Search

Background and Purpose: We explored the feasibility of automated, arterial input function independent, vendor neutral prediction of core infarct, and penumbral tissue using complete and partial computed tomographic perfusion data sets through neural networks., Methods: Using retrospective computed tomographic perfusion data from 57 patients, split as training/validation (60%/40%), we developed and validated separate 2-dimensional U-net models for cerebral blood flow (CBF) and time to maximum (Tmax) maps calculation to predict core infarct and tissue at risk, respectively. Once trained, the full sets of 28 input images were sequentially reduced to equitemporal 14, 10, and 7 time points. The averaged structural similarity index measure between the model-derived images and ground truth perfusion maps was compared. Volumes for core infarct and Tmax were compared using the Pearson correlation coefficient., Results: Both CBF and Tmax maps derived using 28 and 14 time points had similar structural similarity index measure (0.80-0.81; P >0.05) when compared with ground truth images. The Pearson correlation for the CBF and Tmax volumes derived from the model using 28-tp with ground truth volumes derived from the RAPID software was 0.69 for CBF and 0.74 for Tmax. The predicted maps were fully concordant in terms of laterality to the commercial perfusion maps. The mean Dice scores were 0.54 for the core infarct and 0.63 for the hypoperfusion maps., Conclusions: Artificial intelligence model-derived volumes show good correlation with RAPID-derived volumes for CBF and Tmax. Within the constraints of a small sample size, the perfusion map quality is similar when using 14-tp instead of 28-tp. Our findings provide proof of concept that vendor neutral artificial intelligence models for computed tomographic perfusion processing using complete or partial image data sets appear feasible. The model accuracy could be further optimized using larger data sets.

This paper introduces a model-based approach for a fully automatic delineation of kidney and cortex tissue from contrast-enhanced abdominal CT scans. The proposed framework, named CorteXpert, consists of two new strategies for kidney tissue delineation: cortex model adaptation and non-uniform graph search. CorteXpert was validated on a clinical data set of 58 CT scans using the cross-validation evaluation strategy. The experimental results indicated the state-of-the-art segmentation accuracies (as dice coefficient): 97.86% ± 2.41% and 97.48% ± 3.18% for kidney and renal cortex delineations, respectively., (Copyright © 2017 Elsevier B.V. All rights reserved.)

Cortical thickness (CT) is an important morphometric measure that has implications for psychiatric and neurologic processes. We propose a novel approach for automatically computing CT in an accurate and robust manner using LOGISMOS-B: Layered Optimal Graph Image Segmentation of Multiple Objects and Surfaces for the Brain. LOGISMOS-B is a cortical surface segmentation method based on LOGISMOS graph segmentation and generalized gradient vector flows. We evaluate our method on two different datasets (n = 83 total). The results show that LOGISMOS-B is more accurate than the popular FreeSurfer (FS) method and provides more reliable thickness measurements across a variety of challenging images. LOGISMOS-B accurately recovers known CT patterns, both across cortical lobes and locally, such as between the banks of the central sulcus, in healthy subjects and MS patients. Manual landmarks indicate a signed surface distance of 0.081 +/- 0.447mm for WM and 0.018 +/- 0.498mm for LOGISMOS-B, compared to 0.263 +/- 0.452mm for WM and -0.167 +/- 0.556mm for GM for FS, highlighting the surface placement accuracy of LOGISMOS-B. Finally, a regresion study shows that LOGISMOS-B provides strong correlation with age and plausible annual thinning rates across the cortex, with locally discerning thinning patterns, in agreement with the literature.

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.

