Nodule detection and generation on chest X-rays: NODE21 Challenge.

Pulmonary nodules may be an early manifestation of lung cancer, the leading cause of cancer-related deaths among both men and women. Numerous studies have established that deep learning methods can yield high-performance levels in the detection of lung nodules in chest X-rays. However, the lack of gold-standard public datasets slows down the progression of the research and prevents benchmarking of methods for this task. To address this, we organized a public research challenge, NODE21, aimed at the detection and generation of lung nodules in chest X-rays. While the detection track assesses state-of-the-art nodule detection systems, the generation track determines the utility of nodule generation algorithms to augment training data and hence improve the performance of the detection systems. This paper summarizes the results of the NODE21 challenge and performs extensive additional experiments to examine the impact of the synthetically generated nodule training images on the detection algorithm performance.

Assisted versus Manual Interpretation of Low-Dose CT Scans for Lung Cancer Screening: Impact on Lung-RADS Agreement.

Purpose To compare the inter- and intraobserver agreement and reading times achieved when assigning Lung Imaging Reporting and Data System (Lung-RADS) categories to baseline and follow-up lung cancer screening studies by using a dedicated CT lung screening viewer with integrated nodule detection and volumetric support with those achieved by using a standard picture archiving and communication system (PACS)-like viewer. Materials and Methods Data were obtained from the National Lung Screening Trial (NLST). By using data recorded by NLST radiologists, scans were assigned to Lung-RADS categories. For each Lung-RADS category (1 or 2, 3, 4A, and 4B), 40 CT scans (20 baseline scans and 20 follow-up scans) were randomly selected for 160 participants (median age, 61 years; interquartile range, 58-66 years; 61 women) in total. Seven blinded observers independently read all CT scans twice in a randomized order with a 2-week washout period: once by using the standard PACS-like viewer and once by using the dedicated viewer. Observers were asked to assign a Lung-RADS category to each scan and indicate the risk-dominant nodule. Inter- and intraobserver agreement was analyzed by using Fleiss κ values and Cohen weighted κ values, respectively. Reading times were compared by using a Wilcoxon signed rank test. Results The interobserver agreement was moderate for the standard viewer and substantial for the dedicated viewer, with Fleiss κ values of 0.58 (95% CI: 0.55, 0.60) and 0.66 (95% CI: 0.64, 0.68), respectively. The intraobserver agreement was substantial, with a mean Cohen weighted κ value of 0.67. The median reading time was significantly reduced from 160 seconds with the standard viewer to 86 seconds with the dedicated viewer (P < .001). Conclusion Lung-RADS interobserver agreement increased from moderate to substantial when using the dedicated CT lung screening viewer. The median reading time was substantially reduced when scans were read by using the dedicated CT lung screening viewer. Keywords: CT, Thorax, Lung, Computer Applications-Detection/Diagnosis, Observer Performance, Technology Assessment Supplemental material is available for this article. © RSNA, 2021.

Automated Assessment of COVID-19 Reporting and Data System and Chest CT Severity Scores in Patients Suspected of Having COVID-19 Using Artificial Intelligence.

Background The coronavirus disease 2019 (COVID-19) pandemic has spread across the globe with alarming speed, morbidity, and mortality. Immediate triage of patients with chest infections suspected to be caused by COVID-19 using chest CT may be of assistance when results from definitive viral testing are delayed. Purpose To develop and validate an artificial intelligence (AI) system to score the likelihood and extent of pulmonary COVID-19 on chest CT scans using the COVID-19 Reporting and Data System (CO-RADS) and CT severity scoring systems. Materials and Methods The CO-RADS AI system consists of three deep-learning algorithms that automatically segment the five pulmonary lobes, assign a CO-RADS score for the suspicion of COVID-19, and assign a CT severity score for the degree of parenchymal involvement per lobe. This study retrospectively included patients who underwent a nonenhanced chest CT examination because of clinical suspicion of COVID-19 at two medical centers. The system was trained, validated, and tested with data from one of the centers. Data from the second center served as an external test set. Diagnostic performance and agreement with scores assigned by eight independent observers were measured using receiver operating characteristic analysis, linearly weighted κ values, and classification accuracy. Results A total of 105 patients (mean age, 62 years ± 16 [standard deviation]; 61 men) and 262 patients (mean age, 64 years ± 16; 154 men) were evaluated in the internal and external test sets, respectively. The system discriminated between patients with COVID-19 and those without COVID-19, with areas under the receiver operating characteristic curve of 0.95 (95% CI: 0.91, 0.98) and 0.88 (95% CI: 0.84, 0.93), for the internal and external test sets, respectively. Agreement with the eight human observers was moderate to substantial, with mean linearly weighted κ values of 0.60 ± 0.01 for CO-RADS scores and 0.54 ± 0.01 for CT severity scores. Conclusion With high diagnostic performance, the CO-RADS AI system correctly identified patients with COVID-19 using chest CT scans and assigned standardized CO-RADS and CT severity scores that demonstrated good agreement with findings from eight independent observers and generalized well to external data. © RSNA, 2020 Supplemental material is available for this article.

