Knowledge-based segmentation of thoracic computed tomography images for assessment of split lung function

Compensatory function change by segment-counting method in predicted postoperative pulmonary function at 1 year after surgery: systematic review and meta-analysis

BACKGROUND

This systematic review aimed to assess the accuracy of the segment-counting method in predicting long-term pulmonary function recovery and investigate compensatory changes following different extents of lung resection.

METHODS

We included studies that measured forced expiratory volume at 1 s (FEV1) between 6 and 18 months postoperatively, comparing it to the predicted postoperative FEV1 (ppoFEV1) using the segment-counting method. The extent of lung resection was correlated with the ratio of postoperative FEV1 to ppoFEV1. A comprehensive search was conducted in Embase, MEDLINE and Web of Science using terms related to 'lung resection' and 'pulmonary function'. The final search was completed on 18 February 2022. Risk of bias was assessed using the Newcastle-Ottawa Scale.

RESULTS

39 studies comprising 78 observation cohorts met the inclusion criteria. The analysis showed significant differences in pulmonary function in patients with ≥3 resected segments. Meta-regression indicated that the number of resected segments significantly impacted the postoperative FEV1/ppoFEV1 ratio, explaining 57% of the variance (R²=0. 57), with moderate heterogeneity (I²=61. 87%) across studies. Other variables, including patient age, body mass index, video-assisted thoracoscopic surgery use and tumour stage, did not show significant effects.

DISCUSSION

Limitations of the review included moderate heterogeneity between studies and potential selection bias related to the stage of cancer and lung volume reduction effects. The findings suggest that the extent of lung resection correlates with better-than-expected pulmonary function, potentially due to compensatory mechanisms.

PROSPERO REGISTRATION NUMBER

This review was registered on PROSPERO (CRD42021293608).

A Review of Deep Learning Techniques for Lung Cancer Screening and Diagnosis Based on CT Images

One of the most common and deadly diseases in the world is lung cancer. Only early identification of lung cancer can increase a patient's probability of survival. A frequently used modality for the screening and diagnosis of lung cancer is computed tomography (CT) imaging, which provides a detailed scan of the lung. In line with the advancement of computer-assisted systems, deep learning techniques have been extensively explored to help in interpreting the CT images for lung cancer identification. Hence, the goal of this review is to provide a detailed review of the deep learning techniques that were developed for screening and diagnosing lung cancer. This review covers an overview of deep learning (DL) techniques, the suggested DL techniques for lung cancer applications, and the novelties of the reviewed methods. This review focuses on two main methodologies of deep learning in screening and diagnosing lung cancer, which are classification and segmentation methodologies. The advantages and shortcomings of current deep learning models will also be discussed. The resultant analysis demonstrates that there is a significant potential for deep learning methods to provide precise and effective computer-assisted lung cancer screening and diagnosis using CT scans. At the end of this review, a list of potential future works regarding improving the application of deep learning is provided to spearhead the advancement of computer-assisted lung cancer diagnosis systems.

Pulmonary nodules detection assistant platform: An effective computer aided system for early pulmonary nodules detection in physical examination

BACKGROUND AND OBJECTIVE

Early detection of the pulmonary nodule from physical examination low-dose computer tomography (LDCT) images is an effective measure to reduce the mortality rate of lung cancer. Although there are many computer aided diagnosis (CAD) methods used for detecting pulmonary nodules, there are few CAD systems for small pulmonary nodule detection with a large amount of physical examination LDCT images.

METHODS

In this work, we designed a CAD system called Pulmonary Nodules Detection Assistant Platform for early pulmonary nodules detection and classification based on the physical examination LDCT images. Based on the preprocessed physical examination CT images, the three-dimensional (3D) CNN-based model is presented to detect candidate pulmonary nodules and output detection results with quantitative parameters, the 3D ResNet is used to classify the detected nodules into intrapulmonary nodules and pleural nodules to reduce the physician workloads, and the Fully Connected Neural Network (FCNN) is used to classify ground-glass opacity (GGO) nodules and non-GGO nodules to help doctor pay more attention to those suspected early lung cancer nodules.

RESULTS

Experiments are performed on our 1000 samples of physical examinations (LNPE1000) with an average diameter of 5.3 mm and LUNA16 dataset with an average diameter of 8.31 mm, which show that the designed CAD system is automatic and efficient for detecting smaller and larger nodules from different datasets, especially for the detection of smaller nodules with diameter between 3 mm and 6 mm in physical examinations. The accuracy of pulmonary nodule detection reaches 0.879 with an average of 1 false positive per CT in LNPE1000 dataset, which is comparable to the experienced physicians. The classification accuracy reaches 0.911 between intrapulmonary and pleural nodules, and 0.950 between GGO and non-GGO nodules, respectively.

CONCLUSION

Experimental results show that the proposed pulmonary nodule detection model is robust for different datasets, which can successfully detect smaller and larger nodules in CT images obtained by physical examination. The interactive platform of the designed CAD system has been on trial in a hospital by combining with manual reading, which helps doctors analyze clinical data dynamically and improves the nodule detection efficiency in physical examination applications.

