公开(公告)号：US20240021320A1

公开(公告)日：2024-01-18

申请号：US18036833

申请日：2021-11-11

Applicant: KONINKLIJKE PHILIPS N.V.

Inventor： NICOLE SCHADEWALDT ,  ROLF JÜRGEN WEESE ,  MATTHIAS LENGA ,  AXEL SAALBACH ,  STEFFEN RENISCH ,  HEINRICH SCHULZ

IPC: G16H50/70 ,  G16H10/60 ,  G06N3/08

CPC classification number: G16H50/70 ,  G16H10/60 ,  G06N3/08

Abstract: A system and method for training a deep learning network with previously read image studies to provide a prioritized worklist of unread image studies. The method includes collecting training data including a plurality of previously read image studies, each of the previously read image studies including a classification of findings and radiologist-specific data. The method includes training the deep learning neural network with the training data to predict an urgency score for reading of an unread image study.

公开(公告)号：US20140330119A1

公开(公告)日：2014-11-06

申请号：US14334176

申请日：2014-07-17

Applicant: KONINKLIJKE PHILIPS N.V.

Inventor： THOMAS BUELOW ,  RAFAEL WIEMKER ,  CRISTIAN LORENZ ,  STEFFEN RENISCH ,  THOMAS BLAFFERT

IPC: G06T7/00

CPC classification number: G06T7/0012 ,  A61B6/032 ,  A61B6/481 ,  A61B6/5217 ,  G06T5/50 ,  G06T7/10 ,  G06T7/12 ,  G06T7/149 ,  G06T2207/10081 ,  G06T2207/10116 ,  G06T2207/30061 ,  G06T2207/30064 ,  G06T2207/30101

Abstract: An imaging method for identifying abnormal tissue in the lung is provided, comprising the recording of slice images of the lung by means of X-ray radiation, recording of blood vessels, differentiation of blood vessels and abnormal tissue, segmentation of the abnormal tissue and display of the segmented abnormal tissue on an output device. In addition, a computer tomograph for identifying abnormal tissue in the lung is provided, having a radiation source for recording slice images of the lung and blood vessels by means of X-ray radiation, a computer unit for differentiating the blood vessels from the abnormal tissue and for segmenting the abnormal tissue, as well as an output device for displaying the segmented abnormal tissue. Furthermore, a computer program is provided for controlling a computer tomograph for an identification of abnormal tissue in the lung by means of a radiation source, designed to record slice images of the lung and blood vessels by means of X-ray radiation, to differentiate the blood vessels from abnormal tissue, to segment the abnormal tissue and to control an output device for displaying the abnormal tissue.

Abstract translation: 提供了一种用于鉴定肺中异常组织的成像方法，包括通过X射线照射记录肺的切片图像，记录血管，血管和异常组织的分化，异常组织的分割和显示 的输出装置上的分段异常组织。 另外，提供了一种用于识别肺中的异常组织的计算机断层摄影机，具有用于通过X射线辐射记录肺和血管的切片图像的辐射源，用于将血管与异常组织分离的计算机单元 并且用于分割异常组织，以及用于显示分段的异常组织的输出装置。 此外，提供了一种计算机程序，用于通过辐射源来控制用于识别肺中的异常组织的计算机断层摄影机，其被设计成通过X射线辐射记录肺和血管的切片图像，以区分 来自异常组织的血管，分割异常组织并控制用于显示异常组织的输出装置。

公开(公告)号：US20220398740A1

公开(公告)日：2022-12-15

申请号：US17770307

申请日：2020-10-22

Applicant: KONINKLIJKE PHILIPS N.V.

Inventor： MATTHIAS LENGA ,  CHRISTIAN BUERGER ,  STEFFEN RENISCH

IPC: G06T7/149 ,  G06T7/50 ,  G06V10/46 ,  G06V10/82

Abstract: In a method of segmenting a feature in an image, an image product related to the image is provided (102) to a model trained using a machine learning process. An indication of a shape descriptor for the feature in the image is received (104) from the model, based on the image product. The indicated shape descriptor is then used (106) in a model based segmentation, MBS, to initialize the MBS and segment the feature.

公开(公告)号：US20170131375A1

公开(公告)日：2017-05-11

申请号：US15300052

申请日：2015-03-17

Applicant: KONINKLIJKE PHILIPS N.V.

