AI-enabled left atrial volumetry in coronary artery calcium scans (AI-CACTM) predicts atrial fibrillation as early as one year, improves CHARGE-AF, and outperforms NT-proBNP: The multi-ethnic study of atherosclerosis.

BACKGROUND: Coronary artery calcium (CAC) scans contain actionable information beyond CAC scores that is not currently reported. METHODS: We have applied artificial intelligence-enabled automated cardiac chambers volumetry to CAC scans (AI-CACTM) to 5535 asymptomatic individuals (52.2% women, ages 45-84) that were previously obtained for CAC scoring in the baseline examination (2000-2002) of the Multi-Ethnic Study of Atherosclerosis (MESA). AI-CAC took on average 21 â€‹s per CAC scan. We used the 5-year outcomes data for incident atrial fibrillation (AF) and assessed discrimination using the time-dependent area under the curve (AUC) of AI-CAC LA volume with known predictors of AF, the CHARGE-AF Risk Score and NT-proBNP. The mean follow-up time to an AF event was 2.9 â€‹± â€‹1.4 years. RESULTS: At 1,2,3,4, and 5 years follow-up 36, 77, 123, 182, and 236 cases of AF were identified, respectively. The AUC for AI-CAC LA volume was significantly higher than CHARGE-AF for Years 1, 2, and 3 (0.83 vs. 0.74, 0.84 vs. 0.80, and 0.81 vs. 0.78, respectively, all p â€‹< â€‹0.05), but similar for Years 4 and 5, and significantly higher than NT-proBNP at Years 1-5 (all p â€‹< â€‹0.01), but not for combined CHARGE-AF and NT-proBNP at any year. AI-CAC LA significantly improved the continuous Net Reclassification Index for prediction of AF over years 1-5 when added to CHARGE-AF Risk Score (0.60, 0.28, 0.32, 0.19, 0.24), and NT-proBNP (0.68, 0.44, 0.42, 0.30, 0.37) (all p â€‹< â€‹0.01). CONCLUSION: AI-CAC LA volume enabled prediction of AF as early as one year and significantly improved on risk classification of CHARGE-AF Risk Score and NT-proBNP.

Visual scoring of osteoporosis on low-dose CT in lung cancer screening population.

OBJECTIVES: The risk factors for lung cancer screening eligibility, age as well as smoking history, are also present for osteoporosis. This study aims to develop a visual scoring system to identify osteoporosis that can be applied to low-dose CT scans obtained for lung cancer screening. MATERIALS AND METHODS: We retrospectively reviewed 1000 prospectively enrolled participants in the lung cancer screening program at the Mount Sinai Hospital. Optimal window width and level settings for the visual assessment were chosen based on a previously described approach. Visual scoring of osteoporosis and automated measurement using dedicated software were compared. Inter-reader agreement was conducted using six readers with different levels of experience who independently visually assessed 30 CT scans. RESULTS: Based on previously validated formulas for choosing window and level settings, we chose osteoporosis settings of Width = 230 and Level = 80. Of the 1000 participants, automated measurement was successfully performed on 774 (77.4 %). Among these, 138 (17.8 %) had osteoporosis. There was a significant correlation between the automated measurement and the visual score categories for osteoporosis (Kendall's Tau = -0.64, p < 0.0001; Spearman's rho = -0.77, p < 0.0001). We also found substantial to excellent inter-reader agreement on the osteoporosis classification among the 6 radiologists (Fleiss κ = 0.91). CONCLUSIONS: Our study shows that a simple approach of applying specific window width and level settings to already reconstructed sagittal images obtained in the context of low-dose CT screening for lung cancer is highly feasible and useful in identifying osteoporosis.

AI-enabled Left Atrial Volumetry in Cardiac CT Scans Improves CHARGE-AF and Outperforms NT-ProBNP for Prediction of Atrial Fibrillation in Asymptomatic Individuals: Multi-Ethnic Study of Atherosclerosis.

