Automated lung segmentation of diseased and artifact-corrupted magnetic resonance sections

Semiautomatic assessment of respiratory dynamics using cine MRI in chronic obstructive pulmonary disease

Purpose

The quantitative assessment of impaired lung motions and their association with the clinical characteristics of COPD patients is challenging. The aim of this study was to measure respiratory kinetics, including asynchronous movements, and to analyze the relationship between lung area and other clinical parameters.

Materials and methods

This study enrolled 10 normal control participants and 21 COPD patients who underwent dynamic MRI and pulmonary function testing (PFT). The imaging program was implemented using MATLAB®. Each lung area was detected semi-automatically on a coronal image (imaging level at the aortic valve) from the inspiratory phase to the expiratory phase. The Dice index of the manual measurements was calculated, with the relationship between lung area ratio and other clinical parameters, including PFTs then evaluated. The asynchronous movements of the diaphragm were also evaluated using a sagittal image.

Results

The Dice index for the lung region using the manual and semi-automatic extraction methods was high (Dice index = 0.97 ± 0.03). A significant correlation was observed between the time corrected lung area ratio and percentage of forced expiratory volume in 1 s (FEV₁%pred) and residual volume percentage (RV%pred) (r = −0.54, p = 0.01, r = 0.50, p = 0.03, respectively). The correlation coefficient between each point of the diaphragm in the group with visible see-saw like movements was significantly lower than that in the group without see-saw like movements (value = −0.36 vs 0.95, p = 0.001).

Conclusion

Semi-automated extraction of lung area from Cine MRI might be useful for detecting impaired respiratory kinetics in patients with COPD.

[Semi-automated Segmentation of Lungs Using the k-means Method in Cine MRI]

Dynamic magnetic resonance imaging (MRI) provides essential information on the respiratory kinetics in chronic obstructive pulmonary disease (COPD), such as impaired diaphragm and chest wall motions. The purpose of this study was to develop the semi-automated segmentation program of lungs using cine MRI. We enrolled five control participants and five patients with COPD who underwent cine MRI. The coronal balanced FFE images from each subject were used. The procedures were as follows: First, the maximum inspiratory image was selected from the time-sequential series, and the lung area was manually segmented, which was used for a mask image. Second, both mask image and cine image were accumulated to create a weighted cine image. Lung areas were segmented using the k-means method. Finally, lungs were detected as contiguous image regions with similar signal values using the flood-fill technique. We evaluated the correlation coefficients between the lung area segmented by the semi-automated method and those segmented by a pulmonologist. The correlation coefficients between the semi-automated method and the manual segmentations were excellent (r=0.99, p<0.001). The Dice index was also perfect (0.97). The best number of clusters in the k-means method was 8. These results suggested that the new segmentation method can appropriately extract lungs and help analyze respiratory dynamics in patients with COPD.

Holistic segmentation of the lung in cine MRI

Duchenne muscular dystrophy (DMD) is a childhood-onset neuromuscular disease that results in the degeneration of muscle, starting in the extremities, before progressing to more vital areas, such as the lungs. Respiratory failure and pneumonia due to respiratory muscle weakness lead to hospitalization and early mortality. However, tracking the disease in this region can be difficult, as current methods are based on breathing tests and are incapable of distinguishing between muscle involvements. Cine MRI scans give insight into respiratory muscle movements, but the images suffer due to low spatial resolution and poor signal-to-noise ratio. Thus, a robust lung segmentation method is required for accurate analysis of the lung and respiratory muscle movement. We deployed a deep learning approach that utilizes sequence-specific prior information to assist the segmentation of lung in cine MRI. More specifically, we adopt a holistically nested network to conduct image-to-image holistic training and prediction. One frame of the cine MRI is used in the training and applied to the remainder of the sequence ([Formula: see text] frames). We applied this method to cine MRIs of the lung in the axial, sagittal, and coronal planes. Characteristic lung motion patterns during the breathing cycle were then derived from the segmentations and used for diagnosis. Our data set consisted of 31 young boys, age [Formula: see text] years, 15 of whom suffered from DMD. The remaining 16 subjects were age-matched healthy volunteers. For validation, slices from inspiratory and expiratory cycles were manually segmented and compared with results obtained from our method. The Dice similarity coefficient for the deep learning-based method was [Formula: see text] for the sagittal view, [Formula: see text] for the axial view, and [Formula: see text] for the coronal view. The holistic neural network approach was compared with an approach using Demon's registration and showed superior performance. These results suggest that the deep learning-based method reliably and accurately segments the lung across the breathing cycle.

Anatomical pulmonary magnetic resonance imaging segmentation for regional structure-function measurements of asthma

PURPOSE

Pulmonary magnetic-resonance-imaging (MRI) and x-ray computed-tomography have provided strong evidence of spatially and temporally persistent lung structure-function abnormalities in asthmatics. This has generated a shift in their understanding of lung disease and supports the use of imaging biomarkers as intermediate endpoints of asthma severity and control. In particular, pulmonary (1)H MRI can be used to provide quantitative lung structure-function measurements longitudinally and in response to treatment. However, to translate such biomarkers of asthma, robust methods are required to segment the lung from pulmonary (1)H MRI. Therefore, their objective was to develop a pulmonary (1)H MRI segmentation algorithm to provide regional measurements with the precision and speed required to support clinical studies.