Inventor： NICOLE SCHADEWALDT ,  MICHAEL GUNTER HELLE ,  HEINRICH SCHULZ ,  STEFFEN RENISCH

IPC: G01R33/56 ,  A61B5/00 ,  G01R33/48 ,  A61B5/055 ,  G06T7/00 ,  G06T7/11

CPC classification number: G01R33/5608 ,  A61B5/0042 ,  A61B5/055 ,  G01R33/481 ,  G01R33/4828 ,  G06T5/008 ,  G06T5/50 ,  G06T7/0012 ,  G06T7/11 ,  G06T2207/10088 ,  G06T2207/30008 ,  G06T2207/30024

Abstract: The application discloses a method for estimating a pseudo CT Hounsfield Unit value for a volume element within a subject from a plurality of magnetic resonance images having different contrasts. The method comprising the steps of: determination of a relative prevalence of a first tissue class and second tissue class within the volume element from a first magnetic resonance image and second magnetic resonance image respectively. Then a relative prevalence of a third tissue class is determined within the volume element based on substraction of a relative prevalence of the first and/or second tissue class from a total tissue prevalence. A reference Hounsfield Unit value is provided for the first, second and third tissue class. Finally, a pseudo Housfield value is estimated for the volume element by determining a weighted sum of the first, second and third reference Hounsfield unit value, with weight factors which are based on the determined relative prevalences of the first, second and third tissue class.

公开(公告)号：US20210150714A1

公开(公告)日：2021-05-20

申请号：US16961706

申请日：2019-01-09

Applicant: KONINKLIJKE PHILIPS N.V.

Inventor： CHRISTIAN BUERGER ,  STEFFEN RENISCH

IPC: G06T7/00 ,  G01R33/56 ,  G01R33/48 ,  G06K9/62 ,  G16H30/40

Abstract: The invention relates to a medical image data processing system (101) for image segmentation. The medical image data processing system (101) comprises a machine learning framework trained to receive an anatomical position of a voxel and to provide a tissue type classification. An execution of machine executable instructions by a processor (130) of the medical image data processing system (101) causes the processor (130) to control the medical image data processing system (101) to: —receive medical image data (140) comprising an anatomical structure of interest, —fit an anatomical frame of reference (302, 402) to the medical image data (140) using model-based segmentation, —classify tissue types represented by voxels of the medical image data (140) using the machine learning framework, wherein anatomical positions of the voxels with respect to the anatomical frame of reference (302, 402) are used as the input to the machine learning framework.

公开(公告)号：US20180078787A1

公开(公告)日：2018-03-22

申请号：US15565697

申请日：2016-04-12

Applicant: KONINKLIJKE PHILIPS N.V.

Inventor： NICOLE SCHADEWALDT ,  STEFFEN RENISCH ,  SVEN PREVRHAL ,  HEINRICH SCHULZ ,  THOMAS BLAFFERT

IPC: A61N5/10 ,  A61B5/055

CPC classification number: A61N5/1039 ,  A61B5/055 ,  A61N2005/1074

Abstract: The present disclosure relates to a method for controlling a magnetic resonance imaging guided radiation therapy apparatus comprising a magnetic resonance imaging system. The method comprises: acquiring magnetic resonance data using the magnetic resonance imaging system and the pulse sequence from an imaging volume; segmenting the magnetic resonance data into a plurality of segments indicating respective tissues in the imaging volume; creating a bulk electron density map of the imaging volume from the plurality of segments; displaying the bulk electron density map and radiation dose distributions for the plurality of segments on a graphical user interface, wherein the radiation dose distributions are determined using the bulk electron density map; receiving a modification signal for modifying at least a first segment of the segments; recreating the bulk electron density map using the modified first segment, and recalculating the radiation dose distribution using the bulk electron density map; redisplaying the bulk electron density map and the radiation dose distributions on the graphical user interface.

公开(公告)号：US20240037920A1

公开(公告)日：2024-02-01

申请号：US18267800

申请日：2021-12-18

Applicant: KONINKLIJKE PHILIPS N.V.

