Assessing the Relationship Between Lung Cancer Risk and Emphysema Detected on Low-Dose CT of the Chest

doi:10.1378/chest.07-1490

Chest

Volume 132, Issue 6, December 2007, Pages 1932-1938

https://doi.org/10.1378/chest.07-1490 Get rights and content

Rationale: Identification of risk factors for lung cancer can help in selecting patients who may benefit the most from smoking cessation interventions, early detection, or chemoprevention.

Objective

To evaluate whether the presence of emphysema on low-radiation-dose CT (LDCT) of the chest is an independent risk factor for lung cancer.

Methods

The study used data from a prospective cohort of 1,166 former and current smokers participating in a lung cancer screening study. All individuals underwent a baseline LDCT and spirometry followed by yearly repeat LDCT studies. The incidence density of lung cancer among patients with and without emphysema on LDCT was estimated. Stratified and multiple regression analyses were used to assess whether emphysema is an independent risk factor for lung cancer after adjusting for age, gender, smoking history, and the presence of airway obstruction on spirometry.

Results

On univariate analysis, the incidence density of lung cancer among individuals with and without emphysema on LDCT was 25.0 per 1,000 person-years and 7.5 per 1,000 person-years, respectively (risk ratio [RR], 3.33; 95% confidence interval [CI], 1.41 to 7.85). Emphysema was also associated with increased risk of lung cancer when the analysis was limited to individuals without airway obstruction on spirometry (RR, 4.33; 95% CI, 1.04 to 18.16). Multivariate analysis showed that the presence of emphysema (RR, 2.51; 95% CI, 1.01 to 6.23) on LDCT but not airway obstruction (RR, 2.10; 95% CI, 0.79 to 5.58) was associated with increased risk of lung cancer after adjusting for potential cofounders.

Conclusions

Results suggest that the presence of emphysema on LDCT is an independent risk factor for lung cancer.

Section snippets

Materials and Methods

The study was conducted using data from a prospective cohort of individuals enrolled in a lung cancer screening study using LDCT from September 2000 to December 2005.⁸ Eligibility criteria included age ≥ 40 years, > 10 pack-year smoking history, and no symptoms of lung cancer. The study protocol consisted of a baseline LDCT of the chest followed by annual repeat studies for up to 5 years. All patients underwent spirometry at enrollment and a baseline standardized questionnaire to collect

Results

A total of 1,166 individuals were included in the study. Baseline characteristics of the study participants are shown in Table 1. All participants were white western Europeans, mean age was 54 ± 8 years, and 74% were male. The median number of pack-years smoked was 33 (IQR: 22 pack-years). Overall, 29% (95% CI, 26 to 31%) of the subjects had emphysema on baseline LDCT and 25% (95% CI, 22 to 27%) had airway obstruction on spirometry (Fig 1). Fifty-three percent of the participants with emphysema

Discussion

Results of this prospective cohort study of current and former smokers suggest that the presence of emphysema on LDCT is associated with an increased risk for lung cancer. Stratified and multivariate analyses showed that this association was significant even after controlling for the presence of airway obstruction on spirometry, suggesting that emphysema on LDCT is an independent risk factor for lung cancer. This information can help identify patients at high risk for lung cancer who may

Acknowledgments

The authors thank Elena De Miguel, RN, and Teresa Jiménez, RN, for performing the pulmonary function tests.

References (29)

M Pirozynski
100 years of lung cancer
Respir Med
(2006)
CI Henschke et al.
Early Lung Cancer Action Project: overall design and findings from baseline screening
Lancet
(1999)
DM Parkin et al.
Global cancer statistics, 2002
CA Cancer J Clin
(2005)
SU Hasan
ATS statement: cigarette smoking and health
Am J Respir Crit Care Med
(1996)
American Thoracic Society
Standards for the diagnosis and care of patients with chronic obstructive pulmonary disease
Am J Respir Crit Care Med
(1995)
RA Pauwels et al.
Global strategy for the diagnosis, management, and prevention of chronic obstructive pulmonary disease: NHLBI/WHO Global Initiative for Chronic Obstructive Lung Disease (GOLD) workshop summary
Am J Respir Crit Care Med
(2001)
National Emphysema Treatment Trial Research Group
Patients at high risk of death after lung-volume-reduction surgery
N Engl J Med
(2001)
MS Tockman et al.
Airways obstruction and the risk for lung cancer
Ann Intern Med
(1987)
G Bastarrika et al.
Early lung cancer detection using spiral computed tomography and positron emission tomography
Am J Respir Crit Care Med
(2005)
J Roca et al.
References values for forced spirometry: group of the European Community Respiratory Health Survey
Eur Respir J
(1998)

CI Henschke et al.

