GE HealthCare Technologies has filed a patent for a method to determine disease recurrence in patients. The method involves generating medical images of an organ, determining recurrence probabilities from these images, and using a Bayesian network to determine disease recurrence based on these probabilities and clinicopathological data. GlobalData’s report on GE HealthCare Technologies gives a 360-degree view of the company including its patenting strategy. Buy the report here.
According to GlobalData’s company profile on GE HealthCare Technologies, Nucleoside chemical synthesis was a key innovation area identified from patents. GE HealthCare Technologies's grant share as of September 2023 was 44%. Grant share is based on the ratio of number of grants to total number of patents.
Method for determining disease recurrence using medical images and bayesian network
A recently filed patent (Publication Number: US20230317293A1) describes a method for determining the recurrence of a disease in a patient using a Bayesian network. The method involves generating multiple medical images of the patient's organ, determining recurrence probabilities from these images, and using clinicopathological data to determine the disease recurrence.
The patent claims that the plurality of medical images can include various types such as X-ray images, H&E biopsy sample images, molecular images, PET scans images, ultrasound images, MRI scan images, or combinations thereof. This allows for a comprehensive assessment of the patient's condition.
The recurrence probabilities include a first, second, and third recurrence probability. The first recurrence probability is determined from H&E biopsy sample images. The method involves extracting fixed image patches from these samples and mapping them to an initial latent space. The latent space is further refined using a generative adversarial network (GAN) model that captures features of aggressive cancers. Finally, a deep learning (DL) network is used to predict the first recurrence probability based on the refined latent space.
The second recurrence probability is determined from routine mammogram images of the patient. The method involves extracting and analyzing radiomics features from the invasive edge surrounding the disease observed in these images.
The third recurrence probability is determined based on in situ imaging on a small set of tissue images of the patient. This provides additional information for a more accurate assessment of disease recurrence.
The clinicopathological data of the patient, including age, size, location, laterality, and lymph node positivity of the disease, are also considered in determining the recurrence probabilities. These values represent nodes in the Bayesian network, and the network determines the disease recurrence based on the node probability values and conditional probabilities between the nodes.
The patent also describes a system that implements this method. The system includes a memory, a display device, and a processor. The processor is configured to generate medical images, determine recurrence probabilities, and determine disease recurrence using a Bayesian network.
In summary, this patent presents a method and system for determining disease recurrence in a patient using a combination of medical images, clinicopathological data, and Bayesian network analysis. The method utilizes various types of medical images and employs advanced techniques such as deep learning and generative adversarial networks to improve the accuracy of recurrence predictions.