Neural network for generating synthetic medical images

Abstract

Systems, computer-implemented methods, and computer readable media for generating a synthetic image of an anatomical portion based on an origin image of the anatomical portion acquired by an imaging device using a first imaging modality are disclosed. These systems may be configured to receive the origin image of the anatomical portion acquired by the imaging device using the first imaging modality, receive a convolutional neural network model trained for predicting the synthetic image based on the origin image, and convert the origin image to the synthetic image through the convolutional neural network model. The synthetic image may resemble an imaging of the anatomical portion using a second imaging modality differing from the first imaging modality.

Description

[0001] Cross References to Related Applications [0002] This application claims priority to U.S. Provisional Patent Application No. 62 / 384,171, filed September 6, 2016, and U.S. Provisional Patent Application No. 62 / 408,676, filed October 14, 2016, the entire disclosure of the above applications Incorporated herein by reference. technical field [0003] The present disclosure generally relates to the use of machine learning algorithms to generate composite images for radiation therapy. More specifically, the present disclosure relates to systems and methods for generating computed tomography (CT) images from magnetic resonance imaging (MRI) images using neural networks. Background technique [0004] Traditionally, CT imaging has been used as the main source of image data during the planning of external radiation therapy. CT images provide an accurate representation of patient geometry, and CT values ​​can be directly converted to electron density for radiation dose calcul...

AI Technical Summary

Problems solved by technology

This sliding window approach typically requires significant computational time and resources in order to generate a complete composite CT image

Images