Lung lobe segmentation is clinically important for disease classification, treatment and follow-up of pulmonary diseases. Diseases such as tuberculosis and silicolis typically present in specific lobes i.e. almost exclusively the upper ones. However, the fissures separating different lobes are often difficult to detect because of their variable shape, appearance and low contrast in computed tomography images. In addition, a substantial fraction of patients have missing or incomplete fissures. To solve this problem, several methods have been employed to interpolate incomplete or missed fissures. For example, Pu et al. used an implicit surface fitting with different radial basis functions; Ukil et al. apply fast marching methods; and Ross et al. used an interactive thin plate spline (TPS) interpolation where the user selects the points that will be used to compute the fissure interpolation via TPS. In our study, results of an automated fissure detection method based on a plate-filter as well points derived from vessels were fed into an a robust TPS interpolation that ultimately defined the lobes. To improve the selection of detected points, we statistically determined the areas where fissures are localized from 19 data-sets. These areas were also used to constrain TPS fitting so it reflected the expected shape and orientation of the fissures, hence improving result accuracy. Regions where the detection step provided low response were replaced by points derived from a distance-to-vessels map. The error, defined as the Euclidian mean distance between ground truth points and the TPS fitted fissures, was computed for each dataset to validate our results. Ground truth points were defined for both exact fissure locations and approximate fissure locations (when the fissures were not clearly visible). The mean error was 5.64±4.83 mm for the exact ground truth points, and 10.01 ± 8.23 mm for the approximate ground truth points.
In this work, we have developed a novel knowledge-driven quasi-global method for fast and robust registration of thoracic-abdominal CT and cone beam CT (CBCT) scans. While the use of CBCT in operating rooms has become a common practice, there is an increasing demand on the registration of CBCT with pre-operative scans, in many cases, CT scans. One of the major challenges of thoracic-abdominal CT/CBCT registration is from various fields of view (FOVs) of the two imaging modalities. The proposed approach utilizes a priori knowledge of anatomy to generate 2D anatomy targeted projection (ATP) images that surrogate the original volumes. The use of lower dimension surrogate images can significantly reduce the computation cost of similarity evaluation during optimization and make it practically feasible to perform global optimization based registration for image-guided interventional procedures. Another a priori knowledge about the local optima distribution on energy curves is further used to effectively select multi-starting points for registration optimization. 20 clinical data sets were used to validate the method and the target registration error (TRE) and maximum registration error (MRE) were calculated to compare the performance of the knowledge-driven quasi-global registration against a typical local-search based registration. The local search based registration failed on 60% cases, with an average TRE of 22.9mm and MRE of 28.1mm; the knowledge-driven quasi-global registration achieved satisfactory results for all the 20 data sets, with an average TRE of 3.5mm, and MRE of 2.6mm. The average computation time for the knowledge-driven quasi-global registration is 8.7 seconds.
We present a method to automate acquisition of MR brain scans to allow consistent alignment of diagnostic images for
patient follow-up, and to depict standardized anatomy for all patients. The algorithm takes as input a low-resolution
acquisition that depicts the patient position within the scanner. The mid-sagittal plane dividing the brain hemispheres is
automatically detected, as are bony landmarks at the front and back of the skull. The orientation and position of a
subsequent diagnostic, high resolution scan is then aligned based on these landmarks. The method was tested on 91 data
sets, and was completely successful in 93.4% of cases, performed acceptably in 4.4% of cases, and failed for 1.1%. We
conclude that the method is suitable for clinical use and should prove valuable for improving consistency of acquisitions.
