{
  "patent_number": "US 11580646",
  "country": "US",
  "title": "Improving Medical Image Segmentation with AI and Fake Data",
  "original_title": "Medical image segmentation method based on U-Net",
  "summary": "This patent describes a method to make AI better at finding specific things in medical images, like tumors, by using computer-generated fake images to train the AI and a special network design.",
  "what_it_does": "This patent details a method for more accurately segmenting, or outlining, specific areas in medical images using a type of artificial intelligence called a U-Net. First, it takes existing medical images and their manual outlines (called 'real segmentation maps') and feeds them into a Generative Adversarial Network (GAN). This GAN creates new, realistic 'composite images' that look like real medical images but are computer-generated, helping to expand the training data (claim 1, step 3). This expanded dataset is then used to train an 'improved multi-feature fusion segmentation network,' which is a modified U-Net (claim 1, step 5). A key improvement is the addition of a 'Dilated Convolution Module' between the network's shallow and deep feature connections, which helps the network better combine fine details with broader context, making it more adaptable to different target sizes and improving accuracy (claim 1, step 5). Finally, this trained network can accurately segment new medical images, for example, precisely outlining a tumor in an MRI scan.",
  "what_it_does_not_cover": [
    "Does not cover medical image segmentation methods that do not use a Generative Adversarial Network (GAN) for data enhancement.",
    "Does not cover U-Net based segmentation networks that lack a Dilated Convolution Module in their skip connections.",
    "Does not cover image segmentation tasks for non-medical images, such as segmenting objects in photographs or satellite imagery.",
    "Does not cover medical image segmentation techniques that do not rely on a U-Net or a multi-feature fusion segmentation network architecture.",
    "Does not cover methods that do not use a Dice loss function for training the segmentation network, as specified in claim 4."
  ],
  "filed": "2022-01-05",
  "granted": "2023-02-14",
  "expires": "2042-01-05",
  "status": "active",
  "holder": "Nanjing University of Posts and Telecommunications",
  "holder_url": "https://patentbrief.org/company/nanjing-university-of-posts-and-telecommunications",
  "inventors": [
    {
      "name": "Weidan YAN",
      "url": "https://patentbrief.org/inventor/weidan-yan"
    },
    {
      "name": "Dengyin ZHANG",
      "url": "https://patentbrief.org/inventor/dengyin-zhang"
    },
    {
      "name": "Rong Zhao",
      "url": "https://patentbrief.org/inventor/rong-zhao"
    }
  ],
  "times_cited": 0,
  "tags": [
    "ai_ml",
    "biotech",
    "software",
    "medical_devices",
    "telecommunications"
  ],
  "abstract": "A medical image segmentation method based on a U-Net, including: sending real segmentation image and original image to a generative adversarial network for data enhancement to generate a composite image with a label; then putting the composite image into original data set to obtain an expanded data set, and sending the expanded data set to improved multi-feature fusion segmentation network for training. A Dilated Convolution Module is added between the shallow and deep feature skip connections of the segmentation network to obtain receptive fields with different sizes, which enhances the fusion of detail information and deep semantics, improves the adaptability to the size of the segmentation target, and improves the medical image segmentation accuracy. The over-fitting problem that occurs when training the segmentation network is alleviated by using the expanded data set of the generative adversarial network.",
  "url": "https://patentbrief.org/patent/us/11580646/medical-image-segmentation-method-based-on-u-net",
  "markdown_url": "https://patentbrief.org/patent/us/11580646/medical-image-segmentation-method-based-on-u-net/md",
  "google_patents_url": "https://patents.google.com/patent/US11580646",
  "relatedPatents": [
    {
      "patentNumber": "11756161",
      "countryCode": "US",
      "title": "AI Method for Sharpening Low-Dose PET Scans with Multi-Task Learning",
      "url": "https://patentbrief.org/patent/us/11756161/method-and-system-for-generating-multi-task-learning-type-generative-adversarial"
    },
    {
      "patentNumber": "11422217",
      "countryCode": "US",
      "title": "How AI Reconstructs Clearer MRI Scans Using Progressive Networks",
      "url": "https://patentbrief.org/patent/us/11422217/progressive-generative-adversarial-network-in-medical-image-reconstruction"
    },
    {
      "patentNumber": "12154036",
      "countryCode": "US",
      "title": "How an AI Learns to Recognize Objects by Generating Its Own Examples",
      "url": "https://patentbrief.org/patent/us/12154036/enhanced-generative-adversarial-network-and-target-sample-recognition-method"
    },
    {
      "patentNumber": "12141700",
      "countryCode": "US",
      "title": "How AI Generates Images Based on Style and Content Cues",
      "url": "https://patentbrief.org/patent/us/12141700/generative-adversarial-network-for-generating-images"
    },
    {
      "patentNumber": "20230297446",
      "countryCode": "US",
      "title": "How to Train AI Models with Fake Data Using Generative Networks",
      "url": "https://patentbrief.org/patent/us/20230297446/data-model-generation-using-generative-adversarial-networks"
    }
  ]
}