Search

Patients with systemic sclerosis are at high risk of developing systemic sclerosis-associated interstitial lung disease. Symptoms and outcomes of systemic sclerosis-associated interstitial lung disease range from subclinical lung involvement to respiratory failure and death. Early and accurate diagnosis of systemic sclerosis-associated interstitial lung disease is therefore important to enable appropriate intervention. The most sensitive and specific way to diagnose systemic sclerosis-associated interstitial lung disease is by high-resolution computed tomography, and experts recommend that high-resolution computed tomography should be performed in all patients with systemic sclerosis at the time of initial diagnosis. In addition to being an important screening and diagnostic tool, high-resolution computed tomography can be used to evaluate disease extent in systemic sclerosis-associated interstitial lung disease and may be helpful in assessing prognosis in some patients. Currently, there is no consensus with regards to frequency and scanning intervals in patients at risk of interstitial lung disease development and/or progression. However, expert guidance does suggest that frequency of screening using high-resolution computed tomography should be guided by risk of developing interstitial lung disease. Most experienced clinicians would not repeat high-resolution computed tomography more than once a year or every other year for the first few years unless symptoms arose. Several computed tomography techniques have been developed in recent years that are suitable for regular monitoring, including low-radiation protocols, which, together with other technologies, such as lung ultrasound and magnetic resonance imaging, may further assist in the evaluation and monitoring of patients with systemic sclerosis-associated interstitial lung disease. A video abstract to accompany this article is available at: https://www.globalmedcomms.com/respiratory/Khanna/HRCTinSScILD.

Simple Summary: Detecting lung cancer early and initiating treatment promptly can greatly enhance patient outcomes. While low-dose computed tomography (LDCT) screening aids in identifying lung cancer at an early stage, there is a risk of diagnostic delays as patients await follow-up scans. To mitigate this challenge, we developed a deep predictive model leveraging generative AI methods to forecast nodule growth patterns in follow-up LDCT scans based on baseline LDCT scans. Our findings illustrated that utilizing the predicted follow-up nodule images generated by our model during baseline screening improved diagnostic accuracy compared to using baseline nodules alone and achieved comparable performance with using real follow-up nodules. This demonstrated the potential of employing deep generative models to forecast nodule appearance in follow-up imaging from baseline LDCT scans, thereby enhancing risk assessment during initial screening. Early diagnosis of lung cancer can significantly improve patient outcomes. We developed a Growth Predictive model based on the Wasserstein Generative Adversarial Network framework (GP-WGAN) to predict the nodule growth patterns in the follow-up LDCT scans. The GP-WGAN was trained with a training set (N = 776) containing 1121 pairs of nodule images with about 1-year intervals and deployed to an independent test set of 450 nodules on baseline LDCT scans to predict nodule images (GP-nodules) in their 1-year follow-up scans. The 450 GP-nodules were finally classified as malignant or benign by a lung cancer risk prediction (LCRP) model, achieving a test AUC of 0.827 ± 0.028, which was comparable to the AUC of 0.862 ± 0.028 achieved by the same LCRP model classifying real follow-up nodule images (p = 0.071). The net reclassification index yielded consistent outcomes (NRI = 0.04; p = 0.62). Other baseline methods, including Lung-RADS and the Brock model, achieved significantly lower performance (p < 0.05). The results demonstrated that the GP-nodules predicted by our GP-WGAN model achieved comparable performance with the nodules in the real follow-up scans for lung cancer diagnosis, indicating the potential to detect lung cancer earlier when coupled with accelerated clinical management versus the current approach of waiting until the next screening exam. [ABSTRACT FROM AUTHOR]

