-
公开(公告)号：EP4365824A1
公开(公告)日：2024-05-08
申请号：EP22205477.7
申请日：2022-11-04
CPC分类号： G06T2207/2008120130101 , G06T2207/2008420130101 , G06T9/00 , H04N19/85 , G06T5/70
摘要： Proposed concepts aim to provide schemes, solutions, concepts, designs, methods and systems pertaining to the storage, retrieval and/or communication of medical images. In particular, the medical image is de-noised to generate a (substantially) noise-free medical image. De-noising the medical image to this extent allows for a high compression ratio, and thus space-efficient storage of the medical image. However, typically the level to which medical image is de-noised has to be carefully controlled in order to minimise the chance of introducing errors to the medical image. In the present invention, noise information describing residual noise data removed from the medical image is also stored. This allows for the compressed noise-free medical image to be combined with the noise information at a receiver, restoring any potentially lost information. In this way, a space-efficient means for storing a medical image is provided, which also overcomes problems associated with heavily de-noising the medical image.
-
公开(公告)号：EP4207076A1
公开(公告)日：2023-07-05
申请号：EP22171630.1
申请日：2022-05-04
IPC分类号： G06T11/00
摘要： A method is provided for processing images comprising retrieving measured data for a first image. The method then generates partially filtered data by applying a first filter to the measured data. The first filter is a generic filter. The method then reconstructs the partially filtered data to generate a partially filtered image. The method then generates a partially processed image by applying a first processing routine to the partially filtered image. The method then generates a filtered image by applying a second filter to the partially processed image, where the second filter is a filter selected from a plurality of potential secondary filters. The method then outputs the filtered image. Systems are provided for implementing the claimed method and training methods for neural networks used in the method are provided as well.
-
公开(公告)号：EP4009268A1
公开(公告)日：2022-06-08
申请号：EP21169134.0
申请日：2021-04-19
发明人： SCHNELLBÄCHER, Nikolas David , WUELKER, Christian , BERGNER, Frank , BROWN, Kevin Martin , GRASS, Michael
IPC分类号： G06T5/00
摘要： A mechanism for generating a partially denoised image. A residual noise image, obtained by processing an image using a convolutional neural network, is weighted. The blending or combination of the weighted residual noise image and the (original) image generates the partially denoised image.
-
公开(公告)号：EP3123446B1
公开(公告)日：2020-07-08
申请号：EP15710205.4
申请日：2015-03-18
发明人： KOEHLER, Thomas , THRAN, Axel , BERGNER, Frank , BRENDEL, Bernhard Johannes , BIPPUS, Rolf Dieter
IPC分类号： G06T11/00
-
-
公开(公告)号：EP3076872B1
公开(公告)日：2018-06-13
申请号：EP15715306.5
申请日：2015-04-16
IPC分类号： G06T11/00
CPC分类号： A61B6/025 , A61B5/0064 , A61B6/0414 , A61B6/4042 , A61B6/4241 , A61B6/481 , A61B6/482 , A61B6/502 , A61B6/5205 , A61B6/5247 , A61B6/5258 , G06T11/005 , G06T2211/436
摘要： The present invention relates to a device for tomosynthesis imaging, the device comprising: a mask generator module (101) configured to generate a binary mask based on a geometric three-dimensional model of a scanned object; an image capturing module (102) configured to scan a series of two-dimensional projection images of the object; and an image processing module (103) configured to apply the generated binary mask during a reconstruction of a three-dimensional image volume from the scanned series of two-dimensional projection images and to restrict an extent of the reconstructed image volume to the extent of the geometric model.
-
7.发明授权
公开(公告)号：EP2748798B1
公开(公告)日：2018-04-11
申请号：EP12812393.2
申请日：2012-12-04
IPC分类号： G06T11/00
CPC分类号： G06T5/00 , G06T11/006 , G06T2207/20004 , G06T2211/424
摘要： A processing component (122) processes images based on an iterative reconstruction algorithm with regularization and/or de-noising algorithm. The processing component includes a set point determiner (224) that determines a quality set point (216) between predetermined lower and upper quality bounds (226) based on a quality variable (228) indicative of an image quality of interest. The processing component further includes a comparator (214) that compares, each processing iteration, a quality metric of a current generated image with the quality set point and generates a difference value indicative of a difference between the quality metric and the quality set point. The processing component further includes a regularization factor updater (220) that generates an updated regularization factor for a next processing iteration based on a current value (222) of the regularization factor and at least the quality metric in response to the difference value indicating that the quality metric is outside of a predetermined range about the quality set point.
-
公开(公告)号：EP4396700A1
公开(公告)日：2024-07-10
申请号：EP22768367.9
申请日：2022-08-19
发明人： WUELKER, Christian , SCHNELLBAECHER, Nikolas, David , BERGNER, Frank , BROWN, Kevin, Martin , GRASS, Michael
IPC分类号： G06F18/00 , G06T5/00 , G06V30/164
-
-
公开(公告)号：EP4009269A1
公开(公告)日：2022-06-08
申请号：EP21169563.0
申请日：2021-04-21
发明人： WUELKER, Christian , SCHNELLBÄCHER, Nikolas David , BERGNER, Frank , BROWN, Kevin Martin , GRASS, MIchael
摘要： Proposed are concepts for processing an image with a convolutional neural network, CNN. Such concepts include using an additional set of input channels to a CNN to provide supplementary information that is available in the image domain. Such supplementary information can be used to improve the CNN performance.
-
-
-
-
-
-
-
-
-
搜索结果
49 条记录 (耗时 0.018 秒)
