Deep Learning Image Analysis Algorithms to Improve Oral Cancer Risk Assessment for Oral Potentially Malignant Disorders

深度学习图像分析算法可改善口腔潜在恶性疾病的口腔癌风险评估

• 批准号: 10805177
• 负责人: Curtis Pickering
• 金额: $ 68.4万
• 依托单位: YALE UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-05-01 至 2026-04-30
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10805177
• 关键词: Affect; Algorithmic Analysis; Algorithms; Architecture; Biological; Biological Markers; Biology; Biopsy; Case/Control Studies; Cell Nucleus; Cells; Characteristics; Classification; Clinical; Clinical Data; Clinical Trials; Collection; Computational algorithm; Computer Analysis; Computing Methodologies; Data; Development; Diagnosis; Disease; Dysplasia; Epithelial Cells; Evaluation; Exclusion; Future; General Population; Genomics; Goals; Hematoxylin and Eosin Staining Method; Heterogeneity; Histologic; Histology; Histopathologic Grade; Image; Image Analysis; Immune; Immunologic Markers; Individual; Intraepithelial Neoplasia; Lesion; Leukoplakia; Machine Learning; Malignant - descriptor; Malignant Neoplasms; Measurement; Measures; Methods; Modeling; Morphology; Mucous Membrane; Oral; Oral Leukoplakia; Oral cavity; Oral mucous membrane structure; Pathologic; Pathology; Patient Care; Patient risk; Patients; Performance; Persons; Prevention; Procedures; Process; Process Assessment; Prognostic Marker; Protocols documentation; Recording of previous events; Research; Risk; Risk Assessment; Risk Marker; Sampling; Slide; Stains; Standardization; Statistical Models; System; TP53 gene; Testing; Therapeutic Intervention; Tissue Sample; Tissue imaging; Tissues; Uncertainty; Validation; cancer diagnosis; cancer risk; cell type; clinical care; clinical risk; cohort; data integration; deep learning; disorder risk; genomic biomarker; genomic data; high risk; imaging biomarker; improved; innovation; insight; learning algorithm; learning strategy; malignant mouth neoplasm; mouth squamous cell carcinoma; mutational status; novel; oral plaque; phenotypic data; predict clinical outcome; predictive modeling; prognostic value; progression risk; prospective; risk stratification; treatment planning; whole slide imaging

Abstract Oral potentially malignant disorders (OPMD) are a group of mucosal diseases in the oral cavity with a risk of progressing to oral squamous cell carcinoma. Risk assessment is traditionally done through a combination of clinical and histologic evaluation. Leukoplakia is a common type of OPMD that is given a histologic grading score that is supposed to be related to its risk of progression. However, there is tremendous intra- and inter- observer heterogeneity in dysplasia grading, leading to variability and uncertainty in risk assessment and treatment planning. This also hinders the ability to study the biology of these lesions. We propose to use whole slide imaging on routine hematoxylin and eosin (H&E) stained sections in combination with deep learning methods to build a consistent risk scoring system for OPMD. Our methods will identify cell, nucleus, and tissue architectural features relevant to risk of progression in OPMD. These features will be tested in a large retrospective case-control study and then validated prospectively. We will also explore combining them with genomic and immune biomarkers in order to improve the prognostic power and explore the biolo gy of progression in OPMD. We hope that these efforts will improve and standardize risk assessment for OPMD. This could lead to improved treatment and prevention options by enabling risk stratification and allowing future clinical trials be conducted in a more uniform patient cohort. Similarly, it could improve our understanding for the biology of OPMD and the process of progression to cancer.

摘要 口腔潜在恶性疾病（OPMD）是一组口腔粘膜疾病， 发展成口腔鳞状细胞癌传统上，风险评估是通过以下几个方面的结合来完成的： 临床和组织学评价。白斑病是一种常见的OPMD类型， 评分应该与其进展风险相关。然而，有巨大的内部和内部- 观察者异型增生分级的异质性，导致风险评估的可变性和不确定性， 治疗计划这也阻碍了研究这些病变的生物学的能力。我们建议使用整体 常规苏木精和伊红（H&E）染色切片上的载玻片成像结合深度学习 建立OPMD一致的风险评分系统的方法。我们的方法可以识别细胞核和组织 与OPMD进展风险相关的架构特征。这些功能将在大型 回顾性病例对照研究，然后进行前瞻性验证。我们还将探索将它们与 基因组和免疫生物标志物，以提高预后能力，并探索生物戈伊， OPMD的进展。我们希望，这些努力将改善OPMD的风险评估并使之标准化。 这可能会导致改善治疗和预防方案，使风险分层，并允许未来 临床试验将在更统一的患者队列中进行。同样，它可以提高我们对 OPMD的生物学和发展为癌症的过程。

项目成果

Artificial intelligence in mental healthcare: an overview and future perspectives.

精神卫生保健中的人工智能：概述和未来展望。

• DOI: 10.1259/bjr.20230213
• 发表时间: 2023
• 期刊: The British journal of radiology
• 作者: Jin,KevinW;Li,Qiwei;Xie,Yang;Xiao,Guanghua
• 通讯作者: Xiao,Guanghua

ScopeViewer: A Browser-Based Solution for Visualizing Spatial Transcriptomics Data.

ScopeViewer：基于浏览器的空间转录组数据可视化解决方案。

• DOI: 10.1101/2023.07.24.549256
• 发表时间: 2023
• 期刊: bioRxiv : the preprint server for biology
• 作者: Luo,Danni;Robertson,Sophie;Zhan,Yuanchun;Rong,Ruichen;Wang,Shidan;Jiang,Xi;Yang,Sen;Palmer,Suzette;Jia,Liwei;Li,Qiwei;Xiao,Guanghua;Zhan,Xiaowei
• 通讯作者: Zhan,Xiaowei