Background: Coronary artery calcium (CAC) scans contain actionable information beyond CAC scores that is not currently reported. Methods: We have applied artificial intelligence-enabled automated cardiac chambers volumetry to CAC scans (AI-CAC), taking on average 21 seconds per CAC scan, to 5535 asymptomatic individuals (52.2% women, ages 45-84) that were previously obtained for CAC scoring in the baseline examination (2000-2002) of the Multi-Ethnic Study of Atherosclerosis (MESA). We used the 5-year outcomes data for incident atrial fibrillation (AF) and compared the time-dependent AUC of AI-CAC LA volume with known predictors of AF, the CHARGE-AF Risk Score and NT-proBNP (BNP). The mean follow-up time to an AF event was 2.9±1.4 years. Results: At 1,2,3,4, and 5 years follow-up 36, 77, 123, 182, and 236 cases of AF were identified, respectively. The AUC for AI-CAC LA volume was significantly higher than CHARGE-AF or BNP at year 1 (0.836, 0.742, 0.742), year 2 (0.842, 0.807,0.772), and year 3 (0.811, 0.785, 0.745) (p<0.02), but similar for year 4 (0.785, 0.769, 0.725) and year 5 (0.781, 0.767, 0.734) respectively (p>0.05). AI-CAC LA volume significantly improved the continuous Net Reclassification Index for prediction of AF over years 1-5 when added to CAC score (0.74, 0.49, 0.53, 0.39, 0.44), CHARGE-AF Risk Score (0.60, 0.28, 0.32, 0.19, 0.24), and BNP (0.68, 0.44, 0.42, 0.30, 0.37) respectively (p<0.01). Conclusion: AI-CAC LA volume enabled prediction of AF as early as one year and significantly improved on risk classification of CHARGE-AF Risk Score and BNP.

Cluster Analysis of World Trade Center Related Lower Airway Diseases.

ABSTRACT: Introduction: Cluster analysis can classify without a priori assumptions the heterogeneous chronic lower airway diseases found in former workers at the World Trade Center (WTC) disaster site. Methods: We selected the first available chest computed tomography scan with quantitative computed tomography measurements on 311 former WTC workers with complete clinical, and spirometric data from their closest surveillance visit. We performed a nonhierarchical iterative algorithm K-prototype cluster analysis, using gap measure. Results: A five-cluster solution was most satisfactory. Cluster 5 had the healthiest individuals. In cluster 4, smoking was most prevalent and intense but there was scant evidence of respiratory disease. Cluster 3 had symptomatic subjects with reduced forced vital capacity impairment (low FVC). Clusters 1 and 2 had less dyspneic subjects, but more functional and quantitative computed tomography evidence of chronic obstructive pulmonary disease (COPD) in cluster 1, or low FVC in cluster 2. Clusters 1 and 4 had the highest proportion of rapid first-second forced expiratory volume decliners. Conclusions: Cluster analysis confirms low FVC and COPD/pre-COPD as distinctive chronic lower airway disease phenotypes on long-term surveillance of the WTC workers.

Dynamic Differential Image Circle Diameter Measurement Precision Assessment: Application to Burning Droplets.

Dynamic measurement precision assessment has been achieved for a differential circle measurement application. Differential circle diameter measurement, in image analysis, typically requires fitting a circle model that optimizes for image distortions, defects or occlusions. The differential task occurs when precise measurements of diameter change are required given object size variation with time. An automated system was designed to provide diameter measurements and associated measurement precision of images of a fuel droplet undergoing combustion in zero gravity for the FLEX-2 dataset. An image gradient-based, least-squares boundary point fitting method to a circle or ellipse model is used for diameter measurement. The presence of soot aggregates poses significant challenges for diameter measurements when it occludes part of the droplet boundary. The precision of the diameter measurements depends upon the image quality. Using synthetic image simulations that model the soot behavior, we developed a model based on image quality measures that assesses the measurement precision for each individual diameter measurement. Thus, diameter measurements with precision assessments were made available for follow-up scientific analysis. The algorithm's success rate for measurable runs was 98%. In cases of limited occlusion, a measurement precision of ±0.2 pixels for the FLEX-2 dataset was achieved.

The Regimen of Computed Tomography Screening for Lung Cancer: Lessons Learned Over 25 Years From the International Early Lung Cancer Action Program.

