Segmentation of intrathoracic airway trees: a fuzzy logic approach

Coarse-to-fine airway segmentation using multi information fusion network and CNN-based region growing

BACKGROUND AND OBJECTIVES

Automatic airway segmentation from chest computed tomography (CT) scans plays an important role in pulmonary disease diagnosis and computer-assisted therapy. However, low contrast at peripheral branches and complex tree-like structures remain as two mainly challenges for airway segmentation. Recent research has illustrated that deep learning methods perform well in segmentation tasks. Motivated by these works, a coarse-to-fine segmentation framework is proposed to obtain a complete airway tree.

METHODS

Our framework segments the overall airway and small branches via the multi-information fusion convolution neural network (Mif-CNN) and the CNN-based region growing, respectively. In Mif-CNN, atrous spatial pyramid pooling (ASPP) is integrated into a u-shaped network, and it can expend the receptive field and capture multi-scale information. Meanwhile, boundary and location information are incorporated into semantic information. These information are fused to help Mif-CNN utilize additional context knowledge and useful features. To improve the performance of the segmentation result, the CNN-based region growing method is designed to focus on obtaining small branches. A voxel classification network (VCN), which can entirely capture the rich information around each voxel, is applied to classify the voxels into airway and non-airway. In addition, a shape reconstruction method is used to refine the airway tree.

RESULTS

We evaluate our method on a private dataset and a public dataset from EXACT09. Compared with the segmentation results from other methods, our method demonstrated promising accuracy in complete airway tree segmentation. In the private dataset, the Dice similarity coefficient (DSC), Intersection over Union (IoU), false positive rate (FPR), and sensitivity are 93.5%, 87.8%, 0.015%, and 90.8%, respectively. In the public dataset, the DSC, IoU, FPR, and sensitivity are 95.8%, 91.9%, 0.053% and 96.6%, respectively.

CONCLUSION

The proposed Mif-CNN and CNN-based region growing method segment the airway tree accurately and efficiently in CT scans. Experimental results also demonstrate that the framework is ready for application in computer-aided diagnosis systems for lung disease and other related works.

High-quality chest CT segmentation to assess the impact of COVID-19 disease

Purpose

COVID-19 has spread rapidly worldwide since its initial appearance, creating the need for faster diagnostic methods and tools. Due to the high rate of false-negative RT-PCR tests, the role of chest CT examination has been investigated as an auxiliary procedure. The main goal of this work is to establish a well-defined strategy for 3D segmentation of the airways and lungs of COVID-19 positive patients from CT scans, including detected abnormalities. Their identification and the volumetric quantification could allow an easier classification in terms of gravity, extent and progression of the infection. Moreover, these 3D reconstructions can provide a high-impact tool to enhance awareness of the severity of COVID-19 pneumonia.

Methods

Segmentation process was performed utilizing a proprietary software, starting from six different stacks of chest CT images of subjects with and without COVID-19. In this context, a comparison between manual and automatic segmentation methods of the respiratory system was conducted, to assess the potential value of both techniques, in terms of time consumption, required anatomical knowledge and branch detection, in healthy and pathological conditions.

Results

High-quality 3D models were obtained. They can be utilized to assess the impact of the pathology, by volumetrically quantifying the extension of the affected areas. Indeed, based on the obtained reconstructions, an attempted classification for each patient in terms of the severity of the COVID-19 infection has been outlined.

Conclusions

Automatic algorithms allowed for a substantial reduction in segmentation time. However, a great effort was required for the manual identification of COVID-19 CT manifestations. The developed automated procedure succeeded in obtaining sufficiently accurate models of the airways and the lungs of both healthy patients and subjects with confirmed COVID-19, in a reasonable time.

3D Histopathology-a Lung Tissue Segmentation Workflow for Microfocus X-ray-Computed Tomography Scans

Lung histopathology is currently based on the analysis of 2D sections of tissue samples. The use of microfocus X-ray-computed tomography imaging of unstained soft tissue can provide high-resolution 3D image datasets in the range of 2-10 μm without affecting the current diagnostic workflow. Important details of structural features such as the tubular networks of airways and blood vessels are contained in these datasets but are difficult and time-consuming to identify by manual image segmentation. Providing 3D structures permits a better understanding of tissue functions and structural interrelationships. It also provides a more complete picture of heterogeneous samples. In addition, 3D analysis of tissue structure provides the potential for an entirely new level of quantitative measurements of this structure that have previously been based only on extrapolation from 2D sections. In this paper, a workflow for segmenting such 3D images semi-automatically has been created using and extending the ImageJ open-source software and key steps of the workflow have been integrated into a new ImageJ plug-in called LungJ. Results indicate an improved workflow with a modular organization of steps facilitating the optimization for different sample and scan properties with expert input as required. This allows for incremental and independent optimization of algorithms leading to faster segmentation. Representation of the tubular networks in samples of human lung, building on those segmentations, has been demonstrated using this approach.

Developmental model of an automatic production of the human bronchial tree based on L-system

BACKGROUND AND OBJECTIVE

The human lungs exchange air with the external environment via the conducting airways. The application of an anatomically accurate model of the conducting airways can be helpful for simulating gas exchange and fluid distribution throughout the bronchial tree in the lung.

METHODS

In the current study, Lindenmayer system (L-system) has been formulated to generate the bronchial tree structure in a human lung. It has been considered that the structure of the bronchial tree is divided into two main segments: 1) The central airways (from the trachea to segmental bronchi) and 2) the dichotomous structure (from segmental bronchi to terminal bronchioles). Two sets of parametric rewriting rules which can be used to develop central and peripheral airways have been proposed; the first set used to develop central airways consists of seven rules, while the second rule set contains four rules.

RESULTS

The proposed model is capable of generating bronchial tree inside the volume of the host lung; and comparison of the resulting model with those reported in the literature shows that the morphometric characteristics of L-system structure are in good agreement with their corresponding experimental data.

CONCLUSION

The resulting model can be used to obtain a mathematical model required for the study of transport phenomena occurring in the lung during respiration.

Airway Segmentation and Centerline Extraction from Thoracic CT - Comparison of a New Method to State of the Art Commercialized Methods

INTRODUCTION

Our motivation is increased bronchoscopic diagnostic yield and optimized preparation, for navigated bronchoscopy. In navigated bronchoscopy, virtual 3D airway visualization is often used to guide a bronchoscopic tool to peripheral lesions, synchronized with the real time video bronchoscopy. Visualization during navigated bronchoscopy, the segmentation time and methods, differs. Time consumption and logistics are two essential aspects that need to be optimized when integrating such technologies in the interventional room. We compared three different approaches to obtain airway centerlines and surface.

