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

用于资源匮乏环境下口腔癌检测和诊断的多模态口腔内成像系统

• 批准号: 10663873
• 负责人: Rongguang Liang
• 金额: $ 61.82万
• 依托单位: UNIVERSITY OF ARIZONA
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-08-10 至 2026-07-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10663873
• 关键词: Accounting; Address; Adopted; Algorithms; Anatomy; Area; Arizona; Benign; Biopsy; California; Cancer Center; Cancer Detection; Classification; Clinical; Dental; Detection; Diagnosis; Diagnostic; Disease Progression; Dysplasia; Early Diagnosis; Ensure; Faucial pillar; Goals; Heterogeneity; Histopathology; Image; Imaging Techniques; India; Individual; Infrastructure; Institution; Lesion; Light; Location; Malignant - descriptor; Malignant Neoplasms; Maps; Medical; Methods; Modality; Morbidity - disease rate; Multimodal Imaging; Nodal; Oncology; Optical Coherence Tomography; Oral; Oral Diagnosis; Oral cavity; Oropharyngeal; Oropharyngeal Squamous Cell Carcinoma; Output; Participant; Performance; Resolution; Resource-limited setting; Risk; Scanning; Schedule; Screening for Oral Cancer; Sensitivity and Specificity; Site; Stage at Diagnosis; Survival Rate; System; Systems Integration; Techniques; Technology; Training; Translating; Translations; Triage; Universities; Work; cancer diagnosis; cancer imaging; cancer prevention; classification algorithm; clinical decision-making; clinical diagnostics; commercialization; cost; cost effective; deep learning; deep learning algorithm; design; diagnostic algorithm; diagnostic tool; experience; flexibility; follow-up; high risk; image processing; imaging probe; imaging system; impression; improved; industry partner; innovation; intraoral probe; low and middle-income countries; malignant mouth neoplasm; malignant oropharynx neoplasm; miniaturize; mortality; multimodality; neural network; optical imaging; oral care; oral dysplasia; oral lesion; portability; prototype; recruit; response; rural area; screening; standard of care; tongue root; treatment planning; user-friendly

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.

口腔和口咽鳞状细胞癌 (OSCC) 一起成为第六大常见癌症 全球每年新增癌症病例 40 万例，其中三分之二发生在低度和中度癌症中。 中等收入国家 (LMIC) 的 5 年生存率为 62%，而美国的生存率仅为 10%。 发展中国家的治愈率约为 40%，治愈率约为 30%。中低收入国家的生存率较低主要是由于晚期。 诊断以及由此导致的疾病进展至诊断时的晚期阶段。 及早、迅速地诊断 LRS 中的前驱病变和恶性病变。 满足对能够以较低成本实现全面癌症口腔筛查和诊断的技术的需求 资源设置（LRS）来识别可疑病变，对高风险受试者进行分类，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团队 光学成像、肿瘤学、深度学习、技术翻译等领域的互补专业知识 该团队将开发、验证和临床转化多模态口腔内成像。 这项工作将提高口腔癌检测和诊断的灵敏度和特异性。 通过建立团队的基础，解决在 LRS 中采用光学成像技术治疗口腔癌的主要障碍 1) 开发和评估双模式（偏振白光成像 [pWLI] 和 自发荧光成像 [AFI]）移动成像探头；2）评估低成本、便携式光学相干性 印度淋巴结中心用于口腔癌检测和诊断的断层扫描 (OCT) 系统；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 由于这些关键技术中的每一项都已针对 LRS 口腔癌成像进行了单独论证， 成功开发多模态口腔内成像系统的潜力，以实现准确、客观和 口腔癌的定位诊断以及向 LRS 医疗专业人员过渡到新功能 为了实现该项目目标，团队提出了三个目标：1）开发一种便携式、半柔性、 和紧凑型多模态口腔内成像系统；2）评估原型口腔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、 口腔发育不良和恶性病变的绘图；3) 验证口腔内原型的能力 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态口腔内成像系统的转变 和深度学习图像分类，利用多种技术的各自优势并提供 LRS 中的最终用户迫切需要新的功能，该集成系统将 1) 检测可疑内容。 具有高敏感性和特异性的区域；2）对高风险受试者进行分类；3）指导活检的选择； 部位并绘制病变异质性图，以改善治疗计划和术中指导。

项目成果

Inter-observer agreement among specialists in the diagnosis of Oral Potentially Malignant Disorders and Oral Cancer using Store-and-Forward technology.

使用存储转发技术诊断口腔潜在恶性疾病和口腔癌的专家之间的观察者间协议。

• 发表时间: 2023-04-05
• 作者: Gurushanth, Keerthi;Mukhia, Nirza;Sunny, Sumsum P;Song, Bofan;Raghavan, Shubhasini A;Gurudath, Shubha;Mendonca, Pramila;Li, Shaobai;Patrick, Sanjana;Imchen, Tsusennaro;Leivon, Shirley T;Shruti, Tulika;Kolur, Trupti;Shetty, Vivek;Bhushan R, V
• 通讯作者: Bhushan R, V

Classification of Mobile-Based Oral Cancer Images Using the Vision Transformer and the Swin Transformer.

使用 Vision Transformer 和 Swin Transformer 对基于移动的口腔癌图像进行分类。

• 发表时间: 2024-02-29
• 影响因子: 5.2
• 作者: Song, Bofan;Kc, Dharma Raj;Yang, Rubin Yuchan;Li, Shaobai;Zhang, Chicheng;Liang, Rongguang
• 通讯作者: Liang, Rongguang

Interpretable and Reliable Oral Cancer Classifier with Attention Mechanism and Expert Knowledge Embedding via Attention Map.

可解释且可靠的口腔癌分类器，具有注意力机制和通过注意力图嵌入的专家知识。

• 发表时间: 2023-02-23
• 影响因子: 5.2
• 作者: Song, Bofan;Zhang, Chicheng;Sunny, Sumsum;Kc, Dharma Raj;Li, Shaobai;Gurushanth, Keerthi;Mendonca, Pramila;Mukhia, Nirza;Patrick, Sanjana;Gurudath, Shubha;Raghavan, Subhashini;Tsusennaro, Imchen;Leivon, Shirley T;Kolur, Trupti;Shetty, Vivek
• 通讯作者: Shetty, Vivek