Dutch-Belgian Randomized Lung Cancer Screening Research Articles

Explainable machine learning model based on clinical factors for predicting the disappearance of indeterminate pulmonary nodules

BackgroundDuring lung cancer screening, indeterminate pulmonary nodules (IPNs) are a frequent finding. We aim to predict whether IPNs are resolving or non-resolving to reduce follow-up examinations, using machine learning (ML) models. We incorporated dedicated techniques to enhance prediction explainability. MethodsIn total, 724 IPNs (size 50–500 mm3, 575 participants) from the Dutch-Belgian Randomized Lung Cancer Screening Trial were used. We implemented six ML models and 14 factors to predict nodule disappearance. Random search was applied to determine the optimal hyperparameters on the training set (579 nodules). ML models were trained using 5-fold cross-validation and tested on the test set (145 nodules). Model predictions were evaluated by utilizing the recall, precision, F1 score, and the area under the receiver operating characteristic curve (AUC). The best-performing model was used for three feature importance techniques: mean decrease in impurity (MDI), permutation feature importance (PFI), and SHAPley Additive exPlanations (SHAP). ResultsThe random forest model outperformed the other ML models with an AUC of 0.865. This model achieved a recall of 0.646, a precision of 0.816, and an F1 score of 0.721. The evaluation of feature importance achieved consistent ranking across all three methods for the most crucial factors. The MDI, PFI, and SHAP methods highlighted volume, maximum diameter, and minimum diameter as the top three factors. However, the remaining factors revealed discrepant ranking across methods. ConclusionML models effectively predict IPN disappearance using participant demographics and nodule characteristics. Explainable techniques can assist clinicians in developing understandable preliminary assessments.

Why is the screening rate in lung cancer still low? A seven-country analysis of the factors affecting adoption.

Strong evidence of lung cancer screening's effectiveness in mortality reduction, as demonstrated in the National Lung Screening Trial (NLST) in the US and the Dutch-Belgian Randomized Lung Cancer Screening Trial (NELSON), has prompted countries to implement formal lung cancer screening programs. However, adoption rates remain largely low. This study aims to understand how lung cancer screening programs are currently performing. It also identifies the barriers and enablers contributing to adoption of lung cancer screening across 10 case study countries: Canada, China, Croatia, Japan, Poland, South Korea and the United States. Adoption rates vary significantly across studied countries. We find five main factors impacting adoption: (1) political prioritization of lung cancer (2) financial incentives/cost sharing and hidden ancillary costs (3) infrastructure to support provision of screening services (4) awareness around lung cancer screening and risk factors and (5) cultural views and stigma around lung cancer. Although these factors have application across the countries, the weighting of each factor on driving or hindering adoption varies by country. The five areas set out by this research should be factored into policy making and implementation to maximize effectiveness and outreach of lung cancer screening programs.

Preparing CT imaging datasets for deep learning in lung nodule analysis: Insights from four well-known datasets

Background: Deep learning is an important means to realize the automatic detection, segmentation, and classification of pulmonary nodules in computed tomography (CT) images. An entire CT scan cannot directly be used by deep learning models due to image size, image format, image dimensionality, and other factors. Between the acquisition of the CT scan and feeding the data into the deep learning model, there are several steps including data use permission, data access and download, data annotation, and data preprocessing. This paper aims to recommend a complete and detailed guide for researchers who want to engage in interdisciplinary lung nodule research of CT images and Artificial Intelligence (AI) engineering.Methods: The data preparation pipeline used the following four popular large-scale datasets: LIDC-IDRI (Lung Image Database Consortium image collection), LUNA16 (Lung Nodule Analysis 2016), NLST (National Lung Screening Trial) and NELSON (The Dutch-Belgian Randomized Lung Cancer Screening Trial). The dataset preparation is presented in chronological order.Findings: The different data preparation steps before deep learning were identified. These include both more generic steps and steps dedicated to lung nodule research. For each of these steps, the required process, necessity, and example code or tools for actual implementation are provided.Discussion and conclusion: Depending on the specific research question, researchers should be aware of the various preparation steps required and carefully select datasets, data annotation methods, and image preprocessing methods. Moreover, it is vital to acknowledge that each auxiliary tool or code has its specific scope of use and limitations. This paper proposes a standardized data preparation process while clearly demonstrating the principles and sequence of different steps. A data preparation pipeline can be quickly realized by following these proposed steps and implementing the suggested example codes and tools.

