Non-invasive automated wound analysis via deep learning neural networks

通过深度学习神经网络进行非侵入性自动伤口分析

• 批准号: 10460416
• 负责人: Kyle Patrick Quinn
• 金额: $ 39.28万
• 依托单位: UNIVERSITY OF ARKANSAS AT FAYETTEVILLE
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-08-05 至 2025-04-30
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10460416
• 关键词: Address; Adoption; American; Animal Model; Architecture; Artificial Intelligence; Biochemical; Biopsy; Cell Count; Cell Proliferation; Cell physiology; Cellular Infiltration; Cellularity; Classification; Clinic; Clinical; Clinical assessments; Collagen; Collection; Consumption; Contrast Media; Coupled; Data; Debridement; Dermatologic; Dermis; Diabetic Foot Ulcer; Disease; Elastin; Elderly; Epidermis; Excision; Feedback; Fibrosis; Fluorescence; Functional disorder; Future; Generations; Geometry; Goals; Granulation Tissue; Hair follicle structure; Health; Histologic; Histology; Histopathology; Image; Image Analysis; Injury; Keratin; Label; Laboratory Research; Lipids; Machine Learning; Manuals; Measures; Metabolic; Metabolism; Methods; NADH; Operative Surgical Procedures; Optical Biopsy; Outcome; Pathologist; Research; Research Personnel; Series; Skin; Skin Tissue; Source; Stains; Structure; Techniques; Technology; Testing; Three-Dimensional Imaging; Time; Tissues; Training; Visual; Wound Infection; analysis pipeline; automated analysis; automated segmentation; base; cell motility; cell type; chronic wound; cofactor; convolutional neural network; cost; crosslink; deep learning; deep neural network; generative adversarial network; histological image; histological stains; image processing; imaging Segmentation; in silico; in vivo; in vivo optical imaging; insight; microscopic imaging; multiphoton microscopy; neural network; non-healing wounds; non-invasive imaging; optical imaging; pentosidine; point of care; product development; public health relevance; quantitative imaging; radiological imaging; second harmonic; skin wound; tool; transfer learning; two-photon; virtual; wound; wound care; wound closure; wound healing

Project Summary: Each year millions of Americans develop chronic wounds, which require advanced wound care that has been estimated to cost $50 Billion annually. However, our understanding of chronic wounds and how to treat them has been limited by a lack of established methods to objectively characterize and measure wound features. Detailed assessments of wounds in the clinic and research laboratory often occur through histological analysis of tissue biopsies. This information can provide insight into cellular migration into the wound, cellular proliferation at the edge of the wound, infection, and fibrosis. However, the collection, creation, and analysis of histology sections is inherently invasive, time-consuming, and qualitative. The goal of this proposal is to develop an image analysis pipeline that can provide automated quantitative analysis of wounds and lay the groundwork for a non- invasive real-time “optical biopsy” that can provide information identical to standard histopathology. Our central hypothesis is that artificial intelligence approaches using deep learning convolutional neural networks can be coupled with in vivo multiphoton microscopy and existing quantitative image analysis methods to achieve this goal with the same accuracy as traditional biopsies with histological staining and expert analysis. In Aim 1, we will training and validate neural networks capable of segmenting and quantifying standard wound histology based on training from three independent wound healing research labs. In Aim 2, we will adapt this network to perform segmentation and quantification of in vivo label-free multiphoton microscopy images of skin wounds to provide rapid readouts of wound organization and metabolic function. Finally in Aim 3, we will develop and validate a network capable of generating virtual histology images from our stain-free non-invasive in vivo MPM images, which can be coupled with the networks developed in Aim 1 and 2 to provide a comprehensive assessment of wound microstructure and metabolism. In the near-term, this proposal will develop a series of robust analysis tools that can be applied to existing H&E-stained or unstained skin tissue sections commonly studied by wound healing researchers. In the long-term, the combination of label-free multiphoton microscopy and machine learning-based image analysis will enable completely non-invasive wound histology that can be performed in real-time at the point of care to guide debridement and wound care.

项目摘要： 每年数以百万计的美国人发展慢性逻辑逻辑，这需要先进的逻辑护理 估计每年耗资500亿美元。但是，我们对慢性伤口以及如何对待它们的理解 缺乏客观地表征和测量伤口特征的既定方法受到限制。 经常通过组织学分析进行诊所和研究实验室伤口的详细评估 组织活检。这些信息可以洞悉细胞迁移到伤口，细胞增殖中 在伤口的边缘，感染和纤维化。但是，组织学的收集，创建和分析 部分本质上是侵入性的，耗时的和定性的。该提议的目的是制定图像 分析管道可以为伤口提供自动定量分析，并为非 - 侵入性的实时“光学活检”，可以提供与标准组织病理相同的信息。我们的中心 假设是使用深度学习卷积神经网络的人工智能方法可以是 结合体内多光子显微镜和现有的定量图像分析方法，以实现这一目标 目标与传统活检的准确性相同，并具有组织学染色和专家分析。在AIM 1中，我们 将训练和验证能够分割和量化标准伤口组织学的神经网络 关于三个独立增益康复研究实验室的培训。在AIM 2中，我们将调整该网络以执行 对皮肤伤口的体内无标签多光显微镜显微镜显微镜图像进行分割和定量以提供 伤口组织和代谢功能的快速读数。最终在AIM 3中，我们将开发和验证 网络能够从我们的无不锈钢在体内MPM图像中生成虚拟组织学图像， 可以将其与AIM 1和2中开发的网络相结合，以提供有关的全面评估 伤口微观结构和代谢。在近期，该提案将制定一系列强大的分析 可以应用于现有的H＆E染色或未染色的皮肤组织切片的工具，通常由伤口研究 治愈研究人员。从长远来看，无标签的多光子显微镜和机器的组合 基于学习的图像分析将使可以在 在指导清创和伤口护理的护理时实时。