The Quantitative Imaging Biomarker Alliance (QIBA) is a multidisciplinary consortium sponsored by the RSNA to define processes that enable the implementation and advancement of quantitative imaging methods described in a QIBA profile document that outlines the process to reliably and accurately measure imaging features. A QIBA profile includes factors such as technical (product-specific) standards, user activities, and relationship to a clinically meaningful metric, such as with nodule measurement in the course of CT screening for lung cancer. In this report, the authors describe how the QIBA approach is being applied to the measurement of small pulmonary nodules such as those found during low-dose CT-based lung cancer screening. All sources of variance with imaging measurement were defined for this process. Through a process of experimentation, literature review, and assembly of expert opinion, the strongest evidence was used to define how to best implement each step in the imaging acquisition and evaluation process. This systematic approach to implementing a quantitative imaging biomarker with standardized specifications for image acquisition and postprocessing for a specific quantitative measurement of a pulmonary nodule results in consistent performance characteristics of the measurement (eg, bias and variance). Implementation of the QIBA small nodule profile may allow more efficient and effective clinical management of the diagnostic workup of individuals found to have suspicious pulmonary nodules in the course of lung cancer screening evaluation.

The ACR recognizes that low-dose CT for lung cancer screening has the potential to significantly reduce mortality from lung cancer in the appropriate high-risk population. The ACR supports the recommendations of the US Preventive Services Task Force and the National Comprehensive Cancer Network for screening patients. To be effective, lung cancer screening should be performed at sites providing high-quality low-dose CT examinations overseen and interpreted by qualified physicians using a structured reporting and management system. The ACR has developed a set of tools necessary for radiologists to take the lead on the front lines of lung cancer screening. The ACR Lung Cancer Screening Center designation is built upon the ACR CT accreditation program and requires use of Lung-RADS or a similar structured reporting and management system. This designation provides patients and referring providers with the assurance that they will receive high-quality screening with appropriate follow-up care.

The ACR created the Lung CT Screening Reporting and Data System (Lung-RADS) in 2014 to standardize the reporting and management of screen-detected pulmonary nodules. Lung-RADS was updated to version 1.1 in 2019 and revised size thresholds for nonsolid nodules, added classification criteria for perifissural nodules, and allowed for short-interval follow-up of rapidly enlarging nodules that may be infectious in etiology. Lung-RADS v2022, released in November 2022, provides several updates including guidance on the classification and management of atypical pulmonary cysts, juxtapleural nodules, airway-centered nodules, and potentially infectious findings. This new release also provides clarification for determining nodule growth and introduces stepped management for nodules that are stable or decreasing in size. This article summarizes the current evidence and expert consensus supporting Lung-RADS v2022. [ABSTRACT FROM AUTHOR]

Lung cancer screening (LCS) with low-dose CT (LDCT) imaging was recommended in 2013, making approximately 8 million Americans eligible for LCS. The demographic characteristics and outcomes of individuals screened in the United States have not been reported at the population level. What are the outcomes among people screened and entered in the American College of Radiology's Lung Cancer Screening Registry compared with those of trial participants? This was a cohort study of individuals undergoing baseline LDCT imaging for LCS between 2015 and 2019. Predictors of adherence to annual screening were computed. LDCT scan interpretations by Lung Imaging Reporting and Data System (Lung-RADS) score, cancer detection rates (CDRs), and stage at diagnosis were compared with National Lung Cancer Screening Trial data. Adherence was 22.3%, and predictors of poor adherence included current smoking status and Hispanic or Black race. On baseline screening, 83% of patients showed negative results and 17% showed positive screening results. The overall CDR was 0.56%. The percentage of people with cancer detected at baseline was higher in the positive Lung-RADS categories at 0.4% for Lung-RADS category 3, 2.6% for Lung-RADS category 4A, 11.1% for Lung-RADS category 4B, and 19.9% for Lung-RADS category 4X. The cancer stage distribution was similar to that observed in the National Lung Cancer Screening Trial, with 53.5% of patients receiving a diagnosis of stage I cancer and 14.3% with stage IV cancer. Underreporting into the registry may have occurred. This study revealed both the positive aspects of CT scan screening for lung cancer and the challenges that remain. Findings on CT imaging were correlated accurately with lung cancer detection using the Lung-RADS system. A significant stage shift toward early-stage lung cancer was present. Adherence to LCS was poor and likely contributes to the lower than expected cancer detection rate, all of which will impact the outcomes of patients undergoing screening for lung cancer. [Display omitted] [ABSTRACT FROM AUTHOR]