Volumetry versus linear diameter lung nodule measurement: an ultra-low-dose computed tomography lung cancer screening study

BACKGROUND: The DutchBelgian Randomized Lung Cancer Screening Trial (NELSON) used a volume-based protocol and significantly reduced the prevalence of false-positive results (2.1%).
 AIM: To compare the performance of manual linear diameter and semi-automated volumetric nodule measurement in the pilot project Moscow Lung Cancer Screening ultra-low-dose computed tomography pilot study.
 MATERIALS AND METHODS: The study included individuals with a lung nodule of at least 4 mm on baseline-computed tomography of the Moscow lung cancer screening between February 2017 and February 2018, without verified lung cancer diagnosis until 2020. The radiation dose was selected individually and did not exceed 1 mSv. All scans were assessed by three blinded readers to measure the maximum and minimum transversal nodule diameter and extrapolated volume. As a reference value of size and volume, the average value from the results of expert measurements was obtained. A false-positive nodule was defined as a nodule 6 mm/100 mm3 and a false-negative nodule as a nodule 6 mm/100 mm3.
 RESULTS: Overall, 293 patients were included (166 men; mean age, 64.6 5.3years); 199 lung nodules were 6 mm/100 mm3 and 94 were 6 mm/100 mm3. Regarding volumetric measurements, 32 [10.9%; 4 false-positive, 28 false-negative], 29 [9.9%; 17 false-positive, 12 false-negative], and 30 [10.2%; 6 false-positive, 24 false-negative] nodule discrepancies were reported by readers 1, 2, and 3 respectively. For linear diameter measurement, 92 [65.5%; 107 false-positive, 85 false-negative], 146 [49.8%; 58 false-positive, 88 false-negative], and 102 [34.8%; 23 false-positive, 79 false-negative] nodule discrepancies were reported by readers 1, 2, and 3 respectively.
 CONCLUSIONS: The use of lung nodule volumetry strongly reduces the number of false-positive and false-negative nodules compared with nodule diameter measurements, in an ultra-low-dose computed tomography lung cancer screening program.

Multi-source data approach for personalized outcome prediction in lung cancer screening: update from the NELSON trial

Trials show that low-dose computed tomography (CT) lung cancer screening in long-term (ex-)smokers reduces lung cancer mortality. However, many individuals were exposed to unnecessary diagnostic procedures. This project aims to improve the efficiency of lung cancer screening by identifying high-risk participants, and improving risk discrimination for nodules. This study is an extension of the Dutch-Belgian Randomized Lung Cancer Screening Trial, with a focus on personalized outcome prediction (NELSON-POP). New data will be added on genetics, air pollution, malignancy risk for lung nodules, and CT biomarkers beyond lung nodules (emphysema, coronary calcification, bone density, vertebral height and body composition). The roles of polygenic risk scores and air pollution in screen-detected lung cancer diagnosis and survival will be established. The association between the AI-based nodule malignancy score and lung cancer will be evaluated at baseline and incident screening rounds. The association of chest CT imaging biomarkers with outcomes will be established. Based on these results, multisource prediction models for pre-screening and post-baseline-screening participant selection and nodule management will be developed. The new models will be externally validated. We hypothesize that we can identify 15–20% participants with low-risk of lung cancer or short life expectancy and thus prevent ~140,000 Dutch individuals from being screened unnecessarily. We hypothesize that our models will improve the specificity of nodule management by 10% without loss of sensitivity as compared to assessment of nodule size/growth alone, and reduce unnecessary work-up by 40–50%.

Epidemiological Study to Assess the Prevalence of Lung Cancer in patients with smoking-associated atherosclerotic cardiovascular diseases: PREVALUNG study protocol

IntroductionEligibility criteria definition for a lung cancer screening (LCS) is an unmet need. We hypothesised that patients with a history of atheromatous cardiovascular disease (ACVD) associated with tobacco consumption are...

Airway Detection in COPD at Low-Dose CT Using Deep Learning and Multiparametric Freeze and Grow.

