公开(公告)号：WO2006054271A2

公开(公告)日：2006-05-26

申请号：PCT/IB2005/053835

申请日：2005-11-21

Applicant: KONINKLIJKE PHILIPS ELECTRONICS, N.V. ,  BOROCZKY, Lilla ,  LEE, Kwok, Pun ,  ZHAO, Luyin

Inventor： BOROCZKY, Lilla ,  LEE, Kwok, Pun ,  ZHAO, Luyin

CPC classification number: G06T7/0012 ,  G06K9/3233 ,  G06T2207/10081 ,  G06T2207/20081 ,  G06T2207/30061

Abstract: A method for computer aided detection (CAD) and classification of regions of interest detected within HRCT medical image data includes post-CAD machine learning techniques applied to maximize specificity and sensitivity of identification of a region/volume as being a nodule or non-nodule. The regions are identified by a CAD process, and automatically segmented. A feature pool is identified and extracted from each segmented region, and processed by genetic algorithm to identify an optimal feature subset, which subset is used to train the support vector machine to classify candidate region/volumes found within non-training data.

Abstract translation: 在HRCT医学图像数据中检测到的计算机辅助检测（CAD）和感兴趣区域的分类方法包括后CAD机器学习技术，其应用于将区域/体积的识别的特异性和敏感性最大化为结节或非结节。 区域由CAD过程识别，并自动分段。 从每个分段区域识别和提取特征池，并通过遗传算法进行处理以识别最优特征子集，该子集用于训练支持向量机以对在非训练数据内发现的候选区域/体积进行分类。

公开(公告)号：WO2006054269A3

公开(公告)日：2006-05-26

申请号：PCT/IB2005/053824

申请日：2005-11-18

Applicant: KONINKLIJKE PHILIPS ELECTRONICS, N.V. ,  BOROCZKY, Lilla ,  ZHAO, Luyin ,  LEE, Kwok Pun

Inventor： BOROCZKY, Lilla ,  ZHAO, Luyin ,  LEE, Kwok Pun

IPC: G06K9/62

Abstract: A method for computer aided detection (CAD) and classification of regions of interest detected within HRCT medical image data includes post-processing machine learning to maximize specificity and sensitivity of the classification to realize a reduction in number of false positive detections reported. The method includes training a classifier on a set of medical image training data selected to include a number of true and false regions, wherein the true and false regions are identified by a CAD process, and automatically segmented, wherein the segmented training regions are reviewed by at least one specialist to classify each training region for its ground truth, i.e., true or false, essentially qualifying the automatic segmentation, wherein a feature pool is identified and extracted from each segmented region, and wherein the pool of features is processed by genetic algorithm to identify an optimal feature subset, which subset is used to train a support vector machine, detecting, within non- training medical image data, regions that are candidates for classification, segmenting the candidate regions, extracting a set of features from each segmented candidate regions and classifying the candidate region using the support vector machine after training in accordance with the optimal feature subset, and processing the set of candidate features.

公开(公告)号：WO2005073916A1

公开(公告)日：2005-08-11

申请号：PCT/IB2005/050252

申请日：2005-01-21

Applicant: KONINKLIJKE PHILIPS ELECTRONICS, N.V. ,  ZHAO, Luyin

Inventor： ZHAO, Luyin

IPC: G06T7/00

CPC classification number: G06T7/0012 ,  G06F19/00 ,  G06T7/33 ,  G06T2207/30096 ,  G16H50/20

Abstract: A computer-aided diagnosis (CAD) technique matches an image of an undiagnosed tumor against respective images of a group of tumors of known pathology, either malignant or benign(104, 208). Either a database of malignant tumor images is designated, or a database of benign tumors is designated (112). The closest group of reference tumor images in terms of similarity is found from the designated database (228). Similarity between the test image and the group of reference images is determined by the smallest Mahalanobis distance between the test and reference images (216). The group is altered by a genetic algorithm to include different images that are then tested for distance, this process being iteratively executed subject to a stopping criterion (216, 220, 224, 228).

