OCT as a Platform for Non-Invasive Virtual H&E Biopsy

OCT 作为非侵入性虚拟 H 平台

• 批准号: 10254780
• 负责人: Yonatan Winetraub
• 金额: $ 37.64万
• 依托单位: STANFORD UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-09-15 至 2026-08-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10254780
• 关键词: 3-Dimensional; Aerospace Engineering; Affect; Algorithms; Animals; Area; Award; Bar Codes; Biological Markers; Biophysics; Biopsy; Brain; Brain Glioblastoma; Brain Neoplasms; COVID-19; Cancer Patient; Cancerous; Cells; Clinical; Contrast Media; Data; Data Set; Department chair; Detection; Development; Devices; Diagnosis; Disease; Early Diagnosis; Electrical Engineering; Entrepreneurship; Equilibrium; Excision; Feasibility Studies; Funding; Glioblastoma; Glioma; Goals; Gold; Grant; Harvest; Hematoxylin and Eosin Staining Method; Heterogeneity; Histology; Human; Image; Imaging Device; Imaging technology; Industry; Injections; Institutes; Interdisciplinary Study; International; Laboratories; Legal patent; Length; Letters; Location; Machine Learning; Malignant Childhood Neoplasm; Malignant Neoplasms; Malignant neoplasm of brain; Medical Imaging; Mentors; Methods; Modeling; Monitor; Moon; Mus; Noise; Operative Surgical Procedures; Optical Coherence Tomography; Optics; Organ; Pediatric Neoplasm; Physics; Positioning Attribute; Postdoctoral Fellow; Procedures; Process; Protocols documentation; Psychological Transfer; Public Speaking; Publications; Reporting; Research; Residual Cancers; Retina; Sampling; Scanning; Science, Technology, Engineering and Mathematics Education; Secure; Skin; Skin Cancer; Skin Tissue; Slide; Solid; Solid Neoplasm; Stains; Structure; Students; Supervision; Surgeon; System; Techniques; Technology; Time; Tissue Sample; Tissue Stains; Tissues; Training; Translations; Treatment Efficacy; Tumor Tissue; Uncertainty; Universities; Visualization; Work; base; bioimaging; brain tissue; cancer cell; computational neuroscience; experience; high school; human imaging; human tissue; imaging modality; improved; in vivo; in vivo imaging; in vivo optical imaging; instructor; instrumentation; millimeter; mortality; mouse model; neural network; next generation; nonhuman tissue; novel; optical imaging; professor; programs; relating to nervous system; structural biology; success; tenure track; tool; treatment response; tumor; tumor progression; virtual; virtual biopsy

The broad objective of this project is to develop imaging instrumentation and algorithmic technology to perform non-invasive, real-time, in-vivo, 3D, virtual H&E biopsies. One in four people worldwide will ultimately be affected by cancer. Surgical removal is the main treatment for most solid cancers. The surgeon is tasked with the delicate balancing act of excising enough tissue to avoid leaving behind residual cancer cells while not removing too much tissue, which can harm organ function. This is particularly important for brain tumors, the most common type of solid tumor in children and the leading cause of pediatric cancer mortality. The gold standard for detecting most solid cancers and confirming tumor margins is hematoxylin and eosin (H&E) stained tissue sections, which require an invasive biopsy procedure. Unfortunately, current non-invasive in-vivo imaging modalities do not produce images of comparable usefulness. We propose a novel imaging modality called a "virtual H&E biopsy'' that would generate H&E-like images of living tissue in real time. non-invasively up to 1 mm into the tissue. This imaging modality would be able to provide real-time diagnosis of tumor margins and invasiveness by scanning a large tissue area for residual cancer cells. Such information would guide treatment decisions for diseases such as brain and skin cancer. Beyond its clinical benefits, this technology can also be used for research into tumor development and tumor responses to treatment by providing in-vivo H&E-like images of healthy and tumorous tissue microstructures changing over time. To generate virtual H&E images, we will optimize a new imaging instrument we have developed based on optical coherence tomography (OCT) and image translation by a generative adversarial neural network (GAN). The key breakthrough enabling us to train a GAN to generate virtual H&E images is a technique called optical barcoding, which we used to obtain a dataset of OCT images and corresponding real H&E images aligned to single-cell precision. We have demonstrated this virtual H&E system with ex-vivo human skin tissue samples. For the proposed project, we will first train a GAN to generate virtual H&E images of healthy mouse brain tissue and glioblastoma mouse brain tissue ex-vivo (Aim 1 ). Second, we will use transfer learning to retrain the GAN to generate virtual H&E images of mouse brain tissue of in-vivo OCT scan (Aim 2a), and track for the first time how H&E images change as a mouse glioblastoma tumor develops (Aim 2b}. Finally, we will assess whether the GAN can be retrained across species by applying transfer learning on the mouse-brain trained GAN and use it to generate a virtual H&E biopsy of ex-vivo low-grade human glioma (Aim 3). To the best of our knowledge, this will be the first time transfer learning has been applied across species for biomedical images. Such transfer learning can accelerate virtual biopsy research since mouse samples are significantly easier to obtain and handle, thereby opening up applications in locations where acquiring a human dataset for training a virtual biopsy GAN would be difficult or impossible to achieve (e.g., the retina).

