Pattern recognition in medical imaging

医学成像中的模式识别

• 批准号: 9341862
• 负责人: Ilya Goldberg
• 金额: $ 37.73万
• 依托单位: NATIONAL INSTITUTE ON AGING
• 依托单位国家: 美国
• 资助国家: 美国
• 起止时间: 至
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/9341862
• 关键词: Abdomen; Adipose tissue; Age; Age related macular degeneration; Aging; Algorithms; Alzheimer' s Disease; Area; Bacterial Pneumonia; Baltimore; Biopsy; Blood Pressure; Blood flow; Cardiovascular system; Cartilage; Characteristics; Child; Classification; Clinical Data; Collaborations; Collection; Computer software; Computers; Data; Data Analyses; Data Set; Degenerative polyarthritis; Descriptor; Developing Countries; Development; Diagnosis; Disease; Disease Progression; Eye; Fatty acid glycerol esters; Fundus; Future; Genes; Goals; Hematoxylin and Eosin Staining Method; Histologic; Homeostasis; Human; Image; Image Analysis; Indium; Knee; Lead; Life; Linear Regressions; Longitudinal Studies; Lung; MRI Scans; Machine Learning; Magnetic Resonance Imaging; Manuals; Manuscripts; Masks; Measurement; Measures; Medical Imaging; Methods; Mining; Morphology; National Eye Institute; Nature; Participant; Pattern; Pattern Recognition; Physiological; Pneumonia; Population; Procedures; Process; Public Health Schools; Publications; Publishing; Radiology Specialty; Rattus; Reading; Reporting; Resolution; Roentgen Rays; Sampling; Sardinia; Scanning; Scheme; Sensitivity and Specificity; Signal Transduction; Solid; Staining method; Stains; Students; Study Section; System; Systems Analysis; Techniques; Testing; Thick; Thoracic Radiography; Time; Tissues; Training; Translating; Validation; Variant; Viral; Viscera; Visceral; Visit; Work; World Health Organization; X-Ray Computed Tomography; abdominal CT; accurate diagnosis; age group; age related; base; bone; clinical Diagnosis; clinically relevant; density; follow-up; functional decline; genome wide association study; high risk; human disease; imaging system; improved outcome; insight; middle age; outcome forecast; predictive marker; radiologist; research study; screening; sensor; subcutaneous; telomere; tool; trait; treatment strategy; tumor progression

Modern imaging systems far exceed the human eye in spatial and spectral resolution and in dynamic range, thus potentially allowing machine-based image pattern analysis systems to outperform manual image interpretation. In fact, recent work in pattern recognition has demonstrated that computers can equal or even surpass image classification and pattern analysis by human experts. We have previously published work investigating the progression of osteoarthritis (OA) in the human population comprising the Baltimore Longitudinal Study of Aging (BLSA). We were able to show that WND-CHARM (see AG000671-13) is able to diagnose the existence of OA in knee X-Rays with accuracies approaching that of a panel of highly trained radiologists. We have subsequently published work that WND-CHARM can predict the future onset of radiologically detectable osteoarthritis in X-Rays that were scored as radiologically clear. We were able to show that the development of moderate OA two decades in the future can be predicted with > 70% accuracy from X-Rays scored as free of OA by a panel of three radiologists. Subsequently, we were able to further characterize OA progression and identify an early, slow period of change followed by rapid degeneration. We are following up our knee X-ray studies with an MRI dataset obtained from the Osteoarthritis Initiative as well as experimental MRI samples imaged here at NIA through a collaboration with Dr. Richard Spencer (NIA/LCI). In a recently published study, we developed a technique using multivariate linear regression of image features derived from several types of MRI scans to construct a continuously variable cartilage quality score similar to an OARSI grade. The OARSI grade is determined histologically, and involves an invasive procedure that is not amenable to early screening or tracking disease progress. While MRI methods are non-invasive, they must first be correlated with histological grading schemes before