Lung CT Screening Reporting Research Articles

Effectiveness of radiologist training in improving reader agreement for Lung-RADS 4X categorization.

To identify the agreement on Lung CT Screening Reporting and Data System 4X categorization between radiologists and an expert-adjudicated reference standard and to investigate whether training led to improvement of the agreement measures and diagnostic potential for lung cancer. Category 4 nodules in the Korean Lung Cancer Screening Project were identified retrospectively, and each 4X nodule was matched with one 4A or 4B nodule. An expert panel re-evaluated the categories and determined the reference standard. Nineteen radiologists were asked to determine the presence of CT features of malignancy and 4X categorization for each nodule. A review was performed in two sessions, and training material was given after session 1. Agreement on 4X categorization between radiologists and the expert-adjudicated reference standard and agreement between radiologist-assessed 4X categorization and lung cancer diagnosis were evaluated. The 48 expert-adjudicated 4X nodules and 64 non-4X nodules were evenly distributed in each session. The proportion of category 4X decreased after training (56.4% ± 16.9% vs. 33.4% ± 8.0%; p < 0.001). Cohen's κ indicated poor agreement (0.39 ± 0.16) in session 1, but agreement improved in session 2 (0.47 ± 0.09; p = 0.03). The increase in agreement in session 2 was observed among inexperienced radiologists (p < 0.05), and experienced and inexperienced reviewers exhibited comparable agreement performance in session 2 (p > 0.05). All agreement measures between radiologist-assessed 4X categorization and lung cancer diagnosis increased in session 2 (p < 0.05). Radiologist training can improve reader agreement on 4X categorization, leading to enhanced diagnostic performance for lung cancer. • Agreement on 4X categorization between radiologists and an expert-adjudicated reference standard was initially poor, but improved significantly after training. • The mean proportion of 4X categorization by 19 radiologists decreased from 56.4% ± 16.9% in session 1 to 33.4% ± 8.0% in session 2. • All agreement measures between the 4X categorization and lung cancer diagnosis increased significantly in session 2, implying that appropriate training and guidance increased the diagnostic potential of category 4X.

Interobserver variability in Lung CT Screening Reporting and Data System categorisation in subsolid nodule-enriched lung cancer screening CTs.

To assess interobserver agreement in Lung CT Screening Reporting and Data System (Lung-RADS) categorisation in subsolid nodule-enriched low-dose screening CTs. A retrospective review of low-dose screening CT reports from 2013 to 2017 using keyword searches for subsolid nodules identified 54 baseline CT scans. With an additional 108 negative screening CT scans, a total of 162 CT scans were categorised according to the Lung-RADS by two fellowship-trained thoracic radiologists in consensus. We randomly selected 20, 20, 10, and 10 scans from categories 1/2, 3, 4A, and 4B CT scans, respectively, to ensure balanced category representation. Five radiologists classified the 60 CT scans into Lung-RADS categories. The frequencies of concordance and minor and major discordance were calculated, with major discordance defined as at least 6 months of management discrepancy. We used Cohen's κ statistics to analyse reader agreement. An average of 60.3% (181 of 300) of all cases and 45.0% (90 of 200) of positive screens were correctly categorised. The minor and major discordance rates were 12.3% and 27.3% overall and 18.5% and 36.5% in positive screens, respectively. The concordance rate was significantly higher among experienced thoracic radiologists. Overall, the interobserver agreement was moderate (mean κ, 0.45; 95% confidence interval: 0.40-0.51). The proportion of part-solid risk-dominant nodules was significantly higher in cases with low rates of accurate categorisation. This retrospective study observed variable accuracy and moderate interobserver agreement in radiologist categorisation of subsolid nodules in screening CTs. This inconsistency may affect management recommendations for lung cancer screening. • Diagnostic performance for Lung-RADS categorisation is variable among radiologists with fair to moderate interobserver agreement in subsolid nodule-enriched CT scans. • Experienced thoracic radiologists showed more accurate and consistent Lung-RADS categorisation than radiology residents. • The relative abundance of part-solid nodules was a potential factor related to increased disagreement in Lung-RADS categorisation.

Comparison of Radiomic Models Based on Low-Dose and Standard-Dose CT for Prediction of Adenocarcinomas and Benign Lesions in Solid Pulmonary Nodules.