Deep Residual Separable Convolutional Neural Network for lung tumor segmentation

Lung cancer is one of the deadliest types of cancers. Computed Tomography (CT) is a widely used technique to detect tumors present inside the lungs. Delineation of such tumors is particularly essential for analysis and treatment purposes. With the advancement in hardware technologies, Machine Learning and Deep Learning methods are outperforming the traditional methods in the field of medical imaging. In order to delineate lung cancer tumors, we have proposed a deep learning-based methodology which includes a maximum intensity projection based pre-processing method, two novel deep learning networks and an ensemble strategy. The two proposed networks named Deep Residual Separable Convolutional Neural Network 1 and 2 (DRS-CNN1 and DRS-CNN2) achieved better performance over the state-of-the-art U-net network and other segmentation networks. For fair comparison, we have evaluated the performances of all networks on Medical Segmentation Decathlon (MSD) and StructSeg 2019 datasets. The DRS-CNN2 achieved a mean Dice Similarity Coefficient (DSC) of 0.649, mean 95 Hausdorff Distance (HD95) of 18.26, mean Sensitivity 0.737 and a mean Precision of 0.765 on independent test sets.

Precise Segmentation of COVID-19 Infected Lung from CT Images Based on Adaptive First-Order Appearance Model with Morphological/Anatomical Constraints

A new segmentation technique is introduced for delineating the lung region in 3D computed tomography (CT) images. To accurately model the distribution of Hounsfield scale values within both chest and lung regions, a new probabilistic model is developed that depends on a linear combination of Gaussian (LCG). Moreover, we modified the conventional expectation-maximization (EM) algorithm to be run in a sequential way to estimate both the dominant Gaussian components (one for the lung region and one for the chest region) and the subdominant Gaussian components, which are used to refine the final estimated joint density. To estimate the marginal density from the mixed density, a modified k-means clustering approach is employed to classify the Gaussian subdominant components to determine which components belong properly to a lung and which components belong to a chest. The initial segmentation, based on the LCG-model, is then refined by the imposition of 3D morphological constraints based on a 3D Markov-Gibbs random field (MGRF) with analytically estimated potentials. The proposed approach was tested on CT data from 32 coronavirus disease 2019 (COVID-19) patients. Segmentation quality was quantitatively evaluated using four metrics: Dice similarity coefficient (DSC), overlap coefficient, 95th-percentile bidirectional Hausdorff distance (BHD), and absolute lung volume difference (ALVD), and it achieved 95.67±1.83%, 91.76±3.29%, 4.86±5.01, and 2.93±2.39, respectively. The reported results showed the capability of the proposed approach to accurately segment healthy lung tissues in addition to pathological lung tissues caused by COVID-19, outperforming four current, state-of-the-art deep learning-based lung segmentation approaches.

Automatic Approach for Lung Segmentation with Juxta-Pleural Nodules from Thoracic CT Based on Contour Tracing and Correction

This paper presents a fully automatic framework for lung segmentation, in which juxta-pleural nodule problem is brought into strong focus. The proposed scheme consists of three phases: skin boundary detection, rough segmentation of lung contour, and pulmonary parenchyma refinement. Firstly, chest skin boundary is extracted through image aligning, morphology operation, and connective region analysis. Secondly, diagonal-based border tracing is implemented for lung contour segmentation, with maximum cost path algorithm used for separating the left and right lungs. Finally, by arc-based border smoothing and concave-based border correction, the refined pulmonary parenchyma is obtained. The proposed scheme is evaluated on 45 volumes of chest scans, with volume difference (VD) 11.15 ± 69.63 cm³, volume overlap error (VOE) 3.5057 ± 1.3719%, average surface distance (ASD) 0.7917 ± 0.2741 mm, root mean square distance (RMSD) 1.6957 ± 0.6568 mm, maximum symmetric absolute surface distance (MSD) 21.3430 ± 8.1743 mm, and average time-cost 2 seconds per image. The preliminary results on accuracy and complexity prove that our scheme is a promising tool for lung segmentation with juxta-pleural nodules.

An automated lung segmentation approach using bidirectional chain codes to improve nodule detection accuracy

Computer-aided detection and diagnosis (CAD) has been widely investigated to improve radiologists׳ diagnostic accuracy in detecting and characterizing lung disease, as well as to assist with the processing of increasingly sizable volumes of imaging. Lung segmentation is a requisite preprocessing step for most CAD schemes. This paper proposes a parameter-free lung segmentation algorithm with the aim of improving lung nodule detection accuracy, focusing on juxtapleural nodules. A bidirectional chain coding method combined with a support vector machine (SVM) classifier is used to selectively smooth the lung border while minimizing the over-segmentation of adjacent regions. This automated method was tested on 233 computed tomography (CT) studies from the lung imaging database consortium (LIDC), representing 403 juxtapleural nodules. The approach obtained a 92.6% re-inclusion rate. Segmentation accuracy was further validated on 10 randomly selected CT series, finding a 0.3% average over-segmentation ratio and 2.4% under-segmentation rate when compared to manually segmented reference standards done by an expert.

