Multi-modal segmentatin of image data

US9697600B2 · kind B2 · utility

Assignee

• Brainlab AG · DE

Inventors

• Jens Keuchel · Poing, DE
• Daniel Modrow · Munich, DE

Key dates

• Filing date: Jul 26, 2013
• Grant date: Jul 4, 2017
• Expiry date: Jul 26, 2033

Classification

• Technology area (CPC G): Physics
• CPC primary: G06V2201/03
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

The invention relates to a medical data processing method of segmenting image features in medical images generated with different imaging modalities, wherein the image features represent a corresponding anatomical structure in each of the medical images, the method being constituted to be executed by a computer and comprising the following steps: a) acquiring (SI) first modality medical image data describing a first modality medical image containing a first modality image representation of the anatomical structure; b) acquiring (SI) second modality medical image data describing a second modality medical image containing a second modality image representation of the anatomical structure; c) determining, based on the first modality medical image data and the second modality medical image data, modality transformation data describing a mapping transformation between the image information in the first modality image data and the image information in the second modality image data; d) acquiring color value data describing a color value of the image elements in the first modality medical image and in the second modality medical image; e) determining (S2-S7), based on the first modality m…