ObjectivesThis study aimed to develop radiomic models based on low-dose CT (LDCT) and standard-dose CT to distinguish adenocarcinomas from benign lesions in patients with solid solitary pulmonary nodules and compare the performance among these radiomic models and Lung CT Screening Reporting and Data System (Lung-RADS). The reproducibility of radiomic features between LDCT and standard-dose CT were also evaluated.MethodsA total of 141 consecutive pathologically confirmed solid solitary pulmonary nodules were enrolled including 50 adenocarcinomas and 48 benign nodules in primary cohort and 22 adenocarcinomas and 21 benign nodules in validation cohort. LDCT and standard-dose CT scans were conducted using same acquisition parameters and reconstruction method except for radiation dose. All nodules were automatically segmented and 104 original radiomic features were extracted. The concordance correlation coefficient was used to quantify reproducibility of radiomic features between LDCT and standard-dose CT. Radiomic features were selected to build radiomic signature, and clinical characteristics and radiomic signature were combined to develop radiomic nomogram for LDCT and standard-dose CT, respectively. The performance of radiomic models and Lung-RADS was assessed by area under curve (AUC) of receiver operating characteristic curve, sensitivity, and specificity.ResultsShape and first order features, and neighboring gray tone difference matrix features were highly reproducible between LDCT and standard-dose CT. No significant differences of AUCs were found among radiomic signature and nomogram of LDCT and standard-dose CT in both primary and validation cohort (0.915 vs. 0.919 vs. 0.898 vs. 0.909 and 0.976 vs. 0.976 vs. 0.985 vs. 0.987, respectively). These radiomic models had higher specificity than Lung-RADS (all correct P < 0.05), while there were no significant differences of sensitivity between Lung-RADS and radiomic models.ConclusionsThe diagnostic performance of LDCT-based radiomic models to differentiate adenocarcinomas from benign lesions in solid pulmonary nodules were equivalent to that of standard-dose CT. The LDCT-based radiomic model with higher specificity and lower false-positive rate than Lung-RADS might help reduce overdiagnosis and overtreatment of solid pulmonary nodules in lung cancer screening.

Development and Cost Analysis of a Lung Nodule Management Strategy Combining Artificial Intelligence and Lung-RADS for Baseline Lung Cancer Screening.

To develop a lung nodule management strategy combining the Lung CT Screening Reporting and Data System (Lung-RADS) with an artificial intelligence (AI) malignancy risk score and determine its impact on follow-up investigations and associated costs in a baseline lung cancer screening population. Secondary analysis was undertaken of a data set consisting of AI malignancy risk scores and Lung-RADS classifications from six radiologists for 192 baseline low-dose CT studies. Low-dose CT studies were weighted to model a representative cohort of 3,197 baseline screening patients. An AI risk score threshold was defined to match average sensitivity of six radiologists applying Lung-RADS. Cases initially Lung-RADS category 1 or 2 with a high AI risk score were upgraded to category 3, and cases initially category 3 or higher with a low AI risk score were downgraded to category 2. Follow-up investigations resulting from Lung-RADS and the AI-informed management strategy were determined. Investigation costs were based on the 2019 US Medicare Physician Fee Schedule. The AI-informed management strategy achieved sensitivity and specificity of 91% and 96%, respectively. Average sensitivity and specificity of six radiologists using Lung-RADS only was 91% and 66%, respectively. Using the AI-informed management strategy, 41 (0.2%) category 1 or 2 classifications were upgraded to category 3, and 5,750 (30%) category 3 or higher classifications were downgraded to category 2. Minimum net cost savings using the AI-informed management strategy was estimated to be $72 per patient screened. Using an AI risk score combined with Lung-RADS at baseline lung cancer screening may result in fewer follow-up investigations and substantial cost savings.

External validation and comparison of the Brock model and Lung-RADS for the baseline lung cancer CT screening using data from the Korean Lung Cancer Screening Project.

To validate and compare the performance of the Brock model and Lung CT Screening Reporting and Data System (Lung-RADS) on nodules detected by baseline CT screening. We performed a secondary analysis of the Korean Lung Cancer Screening Project (K-LUCAS; ClinicalTrials.gov , NCT03394703), a nationwide, multicenter, prospective cohort study. From April 2017 to December 2018, low-dose CT screening was performed on high-risk subjects. Discrimination and calibration of Brock models 2a and 2b (i.e., full model without and with spiculation, respectively) were assessed, and discrimination was compared with that of Lung-RADS, which utilized subjective assessment categories 2b (b stands for benign) and 4X. Of the 13,150 subjects, 4578 were eligible (median age 62 years; 4458 men; 9929 nodules including 40 lung cancers). Areas under the receiver operating characteristic curve were 0.96 (IQR 0.92-0.99) for Brock model 2a, 0.96 (IQR 0.92-0.99) for Brock model 2b, and 0.95 (IQR 0.91-0.99) for Lung-RADS (p = 0.32 and p = 0.34, respectively). At an equivalent cutoff of 5%, Brock model 2b (sensitivity 87.5% [35/40]; specificity 93.6% [9259/9889]; positive predictive value [PPV] 5.3% [35/665]; negative predictive value [NPV] 99.9% [9259/9264]) and Lung-RADS (sensitivity 87.5% [35/40]; specificity 93.3% [9222/9889]; PPV 5.0% [35/702]; NPV 99.9% [9222/9227]) performed similarly well (all p > 0.05). The calibration performance of both Brock models 2a and 2b was poor (both p < 0.001). Lung-RADS, when reinforced with visual assessment-based categories, has a similar diagnostic performance to the Brock model for baseline CT scans. • Brock model 2b and Lung CT Screening Reporting and Data System (Lung-RADS) demonstrated a similar discrimination performance for lung cancer in the baseline CT screening (areas under the receiver operating characteristic curve 0.96 vs. 0.95; p = 0.34). • When visual assessment-based categories were removed from Lung-RADS, specificity and positive predictive value were lower than those of Brock model 2b (p = 0.001 and p = 0.02, respectively). • The Brock model showed poor calibration (p < 0.001).