The mid-sagittal plane (MSP) is a commonly used anatomic landmark for standardized MR brain acquisition. In addition
to the requirement of accurate detection of the MSP geometry, it is also imperative from clinical point of view to
consistently prescribe scan planning for evaluation of pathology process in follow-up studies. In this work, an adaptive
technique of scan planning has been developed to enforce the consistency among scans acquired at different time points
from the same patient by maximizing image similarity in the proximity of MSP. The geometry parameters of the MSP of
current study are optimized by simplex algorithm to achieve better similarity to the reference study. Meanwhile different
similarity measures are studied and evaluated within the region of the interest of each MSP. The method is successfully
tested on self-reference consistency study by manually setting the reference sagittal image. It is also tested with clinical
follow-up studies of MR images acquired from 30 patients. By visual inspection, the adaptive consistency method
improves the similarity to the reference images in 22 follow-up studies evidently, while the similarity to the reference
images in 7 studies improves slightly. This result demonstrates the efficacy of our method on consistent detection of
mid-sagittal planes for follow-up MR brain study.
The lymphatic system comprises a series of interconnected lymph nodes that are commonly distributed along branching
or linearly oriented anatomic structures. Physicians must evaluate lymph nodes when staging cancer and planning
optimal paths for nodal biopsy. This process requires accurately determining the lymph node's position with respect to
major anatomical landmarks. In an effort to standardize lung cancer staging, The American Joint Committee on Cancer
(AJCC) has classified lymph nodes within the chest into 4 groups and 14 sub groups. We present a method for
automatically labeling lymph nodes according to this classification scheme, in order to improve the speed and accuracy
of staging and biopsy planning. Lymph nodes within the chest are clustered around the major blood vessels and the
airways. Our fully automatic labeling method determines the nodal group and sub-group in chest CT data by use of
computed airway and aorta centerlines to produce features relative to a given node location. A classifier then determines
the label based upon these features. We evaluate the efficacy of the method on 10 chest CT datasets containing 86
labeled lymph nodes. The results are promising with 100% of the nodes assigned to the correct group and 76% to the
correct sub-group. We anticipate that additional features and training data will further improve the results. In addition to
labeling, other applications include automated lymph node localization and visualization. Although we focus on chest
CT data, the method can be generalized to other regions of the body as well as to different imaging modalities.
Multi-Slice Computed Tomography (MSCT) imaging of the lungs allow for detection and follow-up of very small
lesions including solid and ground glass nodules (GGNs). However relatively few computer-based methods have been
implemented for GGN segmentation. GGNs can be divided into pure GGNs and mixed GGNs, which contain both nonsolid
and solid components (SC). This latter category is especially of interest since some studies indicate a higher
likelihood of malignancy in GGNs with SC. Due to their characteristically slow growth rate, GGNs are typically
monitored with multiple follow-up scans, making measurement of the volume of both solid and non-solid component
especially desirable. We have developed an automated method to estimate the SC percentage within a segmented GGN.
First, the SC algorithm uses a novel method to segment out the solid structures, while excluding any vessels passing near
or through the nodule. A gradient distribution analysis around solid structures validates the presence or absence of SC.
We tested 50 GGNs, split between three groups: 15 GGNs with SC, 15 GGNs with a solid nodule added to simulate SC,
and 20 GGNs without SC. With three defined satisfaction levels for the segmentation (A: succeed, B: acceptable, C:
failed), the first group resulted in 60% with score A, 40% with score B, 0% with score C. The second group resulted in
66.7% with score A and 33.3% with score B. In testing the first and 3rd groups, the algorithm correctly detected SC in
all cases where it was present (sensitivity of 100%) and correctly determined absence of SC in 15 out of 20 cases
(specificity 75%).
In most magnetic resonance imaging (MRI) clinical examinations, the orientation and position of diagnostic scans are
manually defined by MRI operators. To accelerate the workflow, algorithms have been proposed to automate the
definition of the MRI scanning planes. A mid-sagittal plane (MSP), which separates the two cerebral hemispheres, is
commonly used to align MRI neurological scans, since it standardizes the visualization of important anatomy. We
propose an algorithm to define the MSP automatically based on lines separating the cerebral hemispheres in 2D coronal
and transverse images. Challenges to the automatic definition of separation lines are disturbances from the inclusion of
the shoulder, and the asymmetry of the brain. The proposed algorithm first detects the position of the head by fitting an
ellipse that maximizes the image gradient magnitude in the boundary region of the ellipse. A symmetrical axis is then
established which minimizes the difference between the image on either side of the axis. The pixels at the space between
the hemispheres are located in the adjacent area of the symmetrical axis, and a linear regression with robust weights
defines a line that best separates the two hemispheres. The geometry of MSP is calculated based on the separation lines
in the coronal and transverse views. Experiments on 100 images indicate that the result of the proposed algorithm is
consistent with the results obtained by domain experts and is significantly faster.
