Software to facilitate multimode, multiscale fused data for Pathology and Radiolo

用于促进病理学和放射学多模式、多尺度融合数据的软件

• 批准号: 8305155
• 负责人: MICHAEL D FELDMAN
• 金额: $ 61.94万
• 依托单位: UNIVERSITY OF PENNSYLVANIA
• 依托单位国家: 美国
• 财政年份: 2009
• 资助国家: 美国
• 起止时间: 2009-07-17 至 2014-06-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/8305155
• 关键词: Active Learning; Algorithms; American Cancer Society; Anatomy; Architecture; Biochemical; Clinic; Clinical; Communities; Computer Assisted; Computer software; Computer-Assisted Diagnosis; Core Biopsy; Data; Data Set; Databases; Decision Support Systems; Detection; Development; Diagnosis; Diagnostic; Diffusion; Disease; Elements; Epigenetic Process; Evaluation; Explosion; Gene Proteins; Gleason Grade for Prostate Cancer; Goals; Health; Healthcare; Histology; Histopathology; Hospitals; Image; Image Analysis; Imagery; Informatics; Label; Lead; Learning; Lesion; Link; Location; MRI Scans; Machine Learning; Magnetic Resonance Imaging; Malignant Neoplasms; Malignant neoplasm of prostate; Medical; Medical Informatics; Methodology; Methods; Modality; Molecular; Nuclear; Outcome; Pathologic; Pathologist; Pathology; Patients; Pennsylvania; Physiological; Population; Premalignant; Procedures; Prostate; Prostate Adenocarcinoma; Prostatectomy; Radical Prostatectomy; Radiology Specialty; Reader; Recommendation; Recording of previous events; Research; Research Infrastructure; Resolution; Schedule; Scientist; Screening procedure; Sensitivity and Specificity; Software Tools; Source; Specimen; Stream; System; Techniques; Therapeutic; Tissues; Training; United States; Universities; Validation; Weight; Work; anticancer research; base; cancer Biomedical Informatics Grid; cancer imaging; computerized; diagnostic accuracy; disease diagnosis; image registration; imaging modality; improved; in vivo; interoperability; malignant breast neoplasm; men; novel; open source; outcome forecast; pre-clinical; radiologist; repository; spectroscopic imaging; tool

DESCRIPTION (provided by applicant): Medical informatics from the macro- to micro-scale is increasingly available for a range of detection/diagnosis/theragnostic applications tailored to each patient's history and current condition. Prostatic adenocarcinoma (CAP) is the second most common malignancy among men with an estimated 220,000 new cases in the USA in 2008. With the advent of multi-parametric high resolution (3 Tesla (T)) prostate MRI, providing anatomic, biochemical, and physiologic information, it has become increasingly important to identify the potential value of this information in pre-operative or pre-therapeutic CAP screening. However, in vivo prostate MRI lacks the resolution and ground truth diagnostic accuracy histopathological examination of biopsy cores provides. A first step toward getting prostate MRI for CAP into the clinic would be validating the information provided from MR at the cellular level. However, validating MRI against histological ground truth currently lacks the means to link the information provided by radiological imaging and pathology seamlessly. This is primarily due to a lack of interoperability between informatics representations and tools. One missing element, for instance, is robust and accurate image registration tools to align the multi-modal volumetric data sets. The overarching goal of this collaborative project between the University of Pennsylvania, Rutgers University, and Siemens Corporate Research is to develop and evaluate multi-modal image analysis and machine learning techniques within a software framework that will enable efficient analysis, correlation, and interpretation of multi-functional, multi-resolution patient data. The availability of these multi-modal, multi- scale analysis tools will enable alignment of radiology and pathological data which in turn will (a) enable building and validation of supervised computerized decision support systems for detection and grading of CAP from radiology and pathology data and (b) building meta-classifiers for CAP by integrating multi- modal, multi-scale disease signatures. Such a set of prostate-specific informatics tools promises clinical benefits including improved patient prognoses, more accurate disease diagnoses, and therapeutic recommendations. More generally, the tools developed as part of this project will also enable radiologic/pathologic studies in other disease entities. The specific goals of this project are 1) to develop cross-platform, open source, grid-enabled annotation, image analysis and image registration tools that will enable cross modality validation of radiology data (multi-functional 3 T prostate MRI) with expert histopathological annotation of prostatectomy specimens and provide independent computer-aided predictions of cancer extent and grade on radiology and histopathology, 2) curate an open source caGRID- connected database of prostate MRI and histopathological specimens that will enable development of quantitative signatures for detection and grading of CAP across multiple scales and imaging modalities. PUBLIC HEALTH RELEVANCE: The goal of this project is to develop a software tool kit (based on the XIP application from Siemens corporation) that will allow scientists to study prostate cancer by combining data from multiple imaging modalities (radiology and pathology) with molecular methodologies (including proteins, genes, epigenetic data). The results of this fused and combined data sets will allow scientists to create a more robust system based view of prostate cancer which allow prediction of diagnosis, follow outcomes of therapeutic treatment and facilitate discovery of new treatment options

