Deep learning technologies for estimating the optimal task performance of medical imaging systems
Deep learning technologies for estimating the optimal task performance of medical imaging systems
批准号:
10635347
负责人:
Mark A Anastasio
金额:
$38.25万
依托单位国家:
美国
项目类别:
财政年份:
2023
资助国家:
美国
项目状态:
未结题
起止时间:
2023-09-01 至 2027-08-31
关键词:
AccelerationAddressAlgorithmsAnatomyAssessment toolCase StudyClinicClinicalClinical TrialsComputing MethodologiesDataDetectionDevelopmentDiagnosticDiagnostic ImagingEffectivenessEthicsEvaluationHumanImageImage AnalysisImaging technologyLearningMeasurementMeasuresMedical ImagingMethodsModalityModelingModernizationNeeds AssessmentPatient-Focused OutcomesPerformancePropertyResearchSpecific qualifier valueSystemTask PerformancesTechnologyTimeTranslationsVariantclinically relevantcohortcomputerized toolsdeep learningdenoisingdigitalexperimental studygenerative adversarial networkideal observer (Bayesian)image processingimaging systemimprovedinterestmultimodal datanext generationnovelopen sourcepublic health relevancerestorationsimulationsuccessultra high resolutionvirtual imaging
中文摘要
摘要
现代医学成像系统包括复杂的硬件和复杂的计算方法。
考虑到影响图像质量的系统参数的绝对数量,将被处理的对象的大量变化是可能的。
成像和伦理问题,通过临床评估和改进新兴成像技术,
审判往往是不可能的。由于这些原因,人们对虚拟成像试验(VITs)非常感兴趣,
临床相关成像实验的自动模拟和分析。在开发和
通过VITs改进新的成像技术,非常需要评估客观图像
质量指标(OIQMs),量化结果图像对不同诊断的最佳效用
任务-独立于解释图像的观察者(人或算法)的能力。实际上,这种
OIQMs可以揭示任务相关信息在成像数据中存在的程度,因此可以
可能由人类观察者或次优的其他数值算法提取;这可以允许
识别改进图像处理或其他技术变化的机会,
执行诊断任务。
拟议研究的广泛目标是通过开发下一代来应对这一挑战
开源和模态不可知的计算方法,用于计算OIQMs,
成像系统的可能性能-所谓的理想观察者性能-对于临床相关
任务使用真实随机的医学成像技术的最佳可实现性能的估计
数字对象幻影和临床相关的诊断任务已经成为医学图像质量的圣杯
评估领域,并且迄今为止缺乏成功将该领域限制在不切实际的对象模型和任务上,
几十年当在VITs中使用时,我们的新方法将允许评估任务相关的
图像数据中的信息,并将加速有前途的新成像技术的改进和转化。
技术到诊所。该项目的具体目标是:目标1:开发和验证环境
生成对抗网络(AmGANs),用于创建临床相关数字幻影的集合;目的
2:开发用于估计成像技术的最佳任务性能的方法;
开发了用于评估基于深度学习的图像恢复的工具。
用于计算OIQMs的开发计算工具将开放源代码。这将完全打开
评估和完善新兴医学成像技术的新途径,具有严格和临床水平
以前不可能的相关性。
英文摘要
ABSTRACT
Modern medical imaging systems comprise complicated hardware and sophisticated computational methods.
Given the sheer number of system parameters that impact image quality, the large variety in objects to be
imaged, and ethical concerns, the assessment and refinement of emerging imaging technologies via clinical
trials often is impossible. For these reasons, there is great interest in virtual imaging trials (VITs) that permit the
automated simulation and analysis of clinically relevant imaging experiments. During the development and
refinement of new imaging technologies via VITs, there is an important need for assessing objective image
quality measures (OIQMs) that quantify the best possible utility of the resulting images for different diagnostic
tasks—independent of the ability of the observer (human or algorithm) who interprets the images. In effect, such
OIQMs can reveal the extent to which task-related information is present in imaging data and thus can be
potentially extracted by a human observer or other numerical algorithm that is sub-optimal; this can permit the
identification of opportunities for improved image processing or other technology changes that lead to improved
performance on diagnostic tasks.
The broad objective of the proposed research is to address this challenge by developing the next generation
of open source and modality-agnostic computational methods for computing OIQMs that quantify the best
possible performance of an imaging system—the so-called ideal observer performance—for clinically relevant
tasks. Estimation of the best achievable performance of medical imaging technologies using realistic stochastic
digital object phantoms and clinically relevant diagnostic tasks has been a holy grail for the medical image-quality
assessment field, and the lack of success to date has limited the field to unrealistic object models and tasks for
decades. When employed in VITs, our new methods will permit assessment of the amount of task-relevant
information in image data and will accelerate the refinement and translation of promising new imaging
technologies to the clinic. The Specific Aims of the project are: Aim 1: To develop and validate ambient
generative adversarial networks (AmGANs) for creating ensembles of clinically relevant digital phantoms; Aim
2: To develop methods for estimating the optimal task performance of an imaging technology; Aim 3: To use the
developed tools for assessing deep learning-based image restoration.
The developed computational tools for computing OIQMs will be made open source. This will open entirely
new avenues for assessing and refining emerging medical imaging technologies with a level of rigor and clinical
relevance previously not possible.