Survival of patients with stage I lung cancer detected on CT screening

N Engl J Med

(2006)

M Maclure et al.

Misinterpretation and misuse of the κ statistic

Am J Epidemiol

(1987)

JL Kesley et al.

Methods in observational epidemiology.

(1996)

PF Griner et al.

Selection and interpretation of diagnostic tests and procedures

Ann Intern Med

(1981)

Cited by (372)

Expert consensus on the evaluation and management of high-risk indeterminate pulmonary nodules
2024, Clinical eHealth
The most effective method for improving the prognosis of lung cancer is the application of low-dose computed tomography (LDCT) for pulmonary nodule screening in populations at high risk. Timely diagnosis and treatment of early-stage lung cancer can contribute to higher long-term survival rates. However, it remains difficult to differentiate malignant from benign pulmonary nodules measuring 8–15 mm, and avoid overtreatment on the one hand and delayed diagnosis on the other hand. In this consensus paper, we aimed to clarify the definition of “high-risk indeterminate pulmonary nodules (IPNs)” and discuss appropriate evaluation and management to facilitate timely diagnosis of lung cancer to improve lung cancer outcome. Direction for future research was discussed.
A multi-disciplinary panel of doctors and IT experts from Asia, Canada and the U.S. were invited to participate. Published evidence and consensus guidelines were used to develop this consensus was clarified. Their evaluation and management were discussed.
The experts believed that the prevalence of pulmonary nodules was very high, and it that was difficult to diagnose early-stage lung cancer due to the small size of the nodules, often leading to delayed diagnosis or overtreatment. To address this issue and to improve long-term outcome, the panel considered important to revise the classification of high-risk IPNs, (1) as pulmonary nodules that cannot be clearly diagnosed with non-surgical biopsy procedures, but is highly suspicious for early-stage lung cancer. The panel also recommends the most responsible should arrange imaging evaluations and follow-ups, taking new technologies into account. Artificial intelligence (AI) assessment based on the Medical Internet of Things (MIoT) can be combined with expert opinion to form a human–computer multidisciplinary team (MDT) that can fully implement the three core procedures of the MIoT, namely, comprehensive perception, reliable transmission, and intelligent processing. This will help to upgrade the non-standard diagnosis and treatment, the so-called “handicraft workshop model”, to a modern assembly-line model that meets international standards. The MIoT technology, which has the potential to realize “simplification of complex problems, digitalization of simple problems, programming of digital problems, and systematization of programming problems”, can promote the homogeneous evaluation of pulmonary nodules by enhancing both the sensitivity and the specificity of detecting early-stage lung cancer, in order to avoid delayed diagnosis and overtreatment.
To optimize the evaluation of early-stage lung cancer, and to avoid delayed diagnosis and overtreatment, it is necessary to propose and promote the concept of “high-risk IPNs”. The application of current technologies, AI, and a human–computer MDT, will facilitate improvement in nodule evaluation, transforming the current diagnosis and treatment model, which is akin to production in handicraft workshops, into a modern assembly-line model that meets international standards, and will ultimately result in better prognosis.
Lung Cancer Screening in People With COPD: The Pamplona-IELCAP Experience
2024, Archivos de Bronconeumologia
The Global Initiative for Obstructive Lung Disease (GOLD) recommends lung cancer screening for patients with Chronic Obstructive Pulmonary Disease (COPD), but data is lacking regarding results of screening in this high-risk population. The main goal of the present work is to explore if lung cancer screening with Low Dose Chest Tomography (LDCT) in people with COPD, allows lung cancer (LC) diagnosis in early stages with survival compatible with curative state.
This is a post hoc exploratory analysis. Pamplona International Early Lung Cancer Action Program (P-IELCAP) participants with a GOLD defined obstructive pattern (post bronchodilator FEV₁/FVC < 0.70) were selected for analysis. The characteristics of those who developed LC and their survival are described. A Cox proportional analysis explored the factors associated with LC diagnosis.
Eight hundred and sixty-five patients (77% male, 93% in spirometric GOLD stage 1 + 2) were followed for 102 ± 63 months. LC prevalence was 2.6% at baseline, with an annual LC diagnosis rate of 0.68%. Early-stage tumors predominated (74%) with a median survival (25–75th percentiles) of 139 (76–185) months. Cumulative tobacco exposure, FEV₁%, and emphysema were the main predictors of an LC diagnosis. Eight (11%) patients with COPD had a second LC, most of them in early stage (92%), and 6 (8%) had recurrence. Median survival (25–75th percentiles) in these patients was 168 (108–191) months.
Lung cancer screening of selected high-risk participants with COPD allowed the LC diagnosis in early stages with survival compatible with curative state.
The International Association for the Study of Lung Cancer Early Lung Imaging Confederation Open-Source Deep Learning and Quantitative Measurement Initiative
2024, Journal of Thoracic Oncology
With global adoption of computed tomography (CT) lung cancer screening, there is increasing interest to use artificial intelligence (AI) deep learning methods to improve the clinical management process. To enable AI research using an open-source, cloud-based, globally distributed, screening CT imaging data set and computational environment that are compliant with the most stringent international privacy regulations that also protect the intellectual properties of researchers, the International Association for the Study of Lung Cancer sponsored development of the Early Lung Imaging Confederation (ELIC) resource in 2018. The objective of this report is to describe the updated capabilities of ELIC and illustrate how this resource can be used for clinically relevant AI research.
