Deep learning for medical computer vision: Beyond more data and more computing power
医学计算机视觉深度学习:超越更多数据和更强计算能力
基本信息
- 批准号:RGPIN-2020-06752
- 负责人:
- 金额:$ 4.01万
- 依托单位:
- 依托单位国家:加拿大
- 项目类别:Discovery Grants Program - Individual
- 财政年份:2020
- 资助国家:加拿大
- 起止时间:2020-01-01 至 2021-12-31
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
Image data is collected for a variety of applications, e.g., manufacturing, transportation, astronomy, security, and agriculture, as interpreting these images can lead to new insights and discoveries, better-informed decisions, and increased productivity. Biomedical images have revolutionized biology and medicine by giving clinicians and scientists visual access to ex/in-vivo anatomy and function of cells, tissues, organs, and whole organisms in healthy and diseased states. As the number and size of biomedical images are growing rapidly, finer details are captured in shorter times, and image dimensionality is increasing from scalar 2D to dynamic multi-valued 3D, images can no longer be interpreted via manual visual inspection. Medical computer vision (MCV), the topic of this proposed research, is the discipline tasked with developing computer systems that interpret biomedical images.
In recent years, deep learning (DL), a subset of machine learning, which in turn is a subset of artificial intelligence, has become the de-facto computational methodology for tackling MCV problems across the spectrums of imaging modalities and clinical applications. The impressive superior performance results of DL methods, reported in research papers, are difficult to ignore. DL is attracting extraordinary attention and the availability of relatively easy to use DL tools is bringing an onrush of users transfixed by the perceived promise that DL is the solution to all problems. Undoubtedly DL has something valuable to offer towards addressing MCV problems. However, there are important challenges to overcome, beyond navely seeking more data and more computing power, before DL-based MCV technologies become trusted, reliable components that can be deployed in critical bioimaging-driven clinical workflows or biological discoveries that ultimately can lead to advancing science and improving healthcare.
The proposed research focuses on creating novel automated MCV techniques capable of accurate, robust, and fast bioimage interpretation by tackling the critical issues surrounding DL and DL-based MCV, such as, fairness, generalizability, explainability, data-reliance, trust, and model design. The proposed research aims at answering the following questions: How to identify, enhance, and leverage resources to train DL MCV systems (e.g., raw image data, example interpretations, and domain-knowledge)? What is the landscape of possible systems and how to explore it in order to arrive at useful systems? What are the different criteria and tradeoffs involved in assessing such systems (e.g., accuracy and explainability)? And what are some of the computational challenges that arise when considering real-world deployment of such systems (e.g., data privacy and continual learning)?
图像数据被收集用于各种应用,例如制造、交通、天文、安全和农业,因为解释这些图像可以带来新的见解和发现、更明智的决策和更高的生产率。生物医学图像使临床医生和科学家能够直观地了解细胞、组织、器官和整个生物体在健康和疾病状态下的体外/体内解剖和功能,从而使生物学和医学发生了革命性的变化。随着生物医学图像的数量和大小的快速增长,更精细的细节在更短的时间内被捕捉到,图像的维度也从标量2D增加到动态多值3D,通过人工视觉检查已经不能解释图像。医学计算机视觉(MCV)是这项拟议研究的主题,是一门负责开发解释生物医学图像的计算机系统的学科。
近年来,深度学习(DL)作为机器学习的一个子集,也是人工智能的一个子集,已经成为事实上的计算方法,用于处理跨成像模式和临床应用的MCV问题。在研究论文中报道的DL方法令人印象深刻的优越性能结果很难被忽视。数字图书馆吸引了非同寻常的关注,相对容易使用的数字图书馆工具的可用性带来了大量用户,他们被认为数字图书馆是所有问题的解决方案的承诺惊呆了。毫无疑问,DL可以为解决MCV问题提供一些有价值的东西。然而,在基于DL的MCV技术成为可信任、可靠的组件之前,除了天真地寻求更多数据和更多计算能力外,还有一些重要的挑战需要克服,这些组件可以部署在关键的生物成像驱动的临床工作流程或生物发现中,最终可以促进科学发展和改善医疗保健。
这项研究的重点是创建新的自动MCV技术,能够准确、稳健和快速地解释生物图像,解决围绕DL和基于DL的MCV的关键问题,如公平性、泛化、可解释性、数据依赖、信任和模型设计。拟议的研究旨在回答以下问题:如何识别、增强和利用资源来培训数字视频监控系统(例如,原始图像数据、示例解释和领域知识)?什么是可能的系统,以及如何探索它以获得有用的系统?评估这类系统涉及哪些不同的标准和权衡(例如,准确性和可解释性)?当考虑在现实世界中部署这类系统时,会出现哪些计算挑战(例如,数据隐私和持续学习)?