Guidelines for the Evaluation of Pulmonary Nodules Detected Incidentally or by Screening: A Survey of Radiologist Awareness, Agreement, and Adherence From the Watch the Spot Trial.

The aim of this study was to examine radiologists' beliefs about existing guidelines for pulmonary nodule evaluation. A self-administered survey was developed to ascertain awareness of, agreement with, and adherence to published guidelines, including those from the Fleischner Society and the Lung CT Screening Reporting and Data System (Lung-RADS™). Surveys were distributed to 514 radiologists at 13 health care systems that are participating in a large, pragmatic trial of pulmonary nodule evaluation. Prespecified comparisons were made among groups defined by type of health system, years of experience, reader volume, and study arm. The response rate was 26.3%. Respondents were most familiar with guidelines from Fleischner (94%) and Lung-RADS (71%). For both incidental and screening-detected nodules, self-reported adherence to preferred guidelines was very high (97% and 94%, respectively), and most respondents believed that the benefits of adherence outweigh the harms (81% and 74%, respectively). Underlying evidence was thought to be high in quality by 68% of respondents for screening-detected nodules and 41% for incidental nodules. Approximately 70% of respondents believed that the frequency of recommended follow-up was "just right" for both guidelines. Radiologists who practice in nonintegrated health care systems were more likely to believe that the evidence was high in quality (79.5% versus 57.1%) and that the benefits of adherence outweigh the harms (85.1% versus 67.5%). Low-volume readers had lower awareness and self-reported adherence than higher volume readers. Radiologists reported high levels of familiarity and agreement with and adherence to guidelines for pulmonary nodule evaluation, but many overestimated the quality of evidence in support of the recommendations.

Implications of the updated Lung CT Screening Reporting and Data System (Lung-RADS version 1.1) for lung cancer screening.

Lung cancer remains the leading cause of cancer death in the United States. Screening with low-dose computed tomography (LDCT) has been proven to aid in early detection of lung cancer and reduce disease specific mortality. In 2014, the American College of Radiology (ACR) released version 1.0 of the Lung CT Screening Reporting and Data System (Lung-RADS) as a quality tool to standardize the reporting of lung cancer screening LDCT. In 2019, 5 years after the implementation of Lung-RADS version 1.0 the ACR released the updated Lung-RADS version 1.1 which incorporates initial experience with lung cancer screening. In this review, we outline the implications of the changes and additions in Lung-RADS version 1.1 and examine relevant literature for many of the updates. We also highlight several challenges and opportunities as Lung-RADS version 1.1 is implemented in lung cancer screening programs.

Operational Challenges of a Low-Dose CT Lung Cancer Screening Program During the Coronavirus Disease 2019 Pandemic

Operational Challenges of a Low-Dose CT Lung Cancer Screening Program During the Coronavirus Disease 2019 Pandemic

Improved Interobserver Agreement on Lung-RADS Classification of Solid Nodules Using Semiautomated CT Volumetry.

