Deep Learning Image Enhancement for Point of Care Ultrasound

用于床旁超声的深度学习图像增强

• 批准号: 10614918
• 负责人: Ouwen Huang
• 金额: $ 3.91万
• 依托单位: DUKE UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-09-03 至 2023-11-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10614918
• 关键词: Abdomen; Acoustics; Adoption; Algorithms; Anatomy; Android; Apple; Architecture; Benchmarking; Blood Vessels; Cardiac; Cardiovascular system; Career Choice; Clinical; Cloud Computing; Clutterings; Computer software; Custom; Data; Devices; Diagnostic; Fatty acid glycerol esters; Future; Generations; Human; Image; Image Analysis; Image Enhancement; Impairment; Liver; Medical; Modeling; Morphologic artifacts; Muscle; Noise; Output; Overweight; Performance; Process; Provider; Publishing; Reader; Research; Research Personnel; Research Proposals; Running; Signal Transduction; Source; Speed; Sum; System; Tablet Computer; Time; Tissues; Training; Translating; Ultrasonography; Work; X-Ray Computed Tomography; abdominal wall; acoustic imaging; attenuation; clinical application; clinical translation; cost; data modeling; deep learning; deep learning model; experimental study; fetal; handheld mobile device; image processing; image reconstruction; imaging modality; imaging properties; improved; in silico; in vivo; interest; learning strategy; novel; obese patients; open source; operation; patient population; performance tests; point of care; portability; preference; real-time images; rib bone structure; signal processing; simulation; skills; tool; translational barrier; ultrasound

Project Summary Ultrasound has many clinical applications due to it’s non-invasive, non-ionizing, and real-time imaging properties. However, ultrasound still relies heavily on operator skills for image acquisition and interpretation. Operator skill is especially challenged in overweight and obese patient populations where imaging artifacts such as acoustic clutter are more prominent and decrease anatomical conspicuity. To decrease the interpretation burden faced by operators, we aim to develop a deep learning framework for real-time acoustic clutter artifact suppression. We generate preliminary in silico training data using a configurable cloud-compute tool that scales to an 8000 CPU cluster. This tool is ideal for deep learning methods as it significantly speeds up the turnaround time for simulating unique ultrasound acquisition configurations enabling data generation in days as opposed to months. In this project, we will open-source our cloud-compute simulations tools, improve our current in silico data model of acoustic clutter by incorporating human abdominal wall tissue information from medical CT scans, and assess our clutter correction model’s performance on in vivo data. To translate our model’s results for medical provider interpretation, image post-processing is necessary. In our recently published work, MimickNet, we use deep learning methods to successfully approximate post-processing algorithms found on some of the best clinical-grade ultrasound scanners. We propose extending MimickNet to incorporate post-processing approximations for anatomy-specific use cases such as cardiac and vascular imaging. This will provide more off-the-shelf tooling for researchers to translate their algorithmic research into image forms familiar to providers, thus easing clinical translation. Lastly, portable ultrasound hardware has significantly decreased in cost, enabling the widespread use of mobile point-of-care ultrasound (POCUS). Since many consumer devices contain hardware accelerators specific for deep learning applications, there is an opportunity to correct ultrasound artifacts in real-time, even while constrained to mobile hardware. Our preliminary data show that beamforming operations and MimickNet can run at > 100 frames-per-second on an NVIDIA P100 GPU. We propose developing a framework to transfer our image processing pipeline completely onto mobile hardware accelerators. This work will enable translating novel image processing algorithms as easy as downloading software. Our work in developing a deep learning framework for POCUS systems covers the full image reconstruction pipeline from simulated data to producing a clinical-grade image familiar to providers. This framework will provide a rapid translational path for improving ultrasound imaging quality on cheap and widely available mobile hardware.

项目摘要 超声具有无创、非电离、实时成像等优点，具有广泛的临床应用前景 属性。然而，超声波仍然在很大程度上依赖操作员的技能来获取和解释图像。 在超重和肥胖的患者群体中，操作技能尤其受到挑战，因为在这些人群中，成像伪影 例如声学杂波更加突出，并降低了解剖的显着性。以减少 面对操作员面临的口译负担，我们的目标是开发一个实时深度学习框架 声杂波伪影抑制。 我们使用可配置的云计算工具生成初步的远程培训数据，该工具可扩展到 8000个CPU的集群。此工具是深度学习方法的理想选择，因为它显著加快了 模拟独特的超声采集配置的周转时间，可在数天内生成数据 而不是几个月。在这个项目中，我们将开源我们的云计算模拟工具，改进我们的 结合人体腹壁组织信息的声杂波电子数据模型研究现状 从医学CT扫描，并评估我们的杂波校正模型的性能在活体数据。 为了将我们的模型结果转换为医疗提供者的解释，图像后处理是 这是必要的。在我们最近出版的作品MimickNet中，我们使用深度学习方法成功地 在一些最好的临床级超声扫描仪上找到的近似后处理算法。我们 建议扩展MimickNet以包含用于特定解剖的后处理近似 心脏和血管成像等病例。这将为研究人员提供更多现成的工具 将他们的算法研究转换为提供商熟悉的图像形式，从而简化临床翻译。 最后，便携式超声硬件显著降低了成本，使广泛的 使用移动医疗点超声波(Pocus)。由于许多消费设备包含硬件 特定于深度学习应用的加速器，有机会在 实时，即使受限于移动硬件也是如此。我们的初步数据显示波束形成 操作和MimickNet可以在NVIDIA P100图形处理器上以每秒100帧的速度运行。我们建议 开发一个框架，将我们的图像处理流水线完全转移到移动硬件上 加速器。这项工作将使翻译新的图像处理算法变得像下载一样容易 软件。 我们为Pocus系统开发深度学习框架的工作涵盖了整个图像。 从模拟数据到产生提供者熟悉的临床级别图像的重建流水线。这 框架将提供一条快速转换路径，以廉价和 随处可见的移动硬件。