To present and validate a fully automated airway detection method at low-dose CT in patients with chronic obstructive pulmonary disease (COPD). In this retrospective study, deep learning (DL) and freeze-and-grow (FG) methods were optimized and applied to automatically detect airways at low-dose CT. Four data sets were used: two data sets consisting of matching standard- and low-dose CT scans from the Genetic Epidemiology of COPD (COPDGene) phase II (2014-2017) cohort (n = 2 × 236; mean age ± SD, 70 years ± 9; 123 women); one data set consisting of low-dose CT scans from the COPDGene phase III (2018-2020) cohort (n = 335; mean age ± SD, 73 years ± 8; 173 women); and one data set consisting of low-dose, anonymized CT scans from the 2003 Dutch-Belgian Randomized Lung Cancer Screening trial (n = 55) acquired by using different CT scanners. Performance measures for different methods were computed and compared by using the Wilcoxon signed rank test. At low-dose CT, 56 294 of 62 480 (90.1%) airways of the reference total airway count (TAC) and 32 109 of 37 864 (84.8%) airways of the peripheral TAC (TACp), detected at standard-dose CT, were detected. Significant losses (P < .001) of 14 526 of 76 453 (19.0%) airways and 884 of 6908 (12.8%) airways in the TAC and 12 256 of 43 462 (28.2%) airways and 699 of 3882 (18.0%) airways in the TACp were observed, respectively, for the multiprotocol and multiscanner data without retraining. When using the automated low-dose CT method, TAC values of 347, 342, 323, and 266 and TACp values of 205, 202, 289, and 141 were observed for those who have never smoked and participants at Global Initiative for Chronic Obstructive Lung Disease stages 0, 1, and 2, respectively, which were superior to the respective values previously reported for matching groups when using a semiautomated method at standard-dose CT. A low-cost, automated CT-based airway detection method was suitable for investigation of airway phenotypes at low-dose CT.Keywords: Airway, Airway Count, Airway Detection, Chronic Obstructive Pulmonary Disease, CT, Deep Learning, Generalizability, Low-Dose CT, Segmentation, Thorax, LungClinical trial registration no. NCT00608764 Supplemental material is available for this article. © RSNA, 2022.

P41.02 Implementation Barriers In US-based Lung Cancer Screening Programs

Both the National Lung Screening Trial and the Dutch-Belgian Randomized Lung Cancer Screening Trial (NELSON) demonstrate that screening by low-dose computed tomography (LDCT) leads to a reduction in lung cancer mortality underscoring the importance of implementing effective LDCT screening programs for those at risk. To better understand implementation barriers that programs face, the GO2 Foundation for Lung Cancer’s Screening Centers of Excellence (SCOE) network was surveyed to assess barriers in US-based screening programs related to patients, workflow and reimbursement. 100 SCOE network members, representing 87753 patients screened, participated in the survey. The survey was conducted online, focused on collecting data from calendar year 2018, and was analyzed by a market research firm ZoomRx. The survey assessed program structure, implementation barriers, capacity, screening rates and workflow. The survey was designed to baseline participants by collecting both quantitative and qualitative data and will be deployed annually to allow for longitudinal analysis. Data analysis allows the comparison of different groups such as academic v community, size of program and age of program. Of the 100 SCOE participants, 22 identified as academic-based programs, 61 as community-based, and the remaining as having other program structures (such as being a stand-alone imaging center). When asked what types of barriers were most challenging to them, the top category reported by academic programs was Patient-Volume/Patient-related barriers (reported by 55% of programs) and the top category reported by community programs was Operational/workflow barriers/lack of institutional buy-in (reported by 36% of programs). In addition to indicating the general categories of barriers that presented the most challenges to them, SCOEs were also asked to indicate what specific barriers they faced. 68% of academic programs indicated patients not returning for annual screenings and 50% reported patients not returning for interval follow up screenings. 46% of academic centers reported experiencing barriers in each of the following three areas: ordering/documenting eligibility, patient tracking/data management, and insurance coding/claims difficulties. When community programs were asked about specific barriers, 64% reported staffing limitations, 61% reported patients not returning for annual screenings, and 56% reported lack of support from referring providers. The impact of barriers differs between center types with academic centers finding patient and volume related issues more challenging in 2018 while community centers found workflow and institutional issues more challenging. In terms of what specific barriers were encountered, lack of patient adherence to annual follow up screening is frequently encountered by all types of programs. However, a majority of community-based programs reported issues with staffing or lack of support from referring providers in direct contrast to academic based centers. This suggests that initiatives to improve screening implementation must address both common barriers and program-type specific issues. The SCOE program represents a unique opportunity to study screening implementation at scale and across settings and is an ideal platform for implementing potential solutions to address barriers.

