System and methods for segmentation and assembly of cardiac MRI images
AssigneeDyad Medical, Inc.
InventorsJohn Long, Ronny Shalev
Life of this patent
Estimating the term…
Abstract
A method and system for image segmentation systems and related methods of automatically segmenting cardiac MRI images using deep learning methods. One example method includes inputting MRI volume data from a MRI scanner, segmenting the MRI volume data with a whole volume segmentation analysis module, assembling the segmented MRI volume data into a 3D volume assembly with a 3D volume assembly module, determining the 3D volume assembly for anatomic plausibility with an anatomic plausibility analysis module, and outputting a final segmented 3D volume assembly.
Claims20
A method for segmentation and assembly of cardiac magnetic resonance imaging (MRI) images, the method comprising:
- inputting MRI volume data from a MRI scanner;
- segmenting the MRI volume data with a whole volume segmentation analysis module;
- assembling the segmented MRI volume data into a 3D volume assembly with a 3D volume assembly module;
- determining the 3D volume assembly for anatomic plausibility with an anatomic plausibility analysis module;
- and
- outputting a final segmented 3D volume assembly,
- wherein the 3D volume assembly module further comprises a large component identification module to identify a largest connected component of each class as true segmentation and to zero out other components.
A method for segmentation and assembly of cardiac magnetic resonance imaging (MRI) images, the method comprising:
- inputting MRI volume data from a MRI scanner;
- segmenting the MRI volume data with a whole volume segmentation analysis module;
- assembling the segmented MRI volume data into a 3D volume assembly with a 3D volume assembly module;
- determining the 3D volume assembly for anatomic plausibility with an anatomic plausibility analysis module;
- and
- outputting a final segmented 3D volume assembly,
- wherein the anatomic plausibility analysis module further comprises a slice segmentation module for segmenting the 2D MRI slices of the input MRI volume data determined to not be anatomically plausible.
A method for segmentation and assembly of cardiac magnetic resonance imaging (MRI) images, the method comprising:
- inputting MRI volume data from a MRI scanner;
- segmenting the MRI volume data with a whole volume segmentation analysis module;
- assembling the segmented MRI volume data into a 3D volume assembly with a 3D volume assembly module;
- determining the 3D volume assembly for anatomic plausibility with an anatomic plausibility analysis module;
- and
- outputting a final segmented 3D volume assembly,
- wherein the input MRI volume data is a tensor of dimensions (256, 256, 1).
A method for segmentation and assembly of cardiac magnetic resonance imaging (MRI) images, the method comprising:
- inputting MRI volume data from a MRI scanner;
- segmenting the MRI volume data with a whole volume segmentation analysis module;
- assembling the segmented MRI volume data into a 3D volume assembly with a 3D volume assembly module;
- determining the 3D volume assembly for anatomic plausibility with an anatomic plausibility analysis module;
- and
- outputting a final segmented 3D volume assembly,
- wherein the final segmented 3D volume assembly is tensor of dimensions (256, 256, 4).
A system for segmenting and assembling cardiac magnetic resonance imaging (MRI) images, the system comprising a processor and a non-transitory computer-readable storage medium storing instruction that, when executed by the processor, cause the processor to perform a method,
- the method comprising:
- receiving MRI volume data from a MRI scanner;
- segmenting the MRI volume data with a whole volume segmentation analysis module;
- assembling the segmented MRI volume data into a 3D volume assembly with a 3D volume assembly module;
- determining the 3D volume assembly for anatomic plausibility with an anatomic plausibility analysis module;
- and
- generating a final segmented 3D volume assembly;
- wherein the 3D volume assembly module further comprises a large component identification module to identify a largest connected component of each class as true segmentation and to zero out other components.
A system for segmenting and assembling cardiac magnetic resonance imaging (MRI) images, the system comprising a processor and a non-transitory computer-readable storage medium storing instruction that, when executed by the processor, cause the processor to perform a method, the method comprising:
- receiving MRI volume data from a MRI scanner;
- segmenting the MRI volume data with a whole volume segmentation analysis module;
- assembling the segmented MRI volume data into a 3D volume assembly with a 3D volume assembly module;
- determining the 3D volume assembly for anatomic plausibility with an anatomic plausibility analysis module;
- and
- generating a final segmented 3D volume assembly,
- wherein the anatomic plausibility analysis module further comprises a slice segmentation module for segmenting the 2D MRI slices of the input MRI volume data determined to not be anatomically plausible.
A system for segmenting and assembling cardiac magnetic resonance imaging (MRI) images, the system comprising a processor and a non-transitory computer-readable storage medium storing instruction that, when executed by the processor, cause the processor to perform a method, the method comprising:
- receiving MRI volume data from a MRI scanner;
- segmenting the MRI volume data with a whole volume segmentation analysis module;
- assembling the segmented MRI volume data into a 3D volume assembly with a 3D volume assembly module;
- determining the 3D volume assembly for anatomic plausibility with an anatomic plausibility analysis module;
- and
- generating a final segmented 3D volume assembly,
- wherein the input MRI volume data is a tensor of dimensions (256, 256, 1).
A system for segmenting and assembling cardiac magnetic resonance imaging (MRI) images, the system comprising a processor and a non-transitory computer-readable storage medium storing instruction that, when executed by the processor, cause the processor to perform a method, the method comprising:
- receiving MRI volume data from a MRI scanner;
- segmenting the MRI volume data with a whole volume segmentation analysis module;
- assembling the segmented MRI volume data into a 3D volume assembly with a 3D volume assembly module;
- determining the 3D volume assembly for anatomic plausibility with an anatomic plausibility analysis module;
- and
- generating a final segmented 3D volume assembly,
- wherein the input MRI volume data is a tensor of dimensions (256, 256, 4).
Dependencies are inferred from the claim text.