描述(由申请人提供)：从宏观到微观的医学信息学越来越多地可用于根据每个患者的病史和当前情况量身定做的一系列检测/诊断/诊断应用。前列腺癌(CAP)是男性中第二常见的恶性肿瘤，2008年美国估计有22万新病例。随着提供解剖、生化和生理信息的多参数高分辨率(3TESLA(T))前列腺MRI的出现，确定这些信息在术前或治疗前CAP筛查中的潜在价值变得越来越重要。然而，活体前列腺MRI缺乏活检核心的组织病理学检查所提供的分辨率和基本真实诊断准确性。将前列腺癌MRI用于CAP临床的第一步将是在细胞水平上验证MR提供的信息。然而，根据组织学基本事实验证MRI目前缺乏将放射成像和病理学提供的信息无缝联系起来的手段。这主要是由于信息学表示和工具之间缺乏互操作性。例如，缺少的一个要素是用于对齐多模体数据集的稳健和准确的图像配准工具。这个由宾夕法尼亚大学、罗格斯大学和西门子企业研究中心合作的项目的主要目标是在一个软件框架内开发和评估多模式图像分析和机器学习技术，以实现对多功能、多分辨率患者数据的高效分析、关联和解释。这些多模式、多尺度分析工具的提供将使放射学和病理数据能够协调一致，从而：(A)能够建立和验证受监督的计算机化决策支持系统，以便从放射和病理数据中检测和分级CAP；以及(B)通过集成多模式、多尺度的疾病特征，为CAP建立元分类器。这样一套特定于前列腺的信息学工具有望带来临床好处，包括改善患者预后、更准确的疾病诊断和治疗建议。更广泛地说，作为该项目的一部分开发的工具还将使其他疾病实体的放射学/病理学研究成为可能。该项目的具体目标是1)开发跨平台、开源、网格启用的注释、图像分析和图像配准工具，从而能够对放射数据(多功能3T前列腺癌MRI)进行跨模式验证，并对前列腺切除标本的组织病理学进行专家注释，并提供独立的计算机辅助预测，包括放射学和组织病理学方面的癌症范围和分级；2)建立一个与caGRID相连的开源前列腺癌MRI和组织病理学标本数据库，该数据库将能够开发用于多尺度和成像方式的CAP检测和分级的定量签名。与公共健康相关：这个项目的目标是开发一个软件工具包(基于西门子公司的XIP应用程序)，允许科学家通过将来自多种成像方式(放射学和病理学)的数据与分子方法(包括蛋白质、基因、表观遗传学数据)相结合来研究前列腺癌。这种融合和组合的数据集的结果将使科学家能够创建一个更强大的基于系统的前列腺癌视图，从而能够预测诊断、跟踪治疗结果并促进发现新的治疗方案