In this second phase of the initiative, metadata and screening CT scans from two time points were collected from 100 screening participants in seven countries. An automated deep learning AI lung segmentation algorithm, automated quantitative emphysema metrics, and a quantitative lung nodule volume measurement algorithm were run on these scans.
A total of 1394 CTs were collected from 697 participants. The LAV950 quantitative emphysema metric was found to be potentially useful in distinguishing lung cancer from benign cases using a combined slice thickness more than or equal to 2.5 mm. Lung nodule volume change measurements had better sensitivity and specificity for classifying malignant from benign lung nodules when applied to solid lung nodules from high-quality CT scans.
These initial experiments revealed that ELIC can support deep learning AI and quantitative imaging analyses on diverse and globally distributed cloud-based data sets.
Perinodular Parenchymal Features Improve Indeterminate Lung Nodule Classification
2023, Academic Radiology
: Radiomics, defined as quantitative features extracted from images, provide a non-invasive means of assessing malignant versus benign pulmonary nodules. In this study, we evaluate the consistency with which perinodular radiomics extracted from low-dose computed tomography images serve to identify malignant pulmonary nodules.
: Using the National Lung Screening Trial (NLST), we selected individuals with pulmonary nodules between 4mm to 20mm in diameter. Nodules were segmented to generate four distinct datasets; 1) a Tumor dataset containing tumor-specific features, 2) a 10 mm Band dataset containing parenchymal features between the segmented nodule boundary and 10mm out from the boundary, 3) a 15mm Band dataset, and 4) a Tumor Size dataset containing the maximum nodule diameter. Models to predict malignancy were constructed using support-vector machine (SVM), random forest (RF), and least absolute shrinkage and selection operator (LASSO) approaches. Ten-fold cross validation with 10 repetitions per fold was used to evaluate the performance of each approach applied to each dataset.
: With respect to the RF, the Tumor, 10mm Band, and 15mm Band datasets achieved areas under the receiver-operator curve (AUC) of 84.44%, 84.09%, and 81.57%, respectively. Significant differences in performance were observed between the Tumor and 15mm Band datasets (adj. p-value <0.001). However, when combining tumor-specific features with perinodular features, the 10mm Band + Tumor and 15mm Band + Tumor datasets (AUC 87.87% and 86.75%, respectively) performed significantly better than the Tumor Size dataset (66.76%) or the Tumor dataset. Similarly, the AUCs from the SVM and LASSO were 84.71% and 88.91%, respectively, for the 10mm Band + Tumor.
: The combined 10mm Band + Tumor dataset improved the differentiation between benign and malignant lung nodules compared to the Tumor datasets across all methodologies. This demonstrates that parenchymal features capture novel diagnostic information beyond that present in the nodule itself. (data agreement: NLST-163)
Lung CT image synthesis using GANs
2023, Expert Systems with Applications
Biomedical engineering has been targeted as a potential research candidate for machine learning applications, with the purpose of detecting or diagnosing pathologies. However, acquiring relevant, high-quality, and heterogeneous medical datasets is challenging due to privacy and security issues and the effort required to annotate the data. Generative models have recently gained a growing interest in the computer vision field due to their ability to increase dataset size by generating new high-quality samples from the initial set, which can be used as data augmentation of a training dataset. This study aimed to synthesize artificial lung images from corresponding positional and semantic annotations using two generative adversarial networks and databases of real computed tomography scans: the Pix2Pix approach that generates lung images from the lung segmentation maps; and the conditional generative adversarial network (cCGAN) approach that was implemented with additional semantic labels in the generation process. To evaluate the quality of the generated images, two quantitative measures were used: the domain-specific Fréchet Inception Distance and Structural Similarity Index. Additionally, an expert assessment was performed to measure the capability to distinguish between real and generated images. The assessment performed shows the high quality of synthesized images, which was confirmed by the expert evaluation. This work represents an innovative application of GAN approaches for medical application taking into consideration the pathological findings in the CT images and the clinical evaluation to assess the realism of these features in the generated images.
Lung cancer screening
2023, The Lancet
Randomised controlled trials, including the National Lung Screening Trial (NLST) and the NELSON trial, have shown reduced mortality with lung cancer screening with low-dose CT compared with chest radiography or no screening. Although research has provided clarity on key issues of lung cancer screening, uncertainty remains about aspects that might be critical to optimise clinical effectiveness and cost-effectiveness. This Review brings together current evidence on lung cancer screening, including an overview of clinical trials, considerations regarding the identification of individuals who benefit from lung cancer screening, management of screen-detected findings, smoking cessation interventions, cost-effectiveness, the role of artificial intelligence and biomarkers, and current challenges, solutions, and opportunities surrounding the implementation of lung cancer screening programmes from an international perspective. Further research into risk models for patient selection, personalised screening intervals, novel biomarkers, integrated cardiovascular disease and chronic obstructive pulmonary disease assessments, smoking cessation interventions, and artificial intelligence for lung nodule detection and risk stratification are key opportunities to increase the efficiency of lung cancer screening and ensure equity of access.

