公开(公告)号：EP4202468A1

公开(公告)日：2023-06-28

申请号：EP21217639.0

申请日：2021-12-23

申请人： Orbem GmbH

发明人： Coello Uribe, Jorge Eduardo ,  Kudielka, Guido ,  Gómez Damián, Pedro Agustín ,  Laparidou, Maria ,  Molina Romero, Miguel

IPC分类号： G01R33/56 ,  A61B5/055 ,  G01R33/561 ,  G06T7/00 ,  G06V10/764 ,  G06N3/02

摘要： The present invention relates to a computer implemented method for identification of at least one predetermined medically relevant feature in undersampled MRI data (300) of a living being of a predefined species with an inference module (200), the method comprising the steps of: a) analysing undersampled MRI data (300) of a living being of the predefined species for identifying at least one predetermined medically relevant feature using a machine learning module (204) that is trained for identifying the at least one predetermined medically relevant feature in living beings of the predefined species from undersampled MRI data (300), and b) classifying the undersampled MRI data (300) of the living being of the predefined species based on the result of the identification of the at least one predetermined medically relevant feature, wherein the undersampled MRI data (300) comprises undersampled raw MRI data, comprising a plurality of time dependent signals for different phases, and/or processed MRI data, obtained from processing undersampled raw MRI data, wherein the method is conducted using an inference module (200), comprising a memory (202) storing the machine learning module (204) and a processor (206) for controlling the inference module (200), wherein the inference module is configured to provide the undersampled MRI data (300) as an input to the machine learning module (204), to analyse the undersampled MRI data (300) using the machine learning module (204) and to classify the undersampled MRI data (300), and wherein the machine learning module (204) is trained for identifying the at least one predetermined medically relevant feature in living beings of the predefined species from undersampled MRI data (300) using a training set (302) comprising undersampled MRI data (300) of different training samples of the predefined species, wherein for each predetermined medically relevant feature a fraction of the training samples comprises the predetermined medically relevant feature and a fraction of the training samples does not comprise the predetermined medically relevant feature.

公开(公告)号：EP4202427A1

公开(公告)日：2023-06-28

申请号：EP21217638.2

申请日：2021-12-23

申请人： Orbem GmbH

发明人： Coello Uribe, Jorge Eduardo ,  Kudielka, Guido ,  Gómez Damián, Pedro Agustín ,  Laparidou, Maria ,  Molina Romero, Miguel

IPC分类号： G01N24/08 ,  G01R33/56 ,  G01R33/561 ,  G06T7/00 ,  B07C5/344 ,  G01N33/08 ,  G01R33/483

摘要： Method for automated non-invasive identification of a predetermined feature in a multitude of industrial samples (102) of a predefined sample type, the method comprising the steps of: a) conveying an industrial sample (102) of the predefined sample type into an MRI scanner (106), b) recording in an MRI measurement for at least one slice or at least a partial volume of the industrial sample undersampled MRI data (300), comprising: - undersampled raw MRI data, comprising a multitude of time dependent signals for different phases, and/or - processed MRI data, obtained from processing undersampled raw MRI data, and c) analysing the undersampled MRI data (300) with an inference module (200) for identifying a predetermined feature of the industrial sample (102) using a machine learning module (204) that is trained for identifying the predetermined feature in industrial samples (102) of the predefined sample type from undersampled MRI data (300), wherein the inference module (200) comprises a memory (202) storing the machine learning module (204) and a processor (206) for controlling the inference module (200), wherein the inference module (200) is configured to provide the undersampled MRI data (300) as an input to the machine learning module (200) and to analyse the undersampled MRI data (300) using the machine learning module (204), wherein the machine learning module (204) is trained for identifying the predetermined feature in industrial samples (102) of the predefined sample type using a training set (302) comprising undersampled MRI data (300) of different training samples of the predefined sample type, wherein a fraction of the training samples comprises the predetermined feature and a fraction of the training samples does not comprise the predetermined feature.