they can be used in diagnosis or evaluating cartilage quality. Our multivariate regression of image features from multimodal MRI scans produced a continuous score that was well correlated with the OARSI grade of the same samples (r > 0.65, p < 10-5). Defining a continuous grading system based on a non-invasive procedure is a key element in evaluating osteoarthritis treatment strategies. A follow-up study to this work is being re-submitted after review, where we evaluated our ability to predict development of OA in a high-risk co-hort derived from the Osteoarthritis Initiative (OAI) study. Here we showed that our sensitivity, specificity and accuracy for predicting development of symptomatic OA from MR scans were 74%, 76% and 75%, respectively. A recently completed study that is in the submission process involves abdominal CT scans. The viscera, bone, subcutaneous and visceral fat in these scans has been segmented into separate image masks using the characteristic densities of these tissues on the Hounsfield scale. Our analysis of these image masks indicates that a strong aging signal is present in adipose tissues as well as in the unsegmented whole CT scans. These results are based on cross-validation of classifiers trained on a middle-age group (56-70) and an older group (81-99). This is by far the largest image-based aging study done in humans, and it clearly shows that adipose tissue is one of the major factors in age-related changes occuring in the abdomen. Another radiology project is in collaboration with Dr. Maria Knoll at the Johns Hopkins Bloomberg School of Public Health. Here the goal is to diagnose viral vs., bacterial pneumonia in children using chest X-rays. A rapid accurate diagnosis of the nature of this disease will dramatically improve outcomes for children in developing countries. A standard set of chest X-rays is available from the World Health Organization that is well annotated, with each X-ray having beenn read by mmultiple expert radiologists forming a solid ground truth for training machine classifiers. The major challenge posed by this set is the extreme variation in the physical size of the subjects due to the variation in their ages. We have developed a strategy to compensate for this size variation by working with a student at JHSPH to manually annotate the X-rays with a set of fiducial marks that are anatomically comparable across the X-rays regardless of subject size. Using these manually aligned regions of the lung, we have preliminary indications that such a diagnosis may be possible. We have also assembled a dataset where areas of the lung X-rays have been manually delineated and annotated. This dataset is being used to train an automated segmentation classifier as described in the report for AG000671-15. A project recently begun involves analyzing fundus images collected by the National Eye Institute. The goal is two-fold: 1) Develop an automated scoring system for age-related macular degeneration (AMD), and use fundus images from SardiNIA for testing and validation using manual reads by our NEI collaborators. 2) Develop a set of numerical descriptors for segmented vasculature in fundus images, correlate them with cardiovascular traits measured in SardiNIA, and use them to determine genome-wide associations to these traits. Currently, preliminary experiments have been able to automatically detect an AMD signal in NEI fundus images, and thuse preliminary findings are being refined. We have some evidence that a new scale based on objective image similarity measures can be derived for scoring AMD. We have evaluated software for automated segmentation of fundus vasculature, and Dr. Nikita Orlov has developed several algorithms to analyze the vessicle segmentation masks for numerical descriptors of vasculature, including various tortuosity measurements, distributions of vessicle thickness, branching patterns, etc. Our work in developing tools and expertise in analyzing images to obtain physiological insights that are not directly observable has recently been translated to non-image-based clinical data. In this