Siemens Healthineers International Ag

Varian Medical Systems International Ag

Varian Medical Systems, Inc.

Tomasz Morgas

Benjamin M Haas

Thomas Coradi

Marco Lessard

Tobias Gass

Jonas Honegger

Christopher Boylan

Pascal Paysan

Angelo Genghi

Joao Neta

Pawel Zak

Yarema Mazuryk

Systems and method for automatically generating structures, such as target volumes, in a treatment image using structure-guided deformation to propagate the structures from a planning image onto the subsequently acquired treatment image.

Systems, methods and devices for automated target volume generation

Systems and methods for augmenting a training data set with annotated pseudo images for training machine learning models. The pseudo images are generated from corresponding images of the training data set and provide a realistic model of the interaction of image generating signals with the patient, while also providing a realistic patient model. The pseudo images are of a target imaging modality, which is different than the imaging modality of the training data set, and are generated using algorithms that account for artifacts of the target imaging modality. The pseudo images may include therein the contours and/or features of the anatomical structures contained in corresponding medical images of the training data set. The trained models can be used to generate contours in medical images of a patient of the target imaging modality or to predict an anatomical condition that may be indicative of a disease.

Systems and methods for pseudo image data augmentation for training machine learning models

Systems and methods for implementing an adaptive therapy workflow that minimizes time needed to create a session patient model, select an appropriate plan for the treatment session, and treat the patient.

Streamlined, guided on-couch adaptive workflow

Techniques for the mapping, selection and import of patient medical objects can include receiving metadata of a plurality of patient medical objects from one or more data sources. Metadata icons can be generated for the received metadata of the plurality of patient medical objects. The metadata icons can be filtered based on one or more received criteria. A patient map including the filtered metadata icons can be generated. In addition, the selection of one or more metadata icons in the patient map can be received and used to determine one or more selected patient medical objects. The selected patient medical objects can thereafter be imported from the one or more data sources.

Patient object mapping techniques

To overcome the difficulties inherent in conventional treatment planning approaches, new techniques are described herein for providing an intuitive user interface for automatic structure derivation in patient modeling. In an embodiment, a graphical user interface is provided that provides a list of structures of a specified region. The interface uses medical terminology instead of mathematical one. In one or more embodiments, the list of structures may be a pre-defined list of structures that correspond to that region for the purposes of treatment planning. A user is able to actuate a toggle to include and/or exclude each of the structures separately. In one or more embodiments, the user is also able to actuate a toggle to define a perimeter around each included structure, and further define a margin around the perimeter. The user is also able to specify whether the desired output should include a union or the intersection of all included structures.

Intuitive automation in patient modeling

Growing community of inventors

Henderson, NV, United States of America

Tomasz Morgas