Recently, the optimal surface finding (OSF) and layered optimal graph image segmentation of multiple objects and surfaces (LOGISMOS) approaches have been reported with applications to medical image segmentation tasks. While providing high levels of performance, these approaches may locally fail in the presence of pathology or other local challenges. Due to the image data variability, finding a suitable cost function that would be applicable to all image locations may not be feasible. This paper presents a new interactive refinement approach for correcting local segmentation errors in the automated OSF-based segmentation. A hybrid desktop/virtual reality user interface was developed for efficient interaction with the segmentations utilizing state-of-the-art stereoscopic visualization technology and advanced interaction techniques. The user interface allows a natural and interactive manipulation of 3-D surfaces. The approach was evaluated on 30 test cases from 18 CT lung datasets, which showed local segmentation errors after employing an automated OSF-based lung segmentation. The performed experiments exhibited significant increase in performance in terms of mean absolute surface distance errors (2.54±0.75 mm prior to refinement vs. 1.11±0.43 mm post-refinement, p≪0.001). Speed of the interactions is one of the most important aspects leading to the acceptance or rejection of the approach by users expecting real-time interaction experience. The average algorithm computing time per refinement iteration was 150 ms, and the average total user interaction time required for reaching complete operator satisfaction was about 2 min per case. This time was mostly spent on human-controlled manipulation of the object to identify whether additional refinement was necessary and to approve the final segmentation result. The reported principle is generally applicable to segmentation problems beyond lung segmentation in CT scans as long as the underlying segmentation utilizes the OSF framework. The two reported segmentation refinement tools were optimized for lung segmentation and might need some adaptation for other application domains., (Copyright © 2013 Elsevier Ltd. All rights reserved.)

Purpose: The purpose of this work was to develop and validate fully automated methods for uptake measurement of cerebellum, liver, and aortic arch in full-body PET/CT scans. Such measurements are of interest in the context of uptake normalization for quantitative assessment of metabolic activity and/or automated image quality control., Methods: Cerebellum, liver, and aortic arch regions were segmented with different automated approaches. Cerebella were segmented in PET volumes by means of a robust active shape model (ASM) based method. For liver segmentation, a largest possible hyperellipsoid was fitted to the liver in PET scans. The aortic arch was first segmented in CT images of a PET/CT scan by a tubular structure analysis approach, and the segmented result was then mapped to the corresponding PET scan. For each of the segmented structures, the average standardized uptake value (SUV) was calculated. To generate an independent reference standard for method validation, expert image analysts were asked to segment several cross sections of each of the three structures in 134 F-18 fluorodeoxyglucose (FDG) PET/CT scans. For each case, the true average SUV was estimated by utilizing statistical models and served as the independent reference standard., Results: For automated aorta and liver SUV measurements, no statistically significant scale or shift differences were observed between automated results and the independent standard. In the case of the cerebellum, the scale and shift were not significantly different, if measured in the same cross sections that were utilized for generating the reference. In contrast, automated results were scaled 5% lower on average although not shifted, if FDG uptake was calculated from the whole segmented cerebellum volume. The estimated reduction in total SUV measurement error ranged between 54.7% and 99.2%, and the reduction was found to be statistically significant for cerebellum and aortic arch., Conclusions: With the proposed methods, the authors have demonstrated that automated SUV uptake measurements in cerebellum, liver, and aortic arch agree with expert-defined independent standards. The proposed methods were found to be accurate and showed less intra- and interobserver variability, compared to manual analysis. The approach provides an alternative to manual uptake quantification, which is time-consuming. Such an approach will be important for application of quantitative PET imaging to large scale clinical trials., (© 2012 American Association of Physicists in Medicine.)

Osteophyte is an additional bony growth on a normal bone surface limiting or stopping motion at a deteriorating joint. Detection and quantification of osteophytes from CT images is helpful in assessing disease status as well as treatment and surgery planning. However, it is difficult to distinguish between osteophytes and healthy bones using simple thresholding or edge/texture features due to the similarity of their material composition. In this paper, we present a new method primarily based active shape model (ASM) to solve this problem and evaluate its application to anterior cruciate ligament transection (ACLT) rabbit femur model via CT imaging. The common idea behind most ASM based segmentation methods is to first build a parametric shape model from a training dataset and apply the model to find a shape instance in a target image. A common challenge with such approaches is that a diseased bone shape is significantly altered at regions with osteophyte deposition misguiding an ASM method and eventually leading to suboptimum segmentations. This difficulty is overcome using a new partial ASM method that uses bone shape over healthy regions and extrapolates it over the diseased region according to the underlying shape model. Finally, osteophytes are segmented by subtracting partial-ASM derived shape from the overall diseased shape. Also, a new semi-automatic method is presented in this paper for efficiently building a 3D shape model for an anatomic region using manual reference of a few anatomically defined fiducial landmarks that are highly reproducible on individuals. Accuracy of the method has been examined on simulated phantoms while reproducibility and sensitivity have been evaluated on CT images of 2-, 4- and 8-week post-ACLT and sham-treated rabbit femurs. Experimental results have shown that the method is highly accurate ( R2 = 0.99), reproducible (ICC = 0.97), and sensitive in detecting disease progression (p-values: 0.065,0.001 and < 0.001 for 2- vs. 4, 4- vs. 8- and 2- vs. 8-weeks, respectively).