We learned many unanticipated and valuable lessons since we started planning our study of low-dose computed tomography (CT) screening for lung cancer in 1991. The publication of the baseline results of the Early Lung Cancer Action Project (ELCAP) in Lancet 1999 showed that CT screening could identify a high proportion of early, curable lung cancers. This stimulated large national screening studies to be quickly started. The ELCAP design, which provided evidence about screening in the context of a clinical program, was able to rapidly expand to a 12-institution study in New York State (NY-ELCAP) and to many international institutions (International-ELCAP), ultimately working with 82 institutions, all using the common I-ELCAP protocol. This expansion was possible because the investigators had developed the ELCAP Management System for screening, capturing data and CT images, and providing for quality assurance. This advanced registry and its rapid accumulation of data and images allowed continual assessment and updating of the regimen of screening as advances in knowledge and new technology emerged. For example, in the initial ELCAP study, introduction of helical CT scanners had allowed imaging of the entire lungs in a single breath, but the images were obtained in 10 mm increments resulting in about 30 images per person. Today, images are obtained in submillimeter slice thickness, resulting in around 700 images per person, which are viewed on high-resolution monitors. The regimen provides the imaging acquisition parameters, imaging interpretation, definition of positive result, and the recommendations for further workup, which now include identification of emphysema and coronary artery calcifications. Continual updating is critical to maximize the benefit of screening and to minimize potential harms. Insights were gained about the natural history of lung cancers, identification and management of nodule subtypes, increased understanding of nodule imaging and pathologic features, and measurement variability inherent in CT scanners. The registry also provides the foundation for assessment of new statistical techniques, including artificial intelligence, and integration of effective genomic and blood-based biomarkers, as they are developed.

Association of quantitative CT lung density measurements and lung function decline in World Trade Center workers.

BACKGROUND: Occupational exposures at the WTC site after 11 September 2001 have been associated with presumably inflammatory chronic lower airway diseases. AIMS: In this study, we describe the trajectories of expiratory air flow decline, identify subgroups with adverse progression, and investigate the association of those trajectories with quantitative computed tomography (QCT) imaging measurement of increased and decreased lung density. METHODS: We examined the trajectories of expiratory air flow decline in a group of 1,321 former WTC workers and volunteers with at least three periodic spirometries, and using QCT-measured low (LAV%, -950 HU) and high (HAV%, from -600 to -250 HU) attenuation volume percent. We calculated the individual regression line slopes for first-second forced expiratory volume (FEV1 slope), identified subjects with rapidly declining ("accelerated decliners") and increasing ("improved"), and compared them to subjects with "intermediate" (0 to -66.5 mL/year) FEV1 slope. We then used multinomial logistic regression to model those three trajectories, and the two lung attenuation metrics. RESULTS: The mean longitudinal FEV1 slopes for the entire study population, and its intermediate, decliner, and improved subgroups were, respectively, -40.4, -34.3, -106.5, and 37.6 mL/year. In unadjusted and adjusted analyses, LAV% and HAV% were both associated with "accelerated decliner" status (ORadj , 95% CI 2.37, 1.41-3.97, and 1.77, 1.08-2.89, respectively), compared to the intermediate decline. CONCLUSIONS: Longitudinal FEV1 decline in this cohort, known to be associated with QCT proximal airway inflammation metric, is also associated with QCT indicators of increased and decreased lung density. The improved FEV1 trajectory did not seem to be associated with lung density metrics.

Quantitative CT Evidence of Airway Inflammation in WTC Workers and Volunteers with Low FVC Spirometric Pattern.