METHOD

CT lung dataset of 17 patients were processed in Mimics (Materialize, Leuven, Belgium), which provides a Basic module and a Pulmonology module (beta version) (MPM), OsiriX (Pixmeo, Geneva, Switzerland) and our Tube Segmentation Framework (TSF) method. Both MPM and TSF were evaluated with reference segmentation. Automatic and manual settings allowed us to segment the airways and obtain 3D models as well as the centrelines in all datasets. We compared the different procedures by user interactions such as number of clicks needed to process the data and quantitative measures concerning the quality of the segmentation and centrelines such as total length of the branches, number of branches, number of generations, and volume of the 3D model.

RESULTS

The TSF method was the most automatic, while the Mimics Pulmonology Module (MPM) and the Mimics Basic Module (MBM) resulted in the highest number of branches. MPM is the software which demands the least number of clicks to process the data. We found that the freely available OsiriX was less accurate compared to the other methods regarding segmentation results. However, the TSF method provided results fastest regarding number of clicks. The MPM was able to find the highest number of branches and generations. On the other hand, the TSF is fully automatic and it provides the user with both segmentation of the airways and the centerlines. Reference segmentation comparison averages and standard deviations for MPM and TSF correspond to literature.

CONCLUSION

The TSF is able to segment the airways and extract the centerlines in one single step. The number of branches found is lower for the TSF method than in Mimics. OsiriX demands the highest number of clicks to process the data, the segmentation is often sparse and extracting the centerline requires the use of another software system. Two of the software systems performed satisfactory with respect to be used in preprocessing CT images for navigated bronchoscopy, i.e. the TSF method and the MPM. According to reference segmentation both TSF and MPM are comparable with other segmentation methods. The level of automaticity and the resulting high number of branches plus the fact that both centerline and the surface of the airways were extracted, are requirements we considered particularly important. The in house method has the advantage of being an integrated part of a navigation platform for bronchoscopy, whilst the other methods can be considered preprocessing tools to a navigation system.

A "loop" shape descriptor and its application to automated segmentation of airways from CT scans

PURPOSE

A novel shape descriptor is presented to aid an automated identification of the airways depicted on computed tomography (CT) images.

METHODS

Instead of simplifying the tubular characteristic of the airways as an ideal mathematical cylindrical or circular shape, the proposed "loop" shape descriptor exploits the fact that the cross sections of any tubular structure (regardless of its regularity) always appear as a loop. In implementation, the authors first reconstruct the anatomical structures in volumetric CT as a three-dimensional surface model using the classical marching cubes algorithm. Then, the loop descriptor is applied to locate the airways with a concave loop cross section. To deal with the variation of the airway walls in density as depicted on CT images, a multiple threshold strategy is proposed. A publicly available chest CT database consisting of 20 CT scans, which was designed specifically for evaluating an airway segmentation algorithm, was used for quantitative performance assessment. Measures, including length, branch count, and generations, were computed under the aid of a skeletonization operation.

RESULTS

For the test dataset, the airway length ranged from 64.6 to 429.8 cm, the generation ranged from 7 to 11, and the branch number ranged from 48 to 312. These results were comparable to the performance of the state-of-the-art algorithms validated on the same dataset.

CONCLUSIONS

The authors' quantitative experiment demonstrated the feasibility and reliability of the developed shape descriptor in identifying lung airways.

A three-stage method for the 3D reconstruction of the tracheobronchial tree from CT scans

This paper proposes a method for segmenting the airways from CT scans of the chest to obtain a 3D model that can be used in the virtual bronchoscopy for the exploration and the planning of paths to the lesions. The method is composed of 3 stages: a gross segmentation that reconstructs the main airway tree using adaptive region growing, a finer segmentation that identifies any potential airway region based on a 2D process that enhances bronchi walls using local information, and a final process to connect any isolated bronchus to the main airways using a morphologic reconstruction process and a path planning technique. The paper includes two examples for the evaluation and discussion of the proposal.

3D TRACHEOBRONCHIAL AIRWAY TREE SEGMENTATION FROM THORAX CT IMAGES

Segmentation of the lung structures is an important operation in the medical analysis. This paper is proposing a region growing algorithm for airway segmentation. The proposed method for the airway tree segmentation works fully in 3D and performs the measurements in the original gray-scale volume for increased accuracy and efficiency. This algorithm uses region growing and morphological operators. The airway segmentation algorithm is intended to serve qualitative and quantitative purposes, and additional three descriptors are being used for evaluation of the airway segmentation. The proposed method was evaluated using the database of 15 patients who underwent lung CT scans, with varying image quality and anatomical changes. Overlap measure is used to show the difference between measured volumes from the established gold standard and the proposed method. The student t-test and Pearson test showed high correlation of the results with the gold standard. Overall, the test results were satisfactory since accurate segmentation was achieved in 95% of the patients.

Optimal graph search based segmentation of airway tree double surfaces across bifurcations

Identification of both the luminal and the wall areas of the bronchial tree structure from volumetric X-ray computed tomography (CT) data sets is of critical importance in distinguishing important phenotypes within numerous major lung diseases including chronic obstructive pulmonary diseases (COPD) and asthma. However, accurate assessment of the inner and outer airway wall surfaces of a complete 3-D tree structure is difficult due to their complex nature, particularly around the branch areas. In this paper, we extend a graph search based technique (LOGISMOS) to simultaneously identify multiple inter-related surfaces of branching airway trees. We first perform a presegmentation of the input 3-D image to obtain basic information about the tree topology. The presegmented image is resampled along judiciously determined paths to produce a set of vectors of voxels (called voxel columns). The resampling process utilizes medial axes to ensure that voxel columns of appropriate lengths and directions are used to capture the object surfaces without interference. A geometric graph is constructed whose edges connect voxels in the resampled voxel columns and enforce validity of the smoothness and separation constraints on the sought surfaces. Cost functions with directional information are employed to distinguish inner and outer walls. The assessment of wall thickness measurement on a CT-scanned double-wall physical phantom (patterned after an in vivo imaged human airway tree) achieved highly accurate results on the entire 3-D tree. The observed mean signed error of wall thickness ranged from -0.09 ±0.24 mm to 0.07 ±0.23 mm in bifurcating/nonbifurcating areas. The mean unsigned errors were 0.16±0.12 mm to 0.20±0.11 mm. When the airway wall surface was partitioned into meaningful subregions, the airway wall thickness accuracy was the same in most tested bifurcation/nonbifurcation and carina/noncarina regions (p=NS). Once validated on phantoms, our method was applied to human in vivo volumetric CT data to demonstrate relationships of airway wall thickness as a function of luminal dimension and airway tree generation. Wall thickness differences between the bifurcation/nonbifurcation regions were statistically significant (p < 0.05) for tree generations 6, 7, 8, and 9. In carina/noncarina regions, the wall thickness was statistically different in generations 1, 4, 5, 6, 7, and 8.