Automated segmentation of pulmonary structures in thoracic computed tomography scans: a review

Computed tomography (CT) is the modality of choice for imaging the lungs in vivo. Sub-millimeter isotropic images of the lungs can be obtained within seconds, allowing the detection of small lesions and detailed analysis of disease processes. The high resolution of thoracic CT and the high prevalence of lung diseases require a high degree of automation in the analysis pipeline. The automated segmentation of pulmonary structures in thoracic CT has been an important research topic for over a decade now. This systematic review provides an overview of current literature. We discuss segmentation methods for the lungs, the pulmonary vasculature, the airways, including airway tree construction and airway wall segmentation, the fissures, the lobes and the pulmonary segments. For each topic, the current state of the art is summarized, and topics for future research are identified.

A novel segmentation approach for improving diagnostic accuracy of CAD systems for detecting lung cancer from chest computed tomography images

Segmentation of lung tissue is an important and challenging task in any computer aided diagnosis system. The accuracy of the segmentation subsystem determines the performance of the other subsystems in any computer aided diagnosis system based on image analysis. We propose a novel technique for segmentation of lung tissue from computed tomography of the chest. Manual segmentation of lung parenchyma becomes difficult with an enormous volume of images. The goal of this work is to present an automated approach to segmentation of lung parenchyma from the rest of the chest CT image. The approach involves the conventional optimal thresholding technique and operations based on convex edge and centroid properties of the lung region. The segmentation technique proposed in this article can be used to preprocess lung images given to a computer aided diagnosis system for diagnosis of lung disorders. This improves the diagnostic performance of the system. This has been tested by using it in a computer aided diagnosis system that was used for detection of lung cancer from chest computed tomography images. The results obtained show that the lungs can be correctly segmented even in the presence of peripheral pathology bearing regions; pathology bearing regions that could not be detected using a CAD system that applies optimal thresholding could be detected using a CAD system using out proposed approach for segmentation of lungs.

Reproducibility of lung and lobar volume measurements using computed tomography

RATIONALE AND OBJECTIVES

Lung and lobar volume measurements from computed tomographic (CT) imaging are being used in clinical trials to assess new minimally invasive emphysema treatments aiming to reduce lung volumes. Establishing the reproducibility of lung volume measurements is important if they are to be accepted as treatment planning and outcome variables. The aims of this study were to (1) investigate the correlation between lung volumes assessed on CT imaging and on pulmonary function testing (PFT), (2) compare the two methods' reproducibility, and (3) assess the reproducibility of CT lobar volumes.

MATERIALS AND METHODS

CT imaging and body plethysmography were performed at baseline and after a 9-month interval in multicenter emphysema treatment trials. Lung volumes were measured at total lung capacity (TLC) and at residual volume (RV). Lobar volumes were measured on CT imaging using a semiautomated technique. The correlations between CT and PFT volumes were computed for 486 subjects at baseline. Reproducibility was assessed in terms of the intraclass correlation coefficient (ICC) for 126 subjects from the control group at TLC and 120 subjects at RV.

RESULTS

Correlations between CT and PFT lung volumes were 0.86 at TLC and 0.67 at RV. At TLC, the ICCs were 0.943 for CT imaging and 0.814 for PFT. At RV, the ICCs were 0.886 for CT imaging and 0.683 for PFT. CT lobar volumes showed good reproducibility (all P values < .05).

CONCLUSION

CT lung and lobar volume measurements could be captured in a multicenter trial setting with high reproducibility and were highly correlated with those obtained on PFT. CT imaging showed significantly better reproducibility than PFT between interval lung volume measurements, offering the potential for designing emphysema treatment trials involving fewer subjects.

Quantitative assessment of the airway wall using computed tomography and optical coherence tomography

Ever since the site and nature of airflow obstruction in chronic obstructive pulmonary disease was described by Hogg, Thurlbeck, and Macklem, investigators have been looking for methods to noninvasively measure the airway wall dimensions. Recent advances in computed tomography technology and new computer algorithms have made it possible to visualize and measure the airway wall and lumen without the need for tissue. However, while there is great hope for computed tomographic assessment of airways, it is well known that the spatial resolution does not allow small airways to be visualized and there are still concerns about the sensitivity of these measurements obtained from these airways. Optical coherence tomography is a new bronchoscopic imaging technique that has generated considerable interest because the spatial resolution is much higher than computed tomography. While relatively more invasive than computed tomography, it has the advantage of not exposing the patient to ionizing radiation. This review discusses some of the data surrounding these two imaging techniques in patients with chronic obstructive pulmonary disease. These imaging techniques are extremely important in the assessment of patients with chronic obstructive pulmonary disease because therapy that is designed to modulate the inflammation in airways may be contraindicated in subjects with the emphysema phenotype and visa versa. Therefore, these new imaging techniques are very likely to play a front-line role in the study of chronic obstructive pulmonary disease and will, hopefully, allow clinicians to phenotype individuals, thereby personalizing their treatment.

