Hackjoon Shim

Knee cartilage: efficient and reproducible segmentation on high-spatial-resolution MR images with the semiautomated graph-cut algorithm method.

This HIPAA-compliant study was exempt from institutional review board approval because the 10 image data sets were deidentified in the Osteoarthritis Initiative database, and they were processed and analyzed without any clinical information being accessed. The purpose of this study was to prospectively evaluate the efficiency and reproducibility of the semiautomated graph-cut method (SA method) in the segmentation of knee cartilage and to compare its performance with that of the conventional manual delineation segmentation method (M method). Two radiologists independently performed segmentation with each method in two separate sessions: They performed the M method (M1 and M2 for the first and second sessions, respectively) for every third section and the SA method (SA1 and SA2 for the first and second sessions, respectively) for every section. The SA method was significantly more efficient (mean processing time, 53 minutes vs 156 minutes for SA1 vs M1 and 53 minutes vs 118 minutes for SA2 vs M2; P < .001) and reproducible (mean volume overlap, 94.3% vs 87.8% for the SA method vs the M method; P < .001) than the M method.

Intra- and inter-observer reproducibility of volume measurement of knee cartilage segmented from the OAI MR image set using a novel semi-automated segmentation method

OBJECTIVEnWe developed a semi-automated method based on a graph-cuts algorithm for segmentation and volumetric measurements of the cartilage from high-resolution knee magnetic resonance (MR) images from the Osteoarthritis Initiative (OAI) database and assessed the intra- and inter-observer reproducibility of measurements obtained via this method.nnnDESIGNnMR image sets from 20 subjects of varying Kellgren-Lawrence (KL) grades (from 0 to IV) on fixed flexion knee radiographs were selected from the baseline double-echo and steady-state (DESS) knee MR images in the OAI database (0.B.1 Imaging Data set). Two trained radiologists independently performed the segmentation of knee cartilage twice using the semi-automated method. The volumes of segmented cartilage were computed and compared. The intra- and inter-observer reproducibility were determined by means of the coefficient of variation (CV%) of repeated cartilage segmented volume measurements. The subjects were also divided into the low- (0, I or II) and high-KL (III or IV) groups. The differences in cartilage volume measurements and CV% within and between the observers were tested with t tests.nnnRESULTSnThe mean (+/-SD) intra-observer CV% for the 20 cases was 1.29 (+/-1.05)% for observer 1 and 1.67 (+/-1.14)% for observer 2, while the mean (+/-SD) inter-observer CV% was 1.31 (+/-1.26)% for session 1 and 1.79 (+/-1.72)% for session 2. There was no significant difference between the two intra-observer CV%s (P=0.272) and between the two inter-observer CV%s (P=0.353). The mean intra-observer CV% of the low-KL group was significantly smaller than that for the high-KL group for observer 1 (0.83 vs 1.86%: P=0.025). The segmentation processing times used by the two observers were significantly different (observer 1 vs 2): (mean 49+/-12 vs 33+/-6min) for session 1 and (49+/-8 vs 32+/-8min) for session 2.nnnCONCLUSIONnThe semi-automated graph-cuts method allowed us to segment and measure cartilage from high-resolution 3T MR images of the knee with high intra- and inter-observer reproducibility in subjects with varying severity of OA.

Robust segmentation of cerebral arterial segments by a sequential Monte Carlo method: Particle filtering

In this paper a method to extract cerebral arterial segments from CT angiography (CTA) is proposed. The segmentation of cerebral arteries in CTA is a challenging task mainly due to bone contact and vein contamination. The proposed method considers a vessel segment as an ellipse travelling in three-dimensional (3D) space and segments it out by tracking the ellipse in spatial sequence. A particle filter is employed as the main framework for tracking and is equipped with adaptive properties to both bone contact and vein contamination. The proposed tracking method is evaluated by the experiments on both synthetic and actual data. A variety of vessels were synthesized to assess the sensitivity to the axis curvature change, obscure boundaries, and noise. The experimental results showed that the proposed method is also insensitive to parameter settings and requires less user intervention than the conventional vessel tracking methods, which proves its improved robustness.