Abstract translation: 计算机辅助诊断（CAD）技术将未确诊的肿瘤的图像与已知病理学的一组肿瘤（恶性或良性）的各自图像相匹配（104,208）。 指定恶性肿瘤图像的数据库，或指定良性肿瘤数据库（112）。 从指定的数据库（228）中可以找到最接近的参照肿瘤图像组。 测试图像和参考图像组之间的相似度由测试和参考图像之间的最小马氏距离（216）确定。 该组被遗传算法改变以包括然后对距离进行测试的不同图像，该过程根据停止标准（216,220,224,228）迭代地执行。

公开(公告)号：WO2009083844A1

公开(公告)日：2009-07-09

申请号：PCT/IB2008/055218

申请日：2008-12-11

Applicant: KONINKLIJKE PHILIPS ELECTRONICS N.V. ,  AGNIHOTRI, Lalitha ,  BOROCZKY, Lilla ,  ZHAO, Luyin ,  LEE, Michael Chun-chieh

Inventor： AGNIHOTRI, Lalitha ,  BOROCZKY, Lilla ,  ZHAO, Luyin ,  LEE, Michael Chun-chieh

IPC: G06F19/00

CPC classification number: G06F19/345 ,  G06F19/00 ,  G16H50/20

Abstract: This invention relates to a method and device for case-based decision support. It proposes that a case-based decision support system is trained on inputs from several radiologists in order to have a "baseline" system, and then the system provides an option to a radiologist to refine the baseline system based on his/her inputs which either refine weights of features for similarity distance computation directly or provide new similarity ground truth clusters. By enabling modifying the similarity distance computation based on user inputs, this invention adapts similarity ground truth to different users with different experience and/or different opinions.

Abstract translation: 本发明涉及用于基于病例的决策支持的方法和装置。 它建议对基于病例的决策支持系统进行培训，对多名放射科医师的投入进行培训，以便建立一个“基线”系统，然后该系统为放射科医师提供一个选择，以便根据他/她的输入来完善基线系统， 优化直接相似度距离计算的特征权重或提供新的相似性地面真值聚类。 通过使用基于用户输入的相似距离计算能够进行修改，本发明通过不同的经验和/或不同的观点，将不同用户的相似性原理进行了调整。

公开(公告)号：WO2009083841A1

公开(公告)日：2009-07-09

申请号：PCT/IB2008/055204

申请日：2008-12-10

Applicant: KONINKLIJKE PHILIPS ELECTRONICS, N.V. ,  BOROCZKY, Lilla ,  AGNIHOTRI, Lalitha ,  ZHAO, Luyin ,  LEE, Michael

Inventor： BOROCZKY, Lilla ,  AGNIHOTRI, Lalitha ,  ZHAO, Luyin ,  LEE, Michael

IPC: G06F19/00

CPC classification number: G16H50/70 ,  G06F19/00

Abstract: The invention relates to search for cases in a database. According to the proposed method and apparatus, similarity matching is performed between an input case and a set of cases in an initial search to receive similar cases by- using a given matching criterion. Then statistics on image and non- image-based features associated with the similar cases are calculated and presented to the user with the similar cases. In a search refinement the similar cases are refined by additional features that are determined by the user based on the statistics. The search refinement can be iterative depending on the user's need.

Abstract translation: 本发明涉及在数据库中搜索案例。 根据所提出的方法和装置，在初始搜索的输入情况和一组情况之间执行相似性匹配，以通过使用给定的匹配准则来接收类似的情况。 然后，与类似情况相关联的图像和基于非图像的特征的统计量被计算并呈现给具有类似情况的用户。 在搜索细化中，类似的情况通过基于统计信息由用户确定的附加特征进行细化。 搜索细化可以根据用户的需要进行迭代。

