SBIR Phase I: Digitizing The Pathologist In The Operating Room

这个小企业创新研究（SBIR）I期项目的更广泛的影响/商业潜力是提高癌症诊断和边缘筛查的质量和可重复性。手术目前代表了治愈浸润性癌症的最佳机会，但受到现代病理学方法的限制。莫氏手术是皮肤癌的首选治疗方法，因为它的治愈率最高，但它往往是分阶段进行的，延长了手术时间。离体共聚焦显微镜（XVM）的使用可能更快，成本更低，并且固有地具有3D和数字化，其益处包括：1）通过丰富的3D信息内容和简化的标本方向维持来增强准确性，精度和边缘控制，减少错误并改善功能结果; 2）减少开放性手术伤口的持续时间，可能降低并发症的发生率;和（3）增强和加速手术流程。这个小企业创新研究（SBIR）第一阶段项目旨在改进莫氏手术和其他边缘筛查应用。使用共焦图像处理软件，所提出的软件将改进当前的病理处理方法，使快速处理和重新着色的XVM图像，可视化而无需重新训练，并自动检测残留肿瘤在病人的床边，所有在几分钟内。本文所述的研究将通过以下开发项目产生功能齐全且强大的软件产品：1）基于人工智能（AI）的图像预处理和着色/增强软件，以及2）基于AI的自动识别关键形态特征和诊断基底细胞癌和鳞状细胞癌的软件。该奖项反映了NSF的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

The broader impact /commercial potential of this Small Business Innovation Research (SBIR) Phase I project is to improve the quality and reproducibility of cancer diagnosis and margin screening.Surgery currently represents the best opportunity for curing invasive cancers but is limited by modern pathology methods. Mohs surgery is the treatment of choice for skin cancer because it results in the highest cure rates, but it often takes place in stages, extending surgical procedures. The use of ex vivo confocal microscopy (XVM) is potentially faster, less costly, and inherently both 3-D and digitized, with benefits including: 1) enhanced accuracy, precision, and margin control via enriched 3D information content and simplified specimen orientation maintenance, decreasing error and improving functional outcomes; 2) decreased duration of open surgical wounds potentially reducing the rate of complications; and (3) enhanced and accelerated surgical workflows.This Small Business Innovation Research (SBIR) Phase I project aims to improve Mohs surgery and other margin screening applications. Using confocal image processing software, the proposed software will improve current pathology processing methods by enabling rapid processing and re-coloring of XVM images, visualization without the need for retraining, and automated detection of residual tumor at the patient’s bedside, all within minutes. The research described here will result in the production of a fully functional and robust software product through the following development projects: 1) Artificial intelligence (AI)-based software for image preprocessing and colorization/enhancement, and 2) AI-based software for automated identification of key morphological features and diagnosis of basal cell and squamous cell carcinoma. The proposed technology will streamline cancer specimen processing, ultimately improving patient outcomes.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.