Siemens Healthcare Gmbh

Siemens Healthineers Ag

Xavier Battle

Thomas Flohr

Sebastian Schmidt

Bernhard Schmidt

Grzegorz Soza

Carsten Thierfelder

Philipp Hoelzer

Rainer Grimmer

Yufan Zhao

A method is for classifying an examination object by way of recordings. In an embodiment, the method includes capturing at least one optical recording of the examination object; determining and quantifying a number of defined characteristics of the examination object based upon an analysis of the optical recordings with the aid of a machine learning method; and affecting the classification of the examination object in respect of a classification criterion, based upon the quantified characteristics with the aid of a machine learning method. Also described are a classification entity and a medical imaging modality.

Classification by means of recordings

A method includes receiving an image data set of an examination volume including a tumor. A tumor region is segmented in the image data set. Furthermore, a texture distribution of the tumor region is determined, the texture distribution in each case assigning a texture parameter to image points in the tumor region, and each of the texture parameters being based on a spatial distribution of first intensity values of the image data set. Furthermore, a biopsy position within the tumor region is determined by applying an optimized position-determining algorithm to the texture distribution, the optimized position-determining algorithm being based on training texture distributions and first training positions, and one of the first training positions being assigned to each of the training texture distributions. In embodiments, the use of an optimized position-determining algorithm enables all relevant influencing variables for the determination of the biopsy position to be taken into account.

Determining a biopsy position

Growing community of inventors

Forchheim, Germany

Xavier Battle