Computerized identification of airway wall in CT examinations using a 3D active surface evolution approach

Airway diseases (e.g., asthma, emphysema, and chronic bronchitis) are extremely common worldwide. Any morphological variations (abnormalities) of airways may physically change airflow and ultimately affect the ability of the lungs in gas exchange. In this study, we describe a novel algorithm aimed to automatically identify airway walls depicted on CT images. The underlying idea is to place a three-dimensional (3D) surface model within airway regions and thereafter allow this model to evolve (deform) under predefined external and internal forces automatically to the location where these forces reach a state of balance. By taking advantage of the geometric and the density characteristics of airway walls, the evolution procedure is performed in a distance gradient field and ultimately stops at regions with the highest contrast. The performance of this scheme was quantitatively evaluated from several perspectives. First, we assessed the accuracy of the developed scheme using a dedicated lung phantom in airway wall estimation and compared it with the traditional full-width at half maximum (FWHM) method. The phantom study shows that the developed scheme has an error ranging from 0.04 mm to 0.36 mm, which is much smaller than the FWHM method with an error ranging from 0.16 mm to 0.84 mm. Second, we compared the results obtained by the developed scheme with those manually delineated by an experienced (>30 years) radiologist on clinical chest CT examinations, showing a mean difference of 0.084 mm. In particular, the sensitivity of the scheme to different reconstruction kernels was evaluated on real chest CT examinations. For the 'lung', 'bone' and 'standard' kernels, the average airway wall thicknesses computed by the developed scheme were 1.302 mm, 1.333 mm and 1.339 mm, respectively. Our preliminary experiments showed that the scheme had a reasonable accuracy in airway wall estimation. For a clinical chest CT examination, it took around 4 min for this scheme to identify the inner and outer airway walls on a modern PC.

CT based computerized identification and analysis of human airways: a review

As one of the most prevalent chronic disorders, airway disease is a major cause of morbidity and mortality worldwide. In order to understand its underlying mechanisms and to enable assessment of therapeutic efficacy of a variety of possible interventions, noninvasive investigation of the airways in a large number of subjects is of great research interest. Due to its high resolution in temporal and spatial domains, computed tomography (CT) has been widely used in clinical practices for studying the normal and abnormal manifestations of lung diseases, albeit there is a need to clearly demonstrate the benefits in light of the cost and radiation dose associated with CT examinations performed for the purpose of airway analysis. Whereas a single CT examination consists of a large number of images, manually identifying airway morphological characteristics and computing features to enable thorough investigations of airway and other lung diseases is very time-consuming and susceptible to errors. Hence, automated and semiautomated computerized analysis of human airways is becoming an important research area in medical imaging. A number of computerized techniques have been developed to date for the analysis of lung airways. In this review, we present a summary of the primary methods developed for computerized analysis of human airways, including airway segmentation, airway labeling, and airway morphometry, as well as a number of computer-aided clinical applications, such as virtual bronchoscopy. Both successes and underlying limitations of these approaches are discussed, while highlighting areas that may require additional work.

A differential geometric approach to automated segmentation of human airway tree

Airway diseases are frequently associated with morphological changes that may affect the physiology of the lungs. Accurate characterization of airways may be useful for quantitatively assessing prognosis and for monitoring therapeutic efficacy. The information gained may also provide insight into the underlying mechanisms of various lung diseases. We developed a computerized scheme to automatically segment the 3-D human airway tree depicted on computed tomography (CT) images. The method takes advantage of both principal curvatures and principal directions in differentiating airways from other tissues in geometric space. A "puzzle game" procedure is used to identify false negative regions and reduce false positive regions that do not meet the shape analysis criteria. The negative impact of partial volume effects on small airway detection is partially alleviated by repeating the developed differential geometric analysis on lung anatomical structures modeled at multiple iso-values (thresholds). In addition to having advantages, such as full automation, easy implementation and relative insensitivity to image noise and/or artifacts, this scheme has virtually no leakage issues and can be easily extended to the extraction or the segmentation of other tubular type structures (e.g., vascular tree). The performance of this scheme was assessed quantitatively using 75 chest CT examinations acquired on 45 subjects with different slice thicknesses and using 20 publicly available test cases that were originally designed for evaluating the performance of different airway tree segmentation algorithms.

Shape "break-and-repair" strategy and its application to automated medical image segmentation

In three-dimensional medical imaging, segmentation of specific anatomy structure is often a preprocessing step for computer-aided detection/diagnosis (CAD) purposes, and its performance has a significant impact on diagnosis of diseases as well as objective quantitative assessment of therapeutic efficacy. However, the existence of various diseases, image noise or artifacts, and individual anatomical variety generally impose a challenge for accurate segmentation of specific structures. To address these problems, a shape analysis strategy termed "break-and-repair" is presented in this study to facilitate automated medical image segmentation. Similar to surface approximation using a limited number of control points, the basic idea is to remove problematic regions and then estimate a smooth and complete surface shape by representing the remaining regions with high fidelity as an implicit function. The innovation of this shape analysis strategy is the capability of solving challenging medical image segmentation problems in a unified framework, regardless of the variability of anatomical structures in question. In our implementation, principal curvature analysis is used to identify and remove the problematic regions and radial basis function (RBF) based implicit surface fitting is used to achieve a closed (or complete) surface boundary. The feasibility and performance of this strategy are demonstrated by applying it to automated segmentation of two completely different anatomical structures depicted on CT examinations, namely human lungs and pulmonary nodules. Our quantitative experiments on a large number of clinical CT examinations collected from different sources demonstrate the accuracy, robustness, and generality of the shape "break-and-repair" strategy in medical image segmentation.

Robust 3-D airway tree segmentation for image-guided peripheral bronchoscopy

A vital task in the planning of peripheral bronchoscopy is the segmentation of the airway tree from a 3-D multidetector computed tomography chest scan. Unfortunately, existing methods typically do not sufficiently extract the necessary peripheral airways needed to plan a procedure. We present a robust method that draws upon both local and global information. The method begins with a conservative segmentation of the major airways. Follow-on stages then exhaustively search for additional candidate airway locations. Finally, a graph-based optimization method counterbalances both the benefit and cost of retaining candidate airway locations for the final segmentation. Results demonstrate that the proposed method typically extracts 2-3 more generations of airways than several other methods, and that the extracted airway trees enable image-guided bronchoscopy deeper into the human lung periphery than past studies.