Lung cancer is a leading cause of cancer death in the United States and globally with the majority of lung cancer cases attributable to cigarette smoking. Given the high societal and personal cost of a diagnosis of lung cancer including that most cases of lung cancer when diagnosed are found at a late stage, work over the past 40 years has aimed to detect lung cancer earlier when curative treatment is possible. Screening trials using chest radiography and sputum failed to show a reduction in lung cancer mortality however multiple studies using low dose CT have shown the ability to detect lung cancer early and a survival benefit to those screened. This review will discuss the history of lung cancer screening, current recommendations and screening guidelines, and implementation and components of a lung cancer screening program. [ABSTRACT FROM AUTHOR]

Background: Lung cancer screening (LCS) with low-dose computed tomography (LDCT) was recommended by the U.S. Preventive Services Task Force (USPSTF) in 2013, making approximately 8 million Americans eligible for screening. The demographic characteristics and adherence of persons screened in the United States have not been reported at the population level.Objective: To define sociodemographic characteristics and adherence among persons screened and entered into the American College of Radiology's Lung Cancer Screening Registry (LCSR).Design: Cohort study.Setting: United States, 2015 to 2019.Participants: Persons receiving a baseline LDCT for LCS from 3625 facilities reporting to the LCSR.Measurements: Age, sex, and smoking status distributions (percentages) were computed among persons who were screened and among respondents in the 2015 National Health Interview Survey (NHIS) who were eligible for screening. The prevalence between the LCSR and the NHIS was compared with prevalence ratios (PRs) and 95% CIs. Adherence to annual screening was defined as having a follow-up test within 11 to 15 months of an initial LDCT.Results: Among 1 159 092 persons who were screened, 90.8% (n = 1 052 591) met the USPSTF eligibility criteria. Compared with adults from the NHIS who met the criteria (n = 1257), screening recipients in the LCSR were older (34.7% vs. 44.8% were aged 65 to 74 years; PR, 1.29 [95% CI, 1.20 to 1.39]), more likely to be female (41.8% vs. 48.1%; PR, 1.15 [CI, 1.08 to 1.23]), and more likely to currently smoke (52.3% vs. 61.4%; PR, 1.17 [CI, 1.11 to 1.23]). Only 22.3% had a repeated annual LDCT. If follow-up was extended to 24 months and more than 24 months, 34.3% and 40.3% were adherent, respectively.Limitations: Underreporting of LCS and missing data may skew demographic characteristics of persons reported to be screened. Underreporting of adherence may result in underestimates of follow-up.Conclusion: Approximately 91% of persons who had LCS met USPSTF eligibility criteria. In addition to continuing to target all eligible adults, men, those who formerly smoked, and younger eligible patients may be less likely to be screened. Adherence to annual follow-up screening was poor, potentially limiting screening effectiveness.Primary Funding Source: None. [ABSTRACT FROM AUTHOR]