Observer variability for Lung-RADS categorisation of lung cancer screening CTs: impact on patient management.

OBJECTIVES: Lung-RADS represents a categorical system published by the American College of Radiology to standardise management in lung cancer screening. The purpose of the study was to quantify how well readers agree in assigning Lung-RADS categories to screening CTs; secondary goals were to assess causes of disagreement and evaluate its impact on patient management. METHODS: For the observer study, 80 baseline and 80 follow-up scans were randomly selected from the NLST trial covering all Lung-RADS categories in an equal distribution. Agreement of seven observers was analysed using Cohen's kappa statistics. Discrepancies were correlated with patient management, test performance and diagnosis of malignancy within the scan year. RESULTS: Pairwise interobserver agreement was substantial (mean kappa 0.67, 95% CI 0.58-0.77). Lung-RADS category disagreement was seen in approximately one-third (29%, 971) of 3360 reading pairs, resulting in different patient management in 8% (278/3360). Out of the 91 reading pairs that referred to scans with a tumour diagnosis within 1 year, discrepancies in only two would have resulted in a substantial management change. CONCLUSIONS: Assignment of lung cancer screening CT scans to Lung-RADS categories achieves substantial interobserver agreement. Impact of disagreement on categorisation of malignant nodules was low. KEY POINTS: • Lung-RADS categorisation of low-dose lung screening CTs achieved substantial interobserver agreement. • Major cause for disagreement was assigning a different nodule as risk-dominant. • Disagreement led to a different follow-up time in 8% of reading pairs.

Incidental perifissural nodules on routine chest computed tomography: lung cancer or not?

OBJECTIVES: Perifissural nodules (PFNs) are a common finding on chest CT, and are thought to represent non-malignant lesions. However, data outside a lung cancer-screening setting are currently lacking. METHODS: In a nested case-control design, out of a total cohort of 16,850 patients ≥ 40 years of age who underwent routine chest CT (2004-2012), 186 eligible subjects with incident lung cancer and 511 controls without were investigated. All non-calcified nodules ≥ 4 mm were semi-automatically annotated. Lung cancer location and subject characteristics were recorded. RESULTS: Cases (56 % male) had a median age of 64 years (IQR 59-70). Controls (60 % male) were slightly younger (p<0.01), median age of 61 years (IQR 51-70). A total of 262/1,278 (21 %) unique non-calcified nodules represented a PFN. None of these were traced to a lung malignancy over a median follow-up of around 4.5 years. PFNs were most often located in the lower lung zones (72 %, p<0.001). Median diameter was 4.6 mm (range: 4.0-8.1), volume 51 mm3 (range: 32-278). Some showed growth rates < 400 days. CONCLUSIONS: Our data show that incidental PFNs do not represent lung cancer in a routine care, heterogeneous population. This confirms prior screening-based results. KEY POINTS: • One-fifth of non-calcified nodules represented a perifissural nodule in our non-screening population. • PFNs fairly often show larger size, and can show interval growth. • When morphologically resembling a PFN, nodules are nearly certainly not a malignancy. • The assumed benign aetiology of PFNs seems valid outside the screening setting.

Malignancy risk estimation of pulmonary nodules in screening CTs: Comparison between a computer model and human observers.

