Title:
AI-BASED ATLAS MAPPING SLICE LOCALIZER FOR DEEP LEARNING AUTOSEGMENTATION
Document Type and Number:
WIPO Patent Application WO/2023/055556
Kind Code:
A3
Abstract:
Embodiments described herein provide a method (300) for generating training data for Al based atlas mapping slice localization, and a system and method (400) for using the training data to train a deep learning network. Training data development maps each slice of an input medical image to a position in a full body reference atlas (510) along the longitudinal body axis. The method constructs a landmarking table (540) of 2D slices indicating known anatomic landmarks of a reference subject, and interpolated slices. A final step for obtaining training data uses regression analysis techniques to create a vector of longitudinal axis coordinates of all slices from the input image. The training data is used to train a deep learning model to create an Al-based atlas mapping slice localizer model. The trained Al-based atlas mapping slice localizer model (720) can be applied to generate mapping inputs to autosegmentation models to improve efficiency and reliability of contouring.
Inventors:
GENGHI ANGELO (US)
SIROKI-GALAMBOS ANNA (US)
CORADI THOMAS (US)
FARTARIA MARIO (US)
FLUCKIGER SIMON (US)
HAAS BENJAMIN (US)
FRANCO FERNANDO (US)
SIROKI-GALAMBOS ANNA (US)
CORADI THOMAS (US)
FARTARIA MARIO (US)
FLUCKIGER SIMON (US)
HAAS BENJAMIN (US)
FRANCO FERNANDO (US)
Application Number:
PCT/US2022/043202
Publication Date:
May 11, 2023
Filing Date:
September 12, 2022
Export Citation:
Assignee:
VARIAN MED SYS INC (US)
International Classes:
G06T7/10
Foreign References:
| US20210125707A1 | 2021-04-29 | |||
| US20190251694A1 | 2019-08-15 | |||
| US9489733B2 | 2016-11-08 |
Attorney, Agent or Firm:
SOPHIR, Eric et al. (US)
Download PDF: