broad range of potential applications. This aroused enthusiasm among clinicians for the potential of augmented reality, but also revealed some technological and human-factor limitations that still hinder its routine adoption in the operating room. In this work, we propose an alternative to head-mounted displays, based on projected augmented reality. Projected augmented reality completely preserves the surgeon's natural view of the operating field, because it requires no perspective conversion and/or optical mediation. We selected a cranio-maxillofacial surgery application as a benchmark to test the proposed system and compare its accuracy with the one obtained with a video see-through system. The augmented reality overlay accuracy was evaluated by measuring the distance between a virtual osteotomy line and its real counterpart. The experimental tests showed that the accuracy of the two augmented reality modes is similar, with a median error discrepancy of about 0.3 mm for the projected augmented reality mode. Results suggest that projected augmented reality can be a valuable alternative to standard see-through head-mounted displays to support in-situ visualization of medical imaging data as surgical guidance. INDEX TERMS augmented reality, projected augmented reality, video see-through, head-mounted display, computer-assisted surgery, cranio-maxillofacial surgery, augmented reality accuracy

show abstract

Monitoring Wound Healing With Contactless Measurements and Augmented Reality

Cited by 26 publications

References 37 publications

Development of a Method for Clinical Evaluation of Artificial Intelligence–Based Digital Wound Assessment Tools

Development of a Method for Clinical Evaluation of Artificial Intelligence–Based Digital Wound Assessment Tools

Prediction and classification of pressure injuries by deep learning

Projected Augmented Reality to Drive Osteotomy Surgery: Implementation and Comparison With Video See-Through Technology

Contact Info

Product

Resources

About