Asare-Baiden Miriam, Sonenblum Sharon Eve, Jordan Kathleen, Chung Andrew, Gichoya Judy Wawira, Hertzberg Vicki Stover, Ho Joyce C
Emory University, Atlanta, GA.
medRxiv. 2024 Oct 16:2024.10.14.24315465. doi: 10.1101/2024.10.14.24315465.
Pressure injury (PI) detection is challenging, especially in dark skin tones, due to the unreliability of visual inspection. Thermography may serve as a viable alternative as temperature differences in the skin can indicate impending tissue damage. Although deep learning models hold considerable promise toward reliably detecting PI, existing work fails to evaluate performance on diverse skin tones and varying data collection protocols. We collected a new dataset of 35 participants focused on darker skin tones where temperature differences are induced through cooling and cupping protocols. The dataset includes different cameras, lighting, patient pose, and camera distance. We compare the performance of three convolutional neural network (CNN) models trained on either the thermal or the optical images on all skin tones. Our results suggest thermography-based CNN is robust to data collection protocols. Moreover, the visual explanation often captures the region of interest without requiring explicit bounding box labels.
压力性损伤（PI）的检测具有挑战性，尤其是对于深肤色人群，因为目视检查的可靠性较低。热成像可能是一种可行的替代方法，因为皮肤中的温度差异可以表明即将发生的组织损伤。尽管深度学习模型在可靠检测PI方面具有很大潜力，但现有工作未能评估其在不同肤色和不同数据收集协议下的性能。我们收集了一个新的数据集，包含35名参与者，重点关注深肤色人群，通过冷却和拔罐协议诱导出温度差异。该数据集包括不同的相机、光照、患者姿势和相机距离。我们比较了在热图像或光学图像上训练的三种卷积神经网络（CNN）模型在所有肤色上的性能。我们的结果表明，基于热成像的CNN对数据收集协议具有鲁棒性。此外，可视化解释通常能够捕捉到感兴趣的区域，而无需明确的边界框标签。