Estimation of the risk of lung cancer in women participating in a population-based breast cancer screening program

IntroductionLung cancer mortality is increasing in women. In Spain, estimates suggest that lung cancer mortality may soon surpass breast cancer mortality, the main cause of cancer mortality among women. The aim of this study was to estimate the proportion of women at high risk of developing lung cancer in a group of participants in a population-based breast cancer screening program. MethodsCross-sectional study in a sample of women who participated in a population-based breast cancer screening program in 2016 in Hospitalet de Llobregat n = 1,601. High risk of lung cancer was defined according to the inclusion criteria of the National Lung Screening Trial (NLST) and the Dutch-Belgian randomized lung cancer screening trial (NELSON). ResultsAround 20% of smokers according to NLST and 40% of smokers according to NELSON criteria, and around 20% of former smokers according to both criteria, are at high risk of developing lung cancer. A positive and statistically significant trend is observed between the proportion of women at high risk and nicotine dependence measured with the brief Fagerström Test. ConclusionsA high proportion of participants in this breast cancer screening program have a high risk of developing lung cancer and would be eligible to participate in a lung cancer screening program. Population-based breast cancer screening programs may be useful to implement lung cancer primary prevention activities.

Advancement in Low-dose CT Screening for Lung Cancer

米国におけるNLST（National Lung Screening Trial），欧州におけるNELSON（Dutch-Belgian randomized lung cancer screening trial）の2つのランダム化比較試験により，高危険群に対する低線量CT（low-dose computed tomography：LDCT）検診による肺癌死亡減少効果が証明された．NLSTでは胸部X線（chest X-ray：CXR）検診に対する，NELSONでは無検診に対する有用性である．ただし，対照の違いに加え，肺癌死亡減少割合，過剰診断割合は観察期間によって変化するため，2試験の単純な比較は困難である．既に，米国では保険による実施が開始されたが，実用化に際しては問題点も抽出されつつある．今後，日本において実用化するには，非～軽喫煙者に対する有用性評価，検診の実施体制（対策型検診及び任意型検診）の確立に加え，computer-aided diagnosis（CAD），人工知能（artificial intelligence：AI）ならびにバイオマーカー技術等の導入による高効率化と省力化，実施施設，読影医ならびに放射線技師等のインフラ整備とこれらの質の担保が必要となり，このための研究が必要となる．

Estimación del riesgo de cáncer de pulmón en mujeres que participan en un programa de cribado poblacional de cáncer de mama

IntroductionLung cancer mortality is increasing in women. In Spain, estimates suggest that lung cancer mortality may soon surpass breast cancer mortality, the main cause of cancer mortality among women. The aim of this study was to estimate the proportion of women at high risk of developing lung cancer in a group of participants in a population-based breast cancer screening program. MethodsCross-sectional study in a sample of women who participated in a population-based breast cancer screening program in 2016 in Hospitalet de Llobregat (n=1,601). High risk of lung cancer was defined according to the criteria of the National Lung Screening Trial (NLST) and the Dutch-Belgian randomized lung cancer screening trial (NELSON). ResultsAround 20% of smokers according to NLST criteria and 40% of smokers according to NELSON criteria, and around 20% of former smokers according to both criteria, are at high risk of developing lung cancer. A positive and statistically significant trend is observed between the proportion of women at high risk and nicotine dependence measured with the brief Fagerström test. ConclusionsA high proportion of participants in this breast cancer screening program have a high risk of developing lung cancer and would be eligible to participate in a lung cancer screening program. Population-based breast cancer screening programs may be useful to implement lung cancer primary prevention activities.

Persisting new nodules in incidence rounds of the NELSON CT lung cancer screening study

BackgroundThe US guidelines recommend low-dose CT (LDCT) lung cancer screening for high-risk individuals. New solid nodules after baseline screening are common and have a high lung cancer probability. Currently, no...