公开(公告)号：WO2008035286A2

公开(公告)日：2008-03-27

申请号：PCT/IB2007/053776

申请日：2007-09-18

Applicant: KONINKLIJKE PHILIPS ELECTRONICS N.V. ,  BOROCZKY, Lilla ,  AGNIHOTRI, Lalitha A. ,  ZHAO, Luyin ,  LEE, Michael C.C. ,  POWELL, Charles ,  BORCZUK, Alain ,  KAWUT, Steven

Inventor： BOROCZKY, Lilla ,  AGNIHOTRI, Lalitha A. ,  ZHAO, Luyin ,  LEE, Michael C.C. ,  POWELL, Charles ,  BORCZUK, Alain ,  KAWUT, Steven

CPC classification number: G06T7/0012 ,  A61B6/5217 ,  A61B6/5223 ,  G06F19/00 ,  G06T7/48 ,  G06T2207/30061

Abstract: Methods are herein provided for decision support in diagnosis of a disease in a subject, and for extracting features from a multi-slice data set. Systems for computer- aided diagnosis are provided. The systems take as input a plurality of medical data and produces as output a diagnosis based upon this data. The inputs may consist of a combination of image data and clinical data. Diagnosis is performed through feature selection and the use of one or more classifier algorithms.

Abstract translation: 这里提供了用于诊断受试者中的疾病以及用于从多切片数据集中提取特征的决策支持的方法。 提供了计算机辅助诊断系统。 该系统将多个医疗数据作为输入，并基于该数据产生诊断结果作为输出。 输入可以由图像数据和临床数据的组合组成。 通过特征选择和使用一个或多个分类器算法来执行诊断。

公开(公告)号：WO2007144854A2

公开(公告)日：2007-12-21

申请号：PCT/IB2007/052307

申请日：2007-06-15

Applicant: KONINKLIJKE PHILIPS ELECTRONICS, N.V. ,  AGNIHOTRI, Lalitha ,  BOROCZKY, Lilla ,  ZHAO, Luyin

Inventor： AGNIHOTRI, Lalitha ,  BOROCZKY, Lilla ,  ZHAO, Luyin

CPC classification number: G16H50/20 ,  G06F19/00 ,  G06F19/321

Abstract: Optimizing example-based computer-aided diagnosis (CADx) is accomplished by clustering volumes-of-interest (VOIs) (116) in a database (120) into respective clusters according to subjective assessment of similarity (S220). An optimal set of volume-of-interest (VOI) features is then selected for fetching examples such that objective assessment of similarity, based on the selected features, clusters, in a feature space, the database VOIs so as to conform to the subjectively -based clustering (S230). The fetched examples are displayed alongside the VOI to be diagnosed for comparison by the clinician. Preferably, the displayed example is user-selectable for further display of prognosis, therapy information, follow up information, current status, and/or clinical information retrieved from an electronic medical record (S260).

Abstract translation: 基于实例的计算机辅助诊断（CADx）通过根据相似性的主观评估将数据库（120）中的感兴趣体积（VOI）（116）聚类成各自的簇来实现（S220）。 然后选择最佳的感兴趣体积（VOI）特征来提取示例，使得基于特征空间的所选特征聚类的客观评估，数据库VOI以符合主观 - （S230）。 所获取的示例显示在VOI旁边以被临床医生诊断以进行比较。 优选地，所显示的示例是用户可选择的，用于进一步显示从电子医疗记录检索的预后，治疗信息，跟踪信息，当前状态和/或临床信息（S260）。

公开(公告)号：WO2006054248A3

公开(公告)日：2006-10-05

申请号：PCT/IB2005053779

申请日：2005-11-16

Applicant: KONINKL PHILIPS ELECTRONICS NV ,  ZHAO LUYIN

Inventor： ZHAO LUYIN

IPC: G06F19/00

CPC classification number: G16H50/20 ,  G06F19/321 ,  G06F19/3418

Abstract: Automated diagnostic decision support (104) in the imaging of potentially-malignant lesions is distributed and streamlined to protect patient confidentiality and to lower bandwidth and transaction costs. At a client hospital site (108a, 108b) , a software agent (132) monitors a database and responsively accesses an image of a lesion and ground truth that the lesion is malignant/benign. After computing at least one feature of the lesion based on the image) , the software agent transmits the feature (s) and ground truth externally from the hospital, to a central diagnostic decision support server . When a client hospital site needs automatic diagnostic support, the lesion feature (s) of the new patient are likewise extracted and transmitted to the external server in a query message. The classifier located on the server will return a diagnosis (benign/malignant) and a confidence level .