项目成果
期刊论文数量(0)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
数据更新时间:{{ journalArticles.updateTime }}
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
数据更新时间:{{ journalArticles.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ monograph.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ sciAawards.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ conferencePapers.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ patent.updateTime }}
Hamarneh, Ghassan其他文献
Different facial cues for different speech styles in Mandarin tone articulation
- DOI:
10.3389/fcomm.2023.1148240 - 发表时间:
2023-04-28 - 期刊:
- 影响因子:2.4
- 作者:
Garg, Saurabh;Hamarneh, Ghassan;Wang, Yue - 通讯作者:
Wang, Yue
Efficient interactive 3D Livewire segmentation of complex objects with arbitrary topology
- DOI:
10.1016/j.compmedimag.2008.07.004 - 发表时间:
2008-12-01 - 期刊:
- 影响因子:5.7
- 作者:
Poon, Miranda;Hamarneh, Ghassan;Abugharbieh, Rafeef - 通讯作者:
Abugharbieh, Rafeef
Caveolae and scaffold detection from single molecule localization microscopy data using deep learning
- DOI:
10.1371/journal.pone.0211659 - 发表时间:
2019-08-26 - 期刊:
- 影响因子:3.7
- 作者:
Khater, Ismail M.;Aroca-Ouellette, Stephane T.;Hamarneh, Ghassan - 通讯作者:
Hamarneh, Ghassan
Mammography segmentation with maximum likelihood active contours
- DOI:
10.1016/j.media.2012.05.005 - 发表时间:
2012-08-01 - 期刊:
- 影响因子:10.9
- 作者:
Rahmati, Peyman;Adler, Andy;Hamarneh, Ghassan - 通讯作者:
Hamarneh, Ghassan
Watershed segmentation using prior shape and appearance knowledge
- DOI:
10.1016/j.imavis.2006.10.009 - 发表时间:
2009-01-01 - 期刊:
- 影响因子:4.7
- 作者:
Hamarneh, Ghassan;Li, Xiaoxing - 通讯作者:
Li, Xiaoxing
Hamarneh, Ghassan的其他文献
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
{{ truncateString('Hamarneh, Ghassan', 18)}}的其他基金
Deep learning for medical computer vision: Beyond more data and more computing power
医学计算机视觉深度学习:超越更多数据和更强计算能力
- 批准号:
RGPIN-2020-06752 - 财政年份:2022
- 资助金额:
$ 4.01万 - 项目类别:
Discovery Grants Program - Individual
Deep learning for medical computer vision: Beyond more data and more computing power
医学计算机视觉深度学习:超越更多数据和更强计算能力
- 批准号:
RGPIN-2020-06752 - 财政年份:2021
- 资助金额:
$ 4.01万 - 项目类别:
Discovery Grants Program - Individual
Computational Methods for Medical Image Interpretation
医学图像解释的计算方法
- 批准号:
RGPIN-2015-06795 - 财政年份:2019
- 资助金额:
$ 4.01万 - 项目类别:
Discovery Grants Program - Individual
Computational Methods for Medical Image Interpretation
医学图像解释的计算方法
- 批准号:
RGPIN-2015-06795 - 财政年份:2018
- 资助金额:
$ 4.01万 - 项目类别:
Discovery Grants Program - Individual
Machine learning and computer vision for plant health
机器学习和计算机视觉促进植物健康
- 批准号:
517528-2017 - 财政年份:2017
- 资助金额:
$ 4.01万 - 项目类别:
Engage Grants Program
Computational Methods for Medical Image Interpretation
医学图像解释的计算方法
- 批准号:
RGPIN-2015-06795 - 财政年份:2017
- 资助金额:
$ 4.01万 - 项目类别:
Discovery Grants Program - Individual
Computational Methods for Medical Image Interpretation
医学图像解释的计算方法
- 批准号:
RGPIN-2015-06795 - 财政年份:2016
- 资助金额:
$ 4.01万 - 项目类别:
Discovery Grants Program - Individual
Computational Methods for Medical Image Interpretation
医学图像解释的计算方法
- 批准号:
RGPIN-2015-06795 - 财政年份:2015
- 资助金额:
