Hui Ding

US Patent:

20210110135, Apr 15, 2021

Filed:

Nov 24, 2020

Appl. No.:

17/102843

Inventors:

- Erlangen, DE
Mingqing Chen - Plainsboro NJ, US
Hui Ding - College Park MD, US
Bogdan Georgescu - Princeton NJ, US
Mehmet Akif Gulsun - Princeton NJ, US
Tae Soo Kim - Baltimore MD, US
Atilla Peter Kiraly - San Jose CA, US
Xiaoguang Lu - West Windsor NJ, US
Puneet Sharma - Princeton Junction NJ, US
Shanhui Sun - Lexington MA, US
Daguang Xu - Princeton NJ, US
Zhoubing Xu - Plainsboro NJ, US
Yefeng Zheng - Princeton Junction NJ, US

International Classification:

G06K 9/00
G06K 9/46
G06N 3/04
G06N 3/08
G06T 7/11

Abstract:

Methods and systems for artificial intelligence based medical image segmentation are disclosed. In a method for autonomous artificial intelligence based medical image segmentation, a medical image of a patient is received. A current segmentation context is automatically determined based on the medical image and at least one segmentation algorithm is automatically selected from a plurality of segmentation algorithms based on the current segmentation context. A target anatomical structure is segmented in the medical image using the selected at least one segmentation algorithm.

US Patent:

20190205606, Jul 4, 2019

Filed:

Jul 19, 2017

Appl. No.:

16/094900

Inventors:

- Erlangen, DE
Mingqing Chen - Plainsboro NJ, US
Hui Ding - College Park MD, US
Bogdan Georgescu - Plainsboro NJ, US
Mehmet Akif Gulsun - Princeton NJ, US
Tae Soo Kim - Baltimore MD, US
Atilla Peter Kiraly - San Jose CA, US
Xiaoguang Lu - West Windsor NJ, US
Puneet Sharma - Princeton Junction NJ, US
Shanhui Sun - Princeton NJ, US
Daguang Xu - Princeton NJ, US
Zhoubing Xu - Plainsboro NJ, US
Yefeng Zheng - Princeton Junction NJ, US

International Classification:

G06K 9/00
G06T 7/11
G06N 3/08
G06N 3/04
G06K 9/46

Abstract:

Methods and systems for artificial intelligence based medical image segmentation are disclosed. In a method for autonomous artificial intelligence based medical image segmentation, a medical image of a patient is received. A current segmentation context is automatically determined based on the medical image and at least one segmentation algorithm is automatically selected from a plurality of segmentation algorithms based on the current segmentation context. A target anatomical structure is segmented in the medical image using the selected at least one segmentation algorithm.