Real-time AI-enhanced Low Dose Fluoroscopy

实时人工智能增强低剂量透视

• 批准号: 10385142
• 负责人: Enhao Gong
• 金额: $ 13.22万
• 依托单位: SUBTLE MEDICAL, INC.
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-09-25 至 2023-09-24
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10385142
• 关键词: Adopted; Anatomy; Architecture; Artificial Intelligence; Breast Cancer Risk Factor; Cadaver; Child; Clinic; Clinical; Clinical Research; Computer software; Data Set; Development; Dose; Exposure to; Feedback; Fluoroscopy; Goals; Hospitals; Image; Image Enhancement; Imaging Device; Industrialization; Ionizing radiation; Learning; Limb structure; Magnetic Resonance Imaging; Malignant Childhood Neoplasm; Malignant Neoplasms; Medical; Medical Imaging; Methods; Modeling; Motivation; Operating Rooms; Operative Surgical Procedures; Orthopedics; Patients; Performance; Phase; Positron-Emission Tomography; Procedures; Radiation Dose Unit; Radiation exposure; Recurrence; Research; Risk; Roentgen Rays; Small Business Innovation Research Grant; Speed; Spinal; Spine surgery; Surgeon; System; Thyroid Gland; Time; Training; Translating; Vertebral column; Visualization; Woman; Work; base; cancer risk; deep learning; denoising; experience; image guided intervention; image processing; image reconstruction; imaging modality; improved; innovation; millisecond; minimally invasive; model design; novel; operation; preservation; processing speed; real time model; software development; success; tool

Project Summary Motivation: Fluoroscopy is an indispensable tool for image-guided interventions in 50 million surgeries performed annually in the US. It leverages ionizing radiation from x-rays to provide surgeons with real-time, high-quality imaging feedback. Radiation exposure is harmful for both the patients and surgeons. Repetitive patient exposure has been shown to double the risk of breast cancer in women; meanwhile, surgeon exposure is also concerning. Orthopedic surgeons are 5x more likely to develop cancer in their lifetime; spine surgeons receive up to 12x more radiation exposure compared to other orthopedic surgeons. With minimally invasive surgery becoming widely adopted in recent years, the use of fluoroscopy has greatly increased. Surgeons rely on the navigation provided by fluoroscopy during these procedures, as they do not have direct visualization of the anatomy. Therefore, reducing the radiation exposure from fluoroscopy while maintaining high imaging quality is a high priority. In the past few years, artificial intelligence (AI) methods have shown promising advances to improve the quality of medical imaging. Subtle Medical Inc. has already received FDA clearance for its AI-based software products to reduce the dose for PET by four times and improve image quality for MRI. The motivation of this proposal is to translate our initial success to another imaging modality and achieve low dose fluoroscopy. Approach: This phase I SBIR project has three aims. Aim 1 is to develop AI software using recurrent deep learning architecture to achieve 6x dose reduction for fluoroscopy. Aim 2 is to design model pruning, kernel optimization, and high-performance inference frameworks to achieve real-time processing. Finally, in Aim 3, we will evaluate both qualitatively and quantitatively the developed software on phantoms and cadavers. Significance: This work will enable six times lower dose fluoroscopy. The completion of the project will have wide impact to greatly reduce radiation exposure in the operating room, hence reducing the risk of cancer development for both patients and clinicians.

项目概要 动机：透视检查是 5000 万人进行图像引导干预不可或缺的工具 每年在美国进行的手术。它利用 X 射线的电离辐射来提供 为外科医生提供实时、高质量的成像反馈。辐射暴露对双方都有害 患者和外科医生。患者重复接触已被证明会使患病风险加倍 女性乳腺癌；与此同时，外科医生的暴露也令人担忧。骨科 外科医生一生中患癌症的可能性高出 5 倍；脊柱外科医生接受高达 12 倍的治疗 与其他骨科医生相比，接受更多的辐射。具有微创 近年来手术的广泛应用，透视检查的使用大大增加。 外科医生在这些手术过程中依赖透视提供的导航，就像他们所做的那样 无法直接观察解剖结构。因此，减少辐射暴露 透视检查同时保持高成像质量是重中之重。在过去的几年里， 人工智能（AI）方法在提高医疗质量方面已显示出有希望的进展 医学成像。 Subtle Medical Inc. 的基于人工智能的产品已获得 FDA 批准 软件产品可将 PET 剂量减少四倍，并提高 MRI 图像质量。 该提案的动机是将我们最初的成功转化为另一种成像方式 实现低剂量透视。 方法：第一阶段 SBIR 项目有三个目标。目标 1 是开发人工智能软件 循环深度学习架构可实现透视剂量减少 6 倍。目标 2 是 设计模型剪枝、内核优化和高性能推理框架 实现实时处理。最后，在目标 3 中，我们将定性和评估 对模型和尸体上开发的软件进行定量分析。 意义：这项工作将使透视剂量降低六倍。完成 项目将产生广泛的影响，大大减少手术室的辐射暴露，因此 降低患者和临床医生患癌症的风险。