KEYWORDS: Image segmentation, Brain, Neuroimaging, Magnetic resonance imaging, 3D modeling, 3D image processing, Medical imaging, Diagnostics, 3D acquisition, Magnetism
Magnetic Resonance (MR) brain scanning is often planned manually with the goal of aligning the imaging plane with
key anatomic landmarks. The planning is time-consuming and subject to inter- and intra- operator variability. An
automatic and standardized planning of brain scans is highly useful for clinical applications, and for maximum utility
should work on patients of all ages. In this study, we propose a method for fully automatic planning that utilizes the
landmarks from two orthogonal images to define the geometry of the third scanning plane. The corpus callosum (CC) is
segmented in sagittal images by an active shape model (ASM), and the result is further improved by weighting the
boundary movement with confidence scores and incorporating region based refinement. Based on the extracted contour
of the CC, several important landmarks are located and then combined with landmarks from the coronal or transverse
plane to define the geometry of the third plane. Our automatic method is tested on 54 MR images from 24 patients and 3
healthy volunteers, with ages ranging from 4 months to 70 years old. The average accuracy with respect to two
manually labeled points on the CC is 3.54 mm and 4.19 mm, and differed by an average of 2.48 degrees from the
orientation of the line connecting them, demonstrating that our method is sufficiently accurate for clinical use.
Magnetic resonance (MR) imaging is frequently used to diagnose abnormalities in the spinal intervertebral discs. Owing to the non-isotropic resolution of typical MR spinal scans, physicians prefer to align the scanner plane with the disc in order to maximize the diagnostic value and to facilitate comparison with prior and follow-up studies. Commonly a planning scan is acquired of the whole spine, followed by a diagnostic scan aligned with selected discs of interest. Manual determination of the optimal disc plane is tedious and prone to operator variation. A fast and accurate method to automatically determine the disc alignment can decrease examination time and increase the reliability of diagnosis. We present a validation study of an automatic spine alignment system for determining the orientation of intervertebral discs in MR studies. In order to measure the effectiveness of the automatic alignment system, we compared its performance with human observers. 12 MR spinal scans of adult spines were tested. Two observers independently indicated the intervertebral plane for each disc, and then repeated the procedure on another day, in order to determine the inter- and intra-observer variability associated with manual alignment. Results were also collected for the observers utilizing the automatic spine alignment system, in order to determine the method's consistency and its accuracy with respect to human observers. We found that the results from the automatic alignment system are comparable with the alignment determined by human observers, with the computer showing greater speed and consistency.
Ground glass nodules (GGNs) have proved especially problematic in lung cancer diagnosis, as despite frequently being malignant they have extremely slow growth rates. In this work, the GGN segmentation results of a computer-based method were compared with manual segmentation performed by two dedicated chest radiologists. CT volumes of 8 patients were acquired by multi-slice CT. 21 pure or mixed GGNs were identified and independently segmented by the computer-based method and by two readers. The computer-based method is initialized by a click point, and uses a Markov random field (MRF) model for segmentation. While the intensity distribution varies for different GGNs, the intensity model used in MRF is adapted for each nodule based on initial estimates. This method was run three times for each nodule using different click points to evaluate consistency. In this work, consistency was defined by the overlap ratio (overlap volume/mean volume). The consistency of the computer-based method with different initial points, with a mean overlap ratio of 0.96±0.02 (95% confidence interval on mean), was significantly higher than the inter-observer consistency between the two radiologists, indicated by a mean overlap ratio of 0.73±0.04. The computer consistency was also significantly higher than the intra-observer consistency of two measurements from the same radiologist, indicated by an overlap ratio of 0.69±0.05 (p-value < 1E-05). The concordance of the computer with the expert interpretation demonstrated a mean overlap ratio of 0.69±0.05. As shown by our data, the consistency provided by the computer-based method is significantly higher than between observers, and the accuracy of the method is no worse than that of one physician’s accuracy with respect to another, allowing more reproducible assessment of nodule growth.