Controlling familywise error rate for matched subspace detection in dynamic FDG PET

Detection of small lesions in fluorodeoxyglucose (FDG) positron emission tomography (PET) is limited by image resolution and low signal to noise ratio. We have previously described a matched subspace detection method that uses the time activity curve to distinguish tumors from background in dynamic FDG PET. Applying this algorithm on a voxel by voxel basis throughout the dynamic image produces a test statistic image or "map" which on thresholding indicates the potential locations of secondary or metastatic tumors. In this paper, we describe a thresholding method that controls familywise error rate (FWER) for the matched subspace detection statistical map. The method involves three steps. First, the PET image is segmented into several homogeneous regions. Then, the statistical map is normalized to a zero mean unit variance Gaussian random field. Finally, the images are thresholded at a fixed FWER by estimating their spatial smoothness and applying a random field theory maximum statistic approach. We evaluate this thresholding method using digital phantoms generated from clinical dynamic images. We also present an application of the proposed approach to clinical PET data from a breast cancer patient with metastatic disease.

Quantitative computed tomography assessment of airway wall dimensions: current status and potential applications for phenotyping chronic obstructive pulmonary disease

Airway remodeling is extremely important in the pathophysiology of chronic obstructive pulmonary disease (COPD). Since the site and nature of airflow obstruction was described by Hogg, Thurlbeck, and Macklem, investigators have been looking for methods to noninvasively measure the airway wall dimensions in subjects with and at risk for COPD. The advent and proliferation of computed tomography (CT) initially allowed investigators to quantify changes in lung parenchymal structure in subjects with emphysema, and more recently attention has turned to the measurement of airway wall dimensions. Unfortunately, while the lung density is relatively easy to quantify, reliable airway measurements have proven to be more difficult to obtain. However, recent advances in CT technology and new computer algorithms have changed the way investigators have measured airways using CT, and it is now hoped that many of the early issues surrounding airway measurements can be resolved. The measurement of airway wall dimensions is important because it is well known that chronic airflow limitation can be caused by a combination of airway and parenchymal changes. The phenotypic expression of these different subtypes of COPD is vital because a therapy designed to modulate the inflammation in airways may be contraindicated in subjects with the emphysema phenotype and visa versa. Therefore, these new imaging techniques are very likely to play a front-line role in the study of COPD and will, hopefully, allow clinicians to phenotype individuals, thereby personalizing their treatment.

Computer-aided detection of endobronchial valves using volumetric CT

RATIONALE AND OBJECTIVES

The ability to automatically detect and monitor implanted devices may serve an important role in patient care by aiding the evaluation of device and treatment efficacy. The purpose of this research was to develop a system for the automated detection of one-way endobronchial valves that were implanted for less invasive lung volume reduction.

MATERIALS AND METHODS

Volumetric thin-section computed tomographic data was obtained for 194 subjects; 95 subjects implanted with 246 devices were used for system development and 99 subjects implanted with 354 devices were reserved for testing. The detection process consisted of preprocessing, pattern recognition based detection, and a final device selection. Following the preprocessing, a set of classifiers was trained using AdaBoost to discriminate true devices from false positives. The classifiers in the cascade used two simple features (either the mean or maximum attenuation) of a local region computed at multiple fixed landmarks relative to a template model of the valve.

RESULTS

Free-response receiver-operating characteristic analysis was performed for the evaluation; the system could be set so the mean sensitivity was 96.5% with a mean of 0.18 false positives per subject. If knowledge of the number of implanted devices were incorporated, the sensitivity would be 96.9% with a mean of 0.061 false positives per subject; this corresponds to a total of 12 false negatives and six false positives for the 99 subjects in the test dataset.

CONCLUSION

Software was developed for automated detection of endobronchial valves on volumetric computed tomography. The proposed device modeling and detection techniques may be applicable to other devices as well as useful for evaluation of treatment response.

Automatic segmentation of lung parenchyma in the presence of diseases based on curvature of ribs

RATIONALE AND OBJECTIVES

Segmentation of lungs using high-resolution computer tomographic images in the setting of diffuse lung diseases is a major challenge in medical image analysis. Threshold-based techniques tend to leave out lung regions that have increased attenuation, such as in the presence of interstitial lung disease. In contrast, streak artifacts can cause the lung segmentation to "leak" into the chest wall. The purpose of this work was to perform segmentation of the lungs using a technique that selects an optimal threshold for a given patient by comparing the curvature of the lung boundary to that of the ribs.

METHODS

Our automated technique goes beyond fixed threshold-based approaches to include lung boundary curvature features. One would expect the curvature of the ribs and the curvature of the lung boundary around the ribs to be very close. Initially, the ribs are segmented by applying a threshold algorithm followed by morphologic operations. The lung segmentation scheme uses a multithreshold iterative approach. The threshold value is verified until the curvature of the ribs and the curvature of the lung boundary are closely matched. The curve of the ribs is represented using polynomial interpolation, and the lung boundary is matched in such a way that there is minimal deviation from this representation. Performance of this technique was compared with conventional (fixed threshold) lung segmentation techniques on 25 subjects using a volumetric overlap fraction measure.