BACKGROUND: The most common abnormal spirometric pattern reported in WTC worker and volunteer cohorts has consistently been that of a nonobstructive reduced forced vital capacity (low FVC). Low FVC is associated with obesity, which is highly prevalent in these cohorts. We used quantitative CT (QCT) to investigate proximal and distal airway inflammation and emphysema in participants with stable low FVC pattern. METHODS: We selected study participants with at least two available longitudinal surveillance spirometries, and a chest CT with QCT measurements of proximal airway inflammation (wall area percent, WAP), end-expiratory air trapping, suggestive of distal airway obstruction (expiratory to inspiratory mean lung attenuation ratio, MLAEI), and emphysema (percentage of lung volume with attenuation below - 950 HU, LAV%). The comparison groups in multinomial logistic regression models were participants with consistently normal spirometries, and participants with stable fixed obstruction (COPD). RESULTS: Compared to normal spirometry participants, and after adjusting for age, sex, race/ethnicity, BMI, smoking, and early arrival at the WTC disaster site, low FVC participants had higher WAP (ORadj 1.24, 95% CI 1.06, 1.45, per 5% unit), suggestive of proximal airway inflammation, but did not differ in MLAEI, or LAV%. COPD participants did not differ in WAP with the low FVC ones and were more likely to have higher MLAEI or LAV% than the other two subgroups. DISCUSSION: WTC workers with spirometric low FVC have higher QCT-measured WAP compared to those with normal spirometries, but did not differ in distal airway and emphysema measurements, independently of obesity, smoking, and other covariates.

Automated measurement of liver attenuation to identify moderate-to-severe hepatic steatosis from chest CT scans.

PURPOSE: Develop and validate an automated method for measuring liver attenuation in non-contrast low-dose chest CT (LDCT) scans and compare it to the standard manual method for identifying moderate-to-severe hepatic steatosis (HS). METHOD: The automated method identifies a region below the right lung within the liver and uses statistical sampling techniques to exclude non-liver parenchyma. The method was used to assess moderate-to-severe HS on two IRB-approved cohorts: 1) 24 patients with liver disease examined between 1/2013-1/2017 with non-contrast chest CT and abdominal MRI scans obtained within three months of liver biopsy, and 2) 319 lung screening participants with baseline LDCT performed between 8/2011-1/2017. Agreement between the manual and automated CT methods, the manual MRI method, and pathology for determining moderate-to-severe HS was assessed using Cohen's Kappa by applying a 40 HU threshold to the CT method and 17.4% fat fraction to MRI. Agreement between the manual and automated CT methods was assessed using the intraclass correlation coefficient (ICC). Variability was assessed using Bland-Altman limits of agreement (LoA). RESULTS: In the first cohort, the manual and automated CT methods had almost perfect agreement (ICC = 0.97, κ = 1.00) with LoA of -7.6 to 4.7 HU. Both manual and automated CT methods had almost perfect agreement with MRI (κ = 0.90) and substantial agreement with pathology (κ = 0.77). In the second cohort, the manual and automated CT methods had almost perfect agreement (ICC = 0.94, κ = 0.87). LoA were -10.6 to 5.2 HU. CONCLUSION: Automated measurements of liver attenuation from LDCT scans can be used to identify moderate-to-severe HS on LDCT.

Increased pulmonary artery diameter is associated with reduced FEV1 in former World Trade Center workers.

RATIONALE: Occupational exposures at the WTC site after September 11, 2001 have been associated with several presumably inflammatory lower airway diseases. Pulmonary arterial enlargement, as suggested by an increased ratio of the diameter of the pulmonary artery to the diameter of the aorta (PAAr) has been reported as a computed tomographic (CT) scan marker of adverse respiratory health outcomes, including WTC-related disease. In this study, we sought to utilize a novel quantitative CT (QCT) measurement of PAAr to test the hypothesis that an increased ratio is associated with FEV1 below each subject's statistically determined lower limit of normal (FEV1  < LLN). METHODS: In a group of 1,180 WTC workers and volunteers, we examined whether FEV1  < LLN was associated with an increased QCT-measured PAAr, adjusting for previously identified important covariates. RESULTS: Unadjusted analyses showed a statistically significant association of FEV1  < LLN with PAAr (35.3% vs 24.7%, P = 0.0001), as well as with height, body mass index, early arrival at the WTC disaster site, shorter WTC exposure duration, post-traumatic stress disorder checklist (PCL) score, wall area percent and evidence of bronchodilator response. The multivariate logistic regression model confirmed the association of FEV1  < LLN with PAAr (OR 1.63, 95% CI 1.21, 2.20, P = 0.0015) and all the unadjusted associations, except for PCL score. CONCLUSIONS: In WTC workers, FEV1  < LLN is associated with elevated PAAr which, although likely multifactorial, may be related to distal vasculopathy, as has been hypothesized for chronic obstructive pulmonary disease.