Efficient segmentation of globally optimal surfaces in volumetric images is a central problem in many medical image analysis applications. Intraclass variance has been successfully utilized for object segmentation, for instance, in the Chan-Vese model, especially for images without prominent edges. In this paper, we study the optimization problem of detecting a region (volume) between two coupled smooth surfaces by minimizing the intraclass variance using an efficient polynomial-time algorithm. Our algorithm is based on the shape probing technique in computational geometry and computes a sequence of minimum-cost closed sets in a derived parametric graph. The method has been validated on computer-synthetic volumetric images and in X-ray CT-scanned datasets of plexiglas tubes of known sizes. Its applicability to clinical data sets was also demonstrated. In all cases, the approach yielded highly accurate results. We believe that the developed technique is of interest on its own. We expect that it can shed some light on solving other important optimization problems arising in medical imaging. Furthermore, we report an approximation algorithm which runs much faster than the exact algorithm while yielding highly comparable segmentation accuracy.

Multi-object segmentation with mutual interaction is a challenging task in medical image analysis. We report a novel solution to a segmentation problem, in which target objects of arbitrary shape mutually interact with terrain-like surfaces, which widely exists in the medical imaging field. The approach incorporates context information used during simultaneous segmentation of multiple objects. The object-surface interaction information is encoded by adding weighted inter-graph arcs to our graph model. A globally optimal solution is achieved by solving a single maximum flow problem in a low-order polynomial time. The performance of the method was evaluated in robust delineation of lung tumors in megavoltage cone-beam CT images in comparison with an expert-defined independent standard. The evaluation showed that our method generated highly accurate tumor segmentations. Compared with the conventional graph-cut method, our new approach provided significantly better results (p < 0.001). The Dice coefficient obtained by the conventional graph-cut approach (0.76 +/- 0.10) was improved to 0.84 +/- 0.05 when employing our new method for pulmonary tumor segmentation.

Despite extensive studies in the past, the problem of segmenting globally optimal single and multiple surfaces in 3D volumetric images remains challenging in medical imaging. The problem becomes even harder in highly noisy and edge-weak images. In this paper we present a novel and highly efficient graph-theoretical iterative method with bi-criteria of global optimality and smoothness for both single and multiple surfaces. Our approach is based on a volumetric graph representation of the 3D image that incorporates curvature information. To evaluate the convergence and performance of our method, we test it on a set of 14 3D OCT images. Our experiments suggest that the proposed method yields optimal (or almost optimal) solutions in 3 to 5 iterations. To the best of our knowledge, this is the first algorithm that utilizes curvature in objective function to ensure the smoothness of the generated surfaces while striving for achieving global optimality. Comparing to the best existing approaches, our method has a much improved running time, yields almost the same global optimality but with much better smoothness, which makes it especially suitable for segmenting highly noisy images.

