Automatic bone detection in MRI images
A method for detecting bone and bone disease using MRI images includes: detecting and segmenting bone borders using dark bone border intensity information from an MRI image; and detecting bone disease within a segmented image region.
1. A computer system, comprising:
a processor; and
a program storage device readable by the computer system, embodying a program of instructions executable by the processor to perform method steps for automatically detecting and registering bone structures from magnetic resonance imaging (MRI) images, the method comprising:
acquiring an MRI image;
automatically detecting low or zero intensity locations within the image and extracting a bone border based upon the detected low or zero intensity locations;
segmenting a region of the image within the extracted bone border;
building a model of a bone using the extracted bone border and the segmented image region by extracting geometric primitives from the detected bone borders; and
registering the extracted bone border to the model.
2. The system of claim 1 , the method further comprising:
detecting low or zero intensity locations within the image using at least one technique selected from: thresholding, machine learning based classification, clustering, region growing, deformable modeling, snaking, live-wire methods, edge detecting, and connected component detecting.
3. The system of claim 2 , the method further comprising:
detecting low or zero intensity locations within the image by thresholding, wherein thresholding comprises at least one of adaptive global thresholding, non-adaptive global thresholding, local thresholding, and local adaptive thresholding.
4. The system of claim 1 , the method further comprising detecting locations of possible bone disease within the segmented region.
5. The system of claim 1 , the method further comprising building the model by extracting geometric primitives by extracting lines using at least one of a Hough transform or a Radon transform.
6. The system of claim 4 , wherein detecting locations of possible bone disease further comprises detecting possible locations of at least one of abnormalities, bone metastasis, fractures, osteoporosis, Shmorl's nodes, osteochondrosis, edemas, inflammation, cysts, hemangiomas, arthrosis or bone infarct.
7. A program storage device accessible by a computer, tangibly embodying a program of instructions executable by said computer to perform method steps for automatically detecting and registering bone structures from magnetic resonance imaging (MRI) images, the method comprising:
acquiring an MRI image;
automatically detecting low or zero intensity locations within the image and extracting a bone border based upon the detected low or zero intensity locations;
segmenting a region of the image within the extracted bone border;
building a model of a bone using the extracted bone border and the segmented image region by extracting geometric primitives from the detected bone borders; and
registering the extracted bone border to the model.
8. The program storage device of claim 7 , the method further comprising:
detecting low or zero intensity locations within the image using at least one technique selected from: thresholding, machine learning based classification, clustering, region growing, deformable modeling, snaking, live-wire methods, edge detecting, and connected component detecting.
9. The program storage device of claim 8 , the method further comprising:
detecting low or zero intensity locations within the image by thresholding, wherein thresholding comprises at least one of adaptive global thresholding, non-adaptive global thresholding, local thresholding, and local adaptive thresholding.
10. The program storage device of claim 7 , the method further comprising detecting locations of possible bone disease within the segmented region.
11. The program storage device of claim 7 , the method further comprising building the model by extracting geometric primitives by extracting lines using at least one of a Hough transform or a Radon transform.
12. The program storage device of claim 10 , wherein detecting locations of possible bone disease further comprises detecting possible locations of at least one of abnormalities, bone metastasis, fractures, osteoporosis, Shmorl's nodes, osteochondrosis, edemas, inflammation, cysts, hemangiomas, arthrosis or bone infarct.