Ground glass nodules (GGNs) have proved especially problematic in lung cancer diagnosis, as despite frequently being
malignant they characteristically have extremely slow rates of growth. This problem is further magnified by the small
size of many of these lesions now being routinely detected following the introduction of multislice CT scanners capable
of acquiring contiguous high resolution 1 to 1.25 mm sections throughout the thorax in a single breathhold period.
Although segmentation of solid nodules can be used clinically to determine volume doubling times quantitatively,
reliable methods for segmentation of pure ground glass nodules have yet to be introduced. Our purpose is to evaluate a
newly developed computer-based segmentation method for rapid and reproducible measurements of pure ground glass
nodules. 23 pure or mixed ground glass nodules were identified in a total of 8 patients by a radiologist and subsequently
segmented by our computer-based method using Markov random field and shape analysis. The computer-based
segmentation was initialized by a click point. Methodological consistency was assessed using the overlap ratio between
3 segmentations initialized by 3 different click points for each nodule. The 95% confidence interval on the mean of the
overlap ratios proved to be [0.984, 0.998]. The computer-based method failed on two nodules that were difficult to
segment even manually either due to especially low contrast or markedly irregular margins. While achieving consistent
manual segmentation of ground glass nodules has proven problematic most often due to indistinct boundaries and interobserver
variability, our proposed method introduces a powerful new tool for obtaining reproducible quantitative
measurements of these lesions. It is our intention to further document the value of this approach with a still larger set of
ground glass nodules.
The positions of the lobar fissures are of growing interest as computer-based quantitative measures to detect early pathologies and to predict or measure outcomes emerge. While we have developed a semi-automatic fissure detection method in our previous work, in this paper we describe the use of an anatomic pulmonary atlas with a priori knowledge about lobar fissures to automatically segment the lobar fissures. 16 volumetric CT scans from 16 subjects are used to construct the pulmonary atlas. After deforming the fissures onto a template image, the average fissure and variability between different subjects can be obtained by local statistical measures. The probabilistic analysis for the atlas shows that the atlas can provide an initialization for the fissure detection in certain regions with a predictable variation, although the initialization may not be close and complete. A ridgeness measure is applied on original images to enhance the fissure contrast. The fissure detection is accomplished by the initial fissure search and the final fissure search. While only parts of the initial search results are correctly delineated, a regional statistic analysis of ridgeness selects the most "reliable" initial search results, which are then used to initialize the final search. Our method has been tested in 22 volumetric thin-slice CT images from 12 subjects, and the results are compared to manual tracings. The mean of the similarity indices between the manual and computer defined lobes is 0.988. The results indicate a strong agreement between the automatic and manual lobe segmentations.
Multi-slice computed tomography (CT) provides a promising technology for lung cancer detection and treatment. To optimize automatic detections of a more complete spectrum of lung nodules on CT requires multiple specialized algorithms in a coherently integrated detection system. We have developed a knowledge-based system for automatic lung nodule detection and analysis, which coherently integrates several robust novel detection algorithms to detect different types of nodules, including those attached to the chest wall, nodules adjacent to or fed by vessels, and solitary nodules, simultaneously. The system architecture can be easily extended in the future to include a still greater range of nodule types, most importantly so-called ground-glass opacities (GGOs). In addition, automatic local adaptive histogram analysis, dynamic cross-correlation analysis, and the automatic volume projection analysis by using by data dimension reduction method, are used in nodule detection. The proposed system has been applied to 10 patients screened with low-dose multi-slice CT. Preliminary clinical tests show that (1) the false positive rate averages about 3.2 per study; and (2) by using the system radiologists are able to detect nearly twice the number of nodules as compared with working alone.