Tumor segmentation in PET and CT images is notoriously challenging due to the low spatial resolution in PET and low contrast in CT images. In this paper, we have proposed a general framework to use both PET and CT images simultaneously for tumor segmentation. Our method utilizes the strength of each imaging modality: the superior contrast of PET and the superior spatial resolution of CT. We formulate this problem as a Markov Random Field (MRF) based segmentation of the image pair with a regularized term that penalizes the segmentation difference between PET and CT. Our method simulates the clinical practice of delineating tumor simultaneously using both PET and CT, and is able to concurrently segment tumor from both modalities, achieving globally optimal solutions in low-order polynomial time by a single maximum flow computation. The method was evaluated on clinically relevant tumor segmentation problems. The results showed that our method can effectively make use of both PET and CT image information, yielding segmentation accuracy of 0.85 in Dice similarity coefficient and the average median hausdorff distance (HD) of 6.4 mm, which is 10% (resp., 16%) improvement compared to the graph cuts method solely using the PET (resp., CT) images.

A novel multiscale topomorphologic approach for opening of two isointensity objects fused at different locations and scales is presented and applied to separating arterial and venous trees in 3-D pulmonary multidetector X-ray computed tomography (CT) images. Initialized with seeds, the two isointensity objects (arteries and veins) grow iteratively while maintaining their spatial exclusiveness and eventually form two mutually disjoint objects at convergence. The method is intended to solve the following two fundamental challenges: how to find local size of morphological operators and how to trace continuity of locally separated regions. These challenges are met by combining fuzzy distance transform (FDT), a morphologic feature with a topologic fuzzy connectivity, and a new morphological reconstruction step to iteratively open finer and finer details starting at large scales and progressing toward smaller scales. The method employs efficient user intervention at locations where local morphological separability assumption does not hold due to imaging ambiguities or any other reason. The approach has been validated on mathematically generated tubular objects and applied to clinical pulmonary noncontrast CT data for separating arteries and veins. The tradeoff between accuracy and the required user intervention for the method has been quantitatively examined by comparing with manual outlining. The experimental study, based on a blind seed selection strategy, has demonstrated that above 95% accuracy may be achieved using 25-40 seeds for each of arteries and veins. Our method is very promising for semiautomated separation of arteries and veins in pulmonary CT images even when there is no object-specific intensity variation at conjoining locations.

The segmentation of soft tissues in medical images is a challenging problem due to the weak boundary, large deformation and serious mutual influence. We present a novel method incorporating both the shape and appearance information in a 3-D graph-theoretic framework to overcome those difficulties for simultaneous segmentation of prostate and bladder. An arc-weighted graph is constructed corresponding to the initial mesh. Both the boundary and region information is incorporated into the graph with learned intensity distribution, which drives the mesh to the best fit of the image. A shape prior penalty is introduced by adding weighted-arcs in the graph, which maintains the original topology of the model and constraints the flexibility of the mesh. The surface-distance constraints are enforced to avoid the leakage between prostate and bladder. The target surfaces are found by solving a maximum flow problem in low-order polynomial time. Both qualitative and quantitative results on prostate and bladder segmentation were promising, proving the power of our algorithm.

A method for computationally efficient skeletonization of three-dimensional tubular structures is reported. The method is specifically targeting skeletonization of vascular and airway tree structures in medical images but it is general and applicable to many other skeletonization tasks. The developed approach builds on the following novel concepts and properties: fast curve-thinning algorithm to increase computational speed, endpoint re-checking to avoid generation of spurious side branches, depth-and-length sensitive pruning, and exact tree-branch partitioning allowing branch volume and surface measurements. The method was validated in computer and physical phantoms and in vivo CT scans of human lungs. The validation studies demonstrated sub-voxel accuracy of branch point positioning, insensitivity to changes of object orientation, and high reproducibility of derived quantitative indices of the tubular structures offering a significant improvement over previously reported methods (p<<0.001).