Background Classification of lung cancer screening CT scans depends on measurement of lung nodule size. Information about interobserver agreement is limited. Purpose To assess interobserver agreement in the measurements and American College of Radiology Lung CT Screening Reporting and Data System (Lung-RADS) classifications of solid lung nodules detected at lung cancer screening using manual measurements of average diameter and computer-aided semiautomated measurements of average diameter and volume (CT volumetry). Materials and Methods Two radiologists and one radiology resident retrospectively measured lung nodules from screening CT scans obtained between September 2016 and June 2018 with a Lung-RADS (version 1.0) classification of 2, 3, 4A, or 4B in the clinical setting. Average manual diameter and semiautomated computer-aided diameter and volume measurements were converted to the corresponding Lung-RADS categories. Interobserver agreement in raw measurements was assessed using intraclass correlation and Bland-Altman indexes, and interobserver agreement in Lung-RADS classification was assessed using bi-rater κ. Results One hundred twenty patients (mean age, 63 years ± 6 [standard deviation]; 67 women) were evaluated. All manual, semiautomated diameter, and semiautomated volume measurements were obtained by all three readers in 120 of 147 nodules (82%). Intraclass correlation coefficients were greater than or equal to 0.95 for all reader pairs using all measurement methods and were highest using volumetry. Bias and 95% limits of agreement for average diameter were smaller with semiautomated measurements than with manual measurements. κ values across all Lung-RADS classifications were greater than or equal to 0.81, with the lowest being for manual measurements and the highest being for volumetric measurements. Forty-three of 120 (36%) of the nodules were classified into a lower Lung-RADS category on the basis of volumetry compared with using manual diameter measurements by at least one reader, whereas the reverse occurred for four of 120 (3%) of the nodules. Conclusion Interobserver agreement was high with manual diameter measurements and increased with semiautomated CT volumetric measurements. Semiautomated CT volumetry enabled classification of more nodules into lower Lung CT Screening Reporting and Data System categories than manual or semiautomated diameter measurements. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Nishino in this issue.

Surgery and invasive diagnostic procedures for benign disease are rare in a large low-dose computed tomography lung cancer screening program

ObjectiveLung cancer screening with low-dose chest computed tomography improves survival. However, concerns about overdiagnosis and unnecessary interventions persist. We reviewed our lung cancer screening program to determine the rate of surgery and invasive procedures for nonmalignant disease. MethodsWe reviewed all patients undergoing lung cancer screening from January 2012 to June 2017 with follow-up through January 2019. Patients with suspicious findings (Lung CT Screening Reporting and Data System 4) were referred for further evaluation. ResultsOf 3280 patients screened, 345 (10.5%) had Lung CT Screening Reporting and Data System 4 findings. A total of 311 patients had complete follow-up, of whom 93 (29.9%) were diagnosed with lung cancer. Eighty-three patients underwent lung surgery (2.5% of screened patients). Forty patients underwent lobectomy (48.2%), 3 patients (3.6%) underwent bilobectomy, and 40 patients (48.2%) underwent sublobar resection. Fourteen patients underwent surgery for benign disease (0.43% of screened patients). Fifty-four patients, 5 with benign disease, had at least 1 invasive diagnostic procedure but never underwent surgery. The incidence of any invasive intervention for nonmalignant disease was 0.95% (31/3280 patients). There were no postprocedural deaths within 60 days. Twenty-five patients (0.76%) underwent stereotactic body radiation therapy; 19 patients (76%) had presumed lung cancer without pretreatment pathologic confirmation. ConclusionsSurgical resection for benign disease occurred in 0.43% of patients undergoing lung cancer screening. The combined incidence of any invasive diagnostic or therapeutic intervention, including surgical resection, for benign disease was only 0.95%. Periprocedural complications were rare. These results indicate that concern over unnecessary interventions is overstated and should not hinder adoption of lung cancer screening. A multidisciplinary team approach, including thoracic surgeons, is critical to maintain an appropriate rate of interventions in lung cancer screening.

Rates of positive lung cancer screening examinations in academic versus community practice.

The benefits and harms of lung cancer screening reported in the National Lung Screening Trial (NLST) likely differ from those observed in academic and community settings. High rates of positive screening findings in the NLST led to the development of the Lung CT Screening Reporting and Data System (Lung-RADS) to standardize interpretation and reporting. We conducted a prospective observational study of lung cancer screening data from four lung cancer screening sites in North Carolina to compare prospective use of Lung-RADS in a real-world screened population versus Lung-RADS retrospectively applied to the NLST, and to determine if Lung-RADS assessment use differs in academic versus community settings. We included 4,037 screening examinations from 11/2014 to 12/2018 in academic and community sites and 75,126 NLST LDCT screening exams. On baseline screening exams, the proportion of positive LDCT exams was higher in community versus academic sites or the NLST (17.7% vs. 11.4% and 13.6%, P value <0.01). On subsequent screens, the proportion of positive exams was lowest in the NLST and higher in community and academic sites (5.9% vs. 12.7% and 11.6%, P value <0.01). After adjusting for age, race, sex, and smoking status, patients screened at academic versus community sites were 34% less likely to have a positive screen at baseline [adjusted odds ratio (aOR) =0.66; 95% confidence interval (95% CI): 0.51–0.86] but on subsequent examinations, there was no difference in academic versus community sites (aOR =0.91; 95% CI: 0.58–1.43). Our findings may be due to differences in radiologists’ training or experiences or the availability of prior images for comparison.