Fully-automated approach to hippocampus segmentation using a graph-cuts algorithm combined with atlas-based segmentation and morphological opening

The hippocampus has been known to be an important structure as a biomarker for Alzheimers disease (AD) and other neurological and psychiatric diseases. However, it requires accurate, robust and reproducible delineation of hippocampal structures. In this study, an automated hippocampal segmentation method based on a graph-cuts algorithm combined with atlas-based segmentation and morphological opening was proposed. First of all, the atlas-based segmentation was applied to define initial hippocampal region for a priori information on graph-cuts. The definition of initial seeds was further elaborated by incorporating estimation of partial volume probabilities at each voxel. Finally, morphological opening was applied to reduce false positive of the result processed by graph-cuts. In the experiments with twenty-seven healthy normal subjects, the proposed method showed more reliable results (similarity index=0.81±0.03) than the conventional atlas-based segmentation method (0.72±0.04). Also as for segmentation accuracy which is measured in terms of the ratios of false positive and false negative, the proposed method (precision=0.76±0.04, recall=0.86±0.05) produced lower ratios than the conventional methods (0.73±0.05, 0.72±0.06) demonstrating its plausibility for accurate, robust and reliable segmentation of hippocampus.

Optimization of local shape and appearance probabilities for segmentation of knee cartilage in 3-D MR images

We propose a fully automatic method for segmenting knee cartilage in 3-D MR images which consists of bone segmentation, bone-cartilage interface (BCI) classification, and cartilage segmentation. For bone segmentation, we propose a modified version of the recently presented branch-and-mincut method, and for classifying the BCI, we propose a voxel classification method based on binary classifiers of position and local appearance. The core contribution of this paper is the cartilage segmentation method where localized Markov random fields (MRF) are separately constructed and optimized for local image patches. The region and boundary potentials of the MRFs are computed from the retrieved segmentation results of training images that are relevant to each local patch. Here, local shape and appearance cues are adaptively combined depending on the local image characteristics. For experimentation, a dataset comprising MR images of ten different subjects and another comprising the baseline and two-year follow-up scans for nine different subjects are constructed. Both qualitative and quantitative comparisons of the results of the proposed method with semi-automatic segmentation methods demonstrate the potential of the proposed method for clinical application.

Partition-Based extraction of cerebral arteries from CT angiography with emphasis on adaptive tracking

In this paper a method to extract cerebral arteries from computed tomographic angiography (CTA) is proposed. Since CTA shows both bone and vessels, the examination of vessels is a difficult task. In the upper part of the brain, the arteries of main interest are not close to bone and can be well segmented out by thresholding and simple connected-component analysis. However in the lower part the separation is challenging due to the spatial closeness of bone and vessels and their overlapping intensity distributions. In this paper a CTA volume is partitioned into two sub-volumes according to the spatial relationship between bone and vessels. In the lower sub-volume, the concerning arteries are extracted by tracking the center line and detecting the border on each cross-section. The proposed tracking method can be characterized by the adaptive properties to the case of cerebral arteries in CTA. These properties improve the tracking continuity with less user-interaction.

Semiautomated Segmentation of Kidney From High-Resolution Multidetector Computed Tomography Images Using a Graph-Cuts Technique

Objectives: To develop a semiautomated segmentation method based on a graph-cuts technique from multidetector computed tomography images for kidney segmentation and to evaluate and compare it with the conventional manual delineation segmentation method. Materials and Methods: We have developed a semiautomated segmentation method that is based on a graph-cuts technique with enhanced features including automated seed growing. Multidetector computed tomography images were obtained from 15 consecutive patients who were being evaluated as possible living donors for kidney transplant. Two observers independently performed the segmentation of the kidney from the multidetector computed tomography images using the manual and semiautomated methods. The efficiency of the 2 methods were measured by segmentation processing times and then compared. The interobserver and method reproducibility was determined by Dice similarity coefficient (DSC), which measures how closely 2 segmented volumes overlap geometrically and the coefficient of variation of volume measurements. Results: The mean segmentation processing time was (manual vs semiautomated, P < 0.001) 96.8 ± 13.6 vs 13.7 ± 3.5 minutes for observer 1 and 44.3 ± 4.7 vs 16.2 ± 5.1 minutes for observer 2. The mean interobserver reproducibility was (manual vs semiautomated, P < 0.001) 93.6 ± 1.6% vs 97.3 ± 0.9% for DSC and 5.3 ± 2.6% vs 2.2 ± 1.3% for coefficient of variation, indicating higher interobserver reproducibility with the semiautomated than manual method. The agreement between the 2 segmentation methods was high (mean intermethod DSC 95.8 ± 1.0% and 94.9 ± 0.8%) for both observers. Conclusions: The semiautomated method was significantly more efficient and reproducible than the manual delineation method for segmentation of kidney from MDCT images.