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.

Relationship between the number of new nodules and lung cancer probability in incidence screening rounds of CT lung cancer screening: The NELSON study

BackgroundNew nodules are regularly found after the baseline round of low-dose computed tomography (LDCT) lung cancer screening. The relationship between a participant’s number of new nodules and lung cancer probability is unknown. MethodsParticipants of the ongoing Dutch-Belgian Randomized Lung Cancer Screening (NELSON) Trial with (sub)solid nodules detected after baseline and registered as new by the NELSON radiologists were included. The correlation between a participant’s new nodule count and the largest new nodule size was assessed using Spearman's rank correlation. To evaluate the new nodule count as predictor for new nodule lung cancer together with largest new nodule size, a multivariable logistic regression analysis was performed. ResultsIn total, 705 participants with 964 new nodules were included. In 48% (336/705) of participants no nodule had been found previously during baseline screening and in 22% (154/705) of participants >1 new nodule was detected (range 1–12 new nodules). Eventually, 9% (65/705) of the participants had lung cancer in a new nodule. In 100% (65/65) of participants with new nodule lung cancer, the lung cancer was the largest or only new nodule at initial detection. The new nodule lung cancer probability did not differ significantly between participants with 1 (10% [56/551], 95%CI 8–13%) or >1 new nodule (6% [9/154], 95%CI 3–11%, P = .116). An increased number of new nodules positively correlated with a participant’s largest nodule size (P < 0.001, Spearman’s rho 0.177). When adjusted for largest new nodule size, the new nodule count had a significant negative association with lung cancer (odds ratio 0.59, 0.37–0.95, P = .03). ConclusionA participant’s new nodule count alone only has limited association with lung cancer. However, a higher new nodule count correlates with an increased largest new nodule size, while the lung cancer probability remains equivalent, and may improve lung cancer risk prediction by size only.

MA01.07 Influence of Nodule Morphology on Inter-Reader Variability of Volume and Diameter Measurements in CT Lung Cancer Screening

The high number of false positive screen results is a major disadvantage of lung cancer screening by low-dose chest computed tomography (CT). Measurement strategy influences the false-positive rate, and nodule morphology may influence measurement of nodule size. Comparison between inter-reader variation for semi-automatic volume measurements and manual diameter measurements are scarce. Therefore, we aimed to evaluate the influence of nodule morphology on inter-reader variability and assessment of growth for semi-automatic volume measurements and manual diameter measurements, in intermediate-sized solid nodules found in CT lung cancer screening. Twenty-five 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. Two chest radiologists independently measured maximum and mean diameters manually. The impact of nodule morphology on inter-reader variability was evaluated based on the systematic error and 95% limits of agreement (LoA). Inter-reader variability was compared to volume change cutoff at 3-month follow-up based on NELSON for nodule growth and Lung-RADS diameter cutoff. For manual diameter measurements, a significant systematic deviation was found between readers in smooth, lobulated, and spiculated nodules. The deviation was up to 1.5 mm based on maximum diameter measurements, and 1.2 mm based on mean diameter measurements. For semi-automatic volume measurements, no statistically significant systematic deviation was found. For lobulated, spiculated, and irregular nodules, the 95%-LoA for mean diameter measurements was up to 66% larger than the 1.5 mm cutoff for nodule growth. For volume measurements, the 95%-LoA exceeded the 25% growth cutoff for spiculated and irregular nodules, but only by up to 12%. Nodule morphology has a greater effect on size assessment based on manual diameter measurements than based on volume measurements. The larger inter-reader variability for manual diameter measurement may cause misclassification of spiculated nodules when assessing growth in 24% of cases. Therefore, semi-automatic volume measurement is recommended for nodule size and growth determination in CT lung cancer screening.