Our goal is to enhance the ability to differentiate normal lung from subtle pathologies via multidetector row CT (MDCT) by extending a two-dimensional (2-D) texturebased tissue classification [adaptive multiple feature method (AMFM)] to use three-dimensional (3-D) texture features. We performed MDCT on 34 humans and classified volumes of interest (VOIs) in the MDCT images into five categories: EC, emphysema in severe chronic obstructive pulmonary disease (COPD); MC, mild emphysema in mild COPD; NC, normal appearing lung in mild COPD; NN, normal appearing lung in normal nonsmokers; and NS, normal appearing lung in normal smokers. COPD severity was based upon pulmonary function tests (PFTs). Airways and vessels were excluded from VOIs; 24 3-D texture features were calculated; and a Bayesian classifier was used for discrimination. A leave-one-out method was employed for validation. Sensitivity of the four-class classification in the form of 3-D/2-D was: EC: 85%/71%, MC: 90%/82%; NC: 88%/50%; NN: 100%/60%. Sensitivity and specificity for NN using a two-class classification of NN and NS in the form of 3-D/2-D were: 99%/72% and 100%/75%, respectively. We conclude that 3-D AMFM analysis of lung parenchyma improves discrimination compared to 2-D AMFM of the same VOIs. Furthermore, our results suggest that the 3-D AMFM may provide a means of discriminating subtle differences between smokers and nonsmokers both with normal PFTs.

Efficient segmentation of globally optimal surfaces representing object boundaries in volumetric data sets is important and challenging in many medical image analysis applications. We have developed an optimal surface detection method capable of simultaneously detecting multiple interacting surfaces, in which the optimality is controlled by the cost functions designed for individual surfaces and by several geometric constraints defining the surface smoothness and interrelations. The method solves the surface segmentation problem by transforming it into computing a minimum s-t cut in a derived arc-weighted directed graph. The proposed algorithm has a low-order polynomial time complexity and is computationally efficient. It has been extensively validated on more than 300 computer-synthetic volumetric images, 72 CT-scanned data sets of different-sized plexiglas tubes, and tens of medical images spanning various imaging modalities. In all cases, the approach yielded highly accurate results. Our approach can be readily extended to higher-dimensional image segmentation.

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.

Matching of corresponding branchpoints between two human airway trees, as well as assigning anatomical names to the segments and branchpoints of the human airway tree, are of significant interest for clinical applications and physiological studies. In the past, these tasks were often performed manually due to the lack of automated algorithms that can tolerate false branches and anatomical variability typical for in vivo trees. In this paper, we present algorithms that perform both matching of branchpoints and anatomical labeling of in vivo trees without any human intervention and within a short computing time. No hand-pruning of false branches is required. The results from the automated methods show a high degree of accuracy when validated against reference data provided by human experts. 92.9% of the verifiable branchpoint matches found by the computer agree with experts' results. For anatomical labeling, 97.1% of the automatically assigned segment labels were found to be correct.

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.

Defining the healthy human airway is important in enhancing our understanding of pulmonary disease states such as inflammation and cancer. The structure of the human airway, both static and dynamic, can be assessed using multi-detector CT (MDCT) scanning. This modality also allows for the evaluation of structures outside of the airway. The airway wall can be directly visualized using CCD chip high-resolution color optical imaging through endoscopy allowing bronchial wall evaluation by traditional biopsy methods, as well as by newer optically based strategies. We suggest that these two imaging modalities, MDCT and optical imaging, provide complementary information about the normal airway, and the airway in various diseases. Methods for evaluating the human airway using MDCT images are presented facilitating automatic airway segmentation, branchpoint finding and airway dimension analysis. The airway wall color is objectively evaluated as an important surrogate for airway wall inflammation and cancer formation, and the integration of the color endoscopic information into the MDCT scan data set is currently ongoing. The amalgamation of these two digital imaging modalities appears increasingly useful for enabling biopsy techniques, and for relating structure and function of the airway. In addition, these developments may be progressively more useful in understanding the normal airway structure and function, for defining airway diseases patterns and for guiding biopsy and therapeutic procedures.

