System and method for segmentation of lung
Disclosed are systems, devices, and methods for determining pleura boundaries of a lung, an exemplary method comprising acquiring image data from an imaging device, generating a set of two-dimensional (2D) slice images based on the acquired image data, determining, by a processor, a seed voxel in a first slice image from the set of 2D slice images, applying, by the processor, a region growing process to the first slice image from the set of 2D slice images starting with the seed voxel using a threshold value, generating, by the processor, a set of binarized 2D slice images based on the region grown from the seed voxel, filtering out, by the processor, connected components of the lung in each slice image of the set of binarized 2D slice images, and identifying, by the processor, the pleural boundaries of the lung based on the set of binarized 2D slice images.
1. A non-transitory computer-readable storage medium storing instructions which, when executed by a processor, cause a computer to:
acquire image data of a patient's chest;
generate a set of two-dimensional (2D) slice images based on the acquired image data;
determine a seed voxel in a trachea connected to a lung in a first slice image from the set of 2D slice images;
apply a region growing process to the first slice image from the set of 2D slice images starting with the seed voxel using a threshold value, wherein a region grown by applying the region growing process corresponds to a lung;
generate a set of binarized 2D slice images based on the region grown from the seed voxel;
filter out connected components of the lung in each slice image of the set of binarized 2D slice images; and
identify the pleural boundaries of the lung based on the set of binarized 2D slice images.
2. The non-transitory computer-readable storage medium storing according to claim 1 , wherein the threshold value is greater than or equal to an intensity of the seed voxel.
3. The non-transitory computer-readable storage medium storing according to claim 1 , wherein the acquired image data is stored in the digital imaging and communications in medicine (DICOM) image format.
4. The non-transitory computer-readable storage medium storing according to claim 1 , wherein the image data is acquired via a network device.
5. The non-transitory computer-readable storage medium storing according to claim 1 , wherein applying the region growing process includes:
in a case where an intensity of a first voxel in the first slice image from the set of 2D slice images is lower than the predetermined threshold value and the first voxel is connected to the seed voxel, setting the intensity of the first voxel as a maximum value; and
in a case where an intensity of a second voxel in the first slice image from the set of 2D slice images is not lower than the predetermined threshold value or the first voxel is not connected to the seed voxel, setting the intensity of the second voxel as a minimum value.
6. The non-transitory computer-readable storage medium storing according to claim 5 , wherein the threshold value causes a high intensity area to appear around the seed voxel in the set of 2D slice images.
7. The non-transitory computer-readable storage medium storing according to claim 5 , wherein applying the region growing process further includes inversely assigning values of voxels in the set of 2D slice images, from the minimum value to the maximum value and from the maximum value to the minimum value, to obtain the set of binarized 2D slice images.
8. The non-transitory computer-readable storage medium storing according to claim 1 , wherein filtering out connected components of the lung includes:
detecting a plurality of connected components in the set of binarized 2D slice images;
calculating an area of each connected component in the set of binarized 2D slice images;
determining whether the area of each connected component is less than a predetermined value;
assigning the minimum value to pixels of a first connected component of the plurality of connected components when it is determined that an area of the first connected component is less than the predetermined value; and
assigning the maximum value to pixels of a second connected component of the plurality of connected components when it is determined that an area of the second connected component is greater than or equal to the predetermined value.
9. The non-transitory computer-readable storage medium storing according to claim 8 , wherein each connected component is an enclosed area with high intensity.
10. The non-transitory computer-readable storage medium storing according to claim 8 , wherein one or more of the plurality of connected components are blood vessels or airways.
11. The non-transitory computer-readable storage medium storing according to claim 8 , wherein an intersection of three 2D slice images, each of which is from each of three independent directions, identifies a voxel in the set of 2D slice images.
12. The non-transitory computer-readable storage medium storing according to claim 11 , wherein the three independent directions are axial, coronal, and sagittal directions.
13. The non-transitory computer-readable storage medium storing according to claim 1 , wherein each voxel of the set of binarized 2D slice images has either high or low intensity.
14. The non-transitory computer-readable storage medium storing according to claim 1 , wherein the image data is acquired from one of computed tomographic technique, radiography, tomogram produced by a computerized axial tomography scan, magnetic resonance imaging, ultrasonography, contrast imaging, fluoroscopy, nuclear scans, and positron emission tomography.