Christian Buerger,Irina Waechter-Stehle,Frank Michael Weber
申请号：
US15314327
公开号：
US20180235577A1
申请日:
2015.06.09
申请国别(地区):
US
年份:
2018
代理人:
摘要：
The present invention relates to a medical image processing device (10), comprising:—a receiving unit (60) for receiving a first and a second medical image (72, 74) of an anatomical object of interest (84), wherein each of the first and the second medical images (72, 74) comprises a different field of view of the anatomical object of interest (84), and wherein the first medical image and the second medical image (72, 74) show a same or similar anatomical state of the anatomical object of interest (84)；—a registration unit (64) that is configured to determine a transformation from an image space of the second medical image (74) to an image space of the first medical image (72)；—a transformation unit (66) that is configured to transform the second medical image (74) into the image space of the first medical image (72) based on said transformation in order to receive a transformed second medical image (74′)； and—a segmentation unit (68) that is configured to perform an overall segmentation that makes use of both the first medical image (72) and the transformed second medical image (74′) without fusing the first medical image (72) and the transformed second medical image (74′), wherein one and the same segmentation model (92) is simultaneously adapted to both the first medical image (72) and the transformed second medical image (74′) by identifying a first set of feature points (80) of the anatomical object of interest (84) within the first medical image (72), by identifying a second set of feature points (82) of the anatomical object of interest (84) within the transformed second medical image (74′), and by adapting the segmentation model (92) to both the first and the second set of feature points (80, 82).