METHODS

The authors developed a method to segment the left and right lung from (1)H MRI acquired in 20 asthmatics including five well-controlled and 15 severe poorly controlled participants who provided written informed consent to a study protocol approved by Health Canada. Same-day spirometry and plethysmography measurements of lung function and volume were acquired as well as (1)H MRI using a whole-body radiofrequency coil and fast spoiled gradient-recalled echo sequence at a fixed lung volume (functional residual capacity + 1 l). We incorporated the left-to-right lung volume proportion prior based on the Potts model and derived a volume-proportion preserved Potts model, which was approximated through convex relaxation and further represented by a dual volume-proportion preserved max-flow model. The max-flow model led to a linear problem with convex and linear equality constraints that implicitly encoded the proportion prior. To implement the algorithm, (1)H MRI was resampled into ∼3 × 3 × 3 mm(3) isotropic voxel space. Two observers placed seeds on each lung and on the background of 20 pulmonary (1)H MR images in a randomized dataset, on five occasions, five consecutive days in a row. Segmentation accuracy was evaluated using the Dice-similarity-coefficient (DSC) of the segmented thoracic cavity with comparison to five-rounds of manual segmentation by an expert observer. The authors also evaluated the root-mean-squared-error (RMSE) of the Euclidean distance between lung surfaces, the absolute, and percent volume error. Reproducibility was measured using the coefficient of variation (CoV) and intraclass correlation coefficient (ICC) for two observers who repeated segmentation measurements five-times.

RESULTS

For five well-controlled asthmatics, forced expiratory volume in 1 s (FEV1)/forced vital capacity (FVC) was 83% ± 7% and FEV1 was 86 ± 9%pred. For 15 severe, poorly controlled asthmatics, FEV1/FV C = 66% ± 17% and FEV1 = 72 ± 27%pred. The DSC for algorithm and manual segmentation was 91% ± 3%, 92% ± 2% and 91% ± 2% for the left, right, and whole lung, respectively. RMSE was 4.0 ± 1.0 mm for each of the left, right, and whole lung. The absolute (percent) volume errors were 0.1 l (∼6%) for each of right and left lung and ∼0.2 l (∼6%) for whole lung. Intra- and inter-CoV (ICC) were <0.5% (>0.91%) for DSC and <4.5% (>0.93%) for RMSE. While segmentation required 10 s including ∼6 s for user interaction, the smallest detectable difference was 0.24 l for algorithm measurements which was similar to manual measurements.

CONCLUSIONS

This lung segmentation approach provided the necessary and sufficient precision and accuracy required for research and clinical studies.

Globally optimal co-segmentation of three-dimensional pulmonary ¹H and hyperpolarized ³He MRI with spatial consistence prior

Pulmonary imaging using hyperpolarized (3)He/(129)Xe gas is emerging as a new way to understand the regional nature of pulmonary ventilation abnormalities in obstructive lung diseases. However, the quantitative information derived is completely dependent on robust methods to segment both functional and structural/anatomical data. Here, we propose an approach to jointly segment the lung cavity from (1)H and (3)He pulmonary magnetic resonance images (MRI) by constraining the spatial consistency of the two segmentation regions, which simultaneously employs the image features from both modalities. We formulated the proposed co-segmentation problem as a coupled continuous min-cut model and showed that this combinatorial optimization problem can be solved globally and exactly by means of convex relaxation. In particular, we introduced a dual coupled continuous max-flow model to study the convex relaxed coupled continuous min-cut model under a primal and dual perspective. This gave rise to an efficient duality-based convex optimization algorithm. We implemented the proposed algorithm in parallel using general-purpose programming on graphics processing unit (GPGPU), which substantially increased its computational efficiency. Our experiments explored a clinical dataset of 25 subjects with chronic obstructive pulmonary disease (COPD) across a wide range of disease severity. The results showed that the proposed co-segmentation approach yielded superior performance compared to single-channel image segmentation in terms of precision, accuracy and robustness.

Automatic lung segmentation method for MRI-based lung perfusion studies of patients with chronic obstructive pulmonary disease

PURPOSE

A novel fully automatic lung segmentation method for magnetic resonance (MR) images of patients with chronic obstructive pulmonary disease (COPD) is presented. The main goal of this work was to ease the tedious and time-consuming task of manual lung segmentation, which is required for region-based volumetric analysis of four-dimensional MR perfusion studies which goes beyond the analysis of small regions of interest.

