US 2016/0104280 A1Published application

Linking breast lesion locations across imaging studies

AssigneeKoninklijke Philips N.V.

InventorsTHOMAS BUELOW, MARTIN BERGTHOLDT, RAFAEL WIEMKER, KIRSTEN REGINA MEETZ, JOERG SABCZYNSKI, DOMINIK BERJAMIN KUTRA

Life of this patent

Estimating the term…

patentgrep

Loading patent…

Abstract

The present invention provides for means for linking breast lesion locations across imaging studies. In particular, a generic three-dimensional representation of the female breast is used. Automatic translation of the lesion location into standard clinical terminology and aligning the breast model with individual patient images is comprised. Moreover, a mechanism for linking image locations showing a lesion to a location in the breast model is presented. If desired, a region of interest can be calculated by a region of interest definition module that predicts a region of interest of a known lesion in terms of the breast model representation in a new imaging study.

Claims15

Dependent claims

A breast model based method for linking breast lesion locations, the method comprising the steps of

receiving first image data of a first image of a patient's breast (S1),
providing coordinates of a lesion location in the first image of the patient's breast (S2);
providing a predefined generic geometric breast model which is a representation of a female breast (S3);
wherein the predefined generic geometric breast model is based on a normalized breast coordinate system;
mapping the first image data with the predefined generic geometric breast model (S4);
and
linking the lesion location of the lesion in the first image with a corresponding location in the predefined generic geometric breast model thereby storing linking data (S5);
receiving second image data of a second image of a patient's breast (S6);
mapping the second image data with the predefined generic geometric breast model (S7);
and
automatically locating the lesion location in the second image based on the stored linking data (S8a).

8 more elements

Dependencies are inferred from the claim text.