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：US20170178340A1

公开(公告)日：2017-06-22

申请号：US15325096

申请日：2015-06-16

Applicant: KONINKLIJKE PHILIPS N.V.

Inventor： NICOLE SCHADEWALDT ,  HEINRICH SCHULZ ,  DANIEL BYSTROV ,  ASTRID RUTH FRANZ

IPC: G06T7/12 ,  G06T7/149 ,  G06T7/00

CPC classification number: G06T7/12 ,  G06T7/0012 ,  G06T7/149 ,  G06T2207/20104 ,  G06T2207/20116 ,  G06T2207/20168 ,  G06T2207/30004 ,  G06T2207/30008

Abstract: The present invention relates to a device for segmenting an image of a subject (36), comprising a data interface for receiving an image of said subject (36), said image depicting a structure of said subject (36), a translation unit for translating a user-initiated motion of an image positioner means into a first contour (38) surrounding said structure, a motion parameter registering unit for registering a motion parameter of said user-initiated motion to said first contour (38), said motion parameter comprising a speed and/or an acceleration of said image positioner means, an image control point unit for distributing a plurality of image control points (40) on said first contour with a density decreasing with said motion parameter, and a segmentation unit for segmenting said image by determining a second contour (44) within said first contour based on said plurality of image control points (40), said segmentation unit being configured to use one or more segmentation functions.

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：US20160358336A1

公开(公告)日：2016-12-08

申请号：US15116687

申请日：2015-02-17

Applicant: KONINKLIJKE PHILIPS N.V,

Inventor： Astrid Ruth Franz ,  NICOLE SCHADEWALDT ,  HEINRICH SCHULZ ,  DANIEL BYSTROV ,  TORBJOERN VIK

IPC: G06T7/00 ,  G06K9/62

CPC classification number: G06T7/0034 ,  G06K9/6255 ,  G06K2009/2045 ,  G06K2209/05 ,  G06T7/32 ,  G06T7/35 ,  G06T2207/10081 ,  G06T2207/20076 ,  G06T2207/20081 ,  G06T2207/30004

Abstract: A method includes obtaining a single training image from a set of training images in a data repository. The method further includes generating an initial tissue class atlas based on the obtained single training image. The initial tissue class atlas includes two or more different tissue class images corresponding to two or more different tissue classes. The method further includes registering the remaining training images of the set of training images to the initial tissue class atlas. The method further includes generating a quality metric for each of the registered images. The method further includes evaluating the quality metric of each of the registered image with a predetermined evaluation criterion. The method further includes identifying a sub-set of images from the set of training images that satisfy the evaluation criterion. The method further includes generating a subsequent tissue class atlas based on the identified sub-set of the set of training images.

Abstract translation: 一种方法包括从数据存储库中的一组训练图像获得单个训练图像。 该方法还包括基于获得的单个训练图像生成初始组织类图集。 初始组织类图集包括对应于两个或多个不同组织类别的两个或更多个不同的组织分类图像。 该方法还包括将该组训练图像的剩余训练图像登记到初始组织分类图集。 该方法还包括为每个登记图像生成质量度量。 该方法还包括以预定的评估标准评估每个登记图像的质量度量。 该方法还包括从满足评估标准的训练图像集合中识别图像的子集。 该方法还包括基于所识别的该组训练图像的子集来生成随后的组织分类图集。

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：US20200038683A1

公开(公告)日：2020-02-06

申请号：US16492186

申请日：2018-03-19

Applicant: KONINKLIJKE PHILIPS N.V.

Inventor： NICOLE SCHADEWALDT ,  TIM NIELSEN ,  CHRISTIAN BUERGER

IPC: A61N5/10

Abstract: For delivering an image-guided radiation therapy treatment to a moving structure included in a region of a patient body a series of first images of the region of the patient body in different phases of a motion of the structure is acquired in accordance with a first imaging mode. The series of first images is associated with a series of second images of the patient body in essentially the same phases of the motion of the target structure, the second images being acquired in a second imaging mode. During the treatment, a third image is acquired using the second imaging mode during the radiation therapy treatment and a continuation of the radiation therapy treatment is planned on the basis of data relating to one of the first images selected on the basis of a comparison between the third image and the second images associated with the first images.

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。

公开(公告)号：US20210077062A1

公开(公告)日：2021-03-18

申请号：US16963680

申请日：2019-01-09

Applicant: KONINKLIJKE PHILIPS N.V.

Inventor： NICOLE SCHADEWALDT ,  CRISTIAN LORENZ ,  ALEXANDER SCHMIDT-RICHBERG ,  TOBIAS KLINDER

IPC: A61B8/08 ,  A61B8/00 ,  G06T7/62 ,  G06T7/00

Abstract: The invention provides a method for making anatomical measurements using a captured ultrasound image representative of the anatomical region of interest. The method comprises receiving (20) data representative of a set of points selected by a user within the image and interpreting from the points a particular anatomical measurement type which the user is intending to perform. In particular, the points are processed to identify (24) a pattern or other geometrical characteristic of the points, and the location (22) of at least one of the points within the image is also identified. These two characteristics are used to identify from the set of points which measurement the operator is performing. Once the measurement is identified, an appropriate measurement template (26) is selected and applied in order to derive (30) from the set of points an anatomical measurement.

公开(公告)号：US20200175674A1

公开(公告)日：2020-06-04

申请号：US16616125

申请日：2018-05-25

Applicant: KONINKLIJKE PHILIPS N.V.

Inventor： RAFAEL WIEMKER ,  HEIKE RUPPERTSHOFEN ,  NICOLE SCHADEWALDT ,  TOBIAS KLINDER

IPC: G06T7/00 ,  G06T7/11 ,  G06T7/73 ,  G16H30/40

Abstract: A system (100) comprises a segmenter (130) and a quantification tool (140). The segmenter segments a lesion (102) in a medical image (104). The quantification tool (140) quantifies an aspect of the segmented lesion according to a set of parameters, wherein the quantified aspect includes spiculation, heterogeneity, vascularization or combinations thereof.