期刊论文(0)
专著(0)
科研奖励(0)
会议论文
A Computational Framework Enabling Virtual Imaging Trials of 3D Quantitative Optoacoustic Tomography Breast Imaging
-
批准号:10665540
-
项目类别:
-
资助金额:$62.95万
-
财政年份:2022
-
负责人:Mark A Anastasio
-
依托单位:
Computational imaging and intelligent specificity (Anastasio)
-
批准号:10705173
-
项目类别:
-
资助金额:$18.81万
-
财政年份:2022
-
负责人:Mark A Anastasio
-
依托单位:
A Computational Framework Enabling Virtual Imaging Trials of 3D Quantitative Optoacoustic Tomography Breast Imaging
-
批准号:10367731
-
项目类别:
-
资助金额:$66.79万
-
财政年份:2022
-
负责人:Mark A Anastasio
-
依托单位:
Quantitative histopathology for cancer prognosis using quantitative phase imaging on stained tissues
-
批准号:10703212
-
项目类别:
-
资助金额:$46.72万
-
财政年份:2019
-
负责人:Mark A Anastasio
-
依托单位:
Advanced image reconstruction for accurate and high-resolution breast ultrasound tomography
-
批准号:10017970
-
项目类别:
-
资助金额:$51.65万
-
财政年份:2019
-
负责人:Mark A Anastasio
-
依托单位:
Development of a Rapid Method for Imaging Regional Ventilation in Small Animals w/o Contrast Agents
-
批准号:9927856
-
项目类别:
-
资助金额:$40.85万
-
财政年份:2019
-
负责人:Mark A Anastasio
-
依托单位:
An Enabling Technology for Preclinical X-Ray Imaging of Biomaterials In-Vivo
-
批准号:9927852
-
项目类别:
-
资助金额:$53.91万
-
财政年份:2019
-
负责人:Mark A Anastasio
-
依托单位:
Advanced image reconstruction for accurate and high-resolution breast ultrasound tomography
-
批准号:10252852
-
项目类别:
-
资助金额:$55.69万
-
财政年份:2019
-
负责人:Mark A Anastasio
-
依托单位:
Quantitative histopathology for cancer prognosis using quantitative phase imaging on stained tissues
-
批准号:10443772
-
项目类别:
-
资助金额:$51.6万
-
财政年份:2019
-
负责人:Mark A Anastasio
-
依托单位:
Advanced image reconstruction for accurate and high-resolution breast ultrasound tomography
-
批准号:10442593
-
项目类别:
-
资助金额:$57.49万
-
财政年份:2019
-
负责人:Mark A Anastasio
-
依托单位:
Development of a Rapid Method for Imaging Regional Ventilation in Small Animals w/o Contrast Agents
-
批准号:9888370
-
项目类别:
-
资助金额:$41.98万
-
财政年份:2019
-
负责人:Mark A Anastasio
-
依托单位:
DEVELOPMENT OF A RAPID METHOD FOR IMAGING REGIONAL VENTILATION IN SMALL ANIMALS W/O CONTRAST AGENTS
-
批准号:9474118
-
项目类别:
-
资助金额:$40.85万
-
财政年份:2017
-
负责人:Mark A Anastasio
-
依托单位:
Safe, rapid & functional pediatric brain imaging using photoacoustic computed tomography
-
批准号:10165840
-
项目类别:
-
资助金额:$61.47万
-
财政年份:2017
-
负责人:Mark A Anastasio
-
依托单位:
AN ENABLING TECHNOLOGY FOR PRECLINICAL X-RAY IMAGING OF BIOMATERIALS IN-VIVO
-
批准号:9119328
-
项目类别:
-
资助金额:$59.4万
-
财政年份:2016
-
负责人:Mark A Anastasio
-
依托单位:
SPARSITY-DRIVEN IDEAL OBSERVERS FOR GUIDING IMAGING HARDWARE OPTIMIZATION
-
批准号:8975499
-
项目类别:
-
资助金额:$21.3万
-
财政年份:2015
-
负责人:Mark A Anastasio
-
依托单位:
WHOLE-BODY SMALL-ANIMAL PHOTOACOUSTIC-ULTRASONIC COMPUTED TOMOGRAPHY
-
批准号:8507343
-
项目类别:
-
资助金额:$60.12万
-
财政年份:2013
-
负责人:Mark A Anastasio
-
依托单位:
WHOLE-BODY SMALL-ANIMAL PHOTOACOUSTIC-ULTRASONIC COMPUTED TOMOGRAPHY
-
批准号:8651915
-
项目类别:
-
资助金额:$57.57万
-
财政年份:2013
-
负责人:Mark A Anastasio
-
依托单位:
WHOLE-BODY SMALL-ANIMAL PHOTOACOUSTIC-ULTRASONIC COMPUTED TOMOGRAPHY
-
批准号:8826741
-
项目类别:
-
资助金额:$63.61万
-
财政年份:2013
-
负责人:Mark A Anastasio
-
依托单位:
Development of Thermoacoustic Tomography Brain Imaging
-
批准号:8256588
-
项目类别:
-
资助金额:$40.94万
-
财政年份:2010
-
负责人:Mark A Anastasio
-
依托单位:
Development of Thermoacoustic Tomography Brain Imaging
-
批准号:8043585
-
项目类别:
-
资助金额:$40.86万
-
财政年份:2010
-
负责人:Mark A Anastasio
-
依托单位:
海外基金