METHODS

The first step in the automatic algorithm is the segmentation of the lungs in morphological MR images with higher spatial resolution than corresponding perfusion MR images. Subsequently, the segmentation mask of the lungs is transferred to the perfusion images via nonlinear registration. Finally, the masks for left and right lungs are subdivided into a user-defined number of partitions. Fourteen patients with two time points resulting in 28 perfusion data sets were available for the preliminary evaluation of the developed methods.

RESULTS

Resulting lung segmentation masks are compared with reference segmentations from experienced chest radiologists, as well as with total lung capacity (TLC) acquired by full-body plethysmography. TLC results were available for thirteen patients. The relevance of the presented method is indicated by an evaluation, which shows high correlation between automatically generated lung masks with corresponding ground-truth estimates.

CONCLUSION

The evaluation of the developed methods indicates good accuracy and shows that automatically generated lung masks differ from expert segmentations about as much as segmentations from different experts.

Quantitative analysis of tumor burden in mouse lung via MRI

Lung cancer is the leading cause of cancer death in the United States. Despite recent advances in screening protocols, the majority of patients still present with advanced or disseminated disease. Preclinical rodent models provide a unique opportunity to test novel therapeutic drugs for targeting lung cancer. Respiratory-gated MRI is a key tool for quantitatively measuring lung-tumor burden and monitoring the time-course progression of individual tumors in mouse models of primary and metastatic lung cancer. However, quantitative analysis of lung-tumor burden in mice by MRI presents significant challenges. Herein, a method for measuring tumor burden based upon average lung-image intensity is described and validated. The method requires accurate lung segmentation; its efficiency and throughput would be greatly aided by the ability to automatically segment the lungs. A technique for automated lung segmentation in the presence of varying tumor burden levels is presented. The method includes development of a new, two-dimensional parametric model of the mouse lungs and a multi-faceted cost function to optimally fit the model parameters to each image. Results demonstrate a strong correlation (0.93), comparable with that of fully manual expert segmentation, between the automated method's tumor-burden metric and the tumor burden measured by lung weight.

Temporal segmentation of lung region MR image sequences using hough transform

In this work, segmentation is an intermediate step in the registration and 3D reconstruction of the lung, where the diaphragmatic surface is automatically and robustly isolated. Usually, segmentation methods are interactive and use different strategies to combine the expertise of humans and computers. Segmentation of lung MR images is particularly difficult because of the large variation in image quality. The breathing is associated to a standard respiratory function, and through 2D image processing, edge detection and Hough transform, respiratory patterns are obtained and, consequently, the position of points in time are estimated. Temporal sequences of MR images are segmented by considering the coherence in time. This way, the lung silhouette can be determined in every frame, even on frames with obscure edges. The lung region is segmented in two steps: a mask containing the lung region is created, and the Hough transform is applied exclusively to mask pixels. The shape of the mask can have a large variation, and the modified Hough transform can handle such shape variation. The result was checked through temporal registration of coronal and sagittal images.

Texture-based identification and characterization of interstitial pneumonia patterns in lung multidetector CT

Identification and characterization of diffuse parenchyma lung disease (DPLD) patterns challenges computer-aided schemes in computed tomography (CT) lung analysis. In this study, an automated scheme for volumetric quantification of interstitial pneumonia (IP) patterns, a subset of DPLD, is presented, utilizing a multidetector CT (MDCT) dataset. Initially, lung-field segmentation is achieved by 3-D automated gray-level thresholding combined with an edge-highlighting wavelet preprocessing step, followed by a texture-based border refinement step. The vessel tree volume is identified and removed from lung field, resulting in lung parenchyma (LP) volume. Following, identification and characterization of IP patterns is formulated as a three-class pattern classification of LP into normal, ground glass, and reticular patterns, by means of k-nearest neighbor voxel classification, exploiting 3-D cooccurrence features. Performance of the proposed scheme in indentifying and characterizing ground glass and reticular patterns was evaluated by means of volume overlap (ground glass: 0.734 +/- 0.057, reticular: 0.815 +/- 0.037), true-positive fraction (ground glass: 0.638 +/- 0.055, reticular: 0.942 +/- 0.023) and false-positive fraction (ground glass: 0.361 +/- 0.027, reticular: 0.147 +/- 0.032) on five MDCT scans.

Advances in Attenuation Correction Techniques in PET

Molecular imaging using PET has evolved from a vigorous academic field into the clinical arena. Considerable advances have been made in the design of high-resolution standalone PET and combined PET/CT units dedicated to clinical whole-body scanning. Likewise, much worthwhile research focused on the development of quantitative imaging protocols incorporating accurate data correction techniques and sophisticated image reconstruction algorithms. Since its inception, photon attenuation in biological tissues has been identified as the most important physical degrading factor affecting PET image quality and quantitative accuracy. Various strategies have been devised to determine an accurate attenuation map to enable correction for nonlinear photon attenuation in whole-body PET studies. This article presents the physical and methodological basis of photon attenuation and summarizes state-of-the-art developments in algorithms used to derive the attenuation map aiming at accurate attenuation compensation of PET data. Future prospects, research trends, and challenges are identified, and directions for future research are discussed.