Objective: Accurate segmentation of the lung nodule in computed tomography images is a critical component of a computer‐assisted lung cancer detection/diagnosis system. However, lung nodule segmentation is a challenging task due to the heterogeneity of nodules. This study is to develop a hybrid deep learning (H‐DL) model for the segmentation of lung nodules with a wide variety of sizes, shapes, margins, and opacities. Materials and methods: A dataset collected from Lung Image Database Consortium image collection containing 847 cases with lung nodules manually annotated by at least two radiologists with nodule diameters greater than 7 mm and less than 45 mm was randomly split into 683 training/validation and 164 independent test cases. The 50% consensus consolidation of radiologists' annotation was used as the reference standard for each nodule. We designed a new H‐DL model combining two deep convolutional neural networks (DCNNs) with different structures as encoders to increase the learning capabilities for the segmentation of complex lung nodules. Leveraging the basic symmetric U‐shaped architecture of U‐Net, we redesigned two new U‐shaped deep learning (U‐DL) models that were expanded to six levels of convolutional layers. One U‐DL model used a shallow DCNN structure containing 16 convolutional layers adapted from the VGG‐19 as the encoder, and the other used a deep DCNN structure containing 200 layers adapted from DenseNet‐201 as the encoder, while the same decoder with only one convolutional layer at each level was used in both U‐DL models, and we referred to them as the shallow and deep U‐DL models. Finally, an ensemble layer was used to combine the two U‐DL models into the H‐DL model. We compared the effectiveness of the H‐DL, the shallow U‐DL and the deep U‐DL models by deploying them separately to the test set. The accuracy of volume segmentation for each nodule was evaluated by the 3D Dice coefficient and Jaccard index (JI) relative to the reference standard. For comparison, we calculated the median and minimum of the 3D Dice and JI over the individual radiologists who segmented each nodule, referred to as M‐Dice, min‐Dice, M‐JI, and min‐JI. Results: For the 164 test cases with 327 nodules, our H‐DL model achieved an average 3D Dice coefficient of 0.750 ± 0.135 and an average JI of 0.617 ± 0.159. The radiologists' average M‐Dice was 0.778 ± 0.102, and the average M‐JI was 0.651 ± 0.127; both were significantly higher than those achieved by the H‐DL model (p < 0.05). The radiologists' average min‐Dice (0.685 ± 0.139) and the average min‐JI (0.537 ± 0.153) were significantly lower than those achieved by the H‐DL model (p < 0.05). The results indicated that the H‐DL model approached the average performance of radiologists and was superior to the radiologist whose manual segmentation had the min‐Dice and min‐JI. Moreover, the average Dice and average JI achieved by the H‐DL model were significantly higher than those achieved by the individual shallow U‐DL model (Dice of 0.745 ± 0.139, JI of 0.611 ± 0.161; p < 0.05) or the individual deep U‐DL model alone (Dice of 0.739 ± 0.145, JI of 0.604 ± 0.163; p < 0.05). Conclusion: Our newly developed H‐DL model outperformed the individual shallow or deep U‐DL models. The H‐DL method combining multilevel features learned by both the shallow and deep DCNNs could achieve segmentation accuracy comparable to radiologists' segmentation for nodules with wide ranges of image characteristics. [ABSTRACT FROM AUTHOR]

Background: Although recommended lung cancer screening with low‐dose computed tomography scanning (LDCT) reduces mortality among high‐risk adults, annual screening rates remain low. This study complements a previous nationwide assessment of access to lung cancer screening within 40 miles by evaluating differences in accessibility across rural and urban settings for the population aged 50 to 80 years and a subset eligible population based on the 2021 US Preventive Services Task Force LDCT lung screening recommendations. Methods: Distances from population centers to screening facilities (American College of Radiology Lung Cancer Screening Registry) were calculated, and the number of individuals who had access within graduating distances, including 10, 20, 40, 50, and 100 miles, were estimated. Census tract results were aggregated to counties, and both geographies were classified with rural‐urban schemas. Results: Approximately 5% of the eligible population did not have access to lung cancer screening facilities within 40 miles; however, different patterns of accessibility were observed at different distances, between regions, and across rural‐urban environments. Across all distances and geographies, there was a larger percentage of the population in rural geographies with no access. Although the rural population represented approximately 8% of the eligible population, the larger percentage of the rural population with no access was noteworthy and translated into a larger number of individuals with no access at longer distance thresholds (≥40 miles). Conclusions: Disparities in access should be examined as both percentages of the population and numbers of individuals with no access in order to tailor interventions to communities and increase access. Geospatial analysis at the census tract level is recommended to help to identify optimal focus areas and reach the most people. Lay Summary: As annual lung cancer screening rates remain low, this study examines access to lung cancer screening nationwide and across rural and urban settings.A geographic information system network analysis of census tract–level populations is used to estimate access at different distances, including 10, 20, 40, 50, and 100 miles, and the results are aggregated to counties.Approximately 5% of the eligible population does not have access to screening facilities within 40 miles; however, different patterns of accessibility are observed at different distances, between regions, and across rural‐urban environments.Across all distances and geographies, there is a larger percentage of the population in rural geographies with no access. This study uses geospatial analysis to examine access to lung cancer screening at graduating distances nationwide and across rural‐urban settings. Approximately 5% of the eligible population does not have access to lung cancer screening facilities within 40 miles; however, different patterns of accessibility are observed at different distances, between regions, and across rural‐urban environments. [ABSTRACT FROM AUTHOR]