Pulmonary lobe segmentation in CT examinations using implicit surface fitting

Lobe identification in computed tomography (CT) examinations is often an important consideration during the diagnostic process as well as during treatment planning because of their relative independence of each other in terms of anatomy and function. In this paper, we present a new automated scheme for segmenting lung lobes depicted on 3-D CT examinations. The unique characteristic of this scheme is the representation of fissures in the form of implicit functions using Radial Basis Functions (RBFs), capable of seamlessly interpolating "holes" in the detected fissures and smoothly extrapolating the fissure surfaces to the lung boundaries resulting in a "natural" segmentation of lung lobes. A previously developed statistically based approach is used to detect pulmonary fissures and the constraint points for implicit surface fitting are selected from detected fissure surfaces in a greedy manner to improve fitting efficiency. In a preliminary assessment study, lobe segmentation results of 65 chest CT examinations, five of which were reconstructed with three section thicknesses of 0.625 mm, 1.25 mm, and 2.5 mm, were subjectively and independently evaluated by two experienced chest radiologists using a five category rating scale (i.e., excellent, good, fair, poor, and unacceptable). Thirty-three of 65 examinations (50.8%) with a section thickness of 0.625 mm were rated as either "excellent" or "good" by both radiologists and only one case (1.5%) was rated by both radiologists as "poor" or "unacceptable." Comparable performance was obtained with a slice thickness of 1.25 mm, but substantial performance deterioration occurred in examinations with a section thickness of 2.5 mm. The advantages of this scheme are its full automation, relative insensitivity to fissure completeness, and ease of implementation.

A Computational geometry approach to automated pulmonary fissure segmentation in CT examinations

Identification of pulmonary fissures, which form the boundaries between the lobes in the lungs, may be useful during clinical interpretation of computed tomography (CT) examinations to assess the early presence and characterization of manifestation of several lung diseases. Motivated by the unique nature of the surface shape of pulmonary fissures in 3-D space, we developed a new automated scheme using computational geometry methods to detect and segment fissures depicted on CT images. After a geometric modeling of the lung volume using the marching cubes algorithm, Laplacian smoothing is applied iteratively to enhance pulmonary fissures by depressing nonfissure structures while smoothing the surfaces of lung fissures. Next, an extended Gaussian image based procedure is used to locate the fissures in a statistical manner that approximates the fissures using a set of plane "patches." This approach has several advantages such as independence of anatomic knowledge of the lung structure except the surface shape of fissures, limited sensitivity to other lung structures, and ease of implementation. The scheme performance was evaluated by two experienced thoracic radiologists using a set of 100 images (slices) randomly selected from 10 screening CT examinations. In this preliminary evaluation 98.7% and 94.9% of scheme segmented fissure voxels are within 2 mm of the fissures marked independently by two radiologists in the testing image dataset. Using the scheme detected fissures as reference, 89.4% and 90.1% of manually marked fissure points have distance </= 2 mm to the reference suggesting a possible under-segmentation of the scheme. The case-based root mean square (rms) distances ("errors") between our scheme and the radiologist ranged from 1.48 +/-0.92 to 2.04 +/-3.88 mm. The discrepancy of fissure detection results between the automated scheme and either radiologist is smaller in this dataset than the interreader variability.

A representation and classification scheme for tree-like structures in medical images: analyzing the branching pattern of ductal trees in X-ray galactograms

We propose a multistep approach for representing and classifying tree-like structures in medical images. Tree-like structures are frequently encountered in biomedical contexts; examples are the bronchial system, the vascular topology, and the breast ductal network. We use tree encoding techniques, such as the depth-first string encoding and the PrUfer encoding, to obtain a symbolic string representation of the tree's branching topology; the problem of classifying trees is then reduced to string classification. We use the tf-idf text mining technique to assign a weight of significance to each string term (i.e., tree node label). Similarity searches and k-nearest neighbor classification of the trees is performed using the tf-idf weight vectors and the cosine similarity metric. We applied our approach to characterize the ductal tree-like parenchymal structure in X-ray galactograms, in order to distinguish among different radiological findings. Experimental results demonstrate the effectiveness of the proposed approach with classification accuracy reaching up to 86%, and also indicate that our method can potentially aid in providing insight to the relationship between branching patterns and function or pathology.

Automated segmentation and morphometric analysis of the human airway tree from multidetector CT images

Remarkable advances in computed tomography (CT) technology geared our research toward investigating the integrative function of the lung and the development of a database of the airway tree incorporating anatomical and functional data with computational models. As part of this project, we are developing the algorithm to construct an anatomically realistic geometric model of airways from CT images. The basic concept of the algorithm is to segment as many airway trees as possible from CT images and later correct quantified parameters based on CT values. CT images are acquired with a 64-channel multidetector CT, and the airway is then extracted from them by the region-growing method while maintaining connectivity. Using this method, we extracted 428 airways up to the 14th branching generation. Although the airway diameters up to the 4th generation showed good agreement with those reported in an autopsy study, those in later generations were all greater than the reported values because of the limited resolution of the CT images. We corrected the errors in diameters by assessing the relationship between the diameter and median value of Hounsfield unit (HU) intensity of each airway; consequently, the diameters up to generation 8 agreed well with the reported values. Based on these results, we conclude that the use of HU-based correction algorithm combined with rough segmentation can be another way to improve data accuracy in the morphometric analysis of airways from CTs.

Finite element 3D reconstruction of the pulmonary acinus imaged by synchrotron X-ray tomography

The alveolated structure of the pulmonary acinus plays a vital role in gas exchange function. Three-dimensional (3D) analysis of the parenchymal region is fundamental to understanding this structure-function relationship, but only a limited number of attempts have been conducted in the past because of technical limitations. In this study, we developed a new image processing methodology based on finite element (FE) analysis for accurate 3D structural reconstruction of the gas exchange regions of the lung. Stereologically well characterized rat lung samples (Pediatr Res 53: 72-80, 2003) were imaged using high-resolution synchrotron radiation-based X-ray tomographic microscopy. A stack of 1,024 images (each slice: 1024 x 1024 pixels) with resolution of 1.4 mum(3) per voxel were generated. For the development of FE algorithm, regions of interest (ROI), containing approximately 7.5 million voxels, were further extracted as a working subunit. 3D FEs were created overlaying the voxel map using a grid-based hexahedral algorithm. A proper threshold value for appropriate segmentation was iteratively determined to match the calculated volume density of tissue to the stereologically determined value (Pediatr Res 53: 72-80, 2003). The resulting 3D FEs are ready to be used for 3D structural analysis as well as for subsequent FE computational analyses like fluid dynamics and skeletonization.

Adaptive border marching algorithm: automatic lung segmentation on chest CT images

Segmentation of the lungs in chest-computed tomography (CT) is often performed as a preprocessing step in lung imaging. This task is complicated especially in presence of disease. This paper presents a lung segmentation algorithm called adaptive border marching (ABM). Its novelty lies in the fact that it smoothes the lung border in a geometric way and can be used to reliably include juxtapleural nodules while minimizing oversegmentation of adjacent regions such as the abdomen and mediastinum. Our experiments using 20 datasets demonstrate that this computational geometry algorithm can re-include all juxtapleural nodules and achieve an average oversegmentation ratio of 0.43% and an average under-segmentation ratio of 1.63% relative to an expert determined reference standard. The segmentation time of a typical case is under 1min on a typical PC. As compared to other available methods, ABM is more robust, more efficient and more straightforward to implement, and once the chest CT images are input, there is no further interaction needed from users. The clinical impact of this method is in potentially avoiding false negative CAD findings due to juxtapleural nodules and improving volumetry and doubling time accuracy.

