US 12,260,294 B2
Generative adversarial network medical image generation for training of a classifier
Ali Madani, Oakland, CA (US); Mehdi Moradi, San Jose, CA (US); and Tanveer F. Syeda-Mahmood, Cupertino, CA (US)
Assigned to International Business Machines Corporation, Armonk, NY (US)
Filed by Merative U.S L.P., Ann Arbor, MI (US)
Filed on Jan. 30, 2020, as Appl. No. 16/777,159.
Application 16/777,159 is a continuation of application No. 15/850,007, filed on Dec. 21, 2017, granted, now 10,592,779.
Prior Publication US 2020/0167608 A1, May 28, 2020
Int. Cl. G16H 30/40 (2018.01); A61B 6/00 (2006.01); G06K 9/62 (2022.01); G06N 3/04 (2006.01); G06N 3/08 (2006.01); G06N 3/082 (2023.01); G06N 5/02 (2006.01); G06N 5/022 (2023.01); G06N 20/00 (2019.01); G06T 7/00 (2017.01); G16H 30/20 (2018.01)
CPC G06K 9/6259 (2013.01) [A61B 6/5217 (2013.01); G06K 9/6267 (2013.01); G06N 3/0454 (2013.01); G06N 3/0472 (2013.01); G06N 3/0481 (2013.01); G06N 3/082 (2013.01); G06N 5/022 (2013.01); G06N 20/00 (2019.01); G06T 7/0014 (2013.01); G16H 30/20 (2018.01); G16H 30/40 (2018.01); G06T 2207/10116 (2013.01); G06T 2207/30048 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method, in a data processing system comprising a processor and a memory, the memory comprising instructions that are executed by the processor to configure the processor to implement a machine learning training model, the method comprising:
training, by the machine learning training model, an image generator of a generative adversarial network (GAN) to generate medical images approximating actual medical images;
augmenting, by the machine learning training model, a set of training medical images to include one or more generated medical images generated by the image generator of the GAN;
training, by the machine learning training model, a machine learning model based on the augmented set of training medical images to identify anomalies in medical images; and
applying the trained machine learning model to new medical image inputs to classify the medical images as having an anomaly or not, wherein training the machine learning model comprises training a discriminator of the GAN based on training data, input to the discriminator, comprising actual labeled medical image data, actual unlabeled medical image data, and generated medical image data generated by the image generator of the GAN.