Emphysema phenotypes and lung cancer risk.

BACKGROUND: To assess the relationship between lung cancer and emphysema subtypes. OBJECTIVE: Airflow obstruction and emphysema predispose to lung cancer. Little is known, however, about the lung cancer risk associated with different emphysema phenotypes. We assessed the risk of lung cancer based on the presence, type and severity of emphysema, using visual assessment. METHODS: Seventy-two consecutive lung cancer cases were selected from a prospective cohort of 3,477 participants enrolled in the Clínica Universidad de Navarra's lung cancer screening program. Each case was matched to three control subjects using age, sex, smoking history and body mass index as key variables. Visual assessment of emphysema and spirometry were performed. Logistic regression and interaction model analysis were used in order to investigate associations between lung cancer and emphysema subtypes. RESULTS: Airflow obstruction and visual emphysema were significantly associated with lung cancer (OR = 2.8, 95%CI: 1.6 to 5.2; OR = 5.9, 95%CI: 2.9 to 12.2; respectively). Emphysema severity and centrilobular subtype were associated with greater risk when adjusted for confounders (OR = 12.6, 95%CI: 1.6 to 99.9; OR = 34.3, 95%CI: 25.5 to 99.3, respectively). The risk of lung cancer decreases with the added presence of paraseptal emphysema (OR = 4.0, 95%CI: 3.6 to 34.9), losing this increased risk of lung cancer when it occurs alone (OR = 0.7, 95%CI: 0.5 to 2.6). CONCLUSIONS: Visual scoring of emphysema predicts lung cancer risk. The centrilobular phenotype is associated with the greatest risk.

Association of Obesity with Quantitative Chest CT Measured Airway Wall Thickness in WTC Workers with Lower Airway Disease.

BACKGROUND: We previously reported that wall area percent (WAP), a quantitative CT (QCT) indicator of airway wall thickness and, presumably, inflammation, is associated with adverse longitudinal expiratory flow trajectories in WTC workers, but that obesity and weight gain also seemed to be independently predictive of the latter. Previous studies have reported no association between WAP and obesity, so we investigated that association in nonsmoking WTC-exposed individuals and healthy unexposed controls. METHODS: We assessed WAP using the Chest Imaging Platform QCT system in a segmental bronchus in 118 former WTC workers, and 89 COPDGene® WTC-unexposed and asymptomatic subjects. We used multiple regression to model WAP vs. body mass index (BMI) in the two groups, adjusting for important subject and CT image characteristics. RESULTS: Unadjusted analyses revealed significant differences between the two groups with regards to WAP, age, gender, scan pixel spacing and slice interval, but not BMI or total lung capacity. In adjusted analysis, there was a significant interaction between BMI and WTC exposure on WAP. BMI was significantly and positively associated with WAP in the WTC group, but not in the COPDGene® group, but stratified analyses revealed that the effect was significant in WTC subjects with clinical evidence of lower airway disease (LAD). DISCUSSION: Unlike non-diseased subjects, BMI was significantly associated with WAP in WTC workers and, in stratified analyses, the association was significant only among those with LAD. Our findings suggest that this adverse effect of obesity on airway structure and inflammation may be confined to already diseased individuals.

Increased Airway Wall Thickness is Associated with Adverse Longitudinal First-Second Forced Expiratory Volume Trajectories of Former World Trade Center workers.