RESULTS

The performance of the rib segmentation technique was significantly different from conventional techniques with an average higher mean volumetric overlap fraction of about 5%.

CONCLUSIONS

The technique described here allows for accurate quantification of volumetric computed tomography and more advanced segmentation of abnormal areas.

Imaging studies in emphysema

Definitions of types of emphysema within the framework of chronic obstructive pulmonary disease are given. The classic findings on the chest radiograph are described, and the advances in sensitivity and specificity achieved with computed tomography (CT) scanning are noted. The "density mask" and the "percentile point" measurements rely on the densitometric property of X-rays, but the scan also shows the severity and distribution of low-attenuation regions that usually represent pathologic emphysema. The alteration of absolute density with changes in lung inflation, CT slice thickness, collimation, and reconstruction algorithm make comparison between CT scans and across studies more difficult. Nevertheless, quantitative CT has superseded subjective scoring of scan appearance by readers as a sensitive way to measure emphysema.

Automatic delineation of the diaphragm in computed tomographic images

Segmentation of the internal organs in medical images is a difficult task. By incorporating a priori information regarding specific organs of interest, results of segmentation may be improved. Landmarking (i.e., identifying stable structures to aid in gaining more knowledge concerning contiguous structures) is a promising segmentation method. Specifically, segmentation of the diaphragm may help in limiting the scope of segmentation methods to the abdominal cavity; the diaphragm may also serve as a stable landmark for identifying internal organs, such as the liver, the spleen, and the heart. A method to delineate the diaphragm is proposed in the present work. The method is based upon segmentation of the lungs, identification of the lower surface of the lungs as an initial representation of the diaphragm, and the application of least-squares modeling and deformable contour models to obtain the final segmentation of the diaphragm. The proposed procedure was applied to nine X-ray computed tomographic (CT) exams of four pediatric patients with neuroblastoma. The results were evaluated against the boundaries of the diaphragm as identified independently by a radiologist. Good agreement was observed between the results of segmentation and the reference contours drawn by the radiologist, with an average mean distance to the closest point of 5.85 mm over a total of 73 CT slices including the diaphragm.

CAD in clinical trials: Current role and architectural requirements

Computer-aided diagnosis (CAD) technology is becoming an important tool to assess treatment response in clinical trials. However, CAD software alone is not sufficient to conduct an imaging-based clinical trial. There are a number of architectural requirements such as image receive (from multiple field sites), a database for storing quantitative measures, and data mining and reporting capabilities. In this paper we describe the architectural requirements to incorporate CAD into clinical trials and illustrate their functionality in therapeutic trials for emphysema.

The effect of lung volume on nodule size on CT

RATIONALE AND OBJECTIVES

We sought to determine how measures of nodule diameter and volume on computed tomography (CT) vary with changes in inspiratory level.

MATERIALS AND METHODS

CT scans were performed with inspiration suspended at total lung capacity (TLC) and then at residual volume (RV) in 41 subjects, in whom 75 indeterminate lung nodules were detected. A fully automated contouring program was used to segment the lungs; followed by segmentation of all nodules and the corresponding lobe using semiautomated contouring in both TLC and RV scans. The percent changes in lung and lobar volumes between TLC and RV were correlated with percent changes in nodule diameters and volumes.

RESULTS

Both nodule diameter and volume varied nonuniformly from TLC to RV-some nodules decreased in size, while others increased. There was a 16.8% mean change in absolute volume across all nodules. Stratified by size, the mean value of the absolute percent volume changes for nodules > or =5 mm and <5 mm were not significantly different (P = .26). Stratified by maximum attenuation, the mean value of the absolute percent volume changes between the TLC and RV series for noncalcified (17.7%, SD = 13.1) and completely calcified nodules (8.6% SD = 5.7) were significantly different (P < .05).

CONCLUSION

Significant differences in nodule size were measured between TLC and RV scans. This has important implications for standardizing acquisition protocols in any setting where size and, more important, size change are being used for purposes of lung cancer staging, nodule characterization, or treatment response assessment.

Feasibility of retinoids for the treatment of emphysema study

BACKGROUND

Retinoids promote alveolar septation in the developing lung and stimulate alveolar repair in some animal models of emphysema.

METHODS

One hundred forty-eight subjects with moderate-to-severe COPD and a primary component of emphysema, defined by diffusing capacity of the lung for carbon monoxide (Dlco) [37.1 +/- 12.0% of predicted] and CT density mask (38.5 +/- 12.8% of voxels <- 910 Hounsfield units) [mean +/- SD] were enrolled into a randomized, double-blind, feasibility study at five university hospitals. Participants received all-trans retinoic acid (ATRA) at either a low dose (LD) [1 mg/kg/d] or high dose (HD) [2 mg/kg/d], 13-cis retinoic acid (13-cRA) [1 mg/kg/d], or placebo for 6 months followed by a 3-month crossover period.