From diagnosis to therapy in lung cancer: management of CT detected pulmonary nodules, a summary of the 2015 Chinese-German Lung Cancer Expert Panel

The first Chinese-German Lung Cancer Expert Panel was held in November 2015 one day after the 7th Chinese-German Lung Cancer Forum, Shanghai. The intention of the meeting was to discuss strategies for the diagnosis and treatment of lung cancer within the context of lung cancer screening. Improved risk classification criteria and novel imaging approaches for screening populations are highly required as more than half of lung cancer cases are false positive during the initial screening round if the National Lung Screening Trial (NLST) demographic criteria [≥30 pack years (PY) of cigarettes, age ≥55 years] are applied. Moreover, if the NLST criteria are applied to the Chinese population a high number of lung cancer patients are not diagnosed due to non-smoking related risk factors in China. The primary goal in the evaluation of pulmonary nodules (PN) is to determine whether they are malignant or benign. Volumetric based screening concepts such as investigated in the Dutch-Belgian randomized lung cancer screening trial (NELSON) seem to achieve higher specificity. Chest CT is the best imaging technique to identify the origin and location of the nodule since 20% of suspected PN found on chest X-ray turn out to be non-pulmonary lesions. Moreover, novel state-of-the-art CT systems can reduce the radiation dose for lung cancer screening acquisitions down to a level of 0.1 mSv with improved image quality to novel reconstruction techniques and thus reduce concerns related to chest CT as the primary screening technology. The aim of the first part of this manuscript was to summarize the current status of novel diagnostic techniques used for lung cancer screening and minimally invasive treatment techniques for progressive PNs that were discussed during the first Chinese-German Lung Cancer. This part should serve as an educational part for the readership of the techniques that were discussed during the Expert Panel. The second part summarizes the consensus recommendations that were interdisciplinary discussed by the Expert Panel.

Occurrence and lung cancer probability of new solid nodules at incidence screening with low-dose CT: analysis of data from the randomised, controlled NELSON trial

US guidelines now recommend lung cancer screening with low-dose CT for high-risk individuals. Reports of new nodules after baseline screening have been scarce and are inconsistent because of differences in definitions used. We aimed to identify the occurrence of new solid nodules and their probability of being lung cancer at incidence screening rounds in the Dutch-Belgian Randomized Lung Cancer Screening Trial (NELSON). In the ongoing, multicentre, randomised controlled NELSON trial, between Dec 23, 2003, and July 6, 2006, 15 822 participants who had smoked at least 15 cigarettes a day for more than 25 years or ten cigarettes a day for more than 30 years and were current smokers, or had quit smoking less than 10 years ago, were enrolled and randomly assigned to receive either screening with low-dose CT (n=7915) or no screening (n=7907). From Jan 28, 2004, to Dec 18, 2006, 7557 individuals underwent baseline screening with low-dose CT; 7295 participants underwent second and third screening rounds. We included all participants with solid non-calcified nodules, registered by the NELSON radiologists as new or smaller than 15 mm(3) (study detection limit) at previous screens. Nodule volume was generated semiautomatically by software. We calculated the maximum volume doubling time for nodules with an estimated percentage volume change of 25% or more, representing the minimum growth rate for the time since the previous scan. Lung cancer diagnosis was based on histology, and benignity was based on histology or stable size for at least 2 years. The NELSON trial is registered at trialregister.nl, number ISRCTN63545820. We analysed data for participants with at least one solid non-calcified nodule at the second or third screening round. In the two incidence screening rounds, the NELSON radiologists registered 1222 new solid nodules in 787 (11%) participants. A new solid nodule was lung cancer in 49 (6%) participants with new solid nodules and, in total, 50 lung cancers were found, representing 4% of all new solid nodules. 34 (68%) lung cancers were diagnosed at stage I. Nodule volume had a high discriminatory power (area under the receiver operating curve 0·795 [95% CI 0·728-0·862]; p<0·0001). Nodules smaller than 27 mm(3) had a low probability of lung cancer (two [0·5%] of 417 nodules; lung cancer probability 0·5% [95% CI 0·0-1·9]), nodules with a volume of 27 mm(3) up to 206 mm(3) had an intermediate probability (17 [3·1%] of 542 nodules; lung cancer probability 3·1% [1·9-5·0]), and nodules of 206 mm(3) or greater had a high probability (29 [16·9%] of 172 nodules; lung cancer probability 16·9% [12·0-23·2]). A volume cutoff value of 27 mm(3) or greater had more than 95% sensitivity for lung cancer. Our study shows that new solid nodules are detected at each screening round in 5-7% of individuals who undergo screening for lung cancer with low-dose CT. These new nodules have a high probability of malignancy even at a small size. These findings should be considered in future screening guidelines, and new solid nodules should be followed up more aggressively than nodules detected at baseline screening. Zorgonderzoek Nederland Medische Wetenschappen and Koningin Wilhelmina Fonds Kankerbestrijding.

