General Electric Company

Image Diagnost International Gmbh

Marco Blumenthal

Peter Heinlein

Wilfried Schneider

Serge Muller

Razvan Iordache

Sylvain Bernard

Giovanni John Jacques Palma

Marcelo Blois Ribeiro

Axel Crasemann

Anca Dima

Eudemberg Fonseca Silva

Felipe Santos De Andrade

Serge Louis Wilfrid Mueller

Dario Augusto Borges Oliveira

Camila Patricia Bazilio Nunes

Marina Lundgren De Almeida Magalhaes

Jörg Teubl

Apparatus, systems, and methods for computer-aided detection are disclosed and described. An example apparatus includes at least one processor and a memory. The example memory includes instructions which, when executed, cause the at least one processor to at least: associate first patient data and first outcome data according to a set of association rules; train a processing model using machine learning and the associated first patient data and first outcome data; generate a computer-aided decision processing algorithm using the processing model; update the computer-aided decision processing algorithm based on at least one of second patient data or second outcome data received from a cloud infrastructure; and deploy the updated computer-aided decision processing algorithm to be applied to third patient data.

Methods and apparatus for self-learning clinical decision support

The present approach relates to providing image quality feedback to personnel (e.g., a technician) acquiring non-invasive images in real-time or near real-time. By way of example, the proposed approach may automatically assess the quality of images in real-time by evaluating the images for the presence or absence of non-conformities using processor-implemented, rule-based algorithms running partly or completely in parallel to one another. The proposed approach improves the image analysis pipeline by efficiently providing notification of and/or discarding low-quality or unsuitable images or exams after they are taken, such as in within seconds or minutes.

Image analysis for assessing image data

A method and apparatus for the improved display of digital mammographic images, which were measured in the context of a mammographic imaging system and displayed on a workstation monitor. The mammogram consists of a plurality of pixels with each pixel having a pixel value assigned thereto. The pixel values of all pixels of the mammogram lie within a pre-determined first range of values and the pixel values of pixels of a subsection of the mammogram lie within a second range of values, which represents a subset of the first range of values. A mammogram having a subsection with increased contrast, such that the second range of pixel values of the pixels in the subsection are spread by a spreading function, whereby the amount of the spreading function changes over the subsection. In this way, an improved display is created, by means of those representations of the mammogram regarding their contrast in subsections being optimized, at the same time the representation for a user is improved without artifacts.

Method and apparatus for improved display of digital mammographic images

A method and apparatus for processing digital mammographic images. The method and apparatus providing comparable mammographic images regardless of the imaging device generating the raw mammographic images. The processed mammographic images may be displayed with optimal global and local contrast, enhanced sharpness, and without the need to apply window level settings or data from lookup tables. A second mammographic image is generated out of a processed first mammographic image in such a way that the projected object, the breast, is more perceptible and obvious for a physician or other medical professional reviewing the mammographic image.

Method and apparatus for processing digital mammographic images with parallel multi-scale decomposition and recombining in an optimized multi-scale reconstruction

A device for the computer-assisted analysis of mammograms. Said device comprises means for detecting a contour line that surrounds an object area of the mammogram, which is defined by an object. The device also comprises a means for positioning and scaling the mammogram. The device is configured to determine the contour line of the object area of the mammogram and to automatically position and scale the mammogram based on the contour line. A method for the computer-assisted analysis of mammograms is also disclosed. The disclosed device and method make it easier for a doctor to comparatively analyze and diagnose mammograms.

Device and method for the computer-assisted analysis of mammograms

A method for processing findings entered in a mammogram. A digital mammogram is displayed via an evaluation device. Via an input device the findings are entered directly into the displayed mammogram and are automatically transferred from the mammogram into a findings input mask. To transfer the findings from the mammogram into the findings input mask, a contour line of an object area surrounding an object of the mammogram is determined. An object area of the mammogram is divided into two partial areas. Each partial area is imaged onto an allocated mask region of the findings input mask. The entered findings are allocated to one of the partial areas and are transferred into the findings input mask with reference to the allocated partial area. In this manner, a location of findings entered in a mammogram relative to the nipple can reliably be determined and transferred into a findings input mask.

Method for processing findings entered in a mammogram

Growing community of inventors

Jena, Germany

Marco Blumenthal