该项目的总体目标是开发成像仪器和算法技术 执行非侵入性、实时、体内、3D、虚拟 H&E 活检。全球四分之一的人会 最终受到癌症的影响。手术切除是大多数实体癌的主要治疗方法。外科医生是 负责切除足够的组织以避免留下残留的癌细胞的微妙平衡行为 同时不要去除过多的组织，否则会损害器官功能。这对大脑尤其重要 肿瘤，儿童最常见的实体瘤类型，也是儿童癌症死亡率的主要原因。这 检测大多数实体癌和确认肿瘤边缘的黄金标准是苏木精和伊红 (H&E) 染色的组织切片，需要侵入性活检程序。不幸的是，目前的非侵入性体内 成像方式不会产生具有可比用途的图像。我们提出了一种新颖的成像方式 称为“虚拟 H&E 活检”，可实时生成类似 H&E 的活体组织图像。 至组织内 1 毫米。这种成像方式将能够提供肿瘤边缘的实时诊断和 通过扫描大面积组织区域以查找残留癌细胞来确定侵袭性。这些信息将指导治疗 脑癌和皮肤癌等疾病的决策。除了其临床益处外，该技术还可以 通过提供体内 H&E 样，用于研究肿瘤发展和肿瘤对治疗的反应 健康和肿瘤组织微观结构随时间变化的图像。 为了生成虚拟 H&E 图像，我们将优化我们开发的新型成像仪器 关于光学相干断层扫描（OCT）和生成对抗神经网络的图像翻译 （甘）。使我们能够训练 GAN 生成虚拟 H&E 图像的关键突破是一种称为 光学条形码，我们用它来获取 OCT 图像和相应的真实 H&E 图像的数据集 与单细胞精度对齐。我们已经用离体人体皮肤组织演示了这个虚拟 H&E 系统 样品。对于拟议的项目，我们将首先训练 GAN 来生成健康小鼠的虚拟 H&E 图像 脑组织和胶质母细胞瘤小鼠离体脑组织（目标 1）。其次，我们将使用迁移学习来重新训练 GAN 生成体内 OCT 扫描的小鼠脑组织的虚拟 H&E 图像（目标 2a），并跟踪 首次观察 H&E 图像如何随着小鼠胶质母细胞瘤的发展而变化（目标 2b}。最后，我们将评估 是否可以通过在小鼠大脑训练的 GAN 上应用迁移学习来跨物种重新训练 GAN 并用它生成离体低级别人类神经胶质瘤的虚拟 H&E 活检（目标 3）。尽我们最大的努力 知识，这将是迁移学习首次跨物种应用于生物医学图像。 这种转移学习可以加速虚拟活检研究，因为小鼠样本更容易获得 获取和处理，从而在获取人类数据集以训练人类的地方打开应用程序 虚拟活检 GAN 很难或不可能实现（例如视网膜）。