Background: Annual lung cancer screening (LCS) with low-dose chest computed tomography in older current and former smokers (ie, eligible adults) has been recommended since 2013. Uptake has been slow and variable across the United States. We estimated the LCS rate and growth at the national and state level between 2016 and 2018.Methods: The American College of Radiology's Lung Cancer Screening Registry was used to capture screening events. Population-based surveys, the US Census, and cancer registry data were used to estimate the number of eligible adults and lung cancer mortality (ie, burden). Lung cancer screening rates (SRs) in eligible adults and screening rate ratios with 95% confidence intervals (CI) were used to measure changes by state and year.Results: Nationally, the SR was steady between 2016 (3.3%, 95% CI = 3.3% to 3.7%) and 2017 (3.4%, 95% CI = 3.4% to 3.9%), increasing to 5.0% (95% CI = 5.0% to 5.7%) in 2018 (2018 vs 2016 SR ratio = 1.52, 95% CI = 1.51 to 1.62). In 2018, several southern states with a high lung-cancer burden (eg, Mississippi, West Virginia, and Arkansas) had relatively low SRs (<4%) among eligible adults, whereas several northeastern states with lower lung cancer burden (eg, Massachusetts, Vermont, and New Hampshire) had the highest SRs (12.8%-15.2%). The exception was Kentucky, which had the nation's highest lung cancer mortality rate and one of the highest SRs (13.7%).Conclusions: Fewer than 1 in 20 eligible adults received LCS nationally, and uptake varied widely across states. LCS rates were not aligned with lung cancer burden across states, except for Kentucky, which has supported comprehensive efforts to implement LCS. [ABSTRACT FROM AUTHOR]

Lung cancer screening with a low radiation dose chest CT scan is the standard of care for screening-eligible individuals. The net benefit of screening may be optimized by delivering high-quality care, capable of maximizing the benefit and minimizing the harms of screening. Valid, feasible, and relevant indicators of the quality of lung cancer screening may help programs to evaluate their current practice and to develop quality improvement plans. The purpose of this project was to develop quality indicators related to the processes and outcomes of screening. Potential quality indicators were explored through surveys of multidisciplinary lung cancer screening experts. Those that achieved predefined measures of consensus for each of the validity, feasibility, and relevance domains are proposed as quality indicators. Each of the proposed indicators is described in detail, with guidance on how to define, measure, and improve program performance within the indicator. [ABSTRACT FROM AUTHOR]

