Multimodal Intraoral Imaging System for Oral Cancer Detection and Diagnosis in Low Resource Setting

口腔和口咽鳞状细胞癌（OSCC）一起列为第六大常见癌症 全球每年新增40万例癌症病例。这些癌症中有三分之二发生在低- 中等收入国家（LMIC）。虽然美国的5年生存率为62%，但生存率仅为10- 发展中国家的治愈率约为30%。低收入国家的生存率低主要是由于晚期 诊断和由此导致的疾病进展到诊断时的晚期。因此，当务之急是 早期和迅速诊断LRS的先兆和恶性病变。 为了满足对能够在低水平进行全面口腔癌筛查和诊断的技术的需求， 资源设置（LRS），以识别可疑病变，分诊高风险受试者，从而使 适当的治疗管理和后续行动，该项目汇集了一个跨学科的团队， 在光学成像、肿瘤学、深度学习、技术翻译和 商业化该团队将开发，验证和临床翻译多模式口内成像 该系统用于口腔癌检测和诊断，具有更好的灵敏度和特异性。这项工作将 解决在LRS中采用光学成像技术治疗口腔癌的关键障碍， 在1）开发和评估双模式（偏振白色光成像[pWLI]和 自体荧光成像[AFI]）移动的成像探针; 2）评估低成本、便携式光学相干 在印度的淋巴结中心设置中用于口腔癌检测和诊断的断层扫描（OCT）系统;以及3） 开发和评估用于临床决策的基于深度学习的图像分类算法 指导由于这些关键技术中的每一种都已分别在LRS中的口腔癌成像中得到证明， 成功开发多模式口内成像系统的潜力， 口腔癌的位置解析诊断，并向LRS的医疗专业人员过渡 非常高。为了实现项目目标，该团队提出了三个目标：1）开发一种便携式，半灵活， 和紧凑的多模态口内成像系统; 2）评估原型口内成像系统的临床可行性， 成像系统，并开发基于深度学习的图像处理算法，用于早期检测，诊断， 和口腔异型增生和恶性病变的映射;和3）验证原型口内的能力 用于诊断口腔发育不良和恶性病变的成像系统。 该项目的成功完成将导致多模式口内成像系统的过渡 和深度学习图像分类，利用多种技术的各自优势， 为LRS中的最终用户提供新的和迫切需要的功能。这个综合系统将1）发现可疑的 敏感性和特异性高的区域; 2）分诊高危受试者; 3）指导活检的选择 研究中心和地图病变异质性，以改善治疗计划和术中指导。

Oral and oropharyngeal squamous cell carcinoma (OSCC) together rank as the sixth most common cancer worldwide, accounting for 400,000 new cancer cases each year. Two-thirds of these cancers occur in low- and middle-income countries (LMICs). While the 5-year survival rate in the U.S. is 62%, the survival rate is only 10- 40% and cure rate around 30% in the developing world. The poor survival rate in LMICs is mainly due to late diagnosis and the resultant progression of disease to an advanced stage at diagnosis. Therefore, it is imperative to diagnose precursor and malignant lesions in LRS early and expeditiously. To meet the need for technologies that enable comprehensive oral cancer screening and diagnosis in low resource settings (LRS) to identify the suspicious lesions, triage the high-risk subjects and thereby enable appropriate treatment management and follow up, this project brings together an interdisciplinary team with complementary expertise in optical imaging, oncology, deep learning, technology translation, and commercialization. The team will develop, validate, and clinically translate a multimodal intraoral imaging system for oral cancer detection and diagnosis with better sensitivity and specificity. This work will address key barriers to adopting optical imaging techniques for oral cancer in LRS by building on the team’s experience in 1) developing and evaluating dual-mode (polarized white light imaging [pWLI] and autofluorescence imaging [AFI]) mobile imaging probes; 2) evaluating a low-cost, portable optical coherence tomography (OCT) system for oral cancer detection and diagnosis in a nodal center setting in India; and 3) developing and evaluating deep learning-based image classification algorithms for clinical decision-making guidance. As each of these key techniques has been demonstrated separately for oral cancer imaging in LRS, the potential of successfully developing a multimodal intraoral imaging system for accurate, objective and location-resolved diagnosis of oral cancer and transitioning to a new capability to medical professionals in LRS is very high. To achieve the project objective, the team proposes three Aims: 1) develop a portable, semi-flexible, and compact multimodal intraoral imaging system; 2) evaluate the clinical feasibility of the prototyped intraoral imaging system and develop deep learning-based image processing algorithms for early detection, diagnosis, and mapping of oral dysplastic and malignant lesions; and 3) validate the capability of the prototyped intraoral imaging system for diagnosing oral dysplasia and malignant lesions. Successful completion of this project will lead to the transition of a multimodal intraoral imaging system and deep learning image classification that leverage the individual strengths of multiple technologies and deliver new and urgently-needed capabilities to the end users in LRS. This integrated system will 1) detect suspicious regions with high sensitivity and specificity; 2) triage the high-risk subjects; and 3) guide the selection of biopsy sites and map lesion heterogeneity to improve treatment planning and intra-operative guidance.