Artificial Intelligence Enabled Multi-Spectral Autofluorescence Imaging for Real-time Determination of Muscle in Bladder Tumor During Resection

人工智能支持多光谱自发荧光成像，可在切除过程中实时确定膀胱肿瘤中的肌肉

• 批准号: 10325131
• 负责人: Rishikesh Pandey
• 金额: $ 39.99万
• 依托单位: CYTOVERIS INC
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-09-27 至 2024-02-29
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10325131
• 关键词: Algorithms; Artificial Intelligence; Biochemical; Biological; Bladder; Bladder Neoplasm; Cells; Characteristics; Classification; Clinic; Clinical; Collagen; Complement; Connective Tissue; Cystoscopes; Data; Detection; Development; Devices; Diagnosis; Diagnostic; Dinucleoside Phosphates; Elastin; Endoscopy; Epithelial; Excision; Extracellular Matrix; Flavin-Adenine Dinucleotide; Fluorescence; Goals; Gold; Guidelines; Hematoxylin and Eosin Staining Method; Histopathology; Hospitals; Image; Imaging Device; Institutional Review Boards; Investigation; Label; Lamina Propria; Malignant neoplasm of urinary bladder; Maps; Measures; Metabolic; Methods; Modeling; Morphology; Muscle; Network-based; Neurons; Niacinamide; Operative Surgical Procedures; Optics; Outpatients; Pathologist; Patient-Focused Outcomes; Patients; Pattern; Performance; Postoperative Period; Predictive Value; Procedures; Process; Prognosis; Reading; Research Personnel; Resected; Sampling; Scanning; Sensitivity and Specificity; Slide; Specimen; Staging; Stains; Surgeon; System; Techniques; Testing; Time; Tissue Sample; Tissues; Training; Transurethral Resection; Ultraviolet Rays; Validation; Work; absorption; algorithm training; base; cancer recurrence; care costs; chromophore; classification algorithm; clinical translation; commercialization; convolutional neural network; cost effective; deep learning; deep neural network; detrusor muscle; fluorophore; histological stains; histopathological examination; imaging system; improved; in vivo; malignant breast neoplasm; minimally invasive; mortality; network models; neural network; optical imaging; performance tests; point of care; prognostic significance; real-time images; research clinical testing; response; standard of care; tool; user-friendly; validation studies; virtual

PROJECT SUMMARY For adequate diagnosis and staging, transurethral resection of bladder tumor (TURBT) specimens must extend into the bladder muscle wall. Studies indicate that for patients with high-grade bladder cancer, 5-year mortality was 8% when the muscle was present in the TURBT specimen, and 13% when absent. For this reason, if there is not sufficient muscle in the specimen after the initial resection, guidelines recommend repeat TURBT. Almost half of TURBTs do not contain muscle as confirmed post-operatively by histopathologic examination. There are currently no practical tools available to surgeons to determine during the procedure whether the resected specimen includes sufficient muscle tissue. The goal of this project is to develop an imaging device that will be used for point-of-surgery detection of muscle in TURBT specimen in real-time. We will use ultraviolet light-emitting diodes to selectively excite different native fluorescent molecules in the tissue sample. We will further increase the biochemical information content by complementing the autofluorescence data with multi-wavelength reflectance images. We hypothesize that the combined multi-spectral autofluorescence and reflectance images will provide a snapshot of the integral biomolecular information of the tissue and, when combined with deep learning, capture latent biochemical and morphological differences that are encoded in the multispectral images. Our hypothesis is based on the fact that the connective tissue lamina propria and epithelial tissue have different biochemical make-up than the muscularis propria. We will employ a deep learning framework on the acquired images to develop a training algorithm from >200 ex vivo TURBT specimens from > 50 patients. The measured tissue will be processed for histopathological investigation to create true labels for algorithm training. We will interpret the deep learning classification results by correlating the extracted class features from the trained neural network with input image parameters, and consequently attribute them with known biological differences of the tissue types. To test the algorithm, we will acquire independent image sets from 80 samples from 20 patients and assess the concordance between our results and pathologists’ reading of the Hematoxylin and Eosin (H&E) slides. We will also use a convolutional neural network trained using a generative adversarial-network model to transform wide-field autofluorescence images acquired from unlabeled tissue sections into H&E images of the same samples. The virtual H&E images will be evaluated by pathologists to recognize major histopathological features in images generated with our virtual staining technique and compared with the histologically stained images of the same samples.

项目总结 为获得充分的诊断和分期，经尿道膀胱肿瘤电切术(TURBT)标本必须扩大 进入膀胱肌壁。研究表明，对于高级别膀胱癌患者，5年死亡率 当TURBT标本中有肌肉时为8%，当肌肉不存在时为13%。因此，如果 初次切除后标本中没有足够的肌肉，指南建议重复TURBT。 几乎一半的TURBT不像术后组织病理学检查所证实的那样含有肌肉。 目前还没有实用的工具可供外科医生在手术过程中确定是否 切除的标本包括足够的肌肉组织。这个项目的目标是开发一种成像设备 这将用于对TURBT标本中的肌肉进行实时手术点检测。我们将使用 紫外光发光二极管，选择性地激发组织样本中不同的天然荧光分子。 我们将通过补充自然荧光数据来进一步增加生化信息含量 多波长反射成像。我们假设多光谱自体荧光和 反射图像将提供组织的完整生物分子信息的快照，当 与深度学习相结合，捕获编码在 多光谱图像。我们的假设是基于结缔组织固有层和 上皮组织与固有肌具有不同的生化组成。我们将雇佣一名深水 基于获取的图像的学习框架，以开发来自&gt；200体外TURBT的训练算法 标本来自&gt；50名患者。测量的组织将被处理以进行组织病理学研究 为算法训练创建真实标签。我们将通过关联来解释深度学习分类结果 利用输入的图像参数，从训练好的神经网络中提取类别特征，从而 将它们归因于组织类型的已知生物学差异。为了测试算法，我们将获取 来自20名患者的80个样本的独立图像集，并评估我们结果之间的一致性 以及病理学家对苏木素和曙红(H&E)玻片的解读。我们还将使用卷积神经 利用产生式对抗性网络模型训练网络来转换广域自发荧光图像 从未标记的组织切片中获取的数据转换成相同样本的H&E图像。虚拟的H&E映像将是 由病理学家评估以识别我们的虚拟生成的图像中的主要组织病理学特征 并与相同标本的组织学染色图像进行比较。