Discrimination between transient and persistent subsolid pulmonary nodules on baseline CT using deep transfer learning

To develop and validate a deep learning model to discriminate transient from persistent subsolid nodules (SSNs) on baseline CT. A cohort of 1414 SSNs, consisting of 319 transient SSNs in 168 individuals and 1095 persistent SSNs in 816 individuals, were identified on chest CT. The cohort was assigned by examination date into a development set of 996 SSNs, a tuning set of 212 SSNs, and a validation set of 206 SSNs. Our model was built by transfer learning, which was transferred from a well-performed deep learning model for pulmonary nodule classification. The performance of the model was compared with that of two experienced radiologists. Each nodule was categorized by Lung CT Screening Reporting and Data System (Lung-RADS) to further evaluate the performance and the potential clinical benefit of the model. Two methods were employed to visualize the learned features. Our model achieved an AUC of 0.926 on the validation set with an accuracy of 0.859, a sensitivity of 0.863, and a specificity of 0.858, and outperformed the radiologists. The model performed the best among Lung-RADS 2 nodules and maintained well performance among Lung-RADS 4 nodules. Feature visualization demonstrated the model's effectiveness in extracting features from images. The transfer learning model presented good performance on the discrimination between transient and persistent SSNs. A reliable diagnosis on nodule persistence can be achieved at baseline CT; thus, an early diagnosis as well as better patient care is available. • Deep learning can be used for the discrimination between transient and persistent subsolid nodules. • A transfer learning model can achieve good performance when it is transferred from a model with a similar task. • With the assistance of deep learning model, a reliable diagnosis on nodule persistence can be achieved at baseline CT, which can bring a better patient care strategy.

Retrospective assessment of Lung-RADS® performance in the Silesian Lung Cancer Screening Pilot Study

Background. A high percentage of false positive results, observed in lung cancer screening studies with low-dose computed tomography (LDCT), caused the modification of radiological assessment methods. According to the International Early Lung Cancer Action Program (IELCAP) all non-calcified nodules with a dimension ≥ 4 mm were considered as positive. Implementation of classification the Lung CT screening Reporting and Data System (Lung-RADS®) recommends additional testing only for nodules ≥ 6 mm, which reduced of false positive results. Methods. We provided a retrospective analysis of 601 LDCT scans, in asymptomatic volunteers of Pilot Silesian Study of Early Lung Cancer Detection, with at least 20 pack-years of cigarette smoking. The analysis of non- and invasive interventions was done. Assessment of nodules according to the Lung-RADS® system was done. Then the percentage of interventions that could be avoided using the Lung-RADS® criteria was estimated. Results. In total, 1016 nodules were identified in 265 participants. The positive result of screening was defined as a presence of solid or part-solid nodule ≥ 5 mm and ≥ 8 mm in the case of a nonsolid nodule in line with the IELCAP protocol. Screening based on the IELCAP protocol resulted in 200 positive results and based on Lung-RADS® in the 116 positives. The frequency of lung cancers among participants with a positive result was 7 of 200 (4.0%) (95% CI: 1.0%, 6.0%) for IELCAP and 7 of 116 (6.0%) (95% CI: 2.7%, 9.3%) for Lung-RADS®. The Lung-RADS® criteria reduced number of non- and invasive procedures by 48.8% and 24.1%, compared to IELCAP protocol. Conclusions. Adopting the Lung-RADS® classification system may reduce harms and improve the efficiency of lung cancer screening programs.

Lung Cancer CT Screening and Lung-RADS in a Tuberculosis-endemic Country: The Korean Lung Cancer Screening Project (K-LUCAS)