PURPOSE: To compare human observers to a mathematically derived computer model for differentiation between malignant and benign pulmonary nodules detected on baseline screening computed tomography (CT) scans. METHODS: A case-cohort study design was chosen. The study group consisted of 300 chest CT scans from the Danish Lung Cancer Screening Trial (DLCST). It included all scans with proven malignancies (n = 62) and two subsets of randomly selected baseline scans with benign nodules of all sizes (n = 120) and matched in size to the cancers, respectively (n = 118). Eleven observers and the computer model (PanCan) assigned a malignancy probability score to each nodule. Performances were expressed by area under the ROC curve (AUC). Performance differences were tested using the Dorfman, Berbaum and Metz method. Seven observers assessed morphological nodule characteristics using a predefined list. Differences in morphological features between malignant and size-matched benign nodules were analyzed using chi-square analysis with Bonferroni correction. A significant difference was defined at p < 0.004. RESULTS: Performances of the model and observers were equivalent (AUC 0.932 versus 0.910, p = 0.184) for risk-assessment of malignant and benign nodules of all sizes. However, human readers performed superior to the computer model for differentiating malignant nodules from size-matched benign nodules (AUC 0.819 versus 0.706, p < 0.001). Large variations between observers were seen for ROC areas and ranges of risk scores. Morphological findings indicative of malignancy referred to border characteristics (spiculation, p < 0.001) and perinodular architectural deformation (distortion of surrounding lung parenchyma architecture, p < 0.001; pleural retraction, p = 0.002). CONCLUSIONS: Computer model and human observers perform equivalent for differentiating malignant from randomly selected benign nodules, confirming the high potential of computer models for nodule risk estimation in population based screening studies. However, computer models highly rely on size as discriminator. Incorporation of other morphological criteria used by human observers to superiorly discriminate size-matched malignant from benign nodules, will further improve computer performance.

Towards automatic pulmonary nodule management in lung cancer screening with deep learning.

The introduction of lung cancer screening programs will produce an unprecedented amount of chest CT scans in the near future, which radiologists will have to read in order to decide on a patient follow-up strategy. According to the current guidelines, the workup of screen-detected nodules strongly relies on nodule size and nodule type. In this paper, we present a deep learning system based on multi-stream multi-scale convolutional networks, which automatically classifies all nodule types relevant for nodule workup. The system processes raw CT data containing a nodule without the need for any additional information such as nodule segmentation or nodule size and learns a representation of 3D data by analyzing an arbitrary number of 2D views of a given nodule. The deep learning system was trained with data from the Italian MILD screening trial and validated on an independent set of data from the Danish DLCST screening trial. We analyze the advantage of processing nodules at multiple scales with a multi-stream convolutional network architecture, and we show that the proposed deep learning system achieves performance at classifying nodule type that surpasses the one of classical machine learning approaches and is within the inter-observer variability among four experienced human observers.

Malignancy risk estimation of screen-detected nodules at baseline CT: comparison of the PanCan model, Lung-RADS and NCCN guidelines.

OBJECTIVES: To compare the PanCan model, Lung-RADS and the 1.2016 National Comprehensive Cancer Network (NCCN) guidelines for discriminating malignant from benign pulmonary nodules on baseline screening CT scans and the impact diameter measurement methods have on performances. METHODS: From the Danish Lung Cancer Screening Trial database, 64 CTs with malignant nodules and 549 baseline CTs with benign nodules were included. Performance of the systems was evaluated applying the system's original diameter definitions: Dlongest-C (PanCan), DmeanAxial (NCCN), both obtained from axial sections, and Dmean3D (Lung-RADS). Subsequently all diameter definitions were applied uniformly to all systems. Areas under the ROC curves (AUC) were used to evaluate risk discrimination. RESULTS: PanCan performed superiorly to Lung-RADS and NCCN (AUC 0.874 vs. 0.813, p = 0.003; 0.874 vs. 0.836, p = 0.010), using the original diameter specifications. When uniformly applying Dlongest-C, Dmean3D and DmeanAxial, PanCan remained superior to Lung-RADS (p < 0.001 - p = 0.001) and NCCN (p < 0.001 - p = 0.016). Diameter definition significantly influenced NCCN's performance with Dlongest-C being the worst (Dlongest-C vs. Dmean3D, p = 0.005; Dlongest-C vs. DmeanAxial, p = 0.016). CONCLUSIONS: Without follow-up information, the PanCan model performs significantly superiorly to Lung-RADS and the 1.2016 NCCN guidelines for discriminating benign from malignant nodules. The NCCN guidelines are most sensitive to nodule size definition. KEY POINTS: • PanCan model outperforms Lung-RADS and 1.2016 NCCN guidelines in identifying malignant pulmonary nodules. • Nodule size definition had no significant impact on Lung-RADS and PanCan model. • 1.2016 NCCN guidelines were significantly superior when using mean diameter to longest diameter. • Longest diameter achieved lowest performance for all models. • Mean diameter performed equivalently when derived from axial sections and from volumetry.

