Graduate Institute of Biomedical Electronics & Bioinformatics, National Taiwan University, Taipei, Taiwan; Division of Plastic Surgery, Department of Surgery, Fu Jen Catholic University Hospital, Fu Jen Catholic University, New Taipei City, Taiwan.
Graduate Institute of Biomedical Electronics & Bioinformatics, National Taiwan University, Taipei, Taiwan.
J Formos Med Assoc. 2022 Nov;121(11):2227-2236. doi: 10.1016/j.jfma.2022.04.010. Epub 2022 May 4.
BACKGROUND/PURPOSE: Pressure ulcers are a common problem in hospital care and long-term care. Pressure ulcers are caused by prolonged compression of soft tissues, which can cause local tissue damage and even lead to serious infections. This study uses a deep learning algorithm to construct a system that diagnoses pressure ulcers and assists in making treatment decisions, thus providing additional reference for first-line caregivers.
We performed a retrospective research of medical records to find photos of patients with pressure ulcers at National Taiwan University Hospital from 2016 to 2020. We used photos from 2016 to 2019 for training and after removing the photos which were vague, underexposed, or overexposed, 327 photos were obtained. The photos were then labeled as "erythema" or "non-erythema" for the first classification task and "extensive necrosis", "moderate necrosis" or "limited necrosis" for the second, by consensus of three recruited physicians. An Inception-ResNet-v2 model, a kind of Convolutional Neural Network (CNN), was applied for training these two classification tasks to construct an assessment system. Finally, we tested the model with the photos of pressure ulcers taken from 2019 to 2020 to verify its accuracy.
For the task of classification of erythema and non-erythema wounds, our CNN model achieved an accuracy of about 98.5%. For the task of classification of necrotic tissue, our model achieved accuracy of about 97%.
Our CNN model, which was based on Inception-ResNet-v2, achieved high accuracy when classifying different types of pressure ulcers, making it applicable in clinical circumstances.
背景/目的：压疮是医院护理和长期护理中常见的问题。压疮是由于软组织长时间受压引起的，可导致局部组织损伤，甚至引发严重感染。本研究使用深度学习算法构建了一个系统，用于诊断压疮并协助制定治疗决策，从而为一线护理人员提供额外的参考。
我们对病历进行了回顾性研究，以寻找台湾大学医院 2016 年至 2020 年期间的压疮患者照片。我们使用 2016 年至 2019 年的照片进行训练，在去除模糊、曝光不足或曝光过度的照片后，共获得 327 张照片。然后，由三位招募的医生共同对这些照片进行分类，将其标记为“红斑”或“非红斑”用于第一项分类任务，标记为“广泛坏死”、“中度坏死”或“有限坏死”用于第二项分类任务。我们应用 Inception-ResNet-v2 模型（一种卷积神经网络（CNN））对这两个分类任务进行训练，以构建评估系统。最后，我们使用 2019 年至 2020 年拍摄的压疮照片对模型进行测试，以验证其准确性。
对于红斑和非红斑伤口的分类任务，我们的 CNN 模型的准确率约为 98.5%。对于坏死组织分类任务，我们的模型的准确率约为 97%。
我们的基于 Inception-ResNet-v2 的 CNN 模型在对不同类型的压疮进行分类时达到了较高的准确性，使其适用于临床情况。
