PRISTINE: Pre-cancer histology identification of Endobronchial biopsies using deep learning

PRISTINE：使用深度学习对支气管内活检进行癌前组织学鉴定

• 批准号: 10059031
• 负责人: Jennifer Ellen Beane
• 金额: $ 42.43万
• 依托单位: BOSTON UNIVERSITY MEDICAL CAMPUS
• 依托单位国家: 美国
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-09-01 至 2024-08-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10059031
• 关键词: Atlases; Biological; Biological Markers; Biopsy; Breast; Bronchoscopy; Cancer Etiology; Carcinoma; Cessation of life; Clinical; Clinical Data; Colon; Computer software; Correlative Study; Data; Development; Dysplasia; Epithelial; Epithelium; Goals; Heterogeneity; Histologic; Histology; Hyperplasia; Image; Immunosuppression; Institution; Intercept; Interobserver Variability; Learning; Lesion; Lung; Lung Adenocarcinoma; Malignant Neoplasms; Malignant neoplasm of lung; Measures; Medical; Metaplasia; Methods; Minor; Molecular; Morphology; Pathologic; Pathologist; Patients; Pattern; Performance; Pharmacologic Substance; Procedures; Process; Prostate; Resolution; Sampling; Semantics; Site; Specimen; Standardization; Structure of parenchyma of lung; System; Testing; Therapeutic; Tissues; Training; Tumor-infiltrating immune cells; advanced disease; base; biomarker development; cancer invasiveness; cancer risk; clinically relevant; cloud based; convolutional neural network; deep learning; deep learning algorithm; genomic biomarker; genomic data; innovation; lung cancer screening; lung development; lung imaging; multiple omics; pathology imaging; premalignant; prevent; screening program; success; therapy development; tumor; tumor-immune system interactions; whole slide imaging

PROJECT SUMMARY Lung cancer is the leading cause of cancer death. In order to increase survival, therapies are urgently needed to intercept the cancer development process and decrease the rate of patients presenting with advanced disease. A potential promising point of interception is to develop therapies to reverse or delay the development of lung premalignant lesions (PMLs). About 20% of lung cancers arise in the epithelial layer of the bronchial airways and these are preceded by the development of PMLs that are important clinical indicators of lung cancer risk in the airways or at remote parenchymal sites. As part of the NCI-Moonshot our group is engaged in creating a multi-omic lung Pre-Cancer Atlas (PCA). The success of this project in creating clinically relevant biomarkers and therapeutics depends on accurate assessments of histology and immune infiltrates in PMLs. Currently, however, pathologic assessment of the morphological stages of increasing abnormality from hyperplasia, metaplasia, dysplasia (mild, moderate, and severe), to invasive carcinoma is challenging and not routine. The objective of the proposed study is to develop and disseminate a computationally efficient deep learning framework to annotate a variety of histologic features in PMLs from the Lung PCA and associate these features with clinical and genomic data. Our central hypothesis is that deep learning can be applied to digitized H&E whole slide images (WSIs) of bronchial PMLs to identify a comprehensive set of histologic features and metrics summarizing their spatial organization that may enhance biomarkers of PML progression to cancer. We will test this hypothesis by pursuing two specific aims. First, we will annotate PMLs and develop a semantic segmentation framework using deep learning to predict histologic features of PMLs. Second, we will disseminate our deep learning framework and show its utility in enhancing PML-associated biomarkers. The proposed study is significant because the framework we develop can be applied to predict other features in the WSIs from PMLs and be modified to encompass other PMLs of the lung (e.g. those associated with lung adenocarcinoma) as well as other premalignant lesions found in other epithelial tissue types such as breast, colon, prostate, etc. Currently, deep learning approaches have not been applied to PMLs, and this proposal is innovative in the unique clinical specimens that it leverages with corresponding genomic and clinical data and in its development of a patch- based convolutional neural network to predict histologic features of PMLs. Our long-term goal is to develop a deep learning framework to predict a variety of features from lung PML WSIs and integrate these with genomic data on these same samples to discover robust biomarkers of PML progression and therapeutics to prevent invasive cancer development.