Rationale and Objectives: Efforts to establish a quantitative approach to the computed tomography (CT)-based character ization of the lung parenchyma in interstitial lung disease (including emphysema) has been sought. The accuracy of these tools must be site independent. Multi-detector row CT has remained the gold standard for imaging the lung, and it provides the ability to image both lung structure as well as lung function., Material and Methods: Imaging is via multi-detector row CT and protocols include careful control of lung volume during scanning. Characterization includes not only anatomic-based measures but also functional measures including regional parameters derived from measures of pulmonary blood flow and ventilation. Image processing includes the automated detection of the lungs, lobes, and airways. The airways provide the road map to the lung parenchyma. Software automatically detects the airways, the airway centerlines, and the branch points, and then automatically labels the airway tree segments with a standardized set of labels, allowing for intersubject as well intrasubject comparisons across time. By warping all lungs to a common atlas, the atlas provides the range of normality for the various parameters provided by CT imaging., Results: Imaged density and textural changes mark underlying structural changes at the most peripheral regions of the lung. Additionally, texture-based alterations in the parameters of blood flow may provide early evidence of pathologic processes. Imaging of stable xenon gas provides a regional measure of ventilation which, when coupled with measures of flow, provide for a textural analysis regional of ventilation-perfusion matching., Conclusion: With the improved resolution and speed of CT imaging, the patchy nature of regional parenchymal pathology can be imaged as texture of structure and function. With careful control of imaging protocols and the use of objective image analysis methods it is possible to provide site-independent tools for the assessment of interstitial lung disease. There remains a need to validate these methods, which requires interdisciplinary and cross-institutional efforts to gather appropriate data bases of images along with a consensus on appropriate ground truths associated with the images. Furthermore, there is the growing need for scanner manufacturers to focus on not just visually pleasing images, but on quantitatifiably accurate images.

We have developed an objective, reproducible, and automated means for the regional evaluation of the pulmonary parenchyma from computed tomography (CT) scans. This method, known as the Adaptive Multiple Feature Method (AMFM) assesses as many as 22 independent texture features in order to classify a tissue pattern. In this study, the six tissue patterns characterized were: honeycombing, ground glass, bronchovascular, nodular, emphysemalike, and normal. The lung slices were evaluated regionally using 31 x 31 pixel regions of interest. In each region of interest, an optimal subset of texture features was evaluated to determine which of the six patterns the region could be characterized as. The computer output was validated against experienced observers in three settings. In the first two readings, when the observers were blinded to the primary diagnosis of the subject, the average computer versus observer agreement was 44.4 +/- 8.7% and 47.3 +/- 9.0%, respectively. The average interobserver agreement for the same two readings were 48.8 +/- 9.1% and 52.2 +/- 10.0%, respectively. In the third reading, when the observers were provided the primary diagnosis, the average computer versus observer agreement was 51.7 +/- 2.9% where as the average interobserver agreement was 53.9 +/- 6.2%. The kappa statistic of agreement between the regions, for which the majority of the observers agreed on a pattern type, versus the computer was found to be 0.62. For regional tissue characterization, the AMFM is 100% reproducible and performs as well as experienced human observers who have been told the patient diagnosis.

A texture-based adaptive multiple feature method (AMFM) for evaluating pulmonary parenchyma from computed tomography (CT) images is described. This method incorporates multiple statistical and fractal texture features. The AMFM was compared to two previously published methods, namely, mean lung density (MLD) and the lowest fifth percentile of the histogram (HIST). First, the ability of these methods to detect subtle differences in ventral-dorsal lung density gradient in the prone normal lung was studied. Second, their abilities to differentiate between normal and emphysematous whole lung slices were compared. Finally, regional analyses comparing normal and emphysematous regions were performed by dividing the lungs. In the CT slices into six equal regions, ventral to dorsal, and analyzing each region separately. The results demonstrated that the AMFM could separate the ventral from the dorsal one-third of the normal prone lung with 89.8% accuracy, compared to an accuracy of 74.6% with the MLD and 64.4% with the HIST methods. The normal and emphysematous slices were separated on a global basis with 100.0% accuracy using the AMFM as compared to an accuracy of 94.7% and 97.4% using the MLD and HIST methods, respectively. The regional normal and emphysematous tissues were discriminated with an average accuracy of 97.9%, 89.9%, and 99.1% with the AMFM, MLD, and HIST methods, respectively. The three methods and the pulmonary function tests in the normal and emphysema groups were poorly correlated. Quantitative texture analysis using adaptive multiple features holds promise for the objective noninvasive evaluation of the pulmonary parenchyma.