Enabling Next Generation Machine Learning for Large Scale Image Analysis

实现大规模图像分析的下一代机器学习

• 批准号: 10698607
• 负责人: Gerald Sabin
• 金额: $ 93.74万
• 依托单位: RNET TECHNOLOGIES, INC.
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-09-30 至 2025-05-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10698607
• 关键词: Acceleration; Adoption; Architecture; Area; Artificial Intelligence; Cancer Detection; Classification; Clinical; Complex; Computer Hardware; Computer software; Computerized Medical Record; Computing Methodologies; Data; Data Set; Development; Diagnosis; Diagnostic; Dimensions; Evolution; Glass; Goals; Government Agencies; Healthcare; Healthcare Systems; High Performance Computing; Human; Image; Image Analysis; Imaging problem; Investments; Label; Laboratories; Learning; Lung; Machine Learning; Magnetic Resonance; Marketing; Medical; Medical Imaging; Memory; Methods; Modeling; Movement; Neural Network Simulation; Outcome; Pathologist; Pathology; Patients; Performance; Phase; Play; Process; Research; Research Personnel; Resolution; Role; Screening for Prostate Cancer; Services; Slice; Slide; Software Framework; Stream; Structure; System; Techniques; Technology; TensorFlow; Time; Training; Visualization software; X-Ray Computed Tomography; clinical diagnostics; cohort; deep learning; deep learning model; design; digital pathology; gigabyte; high resolution imaging; implementation efforts; interest; learning strategy; lung cancer screening; machine learning framework; network architecture; neural network; next generation; novel; operation; pathology imaging; portability; prototype; public health relevance; screening; software development; software infrastructure; spatial relationship; tool; tumor; user-friendly

Project Summary/Abstract Deep learning has transformed medical image analysis by delivering clinically meaningful results on challenging problems like prostate cancer detection and lung cancer screening. FDA approval of whole-slide digital pathology imaging (WSIs) for primary diagnosis is further increasing interest, adoption, and investment in artificial intelli- gence (AI) technology for pathology. Learning from large medical images using patient-level labels (PLLs) has become an active computational pathology research area. PLLs such as pathology diagnosis or clinical outcomes are generated through healthcare operations and are often readily available. In contrast to learning paradigms that depend on the expert annotation of images (e.g., delineating tumor regions) and are therefore time-intensive and limited to smaller cohorts, training directly from WSIs using PLLs will allow the development of realistic training datasets containing tens-of-thousands of subjects that can produce models with clinically-meaningful ac- curacy. GPU accelerators have played a significant role in advancing deep learning methods for computational pathology tools. Machine Learning Frameworks (MLFs), e.g., Pytorch and TensorFlow, provide researchers with abstractions to quickly develop models that utilize GPUs. The evolution of GPUs and MLFs has been driven by the analysis of small images, and so applying these tools directly to WSIs or other large medical images like volumetric magnetic resonance or computed tomography is challenging. Adapting medical imaging problems to the small image paradigm leads to many compromises resulting in suboptimal performance, increased imple- mentation effort, and increased software/design complexity (e.g., patch based techniques or multiple instance learning). As a result, the development of scalable ML models from PLLs by directly processing WSI images through a deep learning pipeline is infeasible today on GPUs. Recent efforts that use unified GPU memory or streaming approaches to overcome GPU memory limits and attempt to perform end-to-end training at WSI scale have demonstrated superior performance to annotation or MIL. However, these approaches are either slow (due to suboptimal data movement strategies), complex to adapt/use, or highly specific to a given network architecture (limiting the ability to develop and explore new architectures). More general-purpose, efficient, and user-friendly frameworks are needed to allow the development of WSI scale deep learning. This project will develop a robust software framework to facilitate seamless development and use of scalable ML models, without the imposition of any limits on the sizes of handled images, unhindered by the limited memory capacity in GPUs. The proposed SSTEP (Seamless Scalable Tensor-Expression Execution via Partitioning) soft- ware framework will allow scalable and portable neural network models that directly process full high-resolution images of arbitrary size for training or inference, on any (multi) GPU platform. SSTEP will allow the development of novel deep learning paradigms that are purpose-built for medical applications, and will enable developers to rapidly create and evaluate these tools using familiar MLFs - PyTorch or TensorFlow.

项目摘要/摘要 深度学习通过在具有挑战性方面提供临床意义的结果来改变医学图像分析 前列腺癌检测和肺癌筛查等问题。 FDA批准全斜体数字病理 用于主要诊断的成像（WSI）是进一步增加对人工智能的兴趣，采用和投资 理想（AI）病理技术。使用患者级标签（PLL）从大型医学图像中学习 成为一个积极的计算病理研究领域。 PLL，例如病理诊断或临床结果 是通过医疗保健运营生成的，通常很容易获得。与学习范式相反 这取决于图像的专家注释（例如描绘肿瘤区域），因此是时间密集型的 并且仅限于较小的队列，直接使用PLL的WSI培训将允许发展现实 培训数据集，其中包含数以千计的受试者，这些受试者可以生产具有临床意义的模型 策划。 GPU加速器在推进计算深度学习方法方面发挥了重要作用 病理工具。机器学习框架（MLFS），例如Pytorch和Tensorflow，为研究人员提供 抽象以快速开发使用GPU的模型。 GPU和MLFS的演变是由 小图像的分析，因此将这些工具直接应用于WSI或其他大型医学图像，例如 体积磁共振或计算机断层扫描具有挑战性。调整医学成像问题 小图像范式导致许多妥协，导致次优的性能，增加 精力工作，并提高软件/设计复杂性（例如，基于补丁的技术或多个实例 学习）。结果，通过直接处理WSI图像来开发PLL的可扩展ML模型 今天，通过深度学习管道在GPU上是不可行的。使用统一的GPU内存或 流媒体方法以克服GPU记忆限制并尝试在WSI量表上进行端到端培训 表现出与注释或MIL相比的表现。但是，这些方法要么很慢（到期 次优的数据移动策略），复杂以适应/使用或高度特定于给定的网络体系结构 （限制开发和探索新体系结构的能力）。更通用，高效和用户友好 需要框架以开发WSI规模深度学习。 该项目将开发一个强大的软件框架，以促进无缝开发和使用可扩展 ML模型，没有对处理图像的尺寸施加任何限制，不受限制记忆 GPU的容量。提出的SSTEP（通过分区无缝可扩展张张表达执行）soft- WARE框架将允许可扩展和便携式神经网络模型直接处理完整的高分辨率 在任何（多）GPU平台上进行培训或推理的任意大小的图像。 SSTEP将允许开发 针对医疗应用专门构建的新型深度学习范例，并将使开发人员能够 使用熟悉的MLF -Pytorch或TensorFlow快速创建和评估这些工具。