Background: Lung cancer risk prediction models do not routinely incorporate imaging metrics available on low-dose CT (LDCT) imaging of the chest ordered for lung cancer screening.Research Question: What is the association between quantitative emphysema measured on LDCT imaging and lung cancer incidence and mortality, all-cause mortality, and airflow obstruction in individuals who currently or formerly smoked and are undergoing lung cancer screening?Study Design and Methods: In 7,262 participants in the CT arm of the National Lung Screening Trial, percent low attenuation area (%LAA) was defined as the percentage of lung volume with voxels less than -950 Hounsfield units on the baseline examination. Multivariable Cox proportional hazards models, adjusting for competing risks where appropriate, were built to test for association between %LAA and lung cancer incidence, lung cancer mortality, and all-cause mortality with censoring at 6 years. In addition, multivariable logistic regression models were built to test the cross-sectional association between %LAA and airflow obstruction on spirometry, which was available in 2,700 participants.Results: The median %LAA was 0.8% (interquartile range, 0.2%-2.7%). Every 1% increase in %LAA was independently associated with higher hazards of lung cancer incidence (hazard ratio [HR], 1.02; 95% CI, 1.01-1.03; P = .004), lung cancer mortality (HR, 1.02; 95% CI, 1.00-1.05; P = .045), and all-cause mortality (HR, 1.01; 95% CI, 1.00-1.03; P = .042). Among participants with spirometry, 892 had airflow obstruction. The likelihood of airflow obstruction increased with every 1% increase in %LAA (odds ratio, 1.07; 95% CI, 1.06-1.09; P < .001). A %LAA cutoff of 1% had the best discriminative accuracy for airflow obstruction in participants aged > 65 years.Interpretation: Quantitative emphysema measured on LDCT imaging of the chest can be leveraged to improve lung cancer risk prediction and help diagnose COPD in individuals who currently or formerly smoked and are undergoing lung cancer screening. [ABSTRACT FROM AUTHOR]

Background: Screening current and former heavy smokers 55 to 80 years of age for lung cancer (LC) with low-dose chest CT scanning has been recommended by the United States Preventive Services Task Force since 2013. Although the number of screening facilities in the United States has increased, screening uptake has been slow.Research Question: To what extent is geographic access to screening facilities a barrier for screening uptake nationally?Study Design and Methods: Screening facilities were defined as American College of Radiology (ACR) Lung Cancer Screening Registry (LCSR) facilities. Analysis was performed at different geographic levels using a road network to calculate travel distances for the recommended age groups. Full access to screening was defined as the entire 55- to 79-year-old population being within 40 miles of an ACR LCSR facility. No access was defined as lack of access by the entire target population. Partial access was expressed in intervening quartiles. A geospatial approach then was used to integrate accessibility with smoking prevalence and LC mortality rates to identify potential focus areas visually.Results: Screening facilities addresses were geocoded to identify 3,592 unique locations. Analysis of census tracts and aggregation to counties revealed that among 3,142 counties, adults 55 to 79 years of age have full access to an LC screening registry facility in 1,988 (63%) counties, partial access in 587 (19%) counties, and no access in 567 (18%) counties. Overall, less than 6% of those 55 to 79 years of age do not have access to registry screening facilities. Variation in screening facility access was noted across the United States, between states, and within some states.Interpretation: It is recommended to calculate accessibility using subcounty geographies and to examine variation regionally and within states. A foundation geographic accessibility layer can be integrated with other variables to identify geographic disparities in access to screening and to focus on areas for interventions. Identifying areas of greatest need can inform state and local officials and healthcare organizations when planning and implementing LC screening programs. [ABSTRACT FROM AUTHOR]

Background: The risks from potential exposure to coronavirus disease 2019 (COVID-19), and resource reallocation that has occurred to combat the pandemic, have altered the balance of benefits and harms that informed current (pre-COVID-19) guideline recommendations for lung cancer screening and lung nodule evaluation. Consensus statements were developed to guide clinicians managing lung cancer screening programs and patients with lung nodules during the COVID-19 pandemic.Methods: An expert panel of 24 members, including pulmonologists (n = 17), thoracic radiologists (n = 5), and thoracic surgeons (n = 2), was formed. The panel was provided with an overview of current evidence, summarized by recent guidelines related to lung cancer screening and lung nodule evaluation. The panel was convened by video teleconference to discuss and then vote on statements related to 12 common clinical scenarios. A predefined threshold of 70% of panel members voting agree or strongly agree was used to determine if there was a consensus for each statement. Items that may influence decisions were listed as notes to be considered for each scenario.Results: Twelve statements related to baseline and annual lung cancer screening (n = 2), surveillance of a previously detected lung nodule (n = 5), evaluation of intermediate and high-risk lung nodules (n = 4), and management of clinical stage I non-small cell lung cancer (n = 1) were developed and modified. All 12 statements were confirmed as consensus statements according to the voting results. The consensus statements provide guidance about situations in which it was believed to be appropriate to delay screening, defer surveillance imaging of lung nodules, and minimize nonurgent interventions during the evaluation of lung nodules and stage I non-small cell lung cancer.Conclusions: There was consensus that during the COVID-19 pandemic, it is appropriate to defer enrollment in lung cancer screening and modify the evaluation of lung nodules due to the added risks from potential exposure and the need for resource reallocation. There are multiple local, regional, and patient-related factors that should be considered when applying these statements to individual patient care. [ABSTRACT FROM AUTHOR]