项目摘要 肺癌是癌症死亡的主要原因。为了提高生存率，迫切需要治疗 阻断癌症发展过程，降低晚期癌症患者的发病率， 疾病一个潜在的有希望的拦截点是开发治疗方法来逆转或延迟发展 肺癌前病变（PML）。大约20%的肺癌发生在支气管上皮层， 气道和这些之前的发展PMLs是肺癌的重要临床指标 气道或远端实质部位的风险。作为NCI-Moonshot的一部分，我们的团队致力于创造 多组学肺癌前病变图谱（PCA）。该项目在创建临床相关生物标志物方面的成功 治疗依赖于对PML组织学和免疫浸润的准确评估。目前， 然而，病理学评估的形态学阶段的增加异常增生， 化生、异型增生（轻度、中度和重度）到浸润性癌是具有挑战性的，并且不是常规的。的 这项研究的目的是开发和传播一种计算效率高的深度学习方法。 一个框架来注释来自肺PCA的PML中的各种组织学特征，并将这些特征 临床和基因组数据。我们的核心假设是，深度学习可以应用于数字化H&E 支气管PML的全切片图像（WSI），以确定一组全面的组织学特征和指标 总结了它们的空间组织，可能增强PML进展为癌症的生物标志物。我们将测试 这一假设通过追求两个具体目标。首先，我们将注释PML并开发语义 使用深度学习的分割框架来预测PML的组织学特征。第二，我们将传播 我们的深度学习框架，并显示其在增强PML相关生物标志物方面的实用性。拟定研究 是重要的，因为我们开发的框架可以应用于从PML预测WSI中的其他功能 并被修改以包括肺的其它PML（例如与肺腺癌相关的那些 如在其它上皮组织类型如乳腺、结肠、前列腺等中发现的其它癌前病变。目前， 深度学习方法尚未应用于PML，该提议在独特的临床应用中具有创新性。 标本，它利用相应的基因组和临床数据，并在其开发的补丁- 基于卷积神经网络预测PMLs的组织学特征。我们的长期目标是发展一个 深度学习框架，用于预测肺部PML WSI的各种特征，并将其与基因组整合 这些相同样本的数据，以发现PML进展的强大生物标志物和预防PML进展的治疗方法。 侵袭性癌症发展。

项目成果

Machine Learning in Clinical Trials: A Primer with Applications to Neurology.

• DOI: 10.1007/s13311-023-01384-2
• 发表时间: 2023-07
• 期刊: NEUROTHERAPEUTICS
• 影响因子: 5.7
• 作者: Miller, Matthew I.;Shih, Ludy C. C.;Kolachalama, Vijaya B.
• 通讯作者: Kolachalama, Vijaya B.

Deep learning for subtyping the Alzheimer's disease spectrum.

• DOI: 10.1016/j.molmed.2021.12.004
• 发表时间: 2022-02
• 期刊: TRENDS IN MOLECULAR MEDICINE
• 影响因子: 13.6
• 作者: Romano, Michael F.;Kolachalama, Vijaya B.
• 通讯作者: Kolachalama, Vijaya B.

Machine Learning Applications in Nephrology: A Bibliometric Analysis Comparing Kidney Studies to Other Medicine Subspecialities.

• DOI: 10.1016/j.xkme.2021.04.012
• 发表时间: 2021-09
• 期刊: Kidney medicine
• 影响因子: 3.9
• 作者: Verma A;Chitalia VC;Waikar SS;Kolachalama VB
• 通讯作者: Kolachalama VB

Machine learning and pre-medical education.

• DOI: 10.1016/j.artmed.2022.102313
• 发表时间: 2022-07
• 期刊: ARTIFICIAL INTELLIGENCE IN MEDICINE
• 影响因子: 7.5
• 作者: Kolachalama, Vijaya B.

Subchondral Bone Length in Knee Osteoarthritis: A Deep Learning-Derived Imaging Measure and Its Association With Radiographic and Clinical Outcomes.

• DOI: 10.1002/art.41808
• 发表时间: 2021-12
• 期刊: Arthritis & rheumatology (Hoboken, N.J.)
• 作者: Chang GH;Park LK;Le NA;Jhun RS;Surendran T;Lai J;Seo H;Promchotichai N;Yoon G;Scalera J;Capellini TD;Felson DT;Kolachalama VB
• 通讯作者: Kolachalama VB