Back to results
US 2020/0051245 A1Published application
Bone suppression for chest radiographs using deep learning
AssigneeCarestream Health, Inc.
InventorsZhimin HUO, Hui ZHAO
Life of this patent
Estimating the term…
Abstract
A system and method for generating a rib suppressed radiographic image using deep learning computation. The method includes using a convolutional neural network module trained with pairs of a chest x-ray image and its counterpart bone suppressed image. The bone suppressed image is obtained using a bone suppression algorithm applied to the chest x-ray image. The convolutional neural network module is then applied to a chest x-ray image or the bone suppressed image to generate an enhanced bone suppressed image.
Claims7
A system comprising:
- a processor programmed to receive a collection of radiographic image pairs that include a plurality of previously captured radiographic images and a corresponding plurality of bone-suppressed radiographic images, wherein the bone-suppressed radiographic image in each pair was generated by applying a bone suppression algorithm on the previously captured radiographic image in said each pair;
- and
- a deep learning module, wherein the processor is further programmed to train the deep learning module using the collection of radiographic image pairs in a repetitive deep learning technique to produce a trained deep learning module,
- wherein the processor is configured to apply the trained deep learning module to the previously captured current radiographic images to generate corresponding enhanced bone-suppressed radiographic images.
1 more element
A system, comprising:
- an x-ray imaging system to capture a current radiographic image;
- a deep learning module trained on a plurality of previously captured radiographic images and a corresponding plurality of bone-suppressed radiographic images generated from the plurality of previously captured radiographic images;
- and
- a processor configured to apply the trained deep learning module to the captured current radiographic image to generate an enhanced bone-suppressed radiographic image.
1 more element
A computer implemented method, the method comprising:
- acquiring a digital radiographic image;
- applying a bone suppression algorithm to the acquired radiographic image to generate a bone suppressed radiographic image;
- providing a convolutional neural network module trained using a plurality of radiographic training images;
- applying the convolutional neural network module to the bone suppressed radiographic image to generate an enhanced bone suppressed radiographic image;
- and
- displaying, storing, or transmitting the enhanced bone suppressed radiographic image.
3 more elements
Dependencies are inferred from the claim text.