Background Low-dose CT screening for lung cancer in a tuberculosis-endemic country may be less effective because of false-positive results caused by tuberculosis sequelae. Purpose To evaluate the impact of tuberculosis sequelae at CT screening according to the American College of Radiology Lung CT Screening Reporting and Data System (Lung-RADS) using data from the Korean Lung Cancer Screening Project (K-LUCAS). Materials and Methods This is a secondary analysis of K-LUCAS (ClinicalTrials.gov identifier NCT03394703), a nationwide Asian population-based, multicenter, prospective cohort study. Participants at high risk for lung cancer were enrolled between April 2017 and December 2018. Associations of tuberculosis sequelae with a positive screening result for lung cancer (defined as Lung-RADS categories 3 or 4) and diagnosis of lung cancer were analyzed with multivariable logistic regression. The diagnostic performance of Lung-RADS in predicting lung cancer was compared between participants with and participants without tuberculosis sequelae by using the χ2 test. Results A total of 11 394 participants (median age, 62 years; interquartile range, 58-67 years; 11 098 men) were evaluated. Positive screening results were found in 1868 of the 11 394 participants (16%); lung cancer was diagnosed in 65 of the 11 394 participants (0.6%). Tuberculosis sequelae were identified in 1509 of the 11 394 participants (13%) on the basis of CT scans. Tuberculosis sequelae were associated with positive CT screening results (odds ratio [OR] with one nodule, 1.22; 95% confidence interval [CI]: 1.02, 1.45; P = .03), but no evidence was found of an association with lung cancer (OR, 0.9; 95% CI: 0.4, 1.6; P = .64). Specificity of Lung-RADS was higher for participants without tuberculosis sequelae (85% [8327 of 9829 participants]; 95% CI: 84.0%, 85.4%) than for those with tuberculosis sequelae (80% [1198 of 1500 participants]; 95% CI: 77.7%, 82%; P < .001). Sensitivity was not different between participants with tuberculosis sequelae (100% [nine of nine participants]; 95% CI: 62.9%, 100%) and those without tuberculosis sequelae (98% [55 of 56 participants]; 95% CI: 89.2%, 99.9%; P > .99). Conclusion In an at-risk population, tuberculosis sequelae resulted in a reduced specificity of CT screening for lung cancer using the Lung CT Screening Reporting and Data System. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Ketai in this issue.

Lung Cancer Screening at a Military Treatment Facility: A Retrospective Review.

Lung cancer is the leading cause of cancer death among men and women, accounting for more fatalities than colon, breast, and prostate cancers combined. Smoking causes about 85% of all lung cancers in the United States and is the single greatest risk factor. In 2013, the US Preventive Services Task Force (USPSTF) published initial guidelines for low-dose computed tomography lung cancer screening (LCS) among patients 55-80years old, with a 30-pack-year history, who are current smokers or who quit within the previous 15years. Smoking prevalence is higher among military personnel compared to the civilian population, demonstrating a need for vigilant screening. A retrospective review of Naval Medical Center San Diego's (NMCSD) LCS data was conducted to examine screening numbers, lung cancer rates, and initial analysis of screening results. Patients were referred for screening if they met the USPSTF criteria. Between September 2013 and September 2018, 962 patients underwent LCS. A total of 1758 examinations were performed, including follow-up and annual surveillance examinations. The American College of Radiology's Lung CT Screening Reporting and Data System (Lung-RADS) was used to classify lung nodules' risk for malignancy. On this initial analysis, 42 enrolled patients received the diagnosis of lung cancer detected by screening. The initial calculated lung cancer rate is 4.4% (42/962) over the 5-year reporting period. The lung cancer rate among those patients with a Lung-RADS score of 3 or 4 was 31% (42/135). Thirty-seven patients were classified as having non-small cell lung cancer (NSCLC), while five were classified as having small cell lung cancer. Of the 37 NSCLC patients, 76% (28/37) were diagnosed at stage I and II, 11% (4/37) were diagnosed at stage III, and 13% (5/37) were diagnosed at stage IV. The total number of years a person smoked was a significant risk factor (P=0.004), but not pack-years a person smoked (P=0.052). These preliminary results demonstrate the success of a Military Treatment Facility (MTF)-based LCS Program in the detection of early stage lung cancer. Earlier stage detection may result in better health outcomes for affected patients. In the population studied, duration of smoking proved to be more significant than pack-years in predicting lung cancer risk. These results validate the newly dedicated resources and continued efforts to strengthen the LCS program at NMCSD and across MTFs.

Lung cancer screening in Appalachian Kentucky: The impact of Lung-RADS on subsequent testing and cancer identification.

The National Lung Cancer Screening Trial (NLST) demonstrated the use of low dose helical computed tomography (LDCT) scans for lung cancer screening. However, the NLST was implemented in urban hospitals and prior to the Lung CT Screening Reporting and Data System (Lung-RADS). In this retrospective cohort study, 774 eligible patients received LDCT screening using Lung-RADS criteria. Eighty-four patients (10.9%) had subsequent testing performed compared to 24.2% in the NLST study. Of those with subsequent testing, 21.4% were diagnosed with lung cancer compared to only 4.6% in the NLST study. Lung-RADS significantly reduced unnecessary testing while identifying higher rates of lung cancer compared to the NLST.

Influence of lung nodule margin on volume- and diameter-based reader variability in CT lung cancer screening.

