Simulating abnormalities in medical images with generative adversarial networks

• Main Authors: Golden, Daniel Irving, Sall, Sean Patrick, Lieman-Sifry, Jesse, Norman, Berk Dell, Didonato, Matthew Joseph, Lau, Hok Kan, Axerio-Cilies, John
• Format: Patent
• Language: English
• Published: 26.12.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATIONTECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING ORPROCESSING OF MEDICAL OR HEALTHCARE DATA; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTEDFOR SPECIFIC APPLICATION FIELDS; PHYSICS

Systems and methods for providing a novel framework to simulate the appearance of pathology on patients who otherwise lack that pathology. The systems and methods include a "simulator" that is a generative adversarial network (GAN). Rather than generating images from scratch, the systems and methods discussed herein simulate the addition of diseases-like appearance on existing scans of healthy patients. Focusing on simulating added abnormalities, as opposed to simulating an entire image, significantly reduces the difficulty of training GANs and produces results that more closely resemble actual, unmodified images. In at least some implementations, multiple GANs are used to simulate pathological tissues on scans of healthy patients to artificially increase the amount of available scans with abnormalities to address the issue of data imbalance with rare pathologies.