Inventor： MATTHIAS LENGA ,  AXEL SAALBACH ,  NICOLE SCHADEWALDT ,  STEFFEN RENISCH ,  HEINRICH SCHULZ

IPC: G06V10/774 ,  G06V10/764 ,  G06V10/776 ,  G06V10/22

CPC classification number: G06V10/774 ,  G06V10/764 ,  G06V10/776 ,  G06V10/235 ,  G06V2201/031

Abstract: A system and method for training a machine learning module to provide classification and localization information for an image study. The method includes receiving a current image study. The method includes applying the machine learning module to the current image study to generate a classification result including a prediction for one or more class labels for the current image study using User Interface 104 a classification module of the machine learning module. The method includes receiving, via a user interface, a user input indicating a spatial location corresponding to a predicted class label. The method includes training a localization module of the machine learning module using the user input indicating the spatial location corresponding to the predicted class label.

公开(公告)号：US20180071550A1

公开(公告)日：2018-03-15

申请号：US15559210

申请日：2016-03-18

Applicant: KONINKLIJKE PHILIPS N.V.

Inventor： STEFFEN RENISCH ,  NICOLE SCHADEWALDT ,  SVEN PREVRHAL ,  HEINRICH SCHULZ ,  THOMAS BLAFFERT

IPC: A61N5/10 ,  A61B5/055 ,  A61B5/00 ,  G01R33/48

CPC classification number: A61N5/1039 ,  A61B5/0033 ,  A61B5/0035 ,  A61B5/055 ,  A61B5/45 ,  A61B5/7278 ,  A61B5/748 ,  A61B2576/00 ,  A61N5/1031 ,  G01R33/4812 ,  G01R33/543 ,  G01R33/5608

Abstract: The present invention teaches a method and system for computing an alternative electron density map of an examination volume. The processing system is configured to compute a first electron density map using a plurality of imaging data, compute a second electron density map, wherein the second electron density map is a simplified version of the first electron density map, and compute the alternative electron density map, using the first electron density map and the second electron density map.

公开(公告)号：US20160054416A1

公开(公告)日：2016-02-25

申请号：US14781596

申请日：2014-03-27

Applicant: KONINKLIJKE PHILIPS N.V.

Inventor： CHRISTIAN STEHNING ,  NICOLE SCHADEWALDT ,  MICHAEL GUNTER HELLE ,  STEFFEN RENISCH ,  HEINRICH SCHULZ

IPC: G01R33/56 ,  A61B6/03 ,  G01R33/48 ,  G06K9/62 ,  G01R33/385 ,  G06T7/00 ,  G06T11/00 ,  G06K9/52 ,  A61N5/10 ,  G01R33/36

CPC classification number: G01R33/5602 ,  A61B5/0035 ,  A61B5/055 ,  A61B5/4504 ,  A61B6/037 ,  A61N5/1039 ,  G01R33/36 ,  G01R33/385 ,  G01R33/4808 ,  G01R33/481 ,  G01R33/4816 ,  G01R33/4828 ,  G01R33/5608 ,  G06K9/52 ,  G06K9/6267 ,  G06T7/0012 ,  G06T7/11 ,  G06T7/35 ,  G06T11/003 ,  G06T2200/04 ,  G06T2207/10081 ,  G06T2207/10088 ,  G06T2207/10124 ,  G06T2207/20128 ,  G06T2207/30008

Abstract: The invention provides for a medical apparatus (300, 400, 500) comprising: a magnetic resonance imaging system (302) for acquiring magnetic resonance data (342) from an imaging zone (308); a processor (330) for controlling the medical apparatus; a memory (336) storing machine executable instructions (350, 352, 354, 356). Execution of the instructions causes the processor to: acquire (100, 200) the magnetic resonance data using a pulse sequence (340) which specifies an echo time greater than 400 μβ; reconstruct (102, 202) a magnetic resonance image using the magnetic resonance data; generate (104, 204) a thresholded image (346) by thresholding the magnetic resonance image to emphasize bone structures and suppressing tissue structures in the magnetic resonance image; and generate (106, 206) a bone-enhanced image by applying a background removal algorithm to the thresholded image.

Abstract translation: 本发明提供一种医疗设备（300,400,500），包括：用于从成像区域（308）获取磁共振数据（342）的磁共振成像系统（302）。 用于控制医疗装置的处理器（330） 存储器（336），用于存储机器可执行指令（350,352,354,356）。 执行指令使处理器：使用指定大于400μs的回波时间的脉冲序列（340）获取（100,200）磁共振数据; 使用磁共振数据重建（102,202）磁共振图像; 通过阈值化磁共振图像来产生（104,204）阈值图像（346），以强调骨结构并抑制磁共振图像中的组织结构; 并通过将背景去除算法应用于阈值图像来生成（106,206）骨骼增强图像。