$ 4.01万 - 项目类别:
Discovery Grants Program - Individual
Adaptation of image analysis and machine learning concepts to the fine arts industry
将图像分析和机器学习概念应用于美术行业
- 批准号:
469893-2014 - 财政年份:2014
- 资助金额:
$ 4.01万 - 项目类别:
Engage Grants Program
Novel optimization strategies for medical image analysis
医学图像分析的新颖优化策略
- 批准号:
298324-2010 - 财政年份:2014
- 资助金额:
$ 4.01万 - 项目类别:
Discovery Grants Program - Individual
相似国自然基金
Scalable Learning and Optimization: High-dimensional Models and Online Decision-Making Strategies for Big Data Analysis
- 批准号:
- 批准年份:2024
- 资助金额:万元
- 项目类别:合作创新研究团队
Understanding structural evolution of galaxies with machine learning
- 批准号:n/a
- 批准年份:2022
- 资助金额:10.0 万元
- 项目类别:省市级项目
煤矿安全人机混合群智感知任务的约束动态多目标Q-learning进化分配
- 批准号:
- 批准年份:2022
- 资助金额:30 万元
- 项目类别:青年科学基金项目
基于领弹失效考量的智能弹药编队短时在线Q-learning协同控制机理
- 批准号:62003314
- 批准年份:2020
- 资助金额:24.0 万元
- 项目类别:青年科学基金项目
集成上下文张量分解的e-learning资源推荐方法研究
- 批准号:61902016
- 批准年份:2019
- 资助金额:24.0 万元
- 项目类别:青年科学基金项目
儿童音乐能力发展对语言与社会认知能力及脑发育的影响
- 批准号:31971003
- 批准年份:2019
- 资助金额:58.0 万元
- 项目类别:面上项目
具有时序迁移能力的Spiking-Transfer learning (脉冲-迁移学习)方法研究
- 批准号:61806040
- 批准年份:2018
- 资助金额:20.0 万元
- 项目类别:青年科学基金项目
基于Deep-learning的三江源区冰川监测动态识别技术研究
- 批准号:51769027
- 批准年份:2017
- 资助金额:38.0 万元
- 项目类别:地区科学基金项目
多场景网络学习中基于行为-情感-主题联合建模的学习者兴趣挖掘关键技术研究
- 批准号:61702207
- 批准年份:2017
- 资助金额:21.0 万元
- 项目类别:青年科学基金项目
基于异构医学影像数据的深度挖掘技术及中枢神经系统重大疾病的精准预测
- 批准号:61672236
- 批准年份:2016
- 资助金额:64.0 万元
- 项目类别:面上项目
相似海外基金
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 - 财政年份:2023
- 资助金额:
$ 4.01万 - 项目类别:
Computer-Aided Triage of Body CT Scans with Deep Learning
利用深度学习对身体 CT 扫描进行计算机辅助分类
- 批准号:
10585553 - 财政年份:2023
- 资助金额:
$ 4.01万 - 项目类别:
Linking endotype and phenotype to understand COPD heterogeneity via deep learning and network science
通过深度学习和网络科学将内型和表型联系起来以了解 COPD 异质性
- 批准号:
10569732 - 财政年份:2023
- 资助金额:
$ 4.01万 - 项目类别:
Adapt innovative deep learning methods from breast cancer to Alzheimers disease
采用从乳腺癌到阿尔茨海默病的创新深度学习方法
- 批准号:
10713637 - 财政年份:2023
- 资助金额:
$ 4.01万 - 项目类别:
Clinical Decision Support System for Early Detection of Cognitive Decline Using Electronic Health Records and Deep Learning
利用电子健康记录和深度学习早期检测认知衰退的临床决策支持系统
- 批准号:
10603902 - 财政年份:2023
- 资助金额:
$ 4.01万 - 项目类别:
Surrogate Augmented Deep Predictive Learning for Retinopathy of Prematurity
早产儿视网膜病变的替代增强深度预测学习
- 批准号:
10740289 - 财政年份:2023
- 资助金额:
$ 4.01万 - 项目类别:
Interpretable Deep Learning Models for Analysis of Longitudinal 3D Mammography Screenings
用于分析纵向 3D 乳房 X 光检查的可解释深度学习模型
- 批准号:
10667745 - 财政年份:2023
- 资助金额:
$ 4.01万 - 项目类别:
Vector Flow Velocity Imaging of Human Placenta using Angle-resolved Ultrasound and Deep Learning
使用角度分辨超声和深度学习对人胎盘进行矢量血流速度成像
- 批准号:
10886180 - 财政年份:2023
- 资助金额:
$ 4.01万 - 项目类别:
Electrocardiogram-based deep learning and decision analysis to improve atrial fibrillation risk estimation
基于心电图的深度学习和决策分析改善房颤风险评估
- 批准号:
10722762 - 财政年份:2023
- 资助金额:
$ 4.01万 - 项目类别:
Opportunistic Atherosclerotic Cardiovascular Disease Risk Estimation at Abdominal CTs with Robust and Unbiased Deep Learning
通过稳健且公正的深度学习进行腹部 CT 机会性动脉粥样硬化性心血管疾病风险评估
- 批准号:
10636536 - 财政年份:2023
- 资助金额:
$ 4.01万 - 项目类别: