Deep Learning has been proposed as promising tool to classify malignant nodules. Our aim was to retrospectively validate our Lung Cancer Prediction Convolutional Neural Network (LCP-CNN), which was trained on US screening data, on an independent dataset of indeterminate nodules in an European multicentre trial, to rule out benign nodules maintaining a high lung cancer sensitivity. The LCP-CNN has been trained to generate a malignancy score for each nodule using CT data from the U.S. National Lung Screening Trial (NLST), and validated on CT scans containing 2106 nodules (205 lung cancers) detected in patients from from the Early Lung Cancer Diagnosis Using Artificial Intelligence and Big Data (LUCINDA) study, recruited from three tertiary referral centers in the UK, Germany and Netherlands. We pre-defined a benign nodule rule-out test, to identify benign nodules whilst maintaining a high sensitivity, by calculating thresholds on the malignancy score that achieve at least 99 % sensitivity on the NLST data. Overall performance per validation site was evaluated using Area-Under-the-ROC-Curve analysis (AUC). The overall AUC across the European centers was 94.5 % (95 %CI 92.6-96.1). With a high sensitivity of 99.0 %, malignancy could be ruled out in 22.1 % of the nodules, enabling 18.5 % of the patients to avoid follow-up scans. The two false-negative results both represented small typical carcinoids. The LCP-CNN, trained on participants with lung nodules from the US NLST dataset, showed excellent performance on identification of benign lung nodules in a multi-center external dataset, ruling out malignancy with high accuracy in about one fifth of the patients with 5-15 mm nodules.
To explore the relationship between nodule count and lung cancer probability in baseline low-dose CT lung cancer screening. Included were participants from the NELSON trial with at least one baseline nodule (3392 participants [45% of screen-group], 7258 nodules). We determined nodule count per participant. Malignancy was confirmed by histology. Nodules not diagnosed as screen-detected or interval cancer until the end of the fourth screening round were regarded as benign. We compared lung cancer probability per nodule count category. 1746 (51.5%) participants had one nodule, 800 (23.6%) had two nodules, 354 (10.4%) had three nodules, 191 (5.6%) had four nodules, and 301 (8.9%) had>4 nodules. Lung cancer in a baseline nodule was diagnosed in 134 participants (139 cancers; 4.0%). Median nodule count in participants with only benign nodules was 1 (Inter-quartile range [IQR]: 1-2), and 2 (IQR 1-3) in participants with lung cancer (p=NS). At baseline, malignancy was detected mostly in the largest nodule (64/66 cancers). Lung cancer probability was 62/1746 (3.6%) in case a participant had one nodule, 33/800 (4.1%) for two nodules, 17/354 (4.8%) for three nodules, 12/191 (6.3%) for four nodules and 10/301 (3.3%) for>4 nodules (p=NS). In baseline lung cancer CT screening, half of participants with lung nodules have more than one nodule. Lung cancer probability does not significantly change with the number of nodules. Baseline nodule count will not help to differentiate between benign and malignant nodules. Each nodule found in lung cancer screening should be assessed separately independent of the presence of other nodules.
1 February 2017 in Translational Lung Cancer Research
Currently, lung cancer screening by low-dose chest CT is implemented in the United States for high-risk persons. A disadvantage of lung cancer screening is the large number of small-to-intermediate sized lung nodules, detected in around 50% of all participants, the large majority being benign. Accurate estimation of nodule size and growth is essential in the classification of lung nodules. Currently, manual diameter measurements are the standard for lung cancer screening programs and routine clinical care. However, European screening studies using semi-automated volume measurements have shown higher accuracy and reproducibility compared to diameter measurements. In addition to this, with the optimization of CT scan techniques and reconstruction parameters, as well as advances in segmentation software, the accuracy of nodule volume measurement can be improved even further. The positive results of previous studies on volume and diameter measurements of lung nodules suggest that manual measurements of nodule diameter may be replaced by semi-automated volume measurements in the (near) future.
Both visual and quantitative emphysema assessed at chest CT were associated with a higher odds ratio of lung cancer, and this association increased with emphysema severity. Background Given the different methods of assessing emphysema, controversy exists as to whether it is associated with lung cancer. Purpose To perform a systematic review and meta-analysis of the as...
Lung cancer, chronic obstructive pulmonary disease (COPD), and coronary artery disease (CAD) are expected to cause most deaths by 2050. State-of-the-art computed tomography (CT) allows early detection of lung cancer and simultaneous evaluation of imaging biomarkers for the early stages of COPD, based on pulmonary density and bronchial wall thickness, and of CAD, based on the coronary artery calcium score (CACS), at low radiation dose. To determine cut-off values for positive tests for elevated risk and presence of disease is one of the major tasks before considