US 11,861,846 B2
Correcting segmentation of medical images using a statistical analysis of historic corrections
Stefan Vilsmeier, Munich (DE); Andreas Blumhofer, Neubiberg (DE); and Jens Schmaler, Mering (DE)
Assigned to BRAINLAB AG, Munich (DE)
Appl. No. 17/281,493
Filed by Brainlab AG, Munich (DE)
PCT Filed Dec. 20, 2019, PCT No. PCT/EP2019/086789
§ 371(c)(1), (2) Date Mar. 30, 2021,
PCT Pub. No. WO2021/121631, PCT Pub. Date Jun. 24, 2021.
Prior Publication US 2022/0122266 A1, Apr. 21, 2022
Int. Cl. G06T 7/143 (2017.01); G06T 7/174 (2017.01); G06T 7/00 (2017.01); G06T 7/11 (2017.01); G06N 3/08 (2023.01); G06N 20/20 (2019.01)
CPC G06T 7/143 (2017.01) [G06T 7/0012 (2013.01); G06T 7/174 (2017.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/20092 (2013.01); G06T 2207/20128 (2013.01); G06T 2207/30004 (2013.01)] 16 Claims
OG exemplary drawing
 
1. A computer-implemented method of determining corrections for correcting segmentation of medical image data, which includes a computer-implemented method of determining distributions of corrections for correcting the segmentation of medical image data comprising:
acquiring initial segmented patient image data which describes an initial segmentation of digital medical images of an anatomical body part of a first plurality of patients;
acquiring segmentation correction data which describes a correction of the initial segmentation for each patient of the first plurality of patients;
acquiring atlas data which describes an image-based model of the anatomical body part;
determining correction transformation data based on the segmentation correction data and the atlas data, wherein the correction transformation data describes a transformation for transforming the corrections into a reference system used for describing positions in the image-based model;
determining transformed correction data based on the segmentation correction data and the correction transformation data by applying the transformation to the corrections to determine transformed corrections;
determining combined correction data based on the transformed correction data, wherein the combined correction data describes the results of a statistical analysis of the corrections;
wherein the computer-implemented method of determining corrections for correcting the segmentation of medical image data further comprises steps in which:
segmented individual patient image data is acquired which describes a segmentation of the anatomical body part of the patient in a digital individual medical image;
correction re-transformation data is determined based on the atlas data and the individual patient image data, wherein the correction re-transformation data describes a transformation for transforming the results of the statistical analysis of the corrections into the reference system used for describing positions in the digital individual medical image;
re-transformed correction data is determined based on the combined correction data and the correction re-transformation data; and
corrected segmented patient image data is determined based on the individual patient image data and the re-transformed correction data, wherein the corrected segmented patient image data describes a result of applying the corrections to the segmentation of the anatomical body part of the patient in the digital individual medical image.