RATIONALE: Occupational exposures at the WTC site after September 11, 2001 have been associated with several presumably inflammatory lower airway diseases. In this study, we describe the trajectories of expiratory air flow decline, identify subgroups with adverse progression, and investigate the association of a quantitative computed tomography (QCT) imaging measurement of airway wall thickness, and other risk factors for adverse progression. METHODS: We examined the trajectories of expiratory air flow decline in a group of 799 former WTC workers and volunteers with QCT-measured (with two independent systems) wall area percent (WAP) and at least 3 periodic spirometries. We calculated individual regression lines for first-second forced expiratory volume (FEV1), identified subjects with rapidly declining and increasing ("gainers"), and compared them to subjects with normal and "stable" FEV1 decline. We used multivariate logistic regression to model decliner vs. stable trajectories. RESULTS: The mean longitudinal FEV1slopes for the entire study population, and its stable, decliner, and gainer subgroups were, respectively, - 35.8, - 8, - 157.6, and + 173.62 ml/year. WAP was associated with "decliner" status (ORadj 1.08, 95% CI 1.02, 1.14, per 5% increment) compared to stable. Age, weight gain, baseline FEV1 percent predicted, bronchodilator response, and pre-WTC occupational exposures were also significantly associated with accelerated FEV1 decline. Analyses of gainers vs. stable subgroup showed WAP as a significant predictor in unadjusted but not consistently in adjusted analyses. CONCLUSIONS: The apparent normal age-related rate of FEV1 decline results from averaging widely divergent trajectories. WAP is significantly associated with accelerated air flow decline in WTC workers.

Automated image quality assessment for chest CT scans.

PURPOSE: Medical image quality needs to be maintained at standards sufficient for effective clinical reading. Automated computer analytic methods may be applied to medical images for quality assessment. METHODS: For chest CT scans in a lung cancer screening context, an automated quality assessment method is presented that characterizes image noise and image intensity calibration. This is achieved by image measurements in three automatically segmented homogeneous regions of the scan: external air, trachea lumen air, and descending aorta blood. Profiles of CT scanner behavior are also computed. RESULTS: The method has been evaluated on both phantom and real low-dose chest CT scans and results show that repeatable noise and calibration measures may be realized by automated computer algorithms. Noise and calibration profiles show relevant differences between different scanners and protocols. CONCLUSIONS: Automated image quality assessment may be useful for quality control for lung cancer screening and may enable performance improvements to automated computer analysis methods.

Evaluation of a semi-automated computer algorithm for measuring total fat and visceral fat content in lambs undergoing in vivo whole body computed tomography.

Computed tomography (CT) is a suitable tool for measuring body fat, since it is non-destructive and can be used to differentiate metabolically active visceral fat from total body fat. Whole body analysis of body fat is likely to be more accurate than single CT slice estimates of body fat. The aim of this study was to assess the agreement between semi-automated computer analysis of whole body volumetric CT data and conventional proximate (chemical) analysis of body fat in lambs. Data were collected prospectively from 12 lambs that underwent duplicate whole body CT, followed by slaughter and carcass analysis by dissection and chemical analysis. Agreement between methods for quantification of total and visceral fat was assessed by Bland-Altman plot analysis. The repeatability of CT was assessed for these measures using the mean difference of duplicated measures. When compared to chemical analysis, CT systematically underestimated total and visceral fat contents by more than 10% of the mean fat weight. Therefore, carcass analysis and semi-automated CT computer measurements were not interchangeable for quantifying body fat content without the use of a correction factor. CT acquisition was repeatable, with a mean difference of repeated measures being close to zero. Therefore, uncorrected whole body CT might have an application for assessment of relative changes in fat content, especially in growing lambs.

Pulmonary nodule classification in lung cancer screening with three-dimensional convolutional neural networks.

A three-dimensional (3-D) convolutional neural network (CNN) trained from scratch is presented for the classification of pulmonary nodule malignancy from low-dose chest CT scans. Recent approval of lung cancer screening in the United States provides motivation for determining the likelihood of malignancy of pulmonary nodules from the initial CT scan finding to minimize the number of follow-up actions. Classifier ensembles of different combinations of the 3-D CNN and traditional machine learning models based on handcrafted 3-D image features are also explored. The dataset consisting of 326 nodules is constructed with balanced size and class distribution with the malignancy status pathologically confirmed. The results show that both the 3-D CNN single model and the ensemble models with 3-D CNN outperform the respective counterparts constructed using only traditional models. Moreover, complementary information can be learned by the 3-D CNN and the conventional models, which together are combined to construct an ensemble model with statistically superior performance compared with the single traditional model. The performance of the 3-D CNN model demonstrates the potential for improving the lung cancer screening follow-up protocol, which currently mainly depends on the nodule size.

