Early imaging biomarkers of lung cancer, COPD and coronary artery disease in the general population: rationale and design of the ImaLife (Imaging in Lifelines) Study

Xia, Congying; Rook, Mieneke; Pelgrim, Gert Jan; Sidorenkov, Grigory; Wisselink, Hendrik Joost; Bolhuis, Jurjen N. van; Ooijen, Peter M. A. van; Guo, Jiapan; Oudkerk, Matthijs; Groen, Harry J.M.; Berge, Maarten van den; Harst, Pim van der; Dijkstra, Hildebrand; Vonder, Marleen; Heuvelmans, Marjolein A; Dorrius, Monique D.; Deyn, Peter Paul De; Bock, Geertruida H. de; Dotinga, Aafje; Vliegenthart, Rozemarijn

doi:10.1007/s10654-019-00519-0

Cited by 45 publications

(41 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ImaLife study is an ongoing study embedded in the Lifelines cohort, 17 which was designed to establish reference values of imaging biomarkers for early stages of the big three diseases: CAD, lung cancer, and chronic obstructive pulmonary disease. 18 In brief, the Lifelines cohort was launched in 2006 (baseline round) to collect data from physical examinations; laboratory tests; and questionnaires on general demographics, health status, lifestyle, and environmental factors. Generally, every 1.5 years, follow-up questionnaires on aforementioned aspects were administered, and every 5 years, follow-up assessments were scheduled for renewed physical examinations and laboratory tests.…”

Section: Methodsmentioning

confidence: 99%

Cardiovascular Risk Factors and Coronary Calcification in a Middle-aged Dutch Population

Xia¹,

Vonder²,

Sidorenkov³

et al. 2020

Journal of Thoracic Imaging

Self Cite

View full text Add to dashboard Cite

Purpose: To assess the presence of coronary artery calcium (CAC) and its association with cardiovascular risk factors and Systematic COronary Risk Evaluation (SCORE) risk in a middle-aged Dutch population. Methods: Classic cardiovascular risk factors and CAC were analyzed in 4083 participants aged 45 to 60 years (57.9% women) from the population-based ImaLife study. CAC scores were quantified on noncontrast cardiac CT scans. Age-specific and sex-specific distribution of CAC categories (0, 1 to 99, 100 to 299, ≥300) and percentiles were determined. SCORE risk categories (<1%, ≥1% to 5%, and ≥5%) were compared with CAC distribution. Population attributable fractions (PAFs) of classic risk factors for CAC were estimated. Results: CAC was present in 54.5% male and 26.5% female participants. The percentage of individuals with CAC increased with increasing age. Mean SCORE was 2.0% in men and 0.7% in women. In SCORE <1%, 32.7% of men and 17.1% of women had CAC. In men with SCORE ≥5%, 26.9% had no CAC. Only 0.1% of women had SCORE ≥5%. PAF of classic risk factors for CAC was 18.5% in men and 31.4% in women. PAF was highest for hypertension (in men 8.0%, 95% confidence interval, 4.2%-11.8%; in women 13.1%, 95% confidence interval, 7.9%-18.2%) followed by hypercholesterolemia and obesity. Conclusion: In this middle-aged cohort, more than half of the men and a quarter of the women had CAC. One out of 4 men at high risk (SCORE ≥5%) could be placed into a lower risk category owing to absence of CAC. Thus, adding CAC scoring to SCORE could have considerable effect on cardiovascular risk classification. Elimination of exposure to classic risk factors could reduce limited proportion of CAC in a middle-aged population.

show abstract

Section: Methodsmentioning

confidence: 99%

Cardiovascular Risk Factors and Coronary Calcification in a Middle-aged Dutch Population

Xia¹,

Vonder²,

Sidorenkov³

et al. 2020

Journal of Thoracic Imaging

Self Cite

View full text Add to dashboard Cite

show abstract

“…The dataset consisted of scans (a minimum of 300 slices per scan) reconstructed in the axial plane with filtered back projection using the Br40 kernel (qualitative-smooth). The acquisition protocol for the dataset has been previously published [36]. The detailed consort of dataset used in the study is provided in the Fig.…”

Section: A Data Descriptionmentioning

confidence: 99%

An unsupervised anomaly detection model to identify emphysema in low-dose computed tomography

Nagaraj¹,

Cornelissen²,

Cai³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

<p>Challenges such as class imbalance, time intensive visual scoring, and limited amounts of labeled data are often encountered while accessing lung cancer screening low-dose computed tomography (LDCT) data for automated emphysema detection. To tackle these issues, we propose a generative adversarial network (GAN) based on unsupervised anomaly detection (UAD) to identify emphysema in LDCT. And to initiate disease specific feature learning, we introduce data augmentation based on minimum intensity projection (minIP) for the adversarial framework. The generator of the UAD model resembles an image latent-image configuration consisting of fully convolutional encoder-decoder architecture with skip connections. The discriminator is an encoder, which acts as a feature extractor and a classifier. We tested the robustness of the minIP based UAD model by adding anomalies to the training set. Furthermore to illustrate the usefulness of minIP and to serve as a comparison methodology for emphysema detection in LDCT, the proposed model was compared to the 2.5D transfer learning model. Visualization techniques like post processed residual images and Grad-cam maps were used to explain the UAD model inference. Our proposed minIP based UAD model showed an area under the curve of 0.91 0.02 for emphysema detection in LDCT. The UAD model was robust to inclusion of anomalies up to 3%. The augmentation improved the sensitivity of the transfer learning model by 2% however the UAD model outperformed the transfer learning model. The UAD model with minIP is a potential computer-aided tool for early detection of emphysema in lung cancer screening data.</p>

show abstract

“…The external validation dataset was collected from the ImaLife study [11]. The ImaLife study is an embedded study of the Lifelines cohort [12], which was designed to establish references values of imaging biomarkers in the Dutch population for the early stage of the big three diseases : lung cancer, chronic obstructive pulmonary disease and coronary artery disease.…”

Section: Study Populationmentioning

confidence: 99%

“…The complete scan protocols and designs of the used studies can be found in the design papers of ROBINSCA [9] and ImaLife [11]. We will mention the main differences between the two.…”

Section: Scan Protocolsmentioning

confidence: 99%

Deep learning for automated exclusion of cardiac CT examinations negative for coronary artery calcium

Oever

Cornelissen

Vonder

et al. 2020

European Journal of Radiology

Self Cite

View full text Add to dashboard Cite

show abstract

Early imaging biomarkers of lung cancer, COPD and coronary artery disease in the general population: rationale and design of the ImaLife (Imaging in Lifelines) Study

Cited by 45 publications

References 50 publications

Cardiovascular Risk Factors and Coronary Calcification in a Middle-aged Dutch Population

Cardiovascular Risk Factors and Coronary Calcification in a Middle-aged Dutch Population

An unsupervised anomaly detection model to identify emphysema in low-dose computed tomography

Deep learning for automated exclusion of cardiac CT examinations negative for coronary artery calcium

Contact Info

Product

Resources

About