Lung cancer screening with low dose computed tomography (CT) is the only method ever proven to reduce lung cancer--specific mortality in high-risk current and former cigarette smokers. Radiation exposure from annual screening CT examinations and subsequent CT and nuclear medicine testing to further evaluate positive screening CTs is sometimes raised as a reason to avoid screening and is often misunderstood. With all testing, there are potential benefits and risks. As we sit on the brink of widespread adoption of lung cancer screening CT, we aim to explain why the risks associated with radiation exposure from lung cancer screening are very low and should not be used to avoid screening or dissuade individuals who qualify for screening CT to participate in a lung cancer screening program. [ABSTRACT FROM AUTHOR]

The National Lung Screening Trial (NLST) reported a 20% reduction in lung cancer specific mortality using low-dose chest CT (LDCT) compared with chest radiograph (CXR) screening. The high number of false positive screens with LDCT (around 25%) raises concerns. NLST radiologists reported LDCT screens as either positive or not positive, based primarily on the presence of a 4+ mm non-calcified lung nodule (NCN). They did not explicitly record a propensity score for lung cancer. However, by using maximum NCN size, or alternatively, radiologists’ recommendations for diagnostic follow-up categorized hierarchically, surrogate propensity scores (PSSZ and PSFR) were created. These scores were then used to compute ROC curves, which determine possible operating points of sensitivity versus false positive rate (1-Specificity). The area under the ROC curve (AUC) was 0.934 and 0.928 for PSFR and PSSZ, respectively; the former was significantly greater than the latter. With the NLST definition of a positive screen, sensitivity and specificity of LDCT was 93.1% and 76.5%, respectively. With cutoffs based on PSFR, a specificity of 92.4% could be achieved while only lowering sensitivity to 86.9%. Radiologists using LDCT have good predictive ability; the optimal operating point for sensitivity and specificity remains to be determined. [ABSTRACT FROM PUBLISHER]

The purpose of this work is to develop a computer-aided diagnosis (CAD) system to differentiate malignant and benign lung nodules on CT scans. A fully automated system was designed to segment the nodule from its surrounding structured background in a local volume of interest (VOI) and to extract image features for classification. Image segmentation was performed with a 3D active contour method. The initial contour was obtained as the boundary of a binary object generated by k-means clustering within the VOI and smoothed by morphological opening. A data set of 256 lung nodules (124 malignant and 132 benign) from 152 patients was used in this study. In addition to morphological and texture features, the authors designed new nodule surface features to characterize the lung nodule surface smoothness and shape irregularity. The effects of two demographic features, age and gender, as adjunct to the image features were also investigated. A linear discriminant analysis (LDA) classifier built with features from stepwise feature selection was trained using simplex optimization to select the most effective features. A two-loop leave-one-out resampling scheme was developed to reduce the optimistic bias in estimating the test performance of the CAD system. The area under the receiver operating characteristic curve, Az, for the test cases improved significantly (p<0.05) from 0.821±0.026 to 0.857±0.023 when the newly developed image features were included with the original morphological and texture features. A similar experiment performed on the data set restricted to primary cancers and benign nodules, excluding the metastatic cancers, also resulted in an improved test Az, though the improvement did not reach statistical significance (p=0.07). The two demographic features did not significantly affect the performance of the CAD system (p>0.05) when they were added to the feature space containing the morphological, texture, and new gradient field and radius features. To investigate if a support vector machine (SVM) classifier can achieve improved performance over the LDA classifier, we compared the performance of the LDA and SVMs with various kernels and parameters. Principal component analysis was used to reduce the dimensionality of the feature space for both the LDA and the SVM classifiers. When the number of selected principal components was varied, the highest test Az among the SVMs of various kernels and parameters was slightly higher than that of the LDA in one-loop leave-one-case-out resampling. However, no SVM with fixed architecture consistently performed better than the LDA in the range of principal components selected. This study demonstrated that the authors’ proposed segmentation and feature extraction techniques are promising for classifying lung nodules on CT images. [ABSTRACT FROM AUTHOR]

