Determining locations in reproductive cellular structures
AssigneesThe General Hospital Corporation, The Brigham and Women's Hospital, Inc.
InventorsHadi Shafiee, Charles Bormann, Manoj Kumar Kanakasabapathy, Prudhvi Thirumalaraju
Life of this patent
Estimating the term…
Abstract
Systems and methods are provided for determining a clinical parameter representing the location of interest within a reproductive cellular structure. An image of the reproductive cellular structure is obtained and provided to a neural network to generate the clinical parameter. The clinical parameter is stored on a non-transitory computer readable medium.
Claims19
A system comprising:
- a processor;
- and
- a non-transitory computer readable medium storing machine executable instructions for assigning a value representing a location of interest within a reproductive cellular structure, the machine executable instructions comprising:
- an imager interface that receives an image of the reproductive cellular structure from an associated imager;
- and
- a neural network that determines, from the image of the reproductive cellular structure, a clinical parameter representing the location of interest within the reproductive cellular structure, the neural network being trained on a set of images, each image labelled with one class of a plurality of classes, with each of the plurality of classes representing one section of a plurality of sections comprising the reproductive cellular structure;
- and
- wherein the clinical parameter is a categorical parameter representing the section of the plurality of sections that contains the location of interest within the reproductive cellular structure as one of the plurality of classes, the clinical parameter being stored at the non-transitory computer readable medium.
A method for determining a clinical parameter representing a location of interest within a reproductive cellular structure, the method comprising:
- obtaining an image of the reproductive cellular structure;
- and
- providing the image of the reproductive cellular structure to a neural network to generate the clinical parameter, the neural network being trained on a set of images, each image labelled with one class of a plurality of classes, with each of the plurality of classes representing one section of a plurality of sections comprising the reproductive cellular structure and the clinical parameter representing being a categorical parameter representing the section of the plurality of sections that contains the location of interest within the reproductive cellular structure as one of the plurality of classes;
- and
- storing the clinical parameter on a non-transitory computer readable medium.
A method for planning an assisted fertility procedure, the method comprising:
- obtaining an image of a reproductive cellular structure;
- and
- providing the image of the reproductive cellular structure to a neural network to generate a clinical parameter representing a location of interest within the reproductive cellular structure, the neural network being trained on a set of images, each image labelled with one class of a plurality of classes, with each of the plurality of classes representing one section a plurality of sections comprising of the reproductive cellular structure and the clinical parameter being a categorical parameter representing the section of the plurality of sections that contains the location of interest within the reproductive cellular structure as one of the plurality of classes;
- and
- performing a procedure on the reproductive cellular structure at a location determined according to the clinical parameter.
Dependencies are inferred from the claim text.