TOPIC #411 - PHASE I SBIR CONTRACT - DE-IDENTIFICATION SOFTWARE TOOLS FOR CANCER IMAGING RESEARCH

话题

• 批准号: 10274086
• 负责人: PAUL BUNTING
• 金额: $ 38.65万
• 依托单位: BIODATA CONSORTIUM, LLC
• 依托单位国家: 美国
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-09-16 至 2021-06-15
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10274086
• 关键词: Algorithms; Artificial Intelligence; Complex; Computer Vision Systems; Consumption; Contracts; Data; Data Set; Digital Imaging and Communications in Medicine; Elements; Excision; Head; Human; Image; Ingestion; Institution; Intervention; Location; Machine Learning; Magnetic Resonance Imaging; Manuals; Maps; Medical Imaging; Medical Technology; Metadata; Methods; Modeling; Natural Language Processing; Pathology; Phase; Process; Radiology Specialty; Research; Sampling; Slide; Small Business Innovation Research Grant; Software Tools; Source; Techniques; Testing; Text; Time; Training; Vendor; Work; cancer imaging; data ingestion; data warehouse; file format; optical character recognition; pathology imaging; patient privacy; purge; radiological imaging; whole slide imaging

Developing artificial intelligence technology for medical imaging applications requires training models on large and diverse datasets. Currently, aggregation of large data repositories, including radiology and pathology images, is limited by concerns around patient privacy. In order to successfully share medical images, an institution must be able to quickly and accurately de-identify large numbers of images in batches. This process is currently manual and time-consuming. We propose a pipeline to remove PHI from both radiology DICOM images and pathology whole slide images by leveraging machine learning, natural language processing, and compartmentalized workflow techniques to significantly reduce the human intervention needed to anonymize medical images. In addition to examining header data in the images, we will use optical character recognition and computer vision algorithms to detect text in any location or orientation in the image, then automatically record and subsequently purge these regions. These techniques will be configured to work on a variety of image types (CT, MRI, radiograph, etc) and cover multiple OEM vendors for both radiology and pathology images. This phase I statement of work will construct the software tools, methods, and datasets necessary to facilitate a phase II where the complex algorithms needed for autonomous deidentification will be developed. This phase II processing will be referred to throughout this document as the workflow.

开发用于医学成像应用的人工智能技术需要在大型且多样化的数据集上训练模型。 目前，包括放射学和病理学图像在内的大型数据存储库的聚合受到对患者隐私的担忧的限制。 为了成功共享医学图像，机构必须能够快速、准确地批量对大量图像进行去标识化。 目前此过程是手动且耗时的。 我们提出了一个管道，通过利用机器学习、自然语言处理和分区工作流程技术，从放射学 DICOM 图像和病理学整个幻灯片图像中删除 PHI，以显着减少匿名医学图像所需的人为干预。 除了检查图像中的标题数据之外，我们还将使用光学字符识别和计算机视觉算法来检测图像中任何位置或方向的文本，然后自动记录并随后清除这些区域。这些技术将被配置为适用于各种图像类型（CT、MRI、射线照片等），并涵盖放射学和病理学图像的多个 OEM 供应商。 第一阶段工作说明书将构建促进第二阶段所需的软件工具、方法和数据集，其中将开发自主去识别所需的复杂算法。 此第二阶段处理将在本文档中称为工作流程。