Advancing Digital Pathology through Novel Machine Learning Methodologies

通过新颖的机器学习方法推进数字病理学

• 批准号: 10458237
• 负责人: Saeed Hassanpour
• 金额: $ 64.26万
• 依托单位: DARTMOUTH COLLEGE
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-09-01 至 2027-05-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10458237
• 关键词: Address; Agreement; Anatomy; Architecture; Archives; Brain; Cells; Characteristics; Classification; Clinical; Colorectal Polyp; Computer Vision Systems; Consumption; Data; Data Set; Databases; Diagnosis; Educational Curriculum; Fruit; Hematoxylin and Eosin Staining Method; Histologic; Histology; Histopathology; Image; Image Analysis; Interobserver Variability; Knowledge; Label; Laboratories; Learning; Manuals; Medical; Medicine; Memory; Metastatic Neoplasm to Lymph Nodes; Methodology; Methods; Microscopy; Modeling; Molecular; Nature; Pathologic; Pathologist; Pathology; Patient Care; Patients; Pattern; Performance; Prognosis; Proxy; Reading; Resolution; Resources; Running; Sampling; Savings; Scanning; Slide; Stains; Standardization; Students; Supervision; Technology; Time; Tissue Banks; Tissues; Training; Translations; Ursidae Family; analysis pipeline; base; care outcomes; clinical practice; cognitive load; computing resources; cost; data resource; deep learning; deep learning model; digital; digital pathology; feature extraction; generative adversarial network; high resolution imaging; histological studies; image translation; improved; lung cancer cell; machine learning method; microscopic imaging; negative affect; novel; novel strategies; standard of care; whole slide imaging

PROJECT SUMMARY/ABSTRACT Pathology is focused on providing medical diagnoses and prognoses based on laboratory methods to guide patient treatment and management. Microscopy is fundamental for pathologists to examine tissues and cells. Despite numerous advancements, there have not been many changes in the last century in terms of how microscopy images are used in pathology. The current approach in anatomic pathology lacks standardization and relies on the cognitive burden imposed on pathologists to manually evaluate millions of cells across hundreds of slides in a typical workday. Deep learning-based methods have recently shown encouraging results for analyzing microscopy images. However, they rely on standard computer vision architectures and pipelines, which are limited due to the required time and cost of slide digitization and the computational constraints of analyzing huge high-resolution images. Furthermore, developing accurate deep learning models requires having access to large databases of labeled microscopy images, which is challenging. In this application, new methodologies are proposed to take advantage of the unique characteristics of histopathology datasets and the range of features in histology microscopy images to address these limitations. This project presents a novel approach based on generative adversarial networks for difficulty translation to generate augmented data with realistic, rare, and hard-to-classify histopathological patterns. This approach will mitigate data imbalances in annotated histology datasets and improve the performance of deep learning models for histological classification, particularly for uncommon and difficult-to-classify cases. Furthermore, a novel curriculum learning approach for histology image classification will be developed based on the range of classification difficulty among histopathological patterns and multi-annotator labeled datasets. This approach trains on progressively harder- to-classify images, as determined by annotator agreement, and significantly improves the performance of the resulting deep learning models without requiring additional data or computational resources. In addition, a self- supervised knowledge distillation method will be developed to enhance the efficiency of histology image classification. As large, labeled datasets are scarce, this method uses a self-supervised approach to distill feature extraction capabilities at a high resolution into a student model operating at a lower resolution by leveraging unlabeled datasets. The resulting distilled student models can achieve high classification accuracy on low- resolution histology images while saving a significant amount of time and resources on digitization efforts and required computational resources. The proposed methods in this application remove current bottlenecks in deep learning applications for digital pathology. Therefore, the results from this project could have a major impact on new opportunities that use deep learning technology in clinical workflows and integrate histopathological information with other clinical and molecular data to improve patients' diagnoses, prognoses, and treatments.

项目总结/摘要 病理学的重点是提供基于实验室方法的医学诊断和诊断，以指导 病人的治疗和管理。显微镜是病理学家检查组织和细胞的基础。 尽管取得了许多进步，但在上个世纪， 显微镜图像用于病理学。目前的解剖病理学方法缺乏标准化 并依赖于病理学家的认知负担，手动评估数百个细胞中的数百万个细胞， 的幻灯片。基于深度学习的方法最近显示出令人鼓舞的结果， 分析显微图像。然而，它们依赖于标准的计算机视觉架构和管道， 由于载玻片数字化所需的时间和成本以及 分析巨大的高分辨率图像。此外，开发准确的深度学习模型需要具备 访问标记的显微图像的大型数据库，这是具有挑战性的。在本申请中，新 提出了利用组织病理学数据集的独特特征和 组织学显微镜图像中的一系列特征来解决这些限制。这个项目提出了一个新的 一种基于生成对抗网络的方法，用于困难翻译以生成增强数据， 现实的，罕见的，难以分类的组织病理学模式。这种方法将缓解数据不平衡， 注释的组织学数据集，并提高用于组织学分类的深度学习模型的性能， 特别是对于不常见和难以分类的病例。此外，一种新的课程学习方法， 组织学图像分类将根据分类难度的范围进行开发， 组织病理学模式和多注释器标记的数据集。这种方法训练的难度越来越大- 对图像进行分类，由注释者协议确定，并显着提高了 从而产生深度学习模型，而不需要额外的数据或计算资源。此外，一个自我- 提出了一种有监督的知识提取方法，以提高组织学图像的提取效率 分类.由于大的、有标签的数据集是稀缺的，该方法使用自监督的方法来提取特征 将高分辨率的提取能力转化为以较低分辨率操作的学生模型， 未标记的数据集由此产生的蒸馏学生模型可以在低成本上实现高分类精度， 分辨率的组织学图像，同时节省了大量的时间和资源的数字化工作， 需要计算资源。本申请中所提出的方法消除了目前的瓶颈， 数字病理学的学习应用。因此，该项目的结果可能对以下方面产生重大影响： 在临床工作流程中使用深度学习技术并整合组织病理学的新机会 信息与其他临床和分子数据，以改善患者的诊断，治疗和治疗。