Towards Generalizable Reasoned Deep Learning for Efficient Interpretable Medical Image Computing

迈向可泛化推理深度学习以实现高效可解释医学图像计算

基本信息

  • 批准号:
    RGPIN-2020-06179
  • 负责人:
  • 金额:
    $ 3.35万
  • 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:
    2021
  • 资助国家:
    加拿大
  • 起止时间:
    2021-01-01 至 2022-12-31
  • 项目状态:
    已结题

项目摘要

Image computing is a key technology area with applications in numerous fields from engineering to medicine. A subset of artificial intelligence (AI) concerned with creating computer systems or machines capable of simulating human vision, the field still grapples with technical challenges arising from the vast variability in imaging data and disparate application-dependent analysis needs. A wave of connectionist machine learning has recently swept the field, in which systems dynamically `learn' to perform a task through training on labelled image examples from huge databases rather than being explicitly programmed. In particular, deep learning (DL), in which multi-layer artificial neural nets that loosely model the human brain are used, has dominated with unprecedented performance levels reported in some applications. Medical image computing poses unique technical challenges to automated analysis that limited success in this area. Quite distinct from pure cognitive vision applications, such as autonomous driving, analysis and interpretation of medical image data involves highly specialized processes connected to complex knowledge bases. Hence, despite their apparent power and universal applicability, current data-driven DL models often result in superficial learning with alarming reports of model fragility and unexpected failures, overfitting to noise and underfitting to meaningful data, poor generalizability and low performance on new data, as well as impracticality of required training databases and prohibitive cost of labelling. This grant will advance DL methods towards `deep reasoning' to enable reliable and safe AI for critical data analysis such as medical image computing. Specifically, the proposed technical methods will evolve data-driven DL models beyond visual perception (seeing) towards integrating logic and context based reasoning (understanding, extrapolating) in order to achieve `common sense' solutions that observe physical realities and incorporate domain knowledge. My work will result in more generalizable, interpretable, efficient and reasoned learning models that can self-test and self-improve, ensuring real life utility and significantly improving the prospects of successful adoption in areas of strategic importance to Canadians. Automation of heterogenous complex medical image data analysis enabled by the proposed technical methods will have significant socio-economic impact including overcoming poor physician to patient ratio, reducing healthcare costs and delays, increasing accuracy and efficiency in diagnostics and care delivery, and enabling new findings and opportunities in health research. My research will train a diverse group of future experts and leaders in AI, a field where severe shortages in much needed talent exist. It will also help ensure Canada remains a world leader in AI research and a major contributor to the `DL revolution'.
图像计算是一个关键的技术领域,在从工程到医学的许多领域都有应用。人工智能(AI)的一个子集,涉及创建能够模拟人类视觉的计算机系统或机器,该领域仍然面临着成像数据的巨大变化和不同的应用程序相关分析需求所带来的技术挑战。连接主义机器学习的浪潮最近席卷了该领域,其中系统通过对来自巨大数据库的标记图像示例进行训练而不是显式编程来动态“学习”执行任务。特别是,深度学习(DL),其中使用松散地模拟人脑的多层人工神经网络,在一些应用中报告了前所未有的性能水平。医学图像计算对自动化分析提出了独特的技术挑战,限制了这一领域的成功。与纯认知视觉应用(如自动驾驶)截然不同,医学图像数据的分析和解释涉及与复杂知识库相关的高度专业化过程。因此,尽管它们具有明显的功能和普遍适用性,但当前的数据驱动的DL模型通常会导致肤浅的学习,并有令人担忧的模型脆弱性和意外失败的报告,对噪声的过度拟合和对有意义的数据的拟合不足,对新数据的泛化能力差和性能低,以及所需的训练数据库的不切实际性和高昂的标签成本。该拨款将推动深度学习方法向“深度推理”方向发展,为医学图像计算等关键数据分析提供可靠和安全的人工智能。具体而言,所提出的技术方法将发展数据驱动的DL模型,超越视觉感知(看到),将逻辑和基于上下文的推理(理解,外推)相结合,以实现观察物理现实并结合领域知识的“常识”解决方案。我的工作将导致更普遍,可解释,有效和合理的学习模式,可以自我测试和自我提高,确保真实的生活效用,并显着提高成功采用的前景在战略重要性的加拿大人的领域。 通过所提出的技术方法实现的异质复杂医学图像数据分析的自动化将具有显著的社会经济影响,包括克服较差的医生与患者比率,降低医疗保健成本和延迟,提高诊断和护理提供的准确性和效率,以及实现健康研究的新发现和机会。我的研究将在人工智能领域培养一批多元化的未来专家和领导者,这是一个急需人才严重短缺的领域。它还将有助于确保加拿大在人工智能研究方面保持世界领先地位,并成为“DL革命”的主要贡献者。

