Skin tear classification using machine learning from digital RGB image |
| |
| Institution: | 1. School of Nursing, Nanjing Medical University, No.140 Hanzhong Road, Nanjing, Jiangsu, 210000, PR China;2. Wound Care Nurse Specialist and Head Nurse, Outpatient Treatment Center, the First Affiliated Hospital of Nanjing Medical University, No.300 Guangzhou Road, Nanjing, Jiangsu, 210029, PR China;3. Liverpool School of Tropical Medicine, Pembroke Place, Liverpool, L3 5QA, UK;4. Dermatology Hospital, Southern Medical University, No.2 Lujing Road, Guangzhou, Guangdong, 510000, PR China;1. Department of Medical Biotechnology, Faculty of Paramedicine, Guilan University of Medical Sciences, Rasht, Iran;2. Burn and Regenerative Medicine Research Center, Medicine Faculty, Guilan University of Medical Sciences, Rasht, Iran;3. Department of Pharmaceutical Biotechnology, School of Pharmacy and Pharmaceutical Sciences, Isfahan University of Medical Sciences, Isfahan, IR Iran;1. Department of Nursing, Faculty of Health Sciences, Gazi University, Ankara, Turkey;2. School of Nursing, Koc University, Istanbul, Turkey;3. Department of Nursing, Faculty of Health Sciences, Bingöl University, Bingöl, Turkey;4. Faculty of Nursing, Hacettepe University, Ankara, Turkey;5. Department of Nursing, Faculty of Health Sciences, Baskent University, Ankara, Turkey;6. Department of Nursing, Faculty of Health Sciences, Lokman Hekim University, Ankara, Turkey;7. School of Nursing, Yildirim Beyazit University, Ankara, Turkey;8. Pursaklar State Hospital, Ankara, Turkey |
| |
| Abstract: | AimSkin tears are traumatic wounds characterised by separation of the skin layers. Severity evaluation is important in the management of skin tears. To support the assessment and management of skin tears, this study aimed to develop an algorithm to estimate a category of the Skin Tear Audit Research classification system (STAR classification) using digital images via machine learning. This was achieved by introducing shape features representing complicated shape of the skin tears.MethodsA skin tear image was separated into small segments, and features of each segment were estimated. The segments were then classified into different classes by machine learning algorithms, namely support vector machine and random forest. Their performance in classifying wound segments and STAR categories was evaluated with 31 images using the leave-one-out cross validation.ResultsSupport vector machine showed an accuracy of 74% and 69% in classifying wound segments and STAR categories, respectively. The corresponding accuracy using random forest were 71% and 63%.ConclusionMachine learning algorithms revealed capable of classifying categories of skin tears. This could offer the potential to aid nurses in their management of skin tears, even if they are not specialised in wound care. |
| |
| Keywords: | Wound assessment Digital image analysis STAR Skin tear classification system Support vector machine Random forest |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