RESULTS

No treatment was associated with an overall improvement in pulmonary function, CT density mask score, or health-related quality of life (QOL) at the end of 6 months. However, time-dependent changes in Dlco (initial decrease with delayed recovery) and St. George Respiratory Questionnaire (delayed improvement) were observed in the HD-ATRA cohort and correlated with plasma drug levels. In addition, 5 of 25 participants in the HD-ATRA group had delayed improvements in their CT scores that also related to ATRA levels. Retinoid-related side effects were common but generally mild.

CONCLUSIONS

No definitive clinical benefits related to the administration of retinoids were observed in this feasibility study. However, time- and dose-dependent changes in Dlco, CT density mask score, and health-related QOL were observed in subjects treated with ATRA, suggesting the possibility of exposure-related biological activity that warrants further investigation.

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

Segmentation of the lungs within magnetic resonance (MR) scans is a necessary step in the computer-based analysis of thoracic MR images. This process is often confounded by image acquisition artifacts and disease-induced morphological deformation. We have developed an automated method for lung segmentation that is insensitive to these complications. The automated method was applied to 23 thoracic MR scans (413 sections) obtained from 10 patients. Two radiologists manually outlined the lung regions in a random sample of 101 sections (n=202 lungs), and the extent to which disease or artifact confounded lung border visualization was evaluated. Accuracy of lung regions extracted by the automated segmentation method was quantified by comparison with the radiologist-defined lung regions using an area overlap measure (AOM) that ranged from 0 (disjoint lung regions) to 1 (complete overlap). The AOM between each observer and the automated method was 0.82 when averaged over all lungs. The average AOM in the lung bases, where lung segmentation is most difficult, was 0.73.

Static versus prospective gated non-breath hold volumetric MDCT imaging of the lungs

RATIONALE AND OBJECTIVES

The study's aim is to establish lung-imaging methods that provide for the ability to image the lung under dynamic non-breath hold conditions while providing "virtual breath hold" quantifiable volumetric image data sets. Static breath hold images are used as the gold standard for evaluating these virtual breath hold images in both a phantom and sheep.

MATERIALS AND METHODS

Axial methods for gating image acquisition to multiple points in the respiratory cycle interleaved with incremental table stepping during multidetector-row computed tomographic (MDCT) scanning were developed. Data sets are generated over multiple breaths, providing volume images representative of multiple points within a respiratory cycle. To determine the reproducibility and accuracy of the methods, six anesthetized sheep were studied by means of MDCT in nongated and airway-pressure (P(awy))-gated modes in which P(awy) was 0, 7, and 15 cm H2O.

RESULTS

No significant differences were found between coefficients of variation in air volume measured from repeated static scans (1.74% +/- 1.78%), gated scans: inspiratory (1.2% +/- 0.44%) or expiratory gated (1.39% +/- 0.98%), or between static (1.74% +/- 1.78%) and gated (1.39% +/- 0.98%) scanning at similar P(awy) (P > .1). Measured air volumes were larger from static versus gated scans by 5.85% +/- 3.77% at 7 cm H2O and 4.45% +/- 3.6% at 15 cm H2O of P(awy) (P < .05), consistent with hysteresis. Differences between air volumes at 7 and 15 cm H2O measured from either static or gated scans or that delivered by a super syringe were insignificant (P < .05). Visual accuracy of three-dimensional anatomic geometry was achieved, and landmark certainty was within 1 mm across respiratory cycles.

CONCLUSIONS

A method has been shown that provides for accurate gating to respiratory signals during axial scanning. High-resolution volumetric image data sets are achievable while the scanned subject is breathing. Images are quantitatively similar to breath hold images, with differences likely explained by known pressure-volume hysteresis effects.

Use of CT Morphometry To Detect Changes in Lung Weight and Gas Volume

STUDY OBJECTIVES

CT estimates of lung density have been used to estimate the extent and severity of emphysema. The present study was designed to test the hypothesis that quantitative CT can track the changes that occur in diffuse lung disease.

DESIGN

The study was based on five patients with pulmonary alveolar proteinosis (PAP) who underwent lung lavage. Pulmonary function was measured before and after each individual lung lavage, and the CT scans before and after lavage were used to compare total lung volume, airspace volume, lung weight, and regional lung inflation. The dry weight of proteinaceous material lavaged from the lung was measured and compared to the change in CT lung weight.

RESULTS

All the patients showed improvements in dyspnea, percentage of predicted diffusion capacity of the lung for carbon monoxide, and FVC. There was no change in CT-measured total lung volume or airspace volume, but there was a reduction in lung weight following lavage (p = 0.001), which correlated with the dry weight of the lavage effluent (R(2) = 0.73). Therefore, there was a shift in the regional lung inflation toward a more inflated lung with a corresponding increase in the mean lung inflation (p = 0.001).

CONCLUSION

These data show that quantitative CT can objectively track the changes in lung weight and airspace inflation produced by a standard intervention in PAP, and we postulate that it can provide similar information about the progression of other diffuse lung diseases.