Subsolid pulmonary nodule morphology and associated patient characteristics in a routine clinical population.

OBJECTIVES: To determine the presence and morphology of subsolid pulmonary nodules (SSNs) in a non-screening setting and relate them to clinical and patient characteristics. METHODS: A total of 16,890 reports of clinically obtained chest CT (06/2011 to 11/2014, single-centre) were searched describing an SSN. Subjects with a visually confirmed SSN and at least two thin-slice CTs were included. Nodule volumes were measured. Progression was defined as volume increase exceeding the software interscan variation. Nodule morphology, location, and patient characteristics were evaluated. RESULTS: Fifteen transient and 74 persistent SSNs were included (median follow-up 19.6 [8.3-36.8] months). Subjects with an SSN were slightly older than those without (62 vs. 58 years; p = 0.01), but no gender predilection was found. SSNs were mostly located in the upper lobes. Women showed significantly more often persistent lesions than men (94 % vs. 69 %; p = 0.002). Part-solid lesions were larger (1638 vs. 383 mm3; p < 0.001) and more often progressive (68 % vs. 38 %; p = 0.02), compared to pure ground-glass nodules. Progressive SSNs were rare under the age of 50 years. Logistic regression analysis did not identify additional nodule parameters of future progression, apart from part-solid nature. CONCLUSIONS: This study confirms previously reported characteristics of SSNs and associated factors in a European, routine clinical population. KEY POINTS: • SSNs in women are significantly more often persistent compared to men. • SSN persistence is not associated with age or prior malignancy. • The majority of (persistent) SSNs are located in the upper lung lobes. • A part-solid nature is associated with future nodule growth. • Progressive solitary SSNs are rare under the age of 50 years.

Automatic classification of pulmonary peri-fissural nodules in computed tomography using an ensemble of 2D views and a convolutional neural network out-of-the-box.

In this paper, we tackle the problem of automatic classification of pulmonary peri-fissural nodules (PFNs). The classification problem is formulated as a machine learning approach, where detected nodule candidates are classified as PFNs or non-PFNs. Supervised learning is used, where a classifier is trained to label the detected nodule. The classification of the nodule in 3D is formulated as an ensemble of classifiers trained to recognize PFNs based on 2D views of the nodule. In order to describe nodule morphology in 2D views, we use the output of a pre-trained convolutional neural network known as OverFeat. We compare our approach with a recently presented descriptor of pulmonary nodule morphology, namely Bag of Frequencies, and illustrate the advantages offered by the two strategies, achieving performance of AUC = 0.868, which is close to the one of human experts.

Predictive Accuracy of the PanCan Lung Cancer Risk Prediction Model -External Validation based on CT from the Danish Lung Cancer Screening Trial.

OBJECTIVES: Lung cancer risk models should be externally validated to test generalizability and clinical usefulness. The Danish Lung Cancer Screening Trial (DLCST) is a population-based prospective cohort study, used to assess the discriminative performances of the PanCan models. METHODS: From the DLCST database, 1,152 nodules from 718 participants were included. Parsimonious and full PanCan risk prediction models were applied to DLCST data, and also coefficients of the model were recalculated using DLCST data. Receiver operating characteristics (ROC) curves and area under the curve (AUC) were used to evaluate risk discrimination. RESULTS: AUCs of 0.826-0.870 were found for DLCST data based on PanCan risk prediction models. In the DLCST, age and family history were significant predictors (p = 0.001 and p = 0.013). Female sex was not confirmed to be associated with higher risk of lung cancer; in fact opposing effects of sex were observed in the two cohorts. Thus, female sex appeared to lower the risk (p = 0.047 and p = 0.040) in the DLCST. CONCLUSIONS: High risk discrimination was validated in the DLCST cohort, mainly determined by nodule size. Age and family history of lung cancer were significant predictors and could be included in the parsimonious model. Sex appears to be a less useful predictor. KEY POINTS: • High accuracy in logistic modelling for lung cancer risk stratification of nodules. • Lung cancer risk prediction is primarily based on size of pulmonary nodules. • Nodule spiculation, age and family history of lung cancer are significant predictors. • Sex does not appear to be a useful risk predictor.

Detection and quantification of the solid component in pulmonary subsolid nodules by semiautomatic segmentation.