Segmentation of ground glass opacities by asymmetric multi-phase deformable model

Recently ground glass opacities (GGOs) have become noteworthy in lung cancer diagnosis. It is crucial to define the boundary a GGO accurately and consistently, since the growth rate is the most manifest evidence of its malignancy. The indefinite and irregular boundary of a GGO makes deformable models adequate for its segmentation. Among deformable models a level set method has the ability to handle topological changes. For the exact estimation of GGOs volume change, the pulmonary airways inside GGO should be excluded in its volume estimation, which necessitate the segmentation into more regions than two of the object and the background. Hence, we adopted a multi-phase deformable model of two level set functions and modified its energy functional into an asymmetric form. The main two modifications are the elimination of one region in four regions of the conventional 4-phase deformable model and the prevention of the outer region from spreading out of the initialization. The proposed model segments the input image into three regions of the inner and outer regions, and the background. The GGO tissues are segmented as the inner region and the outer region plays the role of blockade for the inner region not to leak out to adjacent anatomical structures of similar Hounsfield Unit (HU) values. Our experimental results confirmed the feasibility of the proposed method as a pre-processing step for three dimensional (3-D) volume measurement of the GGO.

Feasibility of an automatic computer-assisted algorithm for the detection of significant coronary artery disease in patients presenting with acute chest pain

Automatic computer-assisted detection (auto-CAD) of significant coronary artery disease (CAD) in coronary computed tomography angiography (cCTA) has been shown to have relatively high accuracy. However, to date, scarce data are available regarding the performance of auto-CAD in the setting of acute chest pain. This study sought to demonstrate the feasibility of an auto-CAD algorithm for cCTA in patients presenting with acute chest pain. We retrospectively investigated 398 consecutive patients (229 male, mean age 50±21 years) who had acute chest pain and underwent cCTA between Apr 2007 and Jan 2011 in the emergency department (ED). All cCTA data were analyzed using an auto-CAD algorithm for the detection of >50% CAD on cCTA. The accuracy of auto-CAD was compared with the formal radiology report. In 380 of 398 patients (18 were excluded due to failure of data processing), per-patient analysis of auto-CAD revealed the following: sensitivity 94%, specificity 63%, positive predictive value (PPV) 76%, and negative predictive value (NPV) 89%. After the exclusion of 37 cases that were interpreted as invalid by the auto-CAD algorithm, the NPV was further increased up to 97%, considering the false-negative cases in the formal radiology report, and was confirmed by subsequent invasive angiogram during the index visit. We successfully demonstrated the high accuracy of an auto-CAD algorithm, compared with the formal radiology report, for the detection of >50% CAD on cCTA in the setting of acute chest pain. The auto-CAD algorithm can be used to facilitate the decision-making process in the ED.

JPEG2000 2D and 3D Reversible Compressions of Thin-Section Chest CT Images: Improving Compressibility by Increasing Data Redundancy Outside the Body Region

PURPOSEnTo propose a preprocessing technique that increases the compressibility in reversible compressions of thin-section chest computed tomographic (CT) images and to measure the increase in compression ratio (CR) in Joint Photographic Experts Group (JPEG) 2000 two-dimensional (2D) and three-dimensional (3D) compressions.nnnMATERIALS AND METHODSnThis study had institutional review board approval, with waiver of informed patient consent. A preprocessing technique that automatically segments pixels outside the body region and replaces their values with a constant value to maximize data redundancy was developed. One hundred CT studies (50 standard-radiation dose and 50 low-radiation dose studies) were preprocessed by using the technique and then reversibly compressed by using the JPEG2000 2D and 3D compression methods. The CRs (defined as the original data size divided by the compressed data size) with and those without use of the preprocessing technique were compared by using paired t tests. The percentage increase in the CR was measured.nnnRESULTSnThe CR increased significantly (without vs with preprocessing) in JPEG2000 2D (mean CR, 2.40 vs 3.80) and 3D (mean CR, 2.61 vs 3.99) compressions for the standard-dose studies and in JPEG2000 2D (mean CR, 2.38 vs 3.36) and 3D (mean CR, 2.54 vs 3.55) compressions for the low-dose studies (P < .001 for all). The mean percentage increases in CR with preprocessing were 58.2% (95% confidence interval [CI]: 53.1%, 63.4%) and 52.4% (95% CI: 47.5%, 57.2%) in JPEG2000 2D and 3D compressions, respectively, for the standard-dose studies and 41.1% (95% CI: 38.8%, 43.4%) and 39.4% (95% CI: 37.4%, 41.7%) in JPEG2000 2D and 3D compressions, respectively, for the low-dose studies.nnnCONCLUSIONnThe described preprocessing technique considerably increases CRs for reversible compressions of thin-section chest CT studies.