US 2020/0265276 A1 · COPD CLASSIFICATION WITH MACHINE-TRAINED ABNORMALITY DETECTION

Abstract

For COPD classification in a medical imaging system, machine learning is used to learn to classify whether a patient has COPD. An image-to-image network deep learns spatial features indicative of various or any type of COPD. The pulmonary function test may be used as the ground truth in training the features and classification from the spatial features. Due to the high availability of pulmonary function test results and corresponding CT scans, there are many training samples. Values from learned features of the image-to-image network are then used to create a spatial distribution of level of COPD, providing information useful for distinguishing between types of COPD without requiring ground truth annotation of spatial distribution of COPD in the training.

Claims20

Dependent claims

A method for chronic obstructive pulmonary disorder (COPD) classification in a medical imaging system, the method comprising:

scanning, by a medical scanner, lungs of a patient, the scanning providing first imaging data representing a multi-dimensional region of the lungs of the patient;
applying, by an image processor, a machine-learned generative network to the first imaging data, the machine-learned generative network trained to output the COPD classification;
generating an activation map from values of features from the machine-learned generative network, the activation map representing a level of COPD by location within the multi-dimensional region;
and
outputting, on a display, an image from the activation map.

2 more elements

Dependencies are inferred from the claim text.

Copd classification with machine-trained abnormality detection

Life of this patent

Copd classification with machine-trained abnormality detection

Life of this patent

Abstract

Claims20