OBJECTIVE: To determine whether semiautomatic volumetric software can differentiate part-solid from nonsolid pulmonary nodules and aid quantification of the solid component. METHODS: As per reference standard, 115 nodules were differentiated into nonsolid and part-solid by two radiologists; disagreements were adjudicated by a third radiologist. The diameters of solid components were measured manually. Semiautomatic volumetric measurements were used to identify and quantify a possible solid component, using different Hounsfield unit (HU) thresholds. The measurements were compared with the reference standard and manual measurements. RESULTS: The reference standard detected a solid component in 86 nodules. Diagnosis of a solid component by semiautomatic software depended on the threshold chosen. A threshold of -300 HU resulted in the detection of a solid component in 75 nodules with good sensitivity (90%) and specificity (88%). At a threshold of -130 HU, semiautomatic measurements of the diameter of the solid component (mean 2.4 mm, SD 2.7 mm) were comparable to manual measurements at the mediastinal window setting (mean 2.3 mm, SD 2.5 mm [p = 0.63]). CONCLUSION: Semiautomatic segmentation of subsolid nodules could diagnose part-solid nodules and quantify the solid component similar to human observers. Performance depends on the attenuation segmentation thresholds. This method may prove useful in managing subsolid nodules. KEY POINTS: • Semiautomatic segmentation can accurately differentiate nonsolid from part-solid pulmonary nodules • Semiautomatic segmentation can quantify the solid component similar to manual measurements • Semiautomatic segmentation may aid management of subsolid nodules following Fleischner Society recommendations • Performance for the segmentation of subsolid nodules depends on the chosen attenuation thresholds.

Interscan variation of semi-automated volumetry of subsolid pulmonary nodules.

RATIONALE: We aimed to test the interscan variation of semi-automatic volumetry of subsolid nodules (SSNs), as growth evaluation is important for SSN management. METHODS: From a lung cancer screening trial all SSNs that were stable over at least 3 months were included (N = 44). SSNs were quantified on the baseline CT by two observers using semi-automatic volumetry software for effective diameter, volume, and mass. One observer also measured the SSNs on the second CT 3 months later. Interscan variation was evaluated using Bland-Altman plots. Observer agreement was calculated as intraclass correlation coefficient (ICC). Data are presented as mean (± standard deviation) or median and interquartile range (IQR). A Mann-Whitney U test was used for the analysis of the influence of adjustments on the measurements. RESULTS: Semi-automatic measurements were feasible in all 44 SSNs. The interscan limits of agreement ranged from -12.0 % to 9.7 % for diameter, -35.4 % to 28.6 % for volume and -27.6 % to 30.8 % for mass. Agreement between observers was good with intraclass correlation coefficients of 0.978, 0.957, and 0.968 for diameter, volume, and mass, respectively. CONCLUSION: Our data suggest that when using our software an increase in mass of 30 % can be regarded as significant growth. KEY POINTS: • Recently, recommendations regarding subsolid nodules have stressed the importance of growth quantification. • Volumetric measurement of subsolid nodules is feasible with good interscan agreement. • Increase of mass of 30 % can be regarded as significant growth.

Bag-of-frequencies: a descriptor of pulmonary nodules in computed tomography images.

We present a novel descriptor for the characterization of pulmonary nodules in computed tomography (CT) images. The descriptor encodes information on nodule morphology and has scale-invariant and rotation-invariant properties. Information on nodule morphology is captured by sampling intensity profiles along circular patterns on spherical surfaces centered on the nodule, in a multi-scale fashion. Each intensity profile is interpreted as a periodic signal, where the Fourier transform is applied, obtaining a spectrum. A library of spectra is created and labeled via unsupervised clustering, obtaining a Bag-of-Frequencies, which is used to assign each spectra a label. The descriptor is obtained as the histogram of labels along all the spheres. Additional contributions are a technique to estimate the nodule size, based on the sampling strategy, as well as a technique to choose the most informative plane to cut a 2-D view of the nodule in the 3-D image. We evaluate the descriptor on several nodule morphology classification problems, namely discrimination of nodules versus vascular structures and characterization of spiculation. We validate the descriptor on data from European screening trials NELSON and DLCST and we compare it with state-of-the-art approaches for 3-D shape description in medical imaging and computer vision, namely SPHARM and 3-D SIFT, outperforming them in all the considered experiments.

Solid, part-solid, or non-solid?: classification of pulmonary nodules in low-dose chest computed tomography by a computer-aided diagnosis system.