Database Design and Implementation for Quantitative Image Analysis Research

Quantitative image analysis (QIA) goes beyond subjective visual assessment to provide computer measurements of the image content, typically following image segmentation to identify anatomical regions of interest (ROIs). Commercially available picture archiving and communication systems focus on storage of image data. They are not well suited to efficient storage and mining of new types of quantitative data. In this paper, we present a system that integrates image segmentation, quantitation, and characterization with database and data mining facilities. The paper includes generic process and data models for QIA in medicine and describes their practical use. The data model is based upon the Digital Imaging and Communications in Medicine (DICOM) data hierarchy, which is augmented with tables to store segmentation results (ROIs) and quantitative data from multiple experiments. Data mining for statistical analysis of the quantitative data is described along with example queries. The database is implemented in PostgreSQL on a UNIX server. Database requirements and capabilities are illustrated through two quantitative imaging experiments related to lung cancer screening and assessment of emphysema lung disease. The system can manage the large amounts of quantitative data necessary for research, development, and deployment of computer-aided diagnosis tools.

Automated lung segmentation for thoracic CT impact on computer-aided diagnosis

RATIONALE AND OBJECTIVES

Automated lung segmentation in thoracic computed tomography scans is essential for the development of computer-aided diagnostic (CAD) methods. A core segmentation method may be developed for general application; however, modifications may be required for specific clinical tasks.

MATERIALS AND METHODS

An automated lung segmentation method has been applied (1) as preprocessing for automated lung nodule detection and (2) as the foundation for computer-assisted measurements of pleural mesothelioma tumor thickness. The core method uses gray-level thresholding to segment the lungs within each computed tomography section. The segmentation is revised through separation of right and left lungs along the anterior junction line, elimination of the trachea and main bronchi from the lung segmentation regions, and suppression of the diaphragm. Segmentation modifications required for nodule detection include a rolling ball algorithm to include juxtapleural nodules and morphologic erosion to eliminate partial volume pixels at the boundary of the segmentation regions.

RESULTS

For automated lung nodule detection, 4 of 82 actual nodules (4.9%) were excluded from the lung segmentation regions when the core segmentation method was modified compared with 14 nodules (17.1%) excluded without modifications. The computer-assisted quantification of mesothelioma method achieved a correlation coefficient of 0.990 with 134 manual measurements when the core segmentation method was used alone; correlation was reduced to 0.977 when the segmentation modifications, as adapted for the lung nodule detection task, were applied to the mesothelioma measurement task.

CONCLUSION

Different CAD applications impose different requirements on the automated lung segmentation process. The specific approach to lung segmentation must be adapted to the particular CAD task.

Emphysema: effect of reconstruction algorithm on CT imaging measures

In the current study, the effects of reconstruction algorithms on quantitative measures derived from computed tomographic (CT) lung images were assessed in patients with emphysema. CT image data sets were reconstructed with a standard algorithm and alternative algorithm(s) for 42 subjects. Algorithms were grouped as overenhancing, sharp, standard, or smooth. Density mask and volume measurements from the alternative algorithm data sets were compared with standard algorithm data sets. The overenhancing category yielded an average shift of 9.4% (ie, a shift in average score from 35.5% to 44.9%); the sharp category, a shift of 2.4%; and the smooth category, a shift of -1.0%. Differences in total lung volume measurements were less than 1%. In conclusion, the CT reconstruction algorithm may strongly affect density mask results, especially for certain reconstruction algorithms.

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.

Functional Analysis in Single-Lung Transplant Recipients

OBJECTIVE

To develop and evaluate a postprocessing tool to quantify ventilated split-lung volumes on the basis of (3)He-MRI and to apply it in patients after single-lung transplantation (SLTX). High-resolution CT (HRCT) was employed as a reference modality providing split air-filled lung volumes. Lung volumes derived from pulmonary function test results served as clinical parameters and were used as the "gold standard."

MATERIAL AND METHODS

Eight patients (mean age, 54 years) with emphysema and six patients (mean age, 58 years) with idiopathic pulmonary fibrosis. All patients were evaluated following SLTX. HRCT was performed during inspiration (slice thickness, 1 mm; increment, 10 mm). For correlation with (3)He-MRI, HRCT images were reconstructed in coronal orientation to match the same anatomic levels. Aerated lung was determined by threshold-based segmentation of CT. (3)He-MRI was performed on a 1.5-T scanner using a two-dimensional, fast low-angle shot sequence in coronal orientation covering the whole lung after inhalation of a 300-mL bolus of hyperpolarized (3)He gas followed by normal room air for the rest of the tidal volume. Lung segmentation on (3)He-MRI was done using different thresholds.

RESULTS

In emphysematous patients, (3)He-MRI showed excellent correlation (r = 0.9) with vital capacity, while CT correlated (r = 0.8) with total lung capacity. (3)He-MRI correlated well with CT (r > 0.8) for grafts and native fibrotic lungs. In emphysematous lungs, MRI showed a good correlation (r = 0.7) with the nonemphysematous lung volume from CT. Increasing thresholds in (3)He-MRI reveal differences between aerated and ventilated lung areas with a different distribution in emphysema and fibrosis.

