High-performance deep neural networks for medical image analysis

用于医学图像分析的高性能深度神经网络

• 批准号: 10723553
• 负责人: Md Tauhidul Islam
• 金额: $ 8.92万
• 依托单位: STANFORD UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-09-01 至 2025-08-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10723553
• 关键词: Adoption; Classification; Clinical; Clinical Data; Communities; Complex; Data; Data Reporting; Data Set; Development; Diagnosis; Dimensions; Discriminant Analysis; Disease; Goals; Image; Image Analysis; Label; Learning; Mathematics; Medial; Medical Imaging; Methods; Modeling; Neural Network Simulation; Output; Performance; Play; Process; Prognosis; Public Domains; Research; Research Personnel; Role; Structure; Techniques; Technology; Testing; Training; Visualization; clinical translation; computerized data processing; data exploration; data space; data visualization; deep learning; deep neural network; design; empowerment; high dimensionality; improved; indexing; multidimensional data; network architecture; neural network architecture; novel; novel strategies; operation; practical application; success; tool; treatment planning; trustworthiness

Project Summary Lack of transparency and trustworthiness of deep neural networks (DNNs) has long been recognized as a major drawback of the technology, hindering its widespread acceptance in many practical applications. The objective of this project is to establish a novel contrastive feature analysis (CFA) framework for reliable visualization of the high dimensional feature space and effective design of high-performance DNNs for medical image analysis. We hypothesize that CFA-based feature visualization will enable us to quantify the quality of the feature space at different layers during training/testing of a DNN and empower us with an effective tool to prune the network architecture for enhanced performance. Specifically, we will (1) develop an efficient visualization technique CFA for high dimensional feature data, 2) apply the CFA visualization framework to automatically refine DNN architecture for improved performance, and 3) demonstrate the potential of CFA in solving clinical problems. Successful completion of the project will enable us to analyze the feature data reliably and quantify the quality of the feature space at different layers of a DNN. The study also promises to provide high-performance DNNs for medical image analysis to substantially improve the AI-based diagnosis, prognosis and treatment planning of different diseases.

项目摘要 长期以来，深度神经网络（DNN）缺乏透明度和可信赖性。 该技术的缺点，阻碍了其在许多实际应用中的广泛接受。目标 这个项目的是建立一个新颖的对比特征分析（CFA）框架，以可靠地可视化 高维特征空间和高性能DNN的有效设计用于医学图像分析。我们 假设基于CFA的功能可视化将使我们能够量化特征空间的质量 在训练/测试DNN期间的不同层，并使用有效的工具来修剪网络 增强性能的体系结构。具体而言，我们将（1）开发有效的可视化技术CFA 对于高维特征数据，2）应用CFA可视化框架自动改进DNN 改善性能的体系结构，3）证明了CFA在解决临床方面的潜力 问题。成功完成项目将使我们能够可靠地分析功能数据并量化 DNN不同层的特征空间的质量。该研究还有望提供高性能 用于医学图像分析的DNN，可大大改善基于AI的诊断，预后和治疗 规划不同的疾病。