OBJECTIVES: The purpose of this study was to develop and validate a computer-aided diagnosis (CAD) tool for automatic classification of pulmonary nodules seen on low-dose computed tomography into solid, part-solid, and non-solid. MATERIALS AND METHODS: Study lesions were randomly selected from 2 sites participating in the Dutch-Belgian NELSON lung cancer screening trial. On the basis of the annotations made by the screening radiologists, 50 part-solid and 50 non-solid pulmonary nodules with a diameter between 5 and 30 mm were randomly selected from the 2 sites. For each unique nodule, 1 low-dose chest computed tomographic scan was randomly selected, in which the nodule was visible. In addition, 50 solid nodules in the same size range were randomly selected. A completely automatic 3-dimensional segmentation-based classification system was developed, which analyzes the pulmonary nodule, extracting intensity-, texture-, and segmentation-based features to perform a statistical classification. In addition to the nodule classification by the screening radiologists, an independent rating of all nodules by 3 experienced thoracic radiologists was performed. Performance of CAD was evaluated by comparing the agreement between CAD and human experts and among human experts using the Cohen κ statistics. RESULTS: Pairwise agreement for the differentiation between solid, part-solid, and non-solid nodules between CAD and each of the human experts had a κ range between 0.54 and 0.72. The interobserver agreement among the human experts was in the same range (κ range, 0.56-0.81). CONCLUSIONS: A novel automated classification tool for pulmonary nodules achieved good agreement with the human experts, yielding κ values in the same range as the interobserver agreement. Computer-aided diagnosis may aid radiologists in selecting the appropriate workup for pulmonary nodules.

Computed tomographic characteristics of interval and post screen carcinomas in lung cancer screening.

OBJECTIVES: To analyse computed tomography (CT) findings of interval and post-screen carcinomas in lung cancer screening. METHODS: Consecutive interval and post-screen carcinomas from the Dutch-Belgium lung cancer screening trial were included. The prior screening and the diagnostic chest CT were reviewed by two experienced radiologists in consensus with knowledge of the tumour location on the diagnostic CT. RESULTS: Sixty-one participants (53 men) were diagnosed with an interval or post-screen carcinoma. Twenty-two (36%) were in retrospect visible on the prior screening CT. Detection error occurred in 20 cancers and interpretation error in two cancers. Errors involved intrabronchial tumour (n = 5), bulla with wall thickening (n = 5), lymphadenopathy (n = 3), pleural effusion (n = 1) and intraparenchymal solid nodules (n = 8). These were missed because of a broad pleural attachment (n = 4), extensive reticulation surrounding a nodule (n = 1) and extensive scarring (n = 1). No definite explanation other than human error was found in two cases. None of the interval or post-screen carcinomas involved a subsolid nodule. CONCLUSIONS: Interval or post-screen carcinomas that were visible in retrospect were mostly due to detection errors of solid nodules, bulla wall thickening or endobronchial lesions. Interval or post-screen carcinomas without explanation other than human errors are rare. KEY POINTS: • 22% of missed carcinomas originally presented as bulla wall thickening on CT. • 22% of missed carcinomas originally presented as endobronchial lesions on CT. • All malignant endobronchial lesions presented as interval carcinomas. • In the NELSON trial subsolid nodules were not a source of missed carcinomas.

Detection of lung cancer through low-dose CT screening (NELSON): a prespecified analysis of screening test performance and interval cancers.