CONCLUSIONS

(3)He-MRI is superior to CT in emphysema to demonstrate ventilated lung areas that participate in gas exchange. In fibrosis, (3)He-MRI and CT have a similar impact. The decrease pattern and the intraindividual ratio between ventilation of native and transplanted lungs will have to be investigated as a new surrogate for the ventilatory follow-up in patients undergoing SLTX.

A computer aided diagnostic system for radiotherapy planning

Planning for radiation therapy intervention implies the definition of treatment volumes as well as a clear delimitation of normal tissue. This paper presents a Computer Aided Diagnostic system for the automatic CT image analysis. Two important problems are solved: the spinal cord segmentation and the detection of lung metastases. Some subordinate problems are also solved: the detection of spinal canal, lamina, lungs, and ribs, as well as the identification of thorax contour. The developed methodologies use a knowledge-driven image processing based on Anatomical Structures Maps and task-oriented architecture. Experiments were performed on CT images from La Chaux de Fonds Hospital (Switzerland). Evaluations were performed using a visual inspection of the contours projected on the CT image slices. The radiologist decided whether each of the contours obtained with our system was acceptable or not. The accuracy of the method was defined as the fraction of CT slices in which the particular contour was correctly located. In the case of spinal cord segmentation, the procedure was tested on 23 patients (1051 images), resulting in an accuracy of 91%. In the case of lung tumors detection, the method showed an accuracy of > 90%, with testing performed on 20 patients for a total of 988 images. The experiments performed show that the method is reliable, with possible future application in an oncology department.

A knowledge-based approach to automatic detection of the spinal cord in CT images

Accurate planning of radiation therapy entails the definition of treatment volumes and a clear delimitation of normal tissue of which unnecessary exposure should be prevented. The spinal cord is a radiosensitive organ, which should be precisely identified because an overexposure to radiation may lead to undesired complications for the patient such as neuronal disfunction or paralysis. In this paper, a knowledge-based approach to identifying the spinal cord in computed tomography images of the thorax is presented. The approach relies on a knowledge-base which consists of a so-called anatomical structures map (ASM) and a task-oriented architecture called the plan solver. The ASM contains a frame-like knowledge representation of the macro-anatomy in the human thorax. The plan solver is responsible for determining the position, orientation and size of the structures of interest to radiation therapy. The plan solver relies on a number of image processing operators. Some are so-called atomic (e.g., thresholding and snakes) whereas others are composite. The whole system has been implemented on a standard PC. Experiments performed on the image material from 23 patients show that the approach results in a reliable recognition of the spinal cord (92% accuracy) and the spinal canal (85% accuracy). The lamina is more problematic to locate correctly (accuracy 72%). The position of the outer thorax is always determined correctly.

Lymphangioleiomyomatosis: correlation of qualitative and quantitative thin-section CT with pulmonary function tests and assessment of dependence on pleurodesis

PURPOSE

To explore the relationship between findings at thin-section computed tomography (CT) and pulmonary function tests in lymphangioleiomyomatosis (LAM) and to evaluate the influence of pleurodesis on this relation and the effectiveness of quantitative versus qualitative CT in the assessment of disease severity.

MATERIALS AND METHODS

Thirty-seven patients with LAM (17 with pleurodesis) underwent CT and pulmonary function tests. The severity of pulmonary cystic involvement was graded qualitatively by two independent readers and measured quantitatively at CT with a thresholding technique. Relationships between findings at CT and pulmonary function tests and the influence of pleurodesis on these findings were assessed with regression analysis and analysis of covariance.

RESULTS

Qualitative ratings had good agreement between observers (kappa = 0.75). Quantitative CT had good repeatability and showed significant correlation with the percent predicted forced expiratory volume in 1 second (FEV(1)%) (r = 0.67, P <.001), percent predicted diffusing capacity of lung for carbon monoxide (DLCO%) (r = 0.48, P <.005), percent predicted ratio of residual volume to total lung capacity (RV/TLC%) (r = -0.65, P <.001), and percent predicted TLC (r = 0.34, P <.04). Quantitative CT results were somewhat better than qualitative CT results. The standard error of the FEV(1)% for the quantitative CT was about 85% of that for the qualitative CT. Pleurodesis had no statistically significant effect on the slope of the regression line between quantitative CT findings, FEV(1)%, and DLCO% (corrected for alveolar volume). The slope between quantitative CT and RV/TLC% was significantly (P =.044) more negative in patients with pleurodesis.

CONCLUSION

Qualitative and quantitative CT findings correlate with pulmonary dysfunction over a wide range of disease severity in patients with LAM. Pleurodesis influences the relationship between CT measurements and pulmonary function test results.

Quantitative CT of the lung

Lung disease is a leading cause of morbidity and mortality. HRCT, currently the best test to assess lung involvement in emphysema and interstitial lung disease, relies on abnormalities being detected when there is sufficient morphologic distortion to result in visually identified changes that, for the most part, correlate poorly with conventional lung function tests and outcome. QIA offers a technique to assess both structure and function on a regional and global basis. With the advent of user-friendly software packages, this approach is finding application in clinical practice and in clinical studies of new treatment alternatives for diffuse lung disease