Abstract translation: 对恶性病变的成像进行自动诊断决策支持（104）的分发和流程化，以保护患者的机密性，降低带宽和交易成本。 在客户医院站点（108a，108b），软件代理（132）监视数据库并且响应地访问病变是恶性/良性的病变和地面真实的图像。 在基于图像计算病变的至少一个特征之后），软件代理将医院外部的特征和地面实体传输到中央诊断决策支持服务器。 当客户医院站点需要自动诊断支持时，同样提取新患者的病变特征并在查询消息中传送到外部服务器。 位于服务器上的分类器将返回诊断（良性/恶性）和置信水平。

公开(公告)号：WO2008035276A3

公开(公告)日：2008-11-20

申请号：PCT/IB2007053750

申请日：2007-09-17

Applicant: KONINKL PHILIPS ELECTRONICS NV ,  ZHAO LUYIN ,  BOROCZKY LILLA ,  AGNIHOTRI LALITHA A ,  LEE MICHAEL C C

Inventor： ZHAO LUYIN ,  BOROCZKY LILLA ,  AGNIHOTRI LALITHA A ,  LEE MICHAEL C C

IPC: G06N3/12 ,  G06F19/00 ,  G06K9/00

CPC classification number: G06N3/126 ,  G06K9/6217 ,  G06K2209/053 ,  G16H50/20 ,  G16H50/30

Abstract: Methods for performing genetic algorithm-based feature selection are provided herein. In certain embodiments, the methods include steps of applying multiple data splitting patterns to a learning data set to build multiple classifiers to obtain at least one classification result; integrating the at least one classification result from the multiple classifiers to obtain an integrated accuracy result; and outputting the integrated accuracy result to a genetic algorithm as a fitness value for a candidate feature subset, in which genetic algorithm-based feature selection is performed.

Abstract translation: 这里提供了用于执行基于遗传算法的特征选择的方法。 在某些实施例中，所述方法包括以下步骤：将多个数据分裂模式应用于学习数据集以构建多个分类器以获得至少一个分类结果; 整合来自多个分类器的至少一个分类结果以获得整合的准确性结果; 以及将整合的准确度结果输出到遗传算法作为候选特征子集的适合度值，其中执行基于遗传算法的特征选择。

公开(公告)号：WO2008017991A3

公开(公告)日：2008-10-30

申请号：PCT/IB2007053048

申请日：2007-08-02

Applicant: KONINKL PHILIPS ELECTRONICS NV ,  ZHAO LUYIN ,  BOROCZKY LILLA ,  LEE KWOK PUN

Inventor： ZHAO LUYIN ,  BOROCZKY LILLA ,  LEE KWOK PUN

IPC: G06N3/12 ,  G06F19/00

CPC classification number: G06N3/126 ,  G06K9/6229 ,  G16H50/20

Abstract: Methods and apparatus for training a system for developing a process of data mining, false positive reduction, computer-aided detection, computer-aided diagnosis and artificial intelligence are provided. A method includes choosing a training set from a set of training cases using systematic data scaling and creating a classifier based on the training set using a classification method. The classifier yields fewer false positives. The method is suitable for use with a variety of data mining techniques including support vector machines, neural networks and decision trees.

Abstract translation: 提供了用于训练用于开发数据挖掘，假阳性减少，计算机辅助检测，计算机辅助诊断和人工智能的系统的方法和装置。 一种方法包括使用系统化数据缩放从一组训练案例中选择一个训练集并且使用分类方法基于训练集创建分类器。 分类器产生的误报较少。 该方法适用于各种数据挖掘技术，包括支持向量机，神经网络和决策树。