BACKGROUND: Low-dose CT screening is recommended for individuals at high risk of developing lung cancer. However, CT screening does not detect all lung cancers: some might be missed at screening, and others can develop in the interval between screens. The NELSON trial is a randomised trial to assess the effect of screening with increasing screening intervals on lung cancer mortality. In this prespecified analysis, we aimed to assess screening test performance, and the epidemiological, radiological, and clinical characteristics of interval cancers in NELSON trial participants assigned to the screening group. METHODS: Eligible participants in the NELSON trial were those aged 50-75 years, who had smoked 15 or more cigarettes per day for more than 25 years or ten or more cigarettes for more than 30 years, and were still smoking or had quit less than 10 years ago. We included all participants assigned to the screening group who had attended at least one round of screening. Screening test results were based on volumetry using a two-step approach. Initially, screening test results were classified as negative, indeterminate, or positive based on nodule presence and volume. Subsequently, participants with an initial indeterminate result underwent follow-up screening to classify their final screening test result as negative or positive, based on nodule volume doubling time. We obtained information about all lung cancer diagnoses made during the first three rounds of screening, plus an additional 2 years of follow-up from the national cancer registry. We determined epidemiological, radiological, participant, and tumour characteristics by reassessing medical files, screening CTs, and clinical CTs. The NELSON trial is registered at www.trialregister.nl, number ISRCTN63545820. FINDINGS: 15,822 participants were enrolled in the NELSON trial, of whom 7915 were assigned to low-dose CT screening with increasing interval between screens, and 7907 to no screening. We included 7155 participants in our study, with median follow-up of 8·16 years (IQR 7·56-8·56). 187 (3%) of 7155 screened participants were diagnosed with 196 screen-detected lung cancers, and another 34 (<1%; 19 [56%] in the first year after screening, and 15 [44%] in the second year after screening) were diagnosed with 35 interval cancers. For the three screening rounds combined, with a 2-year follow-up, sensitivity was 84·6% (95% CI 79·6-89·2), specificity was 98·6% (95% CI 98·5-98·8), positive predictive value was 40·4% (95% CI 35·9-44·7), and negative predictive value was 99·8% (95% CI 99·8-99·9). Retrospective assessment of the last screening CT and clinical CT in 34 patients with interval cancer showed that interval cancers were not visible in 12 (35%) cases. In the remaining cases, cancers were visible when retrospectively assessed, but were not diagnosed because of radiological detection and interpretation errors (17 [50%]), misclassification by the protocol (two [6%]), participant non-compliance (two [6%]), and non-adherence to protocol (one [3%]). Compared with screen-detected cancers, interval cancers were diagnosed at more advanced stages (29 [83%] of 35 interval cancers vs 44 [22%] of 196 screen-detected cancers diagnosed in stage III or IV; p<0·0001), were more often small-cell carcinomas (seven [20%] vs eight [4%]; p=0·003) and less often adenocarcinomas (nine [26%] vs 102 [52%]; p=0·005). INTERPRETATION: Lung cancer screening in the NELSON trial yielded high specificity and sensitivity, with only a small number of interval cancers. The results of this study could be used to improve screening algorithms, and reduce the number of missed cancers. FUNDING: Zorgonderzoek Nederland Medische Wetenschappen and Koningin Wilhelmina Fonds.

Lung cancer probability in patients with CT-detected pulmonary nodules: a prespecified analysis of data from the NELSON trial of low-dose CT screening.

BACKGROUND: The main challenge in CT screening for lung cancer is the high prevalence of pulmonary nodules and the relatively low incidence of lung cancer. Management protocols use thresholds for nodule size and growth rate to determine which nodules require additional diagnostic procedures, but these should be based on individuals' probabilities of developing lung cancer. In this prespecified analysis, using data from the NELSON CT screening trial, we aimed to quantify how nodule diameter, volume, and volume doubling time affect the probability of developing lung cancer within 2 years of a CT scan, and to propose and evaluate thresholds for management protocols. METHODS: Eligible participants in the NELSON trial were those aged 50-75 years, who have smoked 15 cigarettes or more per day for more than 25 years, or ten cigarettes or more for more than 30 years and were still smoking, or had stopped smoking less than 10 years ago. Participants were randomly assigned to low-dose CT screening at increasing intervals, or no screening. We included all participants assigned to the screening group who had attended at least one round of screening, and whose results were available from the national cancer registry database. We calculated lung cancer probabilities, stratified by nodule diameter, volume, and volume doubling time and did logistic regression analysis using diameter, volume, volume doubling time, and multinodularity as potential predictor variables. We assessed management strategies based on nodule threshold characteristics for specificity and sensitivity, and compared them to the American College of Chest Physicians (ACCP) guidelines. The NELSON trial is registered at www.trialregister.nl, number ISRCTN63545820. FINDINGS: Volume, volume doubling time, and volumetry-based diameter of 9681 non-calcified nodules detected by CT screening in 7155 participants in the screening group of NELSON were used to quantify lung cancer probability. Lung cancer probability was low in participants with a nodule volume of 100 mm(3) or smaller (0·6% [95% CI 0·4-0·8]) or maximum transverse diameter smaller than 5 mm (0·4% [0·2-0·7]), and not significantly different from participants without nodules (0·4% [0·3-0·6], p=0·17 and p=1·00, respectively). Lung cancer probability was intermediate (requiring follow-up CT) if nodules had a volume of 100-300 mm(3) (2·4% [95% CI 1·7-3·5]) or a diameter 5-10 mm (1·3% [1·0-1·8]). Volume doubling time further stratified the probabilities: 0·8% (95% CI 0·4-1·7) for volume doubling times 600 days or more, 4·0% (1·8-8·3) for volume doubling times 400-600 days, and 9·9% (6·9-14·1) for volume doubling times of 400 days or fewer. Lung cancer probability was high for participants with nodule volumes 300 mm(3) or bigger (16·9% [95% CI 14·1-20·0]) or diameters 10 mm or bigger (15·2% [12·7-18·1]). The simulated ACCP management protocol yielded a sensitivity and specificity of 90·9% (95% CI 81·2-96·1), and 87·2% (86·4-87·9), respectively. A diameter-based protocol with volumetry-based nodule diameter yielded a higher sensitivity (92·4% [95% CI 83·1-97·1]), and a higher specificity (90·0% [89·3-90·7). A volume-based protocol (with thresholds based on lung cancer probability) yielded the same sensitivity as the ACCP protocol (90·9% [95% CI 81·2-96·1]), and a higher specificity (94·9% [94·4-95·4]). INTERPRETATION: Small nodules (those with a volume <100 mm(3) or diameter <5 mm) are not predictive for lung cancer. Immediate diagnostic evaluation is necessary for large nodules (≥300 mm(3) or ≥10 mm). Volume doubling time assessment is advocated only for intermediate-sized nodules (with a volume ranging between 100-300 mm(3) or diameter of 5-10 mm). Nodule management protocols based on these thresholds performed better than the simulated ACCP nodule protocol. FUNDING: Zorgonderzoek Nederland Medische Wetenschappen and Koningin Wilhelmina Fonds.