Automatic segmentation of the lungs using robust level sets

This paper presents a method for the automatic segmentation of the lungs in X-ray computed tomography (CT) images. The proposed technique is based on the use of a robust geometric active contour that is initialized around the lungs, automatically splits in two, and performs outlier rejection during the curve evolution. The technique starts by grey-level thresholding of the images followed by edge detection. Then the edge connected points are organized into strokes and classified as valid or invalid. A confidence degree (weight) is assigned to each stroke and updated during the evolution process with the valid strokes receiving a high confidence degree and the confidence degrees of the outlier strokes tending to zero. These weights depend on the distance between the stroke points and the curve and also on the stroke size. Initialization of the curve is fully automatic. Experimental results show the effectiveness of the proposed technique.

Gray and white matter delineation in the human spinal cord using diffusion tensor imaging and fuzzy logic

RATIONALE AND OBJECTIVES

Diffusion tensor imaging (DTI) has been used extensively in determining morphology and connectivity of the brain; however, similar analysis in the spinal cord has proven difficult. The objective of this study was to improve the delineation of gray and white matter in the spinal cord by applying signal processing techniques to the eigenvalues of the diffusion tensor. Our approach involved creating anisotropy indices based on the difference between eigenvalues and mean diffusivity then using a fuzzy inference system (FIS) to delineate between gray and white matter in the human cervical spinal cord.

MATERIALS AND METHODS

DTI was performed on the cervical spinal cord in five neurologically intact subjects. Distributions were extracted for regions of gray and white matter through the use of a digitized histologic template. Fuzzy membership functions were created based on these distributions. Detectability index and receiver operating characteristic (ROC) analysis was performed on traditional DTI indices and FIS classified regions.

RESULTS

A significantly higher contrast between gray and white matter was observed using fuzzy classification compared with traditionally used DTI indices based on the detectability index (P < .001) and trends in the ROC analysis. Reconstructed images from the FIS qualitatively showed a better anatomical representation of the spinal cord compared with traditionally used DTI indices.

CONCLUSIONS

Diffusion tensor imaging using an FIS for tissue classification provides high contrast between spinal gray and white matter compared with traditional DTI indices and may provide a noninvasive technique to quantify the integrity and morphology of the human spinal cord following injury.

Automated classification of lung bronchovascular anatomy in CT using AdaBoost

Lung CAD systems require the ability to classify a variety of pulmonary structures as part of the diagnostic process. The purpose of this work was to develop a methodology for fully automated voxel-by-voxel classification of airways, fissures, nodules, and vessels from chest CT images using a single feature set and classification method. Twenty-nine thin section CT scans were obtained from the Lung Image Database Consortium (LIDC). Multiple radiologists labeled voxels corresponding to the following structures: airways (trachea to 6th generation), major and minor lobar fissures, nodules, and vessels (hilum to peripheral), and normal lung parenchyma. The labeled data was used in conjunction with a supervised machine learning approach (AdaBoost) to train a set of ensemble classifiers. Each ensemble classifier was trained to detect voxels part of a specific structure (either airway, fissure, nodule, vessel, or parenchyma). The feature set consisted of voxel attenuation and a small number of features based on the eigenvalues of the Hessian matrix (used to differentiate structures by shape). When each ensemble classifier was composed of 20 weak classifiers, the AUC values for the airway, fissure, nodule, vessel, and parenchyma classifiers were 0.984+/-0.011, 0.949+/-0.009, 0.945+/-0.018, 0.953+/-0.016, and 0.931+/-0.015, respectively. The strong results suggest that this could be an effective input to higher-level anatomical based segmentation models with the potential to improve CAD performance.

Fully automated system for three-dimensional bronchial morphology analysis using volumetric multidetector computed tomography of the chest

Recent advancements in computed tomography (CT) have enabled quantitative assessment of severity and progression of large airway damage in chronic pulmonary disease. The advent of fast multidetector computed tomography scanning has allowed the acquisition of rapid, low-dose 3D volumetric pulmonary scans that depict the bronchial tree in great detail. Volumetric CT allows quantitative indices of bronchial airway morphology to be calculated, including airway diameters, wall thicknesses, wall area, airway segment lengths, airway taper indices, and airway branching patterns. However, the complexity and size of the bronchial tree render manual measurement methods impractical and inaccurate. We have developed an integrated software package utilizing a new measurement algorithm termed mirror-image Gaussian fit that enables the user to perform automated bronchial segmentation, measurement, and database archiving of the bronchial morphology in high resolution and volumetric CT scans and also allows 3D localization, visualization, and registration.

Repulsive force based snake model to segment and track neuronal axons in 3D microscopy image stacks

The branching patterns of axons and dendrites are fundamental structural properties that affect the synaptic connectivity of axons. Although today three-dimensional images of fluorescently labeled processes can be obtained to study axonal branching, there are no robust methods of tracing individual axons. This paper describes a repulsive force based snake model to segment and track axonal profiles in 3D images. This new method segments all the axonal profiles in a 2D image and then uses the results obtained from that image as prior information to help segment the adjacent 2D image. In this way, the segmentation successfully connects axonal profiles over hundreds of images in a 3D image stack. Individual axons can then be extracted based on the segmentation results. The utility and performance of the method are demonstrated using 3D axonal images obtained from transgenic mice that express fluorescent protein.

Segmentation and quantitative analysis of intrathoracic airway trees from computed tomography images

The segmentation of the human airway tree from volumetric multidetector-row computed tomography images is an important prerequisite for many clinical applications and physiologic studies. We present a new airway segmentation method based on fuzzy connectivity. Small adaptive regions of interest are used that follow the airway branches as they are segmented. This method works on various types of scans (low dose and regular dose, normal subjects and diseased subjects) without the need for the user to manually adjust any parameters. Comparison with a commonly used region-growing segmentation algorithm shows that this method retrieves a significantly higher count of airway branches. In an additional processing step, this method provides accurate cross-sectional airway measurements that are conducted in the original gray-level volume. Validation on a phantom shows that subvoxel accuracy is achieved for all airway sizes and airway orientations. The utility of the reported method is demonstrated in a comparative analysis of normal and cystic fibrosis airway trees.

Computer analysis of computed tomography scans of the lung: a survey

Current computed tomography (CT) technology allows for near isotropic, submillimeter resolution acquisition of the complete chest in a single breath hold. These thin-slice chest scans have become indispensable in thoracic radiology, but have also substantially increased the data load for radiologists. Automating the analysis of such data is, therefore, a necessity and this has created a rapidly developing research area in medical imaging. This paper presents a review of the literature on computer analysis of the lungs in CT scans and addresses segmentation of various pulmonary structures, registration of chest scans, and applications aimed at detection, classification and quantification of chest abnormalities. In addition, research trends and challenges are identified and directions for future research are discussed.