View all citing articles on Scopus

The study was approved by the Ethics Committee of the University Clinic of Navarra.

This work was funded in part by the Spanish Ministry of Health (FIS project PI04/2404) and the Department of Health of the Government of Navarra.

The authors have no conflicts of interest to disclose.

View full text

Chest

Original ResearchLung CancerAssessing the Relationship Between Lung Cancer Risk and Emphysema Detected on Low-Dose CT of the Chest

Objective

Methods

Results

Conclusions

Section snippets

Materials and Methods

Results

Discussion

Acknowledgments

Respir Med

Lancet

Global cancer statistics, 2002

CA Cancer J Clin

ATS statement: cigarette smoking and health

Am J Respir Crit Care Med

Standards for the diagnosis and care of patients with chronic obstructive pulmonary disease

Am J Respir Crit Care Med

Global strategy for the diagnosis, management, and prevention of chronic obstructive pulmonary disease: NHLBI/WHO Global Initiative for Chronic Obstructive Lung Disease (GOLD) workshop summary

Am J Respir Crit Care Med

Patients at high risk of death after lung-volume-reduction surgery

N Engl J Med

Airways obstruction and the risk for lung cancer

Ann Intern Med

Early lung cancer detection using spiral computed tomography and positron emission tomography

Am J Respir Crit Care Med

References values for forced spirometry: group of the European Community Respiratory Health Survey

Eur Respir J

Survival of patients with stage I lung cancer detected on CT screening

N Engl J Med

Misinterpretation and misuse of the κ statistic

Am J Epidemiol

Methods in observational epidemiology.

Selection and interpretation of diagnostic tests and procedures

Ann Intern Med

Original Research
Lung Cancer
Assessing the Relationship Between Lung Cancer Risk and Emphysema Detected on Low-Dose CT of the Chest