Automatic detection of subsolid pulmonary nodules in thoracic computed tomography images.

Subsolid pulmonary nodules occur less often than solid pulmonary nodules, but show a much higher malignancy rate. Therefore, accurate detection of this type of pulmonary nodules is crucial. In this work, a computer-aided detection (CAD) system for subsolid nodules in computed tomography images is presented and evaluated on a large data set from a multi-center lung cancer screening trial. The paper describes the different components of the CAD system and presents experiments to optimize the performance of the proposed CAD system. A rich set of 128 features is defined for subsolid nodule candidates. In addition to previously used intensity, shape and texture features, a novel set of context features is introduced. Experiments show that these features significantly improve the classification performance. Optimization and training of the CAD system is performed on a large training set from one site of a lung cancer screening trial. Performance analysis on an independent test from another site of the trial shows that the proposed system reaches a sensitivity of 80% at an average of only 1.0 false positive detections per scan. A retrospective analysis of the output of the CAD system by an experienced thoracic radiologist shows that the CAD system is able to find subsolid nodules which were not contained in the screening database.

Semi-automatic quantification of subsolid pulmonary nodules: comparison with manual measurements.

RATIONALE: Accurate measurement of subsolid pulmonary nodules (SSN) is becoming increasingly important in the management of these nodules. SSNs were previously quantified with time-consuming manual measurements. The aim of the present study is to test the feasibility of semi-automatic SSNs measurements and to compare the results to the manual measurements. METHODS: In 33 lung cancer screening participants with 33 SSNs, the nodules were previously quantified by two observers manually. In the present study two observers quantified these nodules by using semi-automated nodule volumetry software. Nodules were quantified for effective diameter, volume and mass. The manual and semi-automatic measurements were compared using Bland-Altman plots and paired T tests. Observer agreement was calculated as an intraclass correlation coefficient. Data are presented as mean (SD). RESULTS: Semi-automated measurements were feasible in all 33 nodules. Nodule diameter, volume and mass were 11.2 (3.3) mm, 935 (691) ml and 379 (311) milligrams for observer 1 and 11.1 (3.7) mm, 986 (797) ml and 399 (344) milligrams for observer 2, respectively. Agreement between observers and within observer 1 for the semi-automatic measurements was good with an intraclass correlation coefficient >0.89. For observer 1 and observer 2, measured diameter was 8.8% and 10.3% larger (p<0.001), measured volume was 24.3% and 26.5% larger (p<0.001) and measured mass was 10.6% and 12.0% larger (p<0.001) with the semi-automatic program compared to the manual measurements. CONCLUSION: Semi-automated measurement of the diameter, volume and mass of SSNs is feasible with good observer agreement. Semi-automated measurement makes quantification of mass and volume feasible in daily practice.