System and method for automatic segmentation of muscles from high-resolution mri using 3d deep convolutional neural network

An apparatus for automatic muscle segmentation, comprising:

• one or more processors;
• a display;
• and
• a non-transitory computer readable memory storing instructions executable by the one or more processors, wherein the instructions are configured to:
• receive a high-resolution three-dimensional (3D) image obtained by a magnetic resonance imaging (MRI) system;
• split the high-resolution 3D image into high-resolution 3D sub-images;
• acquire low-resolution 3D sub-images of the high-resolution 3D sub-images;
• determine a boundary box within each corresponding low-resolution 3D sub-image, wherein the boundary box encloses at least one target muscle in the low-resolution 3D image;
• determine a crop box for each boundary box, wherein the crop box is the boundary box increased by a ratio along each dimension;
• crop each high-resolution 3D sub-image based on its corresponding crop box;
• segment at least one muscle from the cropped box high-resolution 3D sub-image;
• and
• display the segmented high-resolution 3D image.

A non-transitory computer-readable storage medium having stored therein instructions that, when executed by one or more processors of an apparatus causing the apparatus to perform acts comprising:

• receiving a high-resolution three-dimensional (3D) image obtained by a magnetic resonance imaging (MRI) system;
• splitting the high-resolution 3D image into high-resolution 3D sub-images;
• acquiring low-resolution 3D sub-images of the high-resolution 3D sub-images;
• determining a boundary box within each corresponding low-resolution 3D sub-image, wherein the boundary box encloses at least one target muscle in the low-resolution 3D image;
• determining a crop box for each boundary box, wherein the crop box is the boundary box increased by a ratio along each dimension;
• cropping each high-resolution 3D sub-image based on its corresponding crop box;
• segmenting at least one muscle from the cropped box high-resolution 3D sub-image;
• and
• displaying the segmented high-resolution 3D image.