To evaluate the influence of nodule margin on inter- and intrareader variability in manual diameter measurements and semi-automatic volume measurements of solid nodules detected in low-dose CT lung cancer screening. 25 nodules of each morphological category (smooth, lobulated, spiculated and irregular) were randomly selected from 93 participants of the Dutch-Belgian Randomized Lung Cancer Screening Trial (NELSON). Semi-automatic volume measurements were performed using Syngo LungCARE® software (Version Somaris/5 VB10A-W, Siemens, Forchheim, Germany). Three radiologists independently measured mean diameters manually. Impact of nodule margin on interreader variability was evaluated based on systematic error and 95% limits of agreement. Interreader variability was compared with the nodule growth cut-off as used in Lung CT Screening Reporting and Data System (LungRADS; +1.5-mm diameter) and the Dutch-Belgian Randomized Lung Cancer Screening Trial(acronym: NELSON) /British Thoracic Society (+25% volume). For manual diameter measurements, a significant systematic error (up to 1.2 mm) between readers was found in all morphological categories. For semi-automatic volume measurements, no statistically significant systematic error was found. The interreader variability in mean diameter measurements exceeded the 1.5-mm cut-off for nodule growth for all morphological categories [smooth: ±1.9 mm (+27%), lobulated: ±2.0 mm (+33%), spiculated: ±3.5 mm (+133%), irregular: ±4.5 mm (+200%)]. The 25% vol growth cut-off was exceeded slightly for spiculated [28% (+12%)] and irregular [27% (+8%)] nodules. Lung nodule sizing based on manual diameter measurement is affected by nodule margin. Interreader variability increases especially for nodules with spiculated and irregular margins, and causes substantial misclassification of nodule growth. This effect is almost neglectable for semi-automated volume measurements. Semi-automatic volume measurements are superior for both size and growth determination of pulmonary nodules. Nodule assessment based on manual diameter measurements is susceptible to nodule margin. This effect is almost neglectable for semi-automated volume measurements. The larger interreader variability for manual diameter measurement results in inaccurate lung nodule growth detection and size classification.

Effectiveness of Lung-RADS in Reducing False-Positive Results in a Diverse, Underserved, Urban Lung Cancer Screening Cohort

PurposeThe Lung CT Screening Reporting and Data SystemTM (Lung-RADSTM) was created to standardize lung cancer screening CT reporting and recommendations but has not been well validated prospectively in clinical practice. The aim of this study was to determine the effectiveness of lung cancer screening using Lung-RADS in a diverse, underserved, academic clinical screening program, focusing on whether Lung-RADS would successfully reduce the 23.3% false-positive rate found in the National Lung Screening Trial. MethodsInstitutional review board approval was obtained to study the clinical lung cancer screening cohort. Low-dose CT results were prospectively assigned a Lung-RADS or equivalent score. The proportion of examinations in each Lung-RADS category and the corresponding lung cancer rate, subsequent imaging, interventions, mortality, and compliance were tracked. The National Death Index was queried for follow-up losses. ResultsThe cohort comprised 1,181 patients with 2,270 person-years of follow-up from December 2012 to December 2016. The mean age was 64 ± 16.2 years, with 51% women, 63% nonwhite, 71% current smokers, 69% overweight and obese, and multiple comorbidities. The Lung-RADS false-positive rate was 10.4% (95% confidence interval, 8.8%-12.3%). Baseline CT results were negative in 87% (n = 1,031): for Lung-RADS 1, the lung cancer rate was 0.2%, and for Lung-RADS 2, the cancer rate was 0.5%. Positive baseline examinations were Lung-RADS 3 in 10% (n = 119), 4a in 1.2% (n = 14), and 4b in 1.5% (n = 18). Corresponding cancer rates were 3.4%, 43%, and 83%, respectively. Lung cancer prevalence was 2.1%. Mortality was 40% in patients with lung cancer versus 2.5% in the remaining cohort (P < .001). Fifty-four percent of patients were overdue for first annual examinations. Eighty-four percent of patients (n = 989) had follow-up verified via electronic records or personal contact, and the remainder had vital status ascertained via the National Death Index. ConclusionsLung cancer screening using Lung-RADS was effective in reducing the false-positive rate compared with the National Lung Screening Trial in a diverse and underserved urban population.

