Intraoperative integration of artificial intelligence during cystoscopic surgery

膀胱镜手术中人工智能的术中整合

• 批准号: 10544344
• 负责人: JOSEPH C LIAO
• 金额: $ 49.61万
• 依托单位: STANFORD UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-01-01 至 2026-12-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10544344
• 关键词: Affect; Algorithms; Appearance; Artificial Intelligence; Base Sequence; Benign; Bladder; Bladder Neoplasm; Cancer Detection; Cancer Diagnostics; Cancer Patient; Cancerous; Cessation of life; Clinic; Clinical; Communities; Complex; Computer Vision Systems; Cystoscopy; Data; Data Set; Detection; Diagnosis; Diagnostic; Diagnostic Sensitivity; Ensure; Environment; Equipment; Excision; Future; Goals; Healthcare; Histologic; Hospitals; Human; Image; Image Analysis; Inflammatory; Intervention; Knowledge; Learning; Lesion; Light; Malignant Neoplasms; Malignant neoplasm of urinary bladder; Medical Imaging; Medical center; Modeling; Morbidity - disease rate; Morphology; Newly Diagnosed; Operating Rooms; Operative Surgical Procedures; Outcome; Papillary; Pathologic; Patients; Performance; Physician Assistants; Predictive Value; Process; Protocols documentation; Provider; Recurrence; Recurrent Malignant Neoplasm; Research; Role; Site; Specificity; Staging; Standardization; Surgeon; Technology; Testing; The Cancer Imaging Archive; Time; Training; Translating; Transurethral Resection; United States; Universities; Urologist; Urology; Validation; Washington; Work; annotation system; augmented intelligence; automated segmentation; body system; cancer diagnosis; cancer imaging; cancer recurrence; cancer risk; cancer surgery; care burden; cloud based; convolutional neural network; cost effective; deep learning algorithm; deep neural network; demographics; design; experience; high risk; image guided; image processing; improved; improved outcome; indexing; millisecond; mortality; multidisciplinary; neural; novel; patient stratification; prospective; recruit; recurrent neural network; risk stratification; screening; segmentation algorithm; tool; tumor; tumor progression

PROJECT SUMMARY Bladder cancer is the sixth most common cancer in the U.S., has one of the highest recurrence rates of all cancers, and is the most expensive cancer to treat from diagnosis to death. Current standard for bladder cancer diagnosis relies on clinic-based white light cystoscopy for initial screening, followed by transurethral resection of bladder tumor in the operating room for pathologic diagnosis and local staging. White light cystoscopy has several well recognized shortcomings, particularly incomplete detection, thereby leading to suboptimal resection and contributing to cancer recurrence and progression. Our goal is to improve outcomes for bladder cancer patients through integration of a deep learning algorithm to improve cystoscopic detection and enhance surgical resection. Artificial intelligence (AI)-based on deep neural networks have demonstrated remarkable capacity to learn complex relationships and incorporate existing knowledge into the inference model. We hypothesize that AI- augmented detection of bladder tumor will improve diagnostic cystoscopy in the clinic setting to identify suspicious lesions and improve the quality of transurethral resection in the operating room, thereby reducing overall cancer recurrence and outcome. Towards the goal of establishing a paradigm of AI-based framework for augmented detection of bladder cancer, we will leverage our strong preliminary data and outstanding environment in AI research. We propose three specific aims: 1) To curate a high-quality annotated cystoscopy imaging dataset to optimize deep neural network CystoNet; 2) To design and optimize CystoNet for real-time cystoscopic navigation and cancer detection; and 3) To conduct a prospective multicenter validation of CystoNet during bladder cancer surgery. Successful completion of the studies proposed here will serve to translate deep learning algorithm to the dynamic environment of cystoscopic surgery without the need for specialized instrumentaitons. We foresee our approach will improve the outcome of a major cancer and genearlizable to other organ systems amenable for endsocopic interventions.

项目摘要 膀胱癌是美国第六个最常见的癌症，它是所有人中最高的复发率之一 癌症是从诊断到死亡的最昂贵的癌症。当前膀胱标准 癌症诊断依靠基于临床的白光膀胱镜检查进行初始筛查，然后进行尿道诊断 在手术室切除膀胱肿瘤，以进行病理诊断和局部分期。白光 膀胱镜检查有几个公认的缺点，尤其是不完整的检测，从而导致 次优切除并导致癌症复发和进展。我们的目标是改善结果 通过整合深度学习算法来改善膀胱镜检测，用于膀胱癌患者 并增强手术切除。 基于深层神经网络的人工智能（AI）表现出了显着的学习能力 复杂的关系并将现有知识纳入推理模型。我们假设Ai- 增强膀胱肿瘤的检测将改善诊所环境中的诊断性膀胱镜检查，以鉴定 可疑病变并提高手术室中尿道切除的质量，从而减少 总体癌症复发和结果。目的是建立基于AI的框架的范式 为了增强对膀胱癌的检测，我们将利用强大的初步数据和出色的数据 AI研究的环境。我们提出了三个具体目标：1）策划高质量的注释膀胱镜检查 成像数据集以优化深神经网络囊肿； 2）设计和优化囊肿以实时 膀胱镜导航和癌症检测； 3）进行预期的多中心验证 膀胱癌手术期间的半胱氨酸。 成功完成此处提出的研究将有助于将深度学习算法转化为 膀胱镜手术的动态环境无需专门的仪器。我们预见 我们的方法将改善重大癌症的结果，并可以对其他器官系统进行元素固定 用于端区的末端干预措施。