Rationale and Objectives: The Lung Image Database Consortium (LIDC) is developing a publicly available database of thoracic computed tomography (CT) scans as a medical imaging research resource to promote the development of computer-aided detection or characterization of pulmonary nodules. To obtain the best estimate of the location and spatial extent of lung nodules, expert thoracic radiologists reviewed and annotated each scan. Because a consensus panel approach was neither feasible nor desirable, a unique two-phase, multicenter data collection process was developed to allow multiple radiologists at different centers to asynchronously review and annotate each CT scan. This data collection process was also intended to capture the variability among readers.Materials and Methods: Four radiologists reviewed each scan using the following process. In the first or "blinded" phase, each radiologist reviewed the CT scan independently. In the second or "unblinded" review phase, results from all four blinded reviews were compiled and presented to each radiologist for a second review, allowing the radiologists to review their own annotations together with the annotations of the other radiologists. The results of each radiologist's unblinded review were compiled to form the final unblinded review. An XML-based message system was developed to communicate the results of each reading.Results: This two-phase data collection process was designed, tested, and implemented across the LIDC. More than 500 CT scans have been read and annotated using this method by four expert readers; these scans either are currently publicly available at http://ncia.nci.nih.gov or will be in the near future.Conclusions: A unique data collection process was developed, tested, and implemented that allowed multiple readers at distributed sites to asynchronously review CT scans multiple times. This process captured the opinions of each reader regarding the location and spatial extent of lung nodules. [ABSTRACT FROM AUTHOR]

A letter to the editor is presented discussing the cost-effectiveness of computed-tomography (CT) scanning for lung cancer.

Purpose: Develop a quantitative image analysis method to characterize the heterogeneous patterns of nodule components for the classification of pathological categories of nodules.Materials and Methods: With IRB approval and permission of the National Lung Screening Trial (NLST) project, 103 subjects with low dose CT (LDCT) were used in this study. We developed a radiomic quantitative CT attenuation distribution descriptor (qADD) to characterize the heterogeneous patterns of nodule components and a hybrid model (qADD+) that combined qADD with subject demographic data and radiologist-provided nodule descriptors to differentiate aggressive tumors from indolent tumors or benign nodules with pathological categorization as reference standard. The classification performances of qADD and qADD + were evaluated and compared to the Brock and the Mayo Clinic models by analysis of the area under the receiver operating characteristic curve (AUC).Results: The radiomic features were consistently selected into qADDs to differentiate pathological invasive nodules from (1) preinvasive nodules, (2) benign nodules, and (3) the group of preinvasive and benign nodules, achieving test AUCs of 0.847 ± 0.002, 0.842 ± 0.002 and 0.810 ± 0.001, respectively. The qADD + obtained test AUCs of 0.867 ± 0.002, 0.888 ± 0.001 and 0.852 ± 0.001, respectively, which were higher than both the Brock and the Mayo Clinic models.Conclusion: The pathologic invasiveness of lung tumors could be categorized according to the CT attenuation distribution patterns of the nodule components manifested on LDCT images, and the majority of invasive lung cancers could be identified at baseline LDCT scans. [ABSTRACT FROM AUTHOR]