project, we used machine learning and the totality of the quantitative trait data collected in the SardiNIA study to ascertain each participant's age. This predicted age was excpected to closely correlate to chronological age, but as it was based on broad physiological measurements, be more closely related to each participant's physiological age. The ratio between physiological and chronological age can be viewed as a measure of aging rate, and we determined that this rate is largely preserved for each participant across multiple visits. Moreover, we determined that 40% of the variation in aging rates is heritable, and by performing a GWAS showed that it is significantly associated with two genes related to telomere function. We have been unable to replicate the GWAS results in the InChianti study, but we were able to reproducibly calculate aging rates from physiological data in that study as well. We were able to perform an internal validation using the SardiNIA study, and are now prepared this manuscript for publication. The use of machine learning and pattern recognition to mine new insights from numerical clinical data has great potential, and we are actively pursuing this strategy with new projects. In collaboration with Madhav Thambisetty and Kevin Becker, we are extending this approach to examine traits in BLSA participants that may be predictive of later diagnosis of Alzheimer's disease. In a collaboration with Matt Oberdier and Majd AlGhatrif (LCS) we are applying these tools to analyze data from blood flow and pressure sensors to act as markers of cardiovascular state in rats.

现代成像系统在空间和光谱分辨率以及动态范围方面远远超过了人眼，因此有可能使基于机器的图像模式分析系统优于手动图像解释。事实上，最近在模式识别方面的工作已经证明，计算机可以等同甚至超越人类专家的图像分类和模式分析。 我们之前发表过研究人类骨关节炎 (OA) 进展的研究成果，其中包括巴尔的摩纵向衰老研究 (BLSA)。 我们能够证明 WND-CHARM（参见 AG000671-13）能够诊断膝盖 X 射线中是否存在 OA，其准确度接近训练有素的放射科医生小组的准确度。 我们随后发表了一项研究，表明 WND-CHARM 可以预测 X 射线中放射学可检测到的骨关节炎的未来发病情况，这些骨关节炎的评分为放射学清晰。 我们能够证明，通过由三名放射科医生组成的小组将 X 射线评分为无 OA，可以以 > 70% 的准确度预测未来二十年中度 OA 的发展。 随后，我们能够进一步描述 OA 进展的特征，并确定早期缓慢的变化期，随后是快速退化。 我们正在使用从骨关节炎倡议获得的 MRI 数据集以及通过与 Richard Spencer 博士 (NIA/LCI) 合作在 NIA 成像的实验 MRI 样本来跟踪我们的膝盖 X 射线研究。在最近发表的一项研究中，我们开发了一种技术，使用源自多种 MRI 扫描的图像特征的多元线性回归来构建类似于 OARSI 等级的连续可变软骨质量评分。 OARSI 分级是通过组织学确定的，涉及侵入性操作，不适合早期筛查或跟踪疾病进展。 虽然 MRI 方法是非侵入性的，但它们必须首先与组织学分级方案相关联，然后才能用于诊断或评估软骨质量。 我们对多模态 MRI 扫描的图像特征进行多元回归，得出连续评分，该评分与相同样本的 OARSI 等级密切相关（r > 0.65，p < 10-5）。 定义基于非侵入性手术的连续分级系统是评估骨关节炎治疗策略的关键要素。 这项工作的一项后续研究正在审查后重新提交，我们评估了我们在骨关节炎倡议 (OAI) 研究中得出的高风险队列中预测 OA 发展的能力。 在这里，我们表明，通过 MR 扫描预测症状性 OA 发展的敏感性、特异性和准确性分别为 74%、76% 和 75%。 最近完成的一项研究涉及腹部 CT 扫描，目前正在提交过程中。 这些扫描中的内脏、骨骼、皮下和内脏脂肪已使用这些组织在亨斯菲尔德尺度上的特征密度分割成单独的图像掩模。我们对这些图像掩模的分析表明，脂肪组织以及未分段的整体 CT 扫描中存在强烈的老化信号。这些结果基于对中年组 (56-70) 和老年组 (81-99) 训练的分类器的交叉验证。 这是迄今为止在人类中进行的最大的基于图像的衰老研究，它清楚地表明脂肪组织是腹部发生与年龄相关的变化的主要因素之一。 另一个放射学项目是与约翰·霍普金斯大学彭博公共卫生学院的玛丽亚·诺尔博士合作的。 这里的目标是使用胸部 X 光检查来诊断儿童的病毒性肺炎和细菌性肺炎。 对这种疾病的性质进行快速准确的诊断将极大地改善发展中国家儿童的治疗结果。 世界卫生组织提供了一套标准的胸部 X 射线，并有详细注释，每张 X 射线都经过多位放射专家专家的阅读，为训练机器分类器提供了坚实的基础事实。 该组提出的主要挑战是由于受试者年龄的差异而导致其身体尺寸的极大变化。 我们开发了一种策略来补偿这种尺寸变化，方法是与 JHSPH 的一名学生合作，使用一组基准标记手动注释 X 射线，这些基准标记在 X 射线上具有解剖学上的可比性，无论对象大小如何。 使用这些手动对齐的肺部区域，我们有初步迹象表明这样的诊断是可能的。我们还组装了一个数据集，其中手动描绘和注释了肺部 X 射线区域。该数据集用于训练自动分割分类器，如 AG000671-15 报告中所述。 最近开始的一个项目涉及分析国家眼科研究所收集的眼底图像。我们的目标有两个：1) 开发年龄相关性黄斑变性 (AMD) 的自动评分系统，并使用来自 SardiNIA 的眼底图像进行测试和验证，并由我们的 NEI 合作者手动读取。 2) 开发一组用于眼底图像中分段脉管系统的数字描述符，将它们与撒丁岛测量的心血管特征相关联，并使用它们来确定与这些特征的全基因组关联。 目前，初步实验已能够自动检测NEI眼底图像中的AMD信号，初步结果正在完善中。 我们有一些证据表明，可以导出基于客观图像相似性测量的新量表来对 AMD 进行评分。我们评估了用于眼底脉管系统自动分割的软件，Nikita Orlov 博士开发了多种算法来分析囊泡分割掩模以获取脉管系统的数值描述符，包括各种弯曲度测量、囊泡厚度分布、分支模式等。 我们在开发分析图像的工具和专业知识方面的工作，以获得无法直接观察到的生理见解，最近已转化为非基于图像的临床数据。 在这个项目中，我们使用机器学习和 SardiNIA 研究中收集的全部数量性状数据来确定每个参与者的年龄。 该预测年龄预计与实际年龄密切相关，但由于它基于广泛的生理测量，因此与每个参与者的生理年龄更密切相关。 生理年龄和实际年龄之间的比率可以被视为衰老率的衡量标准，我们确定每个参与者在多次访问中很大程度上保留了这一比率。 此外，我们确定衰老率的变异中有 40% 是可遗传的，并且通过进行 GWAS 表明它与与端粒功能相关的两个基因显着相关。 我们无法复制 InChianti 研究中的 GWAS 结果，但我们也能够根据该研究中的生理数据可重复地计算衰老率。我们能够使用 SardiNIA 研究进行内部验证，现在准备出版这份手稿。 使用机器学习和模式识别从数值临床数据中挖掘新见解具有巨大潜力，我们正在通过新项目积极推行这一策略。 我们与 Madhav Thambisetty 和 Kevin Becker 合作，正在扩展这种方法来检查 BLSA 参与者的特征，这些特征可能预测阿尔茨海默病的后续诊断。 在与 Matt Oberdier 和 Majd AlGhatrif (LCS) 的合作中，我们正在应用这些工具来分析来自血流和压力传感器的数据，作为大鼠心血管状态的标记。