Image segmentation techniques

摘要

Methods for image segmentation are provided herein. A method includes creating an anatomical model from training data comprising one or more imaging modalities, generating one or more simulated images in a target modality based on the anatomical model and one or more principles of physics pertaining to image contrast generation, and comparing the one or more simulated images to an unlabeled input image of a given imaging modality to determine a simulated image of the one or more simulated images to represent the unlabeled input image.

主权项

1. A method comprising:
creating a statistical anatomical model from training data comprising one or more source imaging modalities, wherein the training data comprises multiple anatomical images derived from a population of multiple individuals, wherein each of the multiple anatomical images contains one or more annotations, and wherein said creating comprises:
representing each of the annotations across the multiple anatomical images as a vector of a numerical value; andcalculating an average vector across all of the annotations; generating one or more simulated images based on the statistical anatomical model and one or more principles of physics pertaining to image contrast generation; and comparing the one or more simulated images to an unlabeled input image of a given imaging modality to determine a simulated image of the one or more simulated images to represent the unlabeled input image; wherein the steps are carried out by at least one computing device.