To Screen or not to Screen: Low Dose Computed Tomography in Comparison to Chest Radiography or Usual Care in Reducing Morbidity and Mortality from Lung Cancer

Lung cancer has the highest mortality rate of all cancers. This paper seeks to address the question: Can the mortality of lung cancer be decreased by screening with low-dose computerized tomography (LDCT) in higher risk patients compared to chest X-rays (CXR) or regular patient care? Currently, CXR screening is recommended for certain high-risk patients. Several recent trials have examined the effectiveness of LDCT versus chest radiography or usual care as a control. These trials include National Lung Screening Trial (NLST), Detection And screening of early lung cancer with Novel imaging TEchnology (DANTE), Lung Screening Study (LSS), Depiscan, Italian Lung (ITALUNG), and Dutch-Belgian Randomized Lung Cancer Screening Trial (Dutch acronym: NELSON study). NLST, the largest trial (n=53, 454), demonstrated a decrease in mortality from lung cancer in the LDCT group (RRR=20%, P=0.004). LSS demonstrated a greater sensitivity in detecting both early stage and any stage of lung cancer in comparison to traditional CXR. Although the DANTE trial yielded data consistent with findings in LSS, it also showed that via LDCT screening a greater proportion of patients were placed under unnecessary surgical procedures. The Depiscan trial yielded a high nodule detection rate at the cost of a high false-positive rate compared to CXR screening. The ITALUNG and NELSON trials demonstrated the early detection capabilities of LDCT for lung cancers compared to usual care without surveillance imaging. False-positive findings with unnecessary workup, intervention, and radiation exposure remain significant concerns for routine LDCT screening. However, current data suggests LDCT may provide a highly sensitive and specific means for detecting lung cancers and reducing mortality.

Radiological characteristics of screen-detected lung cancers: predictive for histological subtype?

Methods 197 solid lung cancers (192 participants) detected in all four screening rounds of the Dutch-Belgian randomized lung cancer screening trial (NELSON) were included. CTmorphological features included nodule shape, margin, location, volume, and volume-doubling time (VDT). Based on histopathology, cancers were divided into four groups: adenocarcinoma (N=114), squamous cell carcinoma (N=37), large cell carcinoma (N=28) and neuro-endocrine cancers (N=18). Data were analyzed using ANOVA, Chi-square and Fischer’s exact test.

Chronic respiratory symptoms associated with airway wall thickening measured by thin-slice low-dose CT.

In lung cancer screening, the prevalence of chronic respiratory symptoms is high among heavy smokers. The purpose of this study was to compare CT-derived airway wall measurements between male smokers with and those without chronic respiratory symptoms. Fifty male heavy smokers with chronic respiratory symptoms (cough, excessive mucus secretion, dyspnea, and wheezing) and 50 without any respiratory symptom were randomly selected from the Dutch-Belgian Randomized Lung Cancer Screening Trial. Thin-slice low-dose CT images were evaluated with dedicated software for airway measurements. Wall area percentage and airway wall thickness were measured from trachea to bronchi in five different pulmonary lobes of airways with a luminal diameter of 5 mm or greater. Association between airway wall measurements and respiratory symptoms was analyzed by multiple linear regression adjusted for age, body mass index, smoking status, emphysema, and pulmonary function. After adjustment for relevant factors, a significant positive association between airway wall measurements and respiratory symptoms was found in airways with a luminal diameter between 5 to 10 mm (p < 0.01), but not in airways measuring 10 mm or greater (p > 0.05). At the airway level between 5 to 10 mm, the mean wall area percentages were 51.5% ± 7.9%. Airway wall thicknesses were 1.54 ± 0.39 mm and 1.37 ± 0.35 mm (p < 0.001). Male heavy smokers with chronic respiratory symptoms in lung cancer screening, who are at high-risk of chronic bronchitis, have bronchial wall thickening in airways with a luminal diameter of 5-10 mm but not in larger airways.