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

基本信息

批准号：
10631196
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
项目类别：
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/10631196
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 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 Infection 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 analysis pipeline automated analysis automated segmentation cell motility cell type chronic wound cofactor convolutional neural network cost crosslink deep learning deep neural network disease classification 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

项目摘要

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.

项目概要：每年有数以百万计的美国人出现慢性伤口，这需要先进的伤口护理然而，我们对慢性伤口及其治疗方法的了解估计每年花费 500 亿美元。由于缺乏客观表征和测量伤口特征的既定方法而受到限制。临床和研究实验室对伤口的详细评估通常通过组织学分析进行这些信息可以深入了解细胞迁移到伤口、细胞增殖的情况。然而，伤口边缘、感染和纤维化的收集、创建和分析。切片本质上是侵入性的、耗时的和定性的。该提案的目标是开发图像。分析管道，可以提供伤口的自动定量分析，并为非伤口分析奠定基础侵入性实时“光学活检”，可以提供与标准组织病理学相同的信息。假设使用深度学习卷积神经网络的人工智能方法可以结合体内多光子显微镜和现有的定量图像分析方法来实现这一目标在目标 1 中，我们通过组织学染色和专家分析实现了与传统活检相同的准确性。将训练和验证基于标准伤口组织学的分割和量化神经网络在目标 2 中，我们将调整该网络来执行来自三个独立伤口愈合研究实验室的培训。对皮肤伤口的体内无标记多光子显微镜图像进行分割和量化，以提供最后，在目标 3 中，我们将开发并验证伤口组织和代谢功能。网络能够从我们的免染色非侵入性体内 MPM 图像生成虚拟组织学图像，它可以与目标 1 和 2 中开发的网络相结合，以提供对在短期内，该提案将开展一系列稳健的分析。可应用于伤口通常研究的现有 H&E 染色或未染色皮肤组织切片的工具从长远来看，无标记多光子显微镜和机器的结合。基于学习的图像分析将实现完全非侵入性的伤口组织学，可以在在护理点实时指导清创和伤口护理。