Large-scale image region documentation for fully automated image biomarker algorithm development and evaluation.

With the advent of fully automated image analysis and modern machine learning methods, there is a need for very large image datasets having documented segmentations for both computer algorithm training and evaluation. This paper presents a method and implementation for facilitating such datasets that addresses the critical issue of size scaling for algorithm validation and evaluation; current evaluation methods that are usually used in academic studies do not scale to large datasets. This method includes protocols for the documentation of many regions in very large image datasets; the documentation may be incrementally updated by new image data and by improved algorithm outcomes. This method has been used for 5 years in the context of chest health biomarkers from low-dose chest CT images that are now being used with increasing frequency in lung cancer screening practice. The lung scans are segmented into over 100 different anatomical regions, and the method has been applied to a dataset of over 20,000 chest CT images. Using this framework, the computer algorithms have been developed to achieve over 90% acceptable image segmentation on the complete dataset.

Low-Dose CT Screening for Lung Cancer: Computer-aided Detection of Missed Lung Cancers.

Purpose To update information regarding the usefulness of computer-aided detection (CAD) systems with a focus on the most critical category, that of missed cancers at earlier imaging, for cancers that manifest as a solid nodule. Materials and Methods By using a HIPAA-compliant institutional review board-approved protocol where informed consent was obtained, 50 lung cancers that manifested as a solid nodule on computed tomographic (CT) scans in annual rounds of screening (time 1) were retrospectively identified that could, in retrospect, be identified on the previous CT scans (time 0). Four CAD systems were compared, which were referred to as CAD 1, CAD 2, CAD 3, and CAD 4. The total number of accepted CAD-system-detected nodules at time 0 was determined by consensus of two radiologists and the number of CAD-system-detected nodules that were rejected by the radiologists was also documented. Results At time 0 when all the cancers had been missed, CAD system detection rates for the cancers were 56%, 70%, 68%, and 60% (κ = 0.45) for CAD systems 1, 2, 3, and 4, respectively. At time 1, the rates were 74%, 82%, 82%, and 78% (κ = 0.32), respectively. The average diameter of the 50 cancers at time 0 and time 1 was 4.8 mm and 11.4 mm, respectively. The number of CAD-system-detected nodules that were rejected per CT scan for CAD systems 1-4 at time 0 was 7.4, 1.7, 0.6, and 4.5 respectively. Conclusion CAD systems detected up to 70% of lung cancers that were not detected by the radiologist but failed to detect about 20% of the lung cancers when they were identified by the radiologist, which suggests that CAD may be useful in the role of second reader. (©) RSNA, 2016.

Automated 3D closed surface segmentation: application to vertebral body segmentation in CT images.

PURPOSE: A fully automated segmentation algorithm, progressive surface resolution (PSR), is presented in this paper to determine the closed surface of approximately convex blob-like structures that are common in biomedical imaging. The PSR algorithm was applied to the cortical surface segmentation of 460 vertebral bodies on 46 low-dose chest CT images, which can be potentially used for automated bone mineral density measurement and compression fracture detection. METHODS: The target surface is realized by a closed triangular mesh, which thereby guarantees the enclosure. The surface vertices of the triangular mesh representation are constrained along radial trajectories that are uniformly distributed in 3D angle space. The segmentation is accomplished by determining for each radial trajectory the location of its intersection with the target surface. The surface is first initialized based on an input high confidence boundary image and then resolved progressively based on a dynamic attraction map in an order of decreasing degree of evidence regarding the target surface location. RESULTS: For the visual evaluation, the algorithm achieved acceptable segmentation for 99.35 % vertebral bodies. Quantitative evaluation was performed on 46 vertebral bodies and achieved overall mean Dice coefficient of 0.939 (with max [Formula: see text] 0.957, min [Formula: see text] 0.906 and standard deviation [Formula: see text] 0.011) using manual annotations as the ground truth. CONCLUSIONS: Both visual and quantitative evaluations demonstrate encouraging performance of the PSR algorithm. This novel surface resolution strategy provides uniform angular resolution for the segmented surface with computation complexity and runtime that are linearly constrained by the total number of vertices of the triangular mesh representation.