The lung lobes are natural units for reporting image-based measurements of the respiratory system. Lobar segmentation can also be used in pulmonary image processing to guide registration and drive additional segmentation. We have developed a 3D shape-constrained lobar segmentation technique for volumetric pulmonary CT images. The method consists of a search engine and shape constraints that work together to detect lobar fissures using gray level information and anatomic shape characteristics in two steps: (1) a coarse localization step, (2) a fine tuning step. An error detecting mechanism using shape constraints is used in our method to correct erroneous search results. Our method has been tested in four subjects, and the results are compared to manually traced results. The average RMS difference between the manual results and shape-constrained segmentation results is 2.23 mm. We further validated our method by evaluating the repeatability of lobar volumes measured from repeat scans of the same subject. We compared lobar air and tissue volume variations to show that most of the lobar volume variations are due to difference in air volume scan to scan.
A 3D anatomic atlas can be used to analyze pulmonary structures in CT images. To use an atlas to guide segmentation processing, the image being analyzed must be aligned and registered with the atlas. We have developed a 3D surface- based registration technique to register pulmonary CT volumes. To demonstrate the method, we have constructed an atlas from a CT image volume of a normal human male. The atlas is registered to new images in two steps: (1) a global transformation, and (2) a local elastic transformation. In the local transformation, the image and atlas volumes are divided into small subimages called cubes. The similarity between cubes in the image and atlas is measured to find the best match displacement vectors. These displacement vectors are processed using Burr's dynamic model to give a smoothed deformation vector for each voxel in the image. This method has been tested by three intra-subject registrations and three inter-subject registrations from four different normal human subjects. The results show that lung surface-based registration can register the internal lobar fissures from the atlas to the image within about 2.73 +/- 2.05 mm for intra- subject registration, and 5.96 +/- 4.99 mm for inter-subject registration. This registration can be used as an initialization for additional segmentation processing.
The human lungs are divided into five distinct anatomic compartments called lobes. The physical boundaries between the lung lobes are called the lobar fissures. Detection of the lobar fissures in an image data set can be used to help identify the major components of the pulmonary anatomy, guide image registration with a standard lung atlas, drive additional image segmentation processing to find airways and vessels, and to provide an anatomic framework within which image-based measurements can be reported. Little work has been done to develop methods for detecting the lobar fissures. We have developed a semi-automatic method to identify the left and right oblique fissures in 3-D X-ray CT data sets. Our method is based on using fuzzy sets to describe the anatomic and image-based characteristics of likely fissure pixels, and we then use a graph search to select the most probable fissure location on 2-D slices of the data set. The user initializes the search once by defining starting pixels, initial direction and ending pixels on one slice. Once the fissure has identified on a singe slice, it can be used to guide automatic fissure detection on neighboring slices. Thus, the entire 3-D surface defined by a fissure can be identified with a little intervention. The method has been tested by processing two CT data sets from a normal subject. We present results comparing our method against results obtained by manual analysis. The average RMS error between the manual analysis and our approach is approximately 1.9 pixels (corresponding to about 1.3 mm), while the fissures themselves typically appear 3 to 6 pixels wide on a CT slice.
Coded aperture techniques based on a cyclic difference set uniformly redundant array (URA) can increase sensitivity of an imaging system without degrading the spatial resolution. In this paper, we discuss the pattern design and present its application for diagnostic nuclear medicine imaging with experimental results. Point-like, planar, and three- dimensional 140 keV gamma-ray sources are used in our experiments. We have experimentally demonstrated a three- dimensional coded aperture technique for nuclear medicine imaging and have compared it with conventional collimator systems.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.