Koninklijke Philips Corporation N.V.

Heike Carolus

Juergen Weese

Holger Schmitt

Sven Kabus

Tobias Klinder

Yuechen Qian

Rafael Wiemker

Jochen Peters

Jens Von Berg

Stewart Young

Julien Senegas

Alexandra Groth

Rolf Jürgen Weese

Thusitha Dananjaya De Silva Mabotuwana

Matthias Lenga

Marten Bergtholdt

Presented are concepts for obtaining a confidence measure for a machine learning model. One such concept process input data with the machine learning model to generate a primary result. It also generate a plurality of modified instances of the input data and processes the plurality of modified instances of the input data with the machine learning model to generate a respective plurality of secondary results. A confidence measure relating to the primary result is determined based on the secondary results.

Confidence measure for a deployed machine learning model

The present invention relates to the field of medical ultrasound imaging, and in particular to a medical ultrasound image processing device for supporting reproducible acquisition of 2D ultrasound images. A medical ultrasound image processing device () is presented that comprises a first interface () for receiving a first 3D scout ultrasound image () and a first 2D ultrasound image () of a volumetric region; a second interface () for receiving a second 3D scout ultrasound image () of the volumetric region; and a processing unit () arranged to perform the steps of: determining an orientation of an image plane of the first 2D ultrasound image with respect to the first 3D scout ultrasound image (S); registration of the first 3D scout ultrasound image and the second 3D ultrasound scout image in a common coordinate frame (S); determining an orientation of the image plane of the first 2D ultrasound image with respect to said common coordinate frame based on said registration of the first and second 3D scout ultrasound images and the determined orientation of the image plane of the first 2D ultrasound image with respect to the first 3D scout ultrasound image (S); and providing a control signal adapted to control an acquisition of a second 2D ultrasound image of the volumetric region by an ultrasound probe in accordance with the orientation of the image plane of the first 2D ultrasound image of the volumetric region (S), wherein an orientation of an image plane of the second 2D ultrasound image corresponds to the determined orientation of the image plane of the first 2D ultrasound image of the volumetric region, wherein the acquisition of the second 2D ultrasound image by the ultrasound probe is from either a same position as, or a tracked position with respect to, the position of the acquisition of the second 3D scout ultrasound image.

Medical ultrasound image processing device

A radiology workstation () includes a display device (), at least one user input device (), and an electronic data processor. The workstation provides an image rendering component () for rendering a radiological image, and a report data entry component () for entry of a radiology examination report () via the at least one user input device and for display of the radiology examination report during entry. The workstation further provides a dynamic checklist component () for storing a queue () of open checklist items, and for: displaying a checklist comprising open checklist items stored in the queue; dynamically analyzing the radiology examination report during entry to identify a checklist update trigger; updating the queue of open checklist items based on the identified checklist update trigger; and updating the display of the checklist to comprise the open checklist items stored in the updated queue.

Communication system for dynamic checklists to support radiology reporting

There is provided a method and apparatus for adjusting a model of an anatomical structure in a sequence of images of the anatomical structure. The model is placed with respect to the anatomical structure in the sequence of images. A user input is received to adjust the model in a selected image of the sequence, and based on the user input, a part of the model that lies in the selected image and a previously unadjusted part of the model that lies in one or more other images of the sequence is adjusted, whilst fixing in place a previously adjusted part of the model that lies in other images of the sequence.

Method and apparatus for adjusting a model of an anatomical structure

The invention relates to a device for processing CT imaging data, comprising a processing unit, which is configured to receive a plurality of sets of CT imaging data recorded at different imaging positions and at different points in time. Furthermore, the processing device is configured to provide a plurality of auxiliary sets of CT imaging data, each auxiliary set of CT imaging data comprising processed image data allocated to spatial positions inside a respective spatial section of the object space, wherein a given one of the spatial sections contains those spatial positions which are covered by those sets of CT imaging data acquired at a respective one of the imaging positions, and to generate the processed image data for a given spatial position using those of the sets of CT imaging data acquired at the respective one of the imaging positions.

Device and methods for processing computer tomography imaging data

A method generates and uses a correspondence probability map for visualization of two image datasets. The method includes obtaining two image datasets and obtaining an image registration algorithm that includes a correspondence model. The method further includes registering the two image datasets to generate a displacement vector field and generating a correspondence probability map, using the correspondence model, based on the two image datasets. The method further includes using the correspondence probability map to visualize the two image datasets. A computing system () includes a memory device () configured to store instructions, including a visualization module (), and a processor () that executes the instructions, which causes the processor to generate and employ a correspondence probability map for visualization of two image datasets.

Correspondence probability map driven visualization

The present invention relates to a device and method for registration of two images. To increase the accuracy of the registration the device comprises an input unit () for receiving one or more pairs of negative landmarks, which are indicated in the two images, a pair comprising two negative landmarks, one in each image, which structures are not identical and should not be aligned by the registration. Further, a registration unit () is provided for performing a registration of the two images by determining a transformation for transforming at least one of the images for registering it with the other image and determining a spacing measure of the distance between a first landmark in the transformed image and a second landmark in the other image, wherein the transformation is determined such that the spacing measure for a first landmark and a second landmark of at least one pair of negative landmarks is above a first distance threshold, whereby the negative landmarks are taken into account in the registration but are not aligned by the registration.

Device and method for registration of two images

A method includes visually displaying an electronically formatted medical report, wherein the electronically formatted medical report references a set of electronically formatted images, acquiring the set of electronically formatted images, and linking the electronically formatted medical report and the set of electronically formatted images. A computing apparatus (), includes a memory () with at least one computer readable instruction () and a processor () that executes the at least one computer readable instruction. The processor, in response to executing the at least one computer readable instruction, visually displays an electronically formatted medical report, wherein the electronically formatted medical report references a set of electronically formatted images, acquires the set of electronically formatted images, and links the electronically formatted medical report and the set of electronically formatted images.

Picture archiving system with text-image linking based on text recognition

A device () for determining image quality of a radiogram image includes: an acquiring module (), which is configured to acquire the radiogram image; a segmentation module (), which is configured to segment a thoracic bone structure on the acquired radiogram image into segmented thoracic bone structure contours and a tissue structure on the acquired radiogram image into segmented tissue structure contours; and a quality-determination module (), which is configured to determine a image quality coefficient for the acquired radiogram image based on a comparison of a first position of the segmented thoracic bone structure contours with a second position of the segmented tissue structure contours.

Growing community of inventors

Hamburg, Germany

Heike Carolus