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 }}

Garbi, Rafeef其他文献

AUTOMATICALLY DELINEATING KEY ANATOMY IN 3-D ULTRASOUND VOLUMES FOR HIP DYSPLASIA SCREENING
  • DOI:
    10.1016/j.ultrasmedbio.2021.05.011
  • 发表时间:
    2021-08-06
  • 期刊:
  • 影响因子:
    2.9
  • 作者:
    El-Hariri, Houssam;Hodgson, Antony J.;Garbi, Rafeef
  • 通讯作者:
    Garbi, Rafeef
Learnable image histograms-based deep radiomics for renal cell carcinoma grading and staging
  • DOI:
    10.1016/j.compmedimag.2021.101924
  • 发表时间:
    2021-04-23
  • 期刊:
  • 影响因子:
    5.7
  • 作者:
    Hussain, Mohammad Arafat;Hamarneh, Ghassan;Garbi, Rafeef
  • 通讯作者:
    Garbi, Rafeef
Cascaded Regression Neural Nets for Kidney Localization and Segmentation-free Volume Estimation
  • DOI:
    10.1109/tmi.2021.3060465
  • 发表时间:
    2021-06-01
  • 期刊:
  • 影响因子:
    10.6
  • 作者:
    Hussain, Mohammad Arafat;Hamarneh, Ghassan;Garbi, Rafeef
  • 通讯作者:
    Garbi, Rafeef
Augmented reality visualisation for orthopaedic surgical guidance with pre- and intra-operative multimodal image data fusion
  • DOI:
    10.1049/htl.2018.5061
  • 发表时间:
    2018-10-01
  • 期刊:
  • 影响因子:
    2.1
  • 作者:
    El-Hariri, Houssam;Pandey, Prashant;Garbi, Rafeef
  • 通讯作者:
    Garbi, Rafeef
3-D ULTRASOUND IMAGING RELIABILITY OF MEASURING DYSPLASIA METRICS IN INFANTS
  • DOI:
    10.1016/j.ultrasmedbio.2020.08.008
  • 发表时间:
    2021-01-01
  • 期刊:
  • 影响因子:
    2.9
  • 作者:
    Quader, Niamul;Odgson, Antony J. H.;Garbi, Rafeef
  • 通讯作者:
    Garbi, Rafeef

Garbi, Rafeef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('Garbi, Rafeef', 18)}}的其他基金

Towards Generalizable Reasoned Deep Learning for Efficient Interpretable Medical Image Computing
迈向可泛化推理深度学习以实现高效可解释医学图像计算
  • 批准号:
    RGPIN-2020-06179
  • 财政年份:
    2022
  • 资助金额:
    $ 3.35万
  • 项目类别:
    Discovery Grants Program - Individual
Towards Generalizable Reasoned Deep Learning for Efficient Interpretable Medical Image Computing
迈向可泛化推理深度学习以实现高效可解释医学图像计算
  • 批准号:
    RGPIN-2020-06179
  • 财政年份:
    2020
  • 资助金额:
    $ 3.35万
  • 项目类别:
    Discovery Grants Program - Individual
Integrative Computational Models for Multi-Modal Analysis of Structural and Functional Neuroimaging Data
用于结构和功能神经影像数据多模态分析的综合计算模型
  • 批准号:
    RGPIN-2014-04169
  • 财政年份:
    2019
  • 资助金额:
    $ 3.35万
  • 项目类别:
    Discovery Grants Program - Individual

相似海外基金

Collaborative Research: CDS&E: Generalizable RANS Turbulence Models through Scientific Multi-Agent Reinforcement Learning
合作研究:CDS
  • 批准号:
    2347423
  • 财政年份:
    2024
  • 资助金额:
    $ 3.35万
  • 项目类别:
    Standard Grant
Collaborative Research: CDS&E: Generalizable RANS Turbulence Models through Scientific Multi-Agent Reinforcement Learning
合作研究:CDS
  • 批准号:
    2347422
  • 财政年份:
    2024
  • 资助金额:
    $ 3.35万
  • 项目类别:
    Standard Grant
CAREER: Learning Generalizable and Interpretable Embodied AI with Human Priors
职业:利用人类先验学习可概括和可解释的具体人工智能
  • 批准号:
    2339769
  • 财政年份:
    2024
  • 资助金额:
    $ 3.35万
  • 项目类别:
    Continuing Grant
Incorporating Diversity in Alzheimer's Disease Research: Developing Representative and Generalizable models
将多样性纳入阿尔茨海默病研究:开发代表性和可推广的模型
  • 批准号:
    495662
  • 财政年份:
    2023
  • 资助金额:
    $ 3.35万
  • 项目类别:
    Operating Grants
Bayesian Statistical Learning for Robust and Generalizable Causal Inferences in Alzheimer Disease and Related Disorders Research
贝叶斯统计学习在阿尔茨海默病和相关疾病研究中进行稳健且可推广的因果推论
  • 批准号:
    10590913
  • 财政年份:
    2023
  • 资助金额:
    $ 3.35万
  • 项目类别:
Collaborative Research: A generalizable data framework towards Precision Radiotherapy.
协作研究:精准放射治疗的通用数据框架。
  • 批准号:
    2313443
  • 财政年份:
    2023
  • 资助金额:
    $ 3.35万
  • 项目类别:
    Standard Grant
Bilevel Optimization for Training Generalizable Language Models
用于训练可推广语言模型的双层优化
  • 批准号:
    23K16940
  • 财政年份:
    2023
  • 资助金额:
    $ 3.35万
  • 项目类别:
    Grant-in-Aid for Early-Career Scientists
Geles: A Novel Imaging Informatics System for Generalizable Lesion Identification in Neuroendocrine Tumors
Geles:一种用于神经内分泌肿瘤普遍病变识别的新型影像信息学系统
  • 批准号:
    10740578
  • 财政年份:
    2023
  • 资助金额:
    $ 3.35万
  • 项目类别:
Scalable and Interoperable framework for a clinically diverse and generalizable sepsis Biorepository using Electronic alerts for Recruitment driven by Artificial Intelligence (short title: SIBER-AI)
使用人工智能驱动的招募电子警报的临床多样化和通用脓毒症生物库的可扩展和可互操作框架(简称:SIBER-AI)
  • 批准号:
    10576015
  • 财政年份:
    2023
  • 资助金额:
    $ 3.35万
  • 项目类别:
Real-Time & Generalizable Flood Simulation Emulator using Numerical Analysis and Machine Learning
即时的
  • 批准号:
    23KJ1685
  • 财政年份:
    2023
  • 资助金额:
    $ 3.35万
  • 项目类别:
    Grant-in-Aid for JSPS Fellows
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了