Detection of Subsolid Nodules in Lung Cancer Screening

The aim of this study was to compare computer-aided diagnosis (CAD) and visual reading for the detection of subsolid nodules (SSNs) in volumetrl measuremic low-dose computed tomography (LDCT) for lung cancer screening. Prospective visual detection (VD) and manuaent of SSN were performed in the 2303 baseline volumetric LDCTs of the Multicenter Italian Lung Detection trial. Baseline and 2- and 4-year LDCTs underwent retrospective CAD analysis, subsequently reviewed by 2 experienced thoracic radiologists. The reference standard was defined by the cumulative number of SSNs detected by any reading method between VD and CAD. The number of false-positive CAD marks per scan (FP/scan) was calculated. The positive predictive value of CAD was quantified per nodule (PPV) and per screenee (PPV). The sensitivity and negative predictive value were compared between CAD and VD. The longitudinal 3-time-point sensitivity of CAD was calculated in the subgroup of persistent SSNs seen by VD (ratio between the prevalent SSNs detected by CAD through 3 time points and the total number of persistent prevalent SSNs detected by VD) to test the sensitivity of iterated CAD analysis during a screening program. Semiautomatic characteristics (diameter, volume, and mass; both for whole nodule and solid component) were compared between SSN detected CAD-only or VD-only to investigate whether either reading method could suffer from specific sensitivity weakness related to SSN features. Semiautomatic and manual diameters were compared using Spearman ρ correlation and Bland-Altman plot. Computer-aided diagnosis and VD detected a total of 194 SSNs in 6.7% (155/2,303) of screenees at baseline LDCT. The CAD showed mean FP/scan of 0.26 (604/2,303); PPV 22.5% (175/779) for any SSN, with 54.4% (37/68) for PSN and 19.4% for NSN (138/711; P < 0.001); PPV 25.6% (137/536). The sensitivity of CAD was superior to that of VD (88.4% and 34.2%, P < 0.001), as well as negative predictive value (99.2% and 95.5%, P < 0.001). The longitudinal 3-time-point sensitivity of CAD was 87.5% (42/48). There was no influence of semiautomatic characteristics on the performance of either reading method. The diameter of the solid component in PSN was larger by CAD compared with manual measurement. At baseline, CAD detected 3 of 4 SSNs, which were first overlooked by VD and subsequently evolved to lung cancer. Computer-aided diagnosis and VD as concurrent reading methods showed complementary performance, with CAD having a higher sensitivity, especially for PSN, but requiring visual confirmation to reduce false-positive calls. Computer-aided diagnosis and VD should be jointly used for LDCT reading to reduce false-negatives of either lone method. The semiautomatic measurement of solid core showed systematic shift toward a larger diameter, potentially resulting in an up-shift within Lung CT Screening Reporting and Data System classification.

Radiomics analysis of pulmonary nodules in low-dose CT for early detection of lung cancer.

To develop a radiomics prediction model to improve pulmonary nodule (PN) classification in low-dose CT. To compare the model with the American College of Radiology (ACR) Lung CT Screening Reporting and Data System (Lung-RADS) for early detection of lung cancer. We examined a set of 72 PNs (31 benign and 41 malignant) from the Lung Image Database Consortium image collection (LIDC-IDRI). One hundred three CT radiomic features were extracted from each PN. Before the model building process, distinctive features were identified using a hierarchical clustering method. We then constructed a prediction model by using a support vector machine (SVM) classifier coupled with a least absolute shrinkage and selection operator (LASSO). A tenfold cross-validation (CV) was repeated ten times (10 × 10-fold CV) to evaluate the accuracy of the SVM-LASSO model. Finally, the best model from the 10 × 10-fold CV was further evaluated using 20 × 5- and 50 × 2-fold CVs. The best SVM-LASSO model consisted of only two features: the bounding box anterior-posterior dimension (BB_AP) and the standard deviation of inverse difference moment (SD_IDM). The BB_AP measured the extension of a PN in the anterior-posterior direction and was highly correlated (r = 0.94) with the PN size. The SD_IDM was a texture feature that measured the directional variation of the local homogeneity feature IDM. Univariate analysis showed that both features were statistically significant and discriminative (P = 0.00013 and 0.000038, respectively). PNs with larger BB_AP or smaller SD_IDM were more likely malignant. The 10 × 10-fold CV of the best SVM model using the two features achieved an accuracy of 84.6% and 0.89 AUC. By comparison, Lung-RADS achieved an accuracy of 72.2% and 0.77 AUC using four features (size, type, calcification, and spiculation). The prediction improvement of SVM-LASSO comparing to Lung-RADS was statistically significant (McNemar's test P = 0.026). Lung-RADS misclassified 19 cases because it was mainly based on PN size, whereas the SVM-LASSO model correctly classified 10 of these cases by combining a size (BB_AP) feature and a texture (SD_IDM) feature. The performance of the SVM-LASSO model was stable when leaving more patients out with five- and twofold CVs (accuracy 84.1% and 81.6%, respectively). We developed an SVM-LASSO model to predict malignancy of PNs with two CT radiomic features. We demonstrated that the model achieved an accuracy of 84.6%, which was 12.4% higher than Lung-RADS.