Atlas-driven lung lobe segmentation in volumetric X-ray CT images

High-resolution X-ray computed tomography (CT) imaging is routinely used for clinical pulmonary applications. Since lung function varies regionally and because pulmonary disease is usually not uniformly distributed in the lungs, it is useful to study the lungs on a lobe-by-lobe basis. Thus, it is important to segment not only the lungs, but the lobar fissures as well. In this paper, we demonstrate the use of an anatomic pulmonary atlas, encoded with a priori information on the pulmonary anatomy, to automatically segment the oblique lobar fissures. Sixteen volumetric CT scans from 16 subjects are used to construct the pulmonary atlas. A ridgeness measure is applied to the original CT images to enhance the fissure contrast. Fissure detection is accomplished in two stages: an initial fissure search and a final fissure search. A fuzzy reasoning system is used in the fissure search to analyze information from three sources: the image intensity, an anatomic smoothness constraint, and the atlas-based search initialization. Our method has been tested on 22 volumetric thin-slice CT scans from 12 subjects, and the results are compared to manual tracings. Averaged across all 22 data sets, the RMS error between the automatically segmented and manually segmented fissures is 1.96 +/- 0.71 mm and the mean of the similarity indices between the manually defined and computer-defined lobe regions is 0.988. The results indicate a strong agreement between the automatic and manual lobe segmentations.

Automatic segmentation of the lungs using multiple active contours and outlier model

This paper presents a method for the automatic segmentation of the lungs in X-ray computed tomography (CT) images. The proposed technique is based on the use of multiple active contour models (ACMs) for the simultaneous segmentation of both lungs and outlier detection. The technique starts by grey-level thresholding of the images followed by edge detection. Then the edge points are organized in strokes and a set of weights summing to one is assigned to each stroke. These weights represent the soft assignment of the stroke to each of the ACMs and depend on the distance between the stroke points and the ACM units, on gradient direction information and also on the stroke size. Both the weights and the ACMs energy minimization are computed using the generalized expectation-maximization (EM) algorithm. Initialization of the ACM's is fully automatic. Experimental results show the effectiveness of the proposed technique.

Intrathoracic airway trees: segmentation and airway morphology analysis from low-dose CT scans

The segmentation of the human airway tree from volumetric computed tomography (CT) images builds an important step for many clinical applications and for physiological studies. Previously proposed algorithms suffer from one or several problems: leaking into the surrounding lung parenchyma, the need for the user to manually adjust parameters, excessive runtime. Low-dose CT scans are increasingly utilized in lung screening studies, but segmenting them with traditional airway segmentation algorithms often yields less than satisfying results. In this paper, a new airway segmentation method based on fuzzy connectivity is presented. Small adaptive regions of interest are used that follow the airway branches as they are segmented. This has several advantages. It makes it possible to detect leaks early and avoid them, the segmentation algorithm can automatically adapt to changing image parameters, and the computing time is kept within moderate values. The new method is robust in the sense that it works on various types of scans (low-dose and regular dose, normal subjects and diseased subjects) without the need for the user to manually adjust any parameters. Comparison with a commonly used region-grow segmentation algorithm shows that the newly proposed method retrieves a significantly higher count of airway branches. A method that conducts accurate cross-sectional airway measurements on airways is presented as an additional processing step. Measurements are conducted in the original gray-level volume. Validation on a phantom shows that subvoxel accuracy is achieved for all airway sizes and airway orientations.

Pulmonary airways: 3-D reconstruction from multislice CT and clinical investigation

In the framework of computer-aided diagnosis, this paper proposes a novel functionality for the computerized tomography (CT)-based investigation of the pulmonary airways. It relies on an energy-based three-dimensional (3-D) reconstruction of the bronchial tree from multislice CT acquisitions, up to the sixth- to seventh-order subdivisions. Global and local analysis of the reconstructed airways is possible by means of specific visualization modalities, respectively, the CT bronchography and the virtual bronchoscopy. The originality of the 3-D reconstruction approach consists in combining axial and radial propagation potentials to control the growth of a subset of low-order airways extracted from the CT volume by means of a robust mathematical morphology operator-the selective marking and depth constrained (SMDC) connection cost. The proposed approach proved to be robust with respect to a large spectrum of airway pathologies, including even severe stenosis (bronchial lumen obstruction/collapse). Validated by expert radiologists, examples of airway 3-D reconstructions are presented and discussed for both normal and pathological cases. They highlight the interest in considering CT bronchography and virtual bronchoscopy as complementary tools for clinical diagnosis and follow-up of airway diseases.

3D airway segmentation via hyperpolarized 3He gas MRI by using scale-based fuzzy connectedness

Computerized segmentation of 3D tracheobronchial tree is a necessary first step for subsequent registration and analysis of pulmonary airway and vascular magnetic resonance (MR) images obtained by using hyperpolarized 3Helium gas and Gadolinium. The scientific and clinical implications of acquiring these data on the tracheobronchial tree (for studying ventilation, V) and on the coinciding pulmonary arterioles (for studying perfusion, Q), is the next frontier for static and dynamic pulmonary MRI. In this paper, we report an airway segmentation method from 3He MR images based on the scale-based fuzzy connectedness approach. Incorporated in this method are the pre-processing steps of inhomogeneity correction and intensity standardization. The basic sequential steps in the proposed airway segmentation method are: (1) image acquisition, (2) radio frequency field inhomogeneity correction, (3) standardization of MR image intensity scale, (4) seed specification, (5) scale-based fuzzy connected segmentation of airways, and (6) thresholding and binarization. The majority of these steps are automatically executed; others allow interaction through a graphical interface provided in the 3DVIEWNIX software system, in which the algorithms are implemented. The method achieves an overall precision of about 98% in terms of the extent of overlap in repeated segmentations. Its level of accuracy can be described by a true positive volume fraction of about 98% (considering manual delineation as the surrogate of true delineation), and a false negative and positive volume fraction of about 1%. The total operator and computational time required per study are on the average 2 and 20 min.

Hybrid segmentation and virtual bronchoscopy based on CT images

RATIONALE AND OBJECTIVES

Introduction of combination of the segmentation tool SegoMeTex and the virtual endoscopy system VIVENDI to perform virtual endoscopic inspections of the human lung. This virtual bronchoscopy system enables visualization of the tracheobronchial tree down to seventh generation. Furthermore, the modified virtual system visualizes hidden structures such as segmented vascular system or tumors.

