Schumaker Grant, Becker Andrew, An Gary, Badylak Stephen, Johnson Scott, Jiang Peng, Vodovotz Yoram, Cockrell R Chase
Department of Surgery, University of Vermont, Burlington, Vermont.
McGowan Institute of Regenerative Medicine, University of Pittsburgh, Pittsburgh, Pennsylvania.
J Surg Res. 2022 Feb;270:547-554. doi: 10.1016/j.jss.2021.10.017. Epub 2021 Nov 23.
The clinical characterization of the biological status of complex wounds remains a considerable challenge. Digital photography provides a non-invasive means of obtaining wound information and is currently employed to assess wounds qualitatively. Advances in machine learning (ML) image processing provide a means of identifying "hidden" features in pictures. This pilot study trains a convolutional neural network (CNN) to predict gene expression based on digital photographs of wounds in a canine model of volumetric muscle loss (VML).
Images of volumetric muscle loss injuries and tissue biopsies were obtained in a canine model of VML. A CNN was trained to regress gene expression values as a function of the extracted image segment (color and spatial distribution). Performance of the CNN was assessed in a held-back test set of images using Mean Absolute Percentage Error (MAPE).
The CNN was able to predict the gene expression of certain genes based on digital images, with a MAPE ranging from ∼10% to ∼30%, indicating the presence and identification of distinct, and identifiable patterns in gene expression throughout the wound.
These initial results suggest promise for further research regarding this novel use of ML regression on medical images. Specifically, the use of CNNs to determine the mechanistic biological state of a VML wound could aid both the design of future mechanistic interventions and the design of trials to test those therapies. Future work will expand the CNN training and/or test set, with potential expansion to predicting functional gene modules.
复杂伤口生物学状态的临床特征描述仍然是一项重大挑战。数字摄影提供了一种获取伤口信息的非侵入性方法，目前用于定性评估伤口。机器学习（ML）图像处理技术的进步提供了一种识别图片中“隐藏”特征的方法。这项初步研究训练了一个卷积神经网络（CNN），以基于体积性肌肉损失（VML）犬模型中伤口的数字照片来预测基因表达。
在VML犬模型中获取体积性肌肉损失损伤的图像和组织活检样本。训练一个CNN，将基因表达值作为提取的图像片段（颜色和空间分布）的函数进行回归。使用平均绝对百分比误差（MAPE）在一组保留的图像测试集中评估CNN的性能。
CNN能够基于数字图像预测某些基因的表达，MAPE范围约为10%至30%，表明在整个伤口的基因表达中存在并可识别出不同的模式。
这些初步结果表明，关于在医学图像上使用这种新型ML回归方法的进一步研究具有前景。具体而言，使用CNN来确定VML伤口的机械生物学状态，可能有助于未来机械干预措施的设计以及测试这些疗法的试验设计。未来的工作将扩大CNN训练集和/或测试集，并有可能扩展到预测功能基因模块。
