Automated Assessment for Robotic Suturing Utilizing Deep Learning Algorithms

利用深度学习算法自动评估机器人缝合

• 批准号: 10594534
• 负责人: Andrew Hung
• 金额: $ 27.97万
• 依托单位: UNIVERSITY OF SOUTHERN CALIFORNIA
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-04-01 至 2023-07-10
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10594534
• 关键词: Address; Assessment tool; Automobile Driving; Behavior; Benchmarking; Bladder Control; Cause of Death; Cessation of life; Characteristics; Classification; Clinical; Computer Vision Systems; Consumption; Data; Data Set; E-learning; Environment; Exercise; Feedback; Gestures; Impotence; Incontinence; Knowledge; Label; Learning; Link; Machine Learning; Malignant Neoplasms; Malignant neoplasm of prostate; Maps; Measurable; Measures; Medical Errors; Methods; Modality; Modeling; Motion; Movement; Needles; Operative Surgical Procedures; Outcome; Patient-Focused Outcomes; Patients; Performance; Positioning Attribute; Prostatectomy; Publishing; Quality of life; Radical Prostatectomy; Recovery; Recurrence; Risk; Robotics; Statistical Models; Surgeon; Surgical Error; Surgical Specialties; Surgical complication; Surgical sutures; Technical Expertise; Techniques; Technology; Time; Tissues; Training; Travel; Vision; Work; clinically relevant; cognitive task; cost; deep learning; deep learning algorithm; empowerment; improved; innovation; instrument; kinematics; learning network; learning strategy; machine learning algorithm; men; multimodality; novel; operation; predictive modeling; prospective; robot assistance; skills; surgery outcome; surgical risk; task analysis; virtual coach; virtual reality; virtual reality simulation; virtual reality simulator

ABSTRACT Medical errors are the third leading cause of death in the US at a cost of $20 billion annually. Surgical complications account for a third of these deaths and cost. Surgical performance directly impacts patient outcomes. Prostate cancer, the most common cancer in men, is treated with surgery (robot-assisted radical prostatectomy (RARP)) that can lead to impotence, incontinence, and even death. Reliable means of objectively assessing technique are required. In this project we will focus on assessing surgeon suturing skills during RARP through virtual reality (VR) simulation. Suturing is a common skill in many types of surgeries, can be tracked with performance metrics, and has been correlated with patient outcomes after RARP. In this proposal we seek to first determine the critical sub-step maneuvers of suturing and the technical skills necessary to achieve them successfully (Aim 1a). Further, we intend to develop an automated skills assessment pipeline through the analysis of raw kinematic data (Aim 1b), video (Aim 2b), and both kinematic/video (Aim 2c), from VR simulation performance by innovative machine learning strategies and deep-learning-based computer vision. The primary differentiator of the proposed work is determining how well granular sub-step maneuvers in suturing are performed. Surgeons participating in this study will not only provide data through their VR simulation performance, but will also contribute real patient data from the RARP to establish the relationship between surgeon skill, patient factors, and surgical outcomes. Statistical modeling will measure the differential impact of surgeon skill and patient factors to patient outcomes (Aim 3). We hypothesize that innovative application of machine learning algorithms can accurately assess surgeon technical skills, and can further anticipate likelihood of relevant clinical outcomes. The proposed work will enable scalable and actionable feedback in VR, empowering surgeons with valuable knowledge to minimize surgical risk in live surgery.

抽象的 医疗错误是美国第三大死亡原因，每年造成 200 亿美元的损失。 手术并发症占这些死亡和费用的三分之一。手术表现 直接影响患者的治疗效果。前列腺癌是男性最常见的癌症，已得到治疗 可能导致阳痿的手术（机器人辅助根治性前列腺切除术（RARP））， 失禁，甚至死亡。需要客观评估技术的可靠方法。 在这个项目中，我们将重点通过虚拟方式评估 RARP 期间外科医生的缝合技能 现实（VR）模拟。缝合是多种手术中的常用技能，可追踪 与绩效指标相关，并且与 RARP 后的患者结果相关。 在本提案中，我们首先寻求确定缝合的关键子步骤操作和 成功实现这些目标所需的技术技能（目标 1a）。此外，我们打算开发 通过分析原始运动学数据建立自动化技能评估流程（目标 1b）， 视频 (Aim 2b) 以及运动/视频 (Aim 2c)，来自 VR 模拟性能 创新的机器学习策略和基于深度学习的计算机视觉。 所提出的工作的主要区别在于确定子步骤的粒度如何 进行缝合操作。参与这项研究的外科医生不仅会提供 通过他们的 VR 模拟性能数据，但也将提供真实的患者数据 RARP 建立外科医生技能、患者因素和手术之间的关系 结果。统计模型将衡量外科医生技能和患者的不同影响 影响患者结果的因素（目标 3）。我们假设机器的创新应用 学习算法可以准确评估外科医生的技术技能，并可以进一步预测 相关临床结果的可能性。 拟议的工作将在 VR 中实现可扩展且可操作的反馈，从而增强外科医生的能力 拥有宝贵的知识，可最大限度地降低现场手术中的手术风险。