MATERIALS AND METHODS

The segmentation is based on image data acquired by a multislice computed tomography scanner. SegoMeTex is used to segment the tracheobronchial tree by a hybrid system with minimal user action. Similarly, the complementary pulmonary arterial can be segmented, whereas additional structures such as tumors are marked manually. On this dataset, subsequently, data structures of the inner surface for virtual endoscopy are generated. Finally, the dataset can be explored by a virtual bronchoscopy procedure using the VIVENDI system.

RESULTS

The segmentation method was successfully tested on 22 patients. The hybrid segmentation system identified bronchi up to the sixth generation with a sensitivity of more than 58%, and a positive predictive value of more than 90%. After the segmentation, the datasets are explored interactively (>30 fps on a standard personal computer platform in real-time rendering) using the virtual endoscopy software. The exploration exposed a high-quality reconstruction, even of small structures throughout the dataset.

CONCLUSION

Virtual bronchoscopy in combining with a highly sensitive segmentation is a valuable tool for the localization and measurement of stenosis for resection planning.

A computer-aided diagnosis for locating abnormalities in bone scintigraphy by a fuzzy system with a three-step minimization approach

Bone scintigraphy is an effective method to diagnose bone diseases such as bone tumors. In the scintigraphic images, bone abnormalities are widely scattered on the whole body. Conventionally, radiologists visually check the whole-body images and find the distributed abnormalities based on their expertise. This manual process is time-consuming and it is not unusual to miss some abnormalities. In this paper, a computer-aided diagnosis (CAD) system is proposed to assist radiologists in the diagnosis of bone scintigraphy. The system will provide warning marks and abnormal scores on some locations of the images to direct radiologists' attention toward these locations. A fuzzy system called characteristic-point-based fuzzy inference system (CPFIS) is employed to implement the diagnosis system and three minimizations are used to systematically train the CPFIS. Asymmetry and brightness are chosen as the two inputs to the CPFIS according to radiologists' knowledge. The resulting CAD system is of a small-sized rule base such that the resulting fuzzy rules can be not only easily understood by radiologists, but also matched to and compared with their expert knowledge. The prototype CAD system was tested on 82 abnormal images and 27 normal images. We employed free-response receiver operating characteristics method with the mean number of false positives (FPs) and the sensitivity as performance indexes to evaluate the proposed system. The sensitivity is 91.5% (227 of 248) and the mean number of FPs is 37.3 per image. The high sensitivity and moderate numbers of FP marks per image shows that the proposed method can provide an effective second-reader information to radiologists in the diagnosis of bone scintigraphy.

Automated lung segmentation in X-ray computed tomography: development and evaluation of a heuristic threshold-based scheme

RATIONALE AND OBJECTIVES

To develop and evaluate a reliable, fully-automated lung segmentation scheme for application in X-ray computed tomography.

MATERIALS AND METHODS

The automated scheme was heuristically developed using a slice-based, pixel-value threshold and two sets of classification rules. Features used in the rules include size, circularity, and location. The segmentation scheme operates slice-by-slice and performs three key operations: (1) image preprocessing to remove background pixels, (2) computation and application of a pixel-value threshold to identify lung tissue, and (3) refinement of the initial segmented regions to prune incorrectly detected airways and separate fused right and left lungs.

RESULTS

The performance of the automated segmentation scheme was evaluated using 101 computed tomography cases (91 thick slice, 10 thin slice scans). The 91 thick cases were pre- and post-surgery from 50 patients and were not independent. The automated scheme successfully segmented 94.0% of the 2,969 thick slice images and 97.6% of the 1,161 thin slice images. The mean difference of the total lung volumes calculated by the automated scheme and functional residual capacity plus 60% inspiratory capacity was -24.7 +/- 508.1 mL. The mean differences of the total lung volumes calculated by the automated scheme and an established, commonly used semi-automated scheme were 95.2 +/- 52.5 mL and -27.7 +/- 66.9 mL for the thick and thin slice cases, respectively.

CONCLUSION

This simple, fully-automated lung segmentation scheme provides an objective tool to facilitate lung segmentation from computed tomography scans.

Maximizing quantitative accuracy of lung airway lumen and wall measures obtained from X-ray CT imaging

To objectively quantify airway geometry from three-dimensional computed tomographic (CT) images, an idealized (circular cross section) airway model is parameterized by airway luminal caliber, wall thickness, and tilt angle. Using a two-dimensional CT slice, an initial guess for the airway center, and the full-width-half-maximum principle, we form an estimate of inner and outer airway wall locations. We then fit ellipses to the inner and outer airway walls via a direct least squares fit and use the major and minor axes of the ellipses to estimate the tilt and in-plane rotation angles. Convolving the airway model, initialized with these estimates, with the three-dimensional scanner point-spread function forms the predicted image. The difference between predicted and actual images is minimized by refining the model parameter estimates via a multidimensional, unconstrained, nonlinear minimization routine. When optimization converges, airway model parameters estimate the airway inner and outer radii and tilt angle. Results using a Plexiglas phantom show that tilt angle is estimated to within +/-4 degrees and both inner and outer radii to within one-half pixel when a "standard" CT reconstruction kernel is used. By opening up the ability to measure airways that are not oriented perpendicular to the scanning plane, this method allows evaluation of a greater sampling of airways in a two-dimensional CT slice than previously possible. In addition, by combining the tilt-angle compensation with the deconvolution method, we provide significant improvement over the previous full-width-half-maximum method for assessing location of the luminal edge but not the outer edge of the airway wall.

Segmentation and analysis of the human airway tree from three-dimensional X-ray CT images

The lungs exchange air with the external environment via the pulmonary airways. Computed tomography (CT) scanning can be used to obtain detailed images of the pulmonary anatomy, including the airways. These images have been used to measure airway geometry, study airway reactivity, and guide surgical interventions. Prior to these applications, airway segmentation can be used to identify the airway lumen in the CT images. Airway tree segmentation can be performed manually by an image analyst, but the complexity of the tree makes manual segmentation tedious and extremely time-consuming. We describe a fully automatic technique for segmenting the airway tree in three-dimensional (3-D) CT images of the thorax. We use grayscale morphological reconstruction to identify candidate airways on CT slices and then reconstruct a connected 3-D airway tree. After segmentation, we estimate airway branchpoints based on connectivity changes in the reconstructed tree. Compared to manual analysis on 3-mm-thick electron-beam CT images, the automatic approach has an overall airway branch detection sensitivity of approximately 73%.

A method for the reconstruction of four-dimensional synchronized CT scans acquired during free breathing

Breathing motion is a significant source of error in radiotherapy treatment planning for the thorax and upper abdomen. Accounting for breathing motion has a profound effect on the size of conformal radiation portals employed in these sites. Breathing motion also causes artifacts and distortions in treatment planning computed tomography (CT) scans acquired during free breathing and also causes a breakdown of the assumption of the superposition of radiation portals in intensity-modulated radiation therapy, possibly leading to significant dose delivery errors. Proposed voluntary and involuntary breath-hold techniques have the potential for reducing or eliminating the effects of breathing motion, however, they are limited in practice, by the fact that many lung cancer patients cannot tolerate holding their breath. We present an alternative solution to accounting for breathing motion in radiotherapy treatment planning, where multislice CT scans are collected simultaneously with digital spirometry over many free breathing cycles to create a four-dimensional (4-D) image set, where tidal lung volume is the additional dimension. An analysis of this 4-D data leads to methods for digital-spirometry, based elimination or accounting of breathing motion artifacts in radiotherapy treatment planning for free breathing patients. The 4-D image set is generated by sorting free-breathing multislice CT scans according to user-defined tidal-volume bins. A multislice CT scanner is operated in the ciné mode, acquiring 15 scans per couch position, while the patient undergoes simultaneous digital-spirometry measurements. The spirometry is used to retrospectively sort the CT scans by their correlated tidal lung volume within the patient's normal breathing cycle. This method has been prototyped using data from three lung cancer patients. The actual tidal lung volumes agreed with the specified bin volumes within standard deviations ranging between 22 and 33 cm3. An analysis of sagittal and coronal images demonstrated relatively small (<1 cm) motion artifacts along the diaphragm, even for tidal volumes where the rate of breathing motion is greatest. While still under development, this technology has the potential for revolutionizing the radiotherapy treatment planning for the thorax and upper abdomen.

Establishing a normative atlas of the human lung: intersubject warping and registration of volumetric CT images

RATIONALE AND OBJECTIVES

To establish the range of normal values for quantitative CT-based measures of lung structure and function, the authors developed a method for matching pulmonary structures across individuals and creating a normative human lung atlas.

MATERIALS AND METHODS

A computerized human lung atlas was synthesized from computed tomographic (CT) images from six subjects by means of three-dimensional image registration. The authors identified a set of reproducible feature points for each CT image and used these points to establish correspondences across subjects, used a landmark- and intensity-based consistent image registration algorithm to register a template image volume from the population to the rest of the pulmonary CT volumes in the population, averaged these transformations, and constructed an atlas by deforming the template with the average transformation.

RESULTS

The effectiveness of the authors' method was evaluated and visualized by means of both gray-level and segmented CT images. The method reduced the average landmark registration error from 10.5 mm to 0.4 mm and the average relative volume overlap error from 0.7 to 0.11 for the six data sets studied.

CONCLUSION

The method, and the computerized human lung atlas constructed and visualized by the authors with this method, provides a basis for establishing regional ranges of normative values for structural and functional measures of the human lung.

System for upper airway segmentation and measurement with MR imaging and fuzzy connectedness

RATIONALE AND OBJECTIVES

The purpose of this study was to evaluate whether a computerized system developed to help delineate the upper airway and surrounding structures with magnetic resonance (MR) imaging was effective for aiding in the diagnosis of upper airway disorders in children.

MATERIALS AND METHODS

The authors performed axial T2-weighted MR imaging to gather information about different aspects of the airway and its surrounding soft-tissue structures, including the adenoid and palatine tonsils, tongue, and soft palate. Images were processed and segmented to compute the architectural parameters of the airway (eg, surface description, volume, central [medial] line, and cross-sectional areas at planes perpendicular to the central line). The authors built a software package for the visualization, segmentation, registration, prefiltering, interpolation, standardization, and quantitative analysis of the airway and tonsils.

RESULTS

The system was tested with 40 patient studies. For every study, the system segmented and displayed a smooth three-dimensional rendition of the airway and its central line and a plot of the cross-sectional area of the airway orthogonal to the central line as a function of the distance from one end of the central line. The precision and accuracy for segmentation was 97%. The mean time taken per study was about 4 minutes and included the operator interaction time and processing time.

CONCLUSION

This method provides a robust and fast means of assessing the airway size, shape, and level of restriction, as well as a structural data set suitable for use in modeling studies of airflow and mechanics.

Three-dimensional human airway segmentation methods for clinical virtual bronchoscopy

RATIONALE AND OBJECTIVES

The segmentation of airways from CT images is a critical first step for numerous virtual bronchoscopic (VB) applications. Automatic or semiautomatic methods are necessary, since manual segmentation is prohibitively time consuming. The methods must be robust and operate within a reasonable time frame to be useful for clinical VB use. The authors developed an integrated airway segmentation system and demonstrated its effectiveness on a series of human images.

MATERIALS AND METHODS

The authors' airway segmentation system draws on two segmentation algorithms: (a) an adaptive region-growing algorithm and (b) a new hybrid algorithm that uses both region growing and mathematical morphology. Images from an ongoing VB study were segmented by means of both the adaptive region-growing and the new hybrid methods. The segmentation volume, branch number estimate, and segmentation quality were determined for each case.

RESULTS

The results demonstrate the need for an integrated segmentation system, since no single method is superior for all clinically relevant cases. The region-growing algorithm is the fastest and provides acceptable segmentations for most VB applications, but the hybrid method provides superior airway edge localization, making it better suited for quantitative applications. In addition, the authors show that prefiltering the image data before airway segmentation increases the robustness of both region-growing and hybrid methods.

CONCLUSION

The combination of these two algorithms with the prefiltering options allowed the successful segmentation of all test images. The times required for all segmentations were acceptable, and the results were suitable for the authors' VB application needs.

Computer-aided diagnosis of small pulmonary nodules

Computer-aided methods are now being developed for the detection and characterization of pulmonary nodules found in CT images, based on techniques from computer vision, image processing, and pattern classification. With the increasing resolution of modern CT scanners, computer methods provide continually improving accuracy, reproducibility, and utility in analyzing the larger numbers of images acquired in a lung screening exam or diagnostic study. This article describes the fundamental tools and issues involved in computer-aided nodule detection and characterization, as we move from two-dimensional toward three-dimensional automated methods. In particular, we focus on the new domain of "small" pulmonary nodules.

Cone-beam CT angiography of the thorax: an experimental study

The authors recently developed a cone-beam computed tomography (CT) scanner and this report presents their evaluation of its potential for thoracic vascular imaging. An X-ray tube and a video-fluoroscopic system were rotated around the objects and 360 projected images were collected in a 12-s scan. Each image was digitized and a 3 dimensional (D) image (256x256x256 voxel volume with a voxel dimension of 0.9x0.9x0.9 mm) was reconstructed. Two different 3D-CT angiographies were investigated in 2 pigs: right atriography and thoracic aortography. Each pig was anesthetized, mechanically ventilated and positioned within the scanner. Contrast agent was infused through the right atrium or the aortic root at a rate of 3 ml/s during the scan. The right atriography scan clearly delineated the anatomy of the pulmonary artery, heart chambers and thoracic aorta. The thoracic aortography scan also clearly delineated the aortic anatomy including the internal thoracic and intercostal arteries. In conclusion, cone-beam CT angiography is potentially useful for thoracic vascular imaging.