-
公开(公告)号:EP4428836A1
公开(公告)日:2024-09-11
申请号:EP23305325.5
申请日:2023-03-10
发明人: OLIVIER, Antoine , RAYNAUD, Caroline , ORASANU, Eliza , LORENZ, Cristian , SCHMIDT-RICHBERG, Alexander , CIOFOLO-VEIT, Cybele , FRANZ, Astrid
IPC分类号: G06V20/62 , G06V10/44 , G06V10/82 , G06V30/10 , G06V10/774
CPC分类号: G06V20/635 , G06V10/454 , G06V10/82 , G06V30/10 , G06V2201/0320220101 , G06V10/774 , G06V10/7753
摘要: A computer-implemented method and system for curating annotated images (101), the method comprising the following steps: receiving an annotated image (101) having at least one annotation; applying a trained neural network (211) to the annotated image (101) and thereby generating an amended image (102) without the at least one annotation; providing the amended image (102).
-
公开(公告)号:EP3514757A1
公开(公告)日:2019-07-24
申请号:EP18152312.7
申请日:2018-01-18
摘要: The invention relates to a medical image data processing system (101) for image segmentation. The medical image data processing system (101) comprises a processor (130) for controlling the medical image data processing system (101), wherein execution of the machine executable instructions by the processor (130) causes the processor (130) to control the image data processing system (101) to:
- receive medical image data (140),
- generate a segmentation of an anatomical structure of interest comprised by the medical image data (140),
- convert the segmentation to a surface mesh representation of the anatomical structure of interest,
- compare the surface mesh representation with the reference surface mesh representation of the anatomical reference structure using spectral matching, wherein one or more spectral embeddings of the two meshes are matched,
- providing an area of topological mismatch of the surface mesh representation with the reference surface mesh representation.-
公开(公告)号:EP3657435A1
公开(公告)日:2020-05-27
申请号:EP18208216.4
申请日:2018-11-26
发明人: ORASANU, Eliza , WENZEL, Fabian
IPC分类号: G06T7/00
摘要: The invention relates to a regions identifying apparatus (1) for identifying regions in an image like a computed tomography image showing a brain. A model providing unit (6) provides a three-dimensional model of a head of a living being, wherein the three-dimensional model includes Alberta Stroke Program Early CT Score (ASPECTS) regions of a brain, and a regions identifying unit (7) identifies ASPECTS regions in the three-dimensional image by applying the three-dimensional model to the three-dimensional image. This allows for an accurate, automatic identification of the ASPECTS regions independently of the orientation of the head in an imaging system, independently of an image slice thickness and also independently of a respective user like a physician. This leads to an improved accuracy of determining the ASPECTS regions which allows for an improved quantification of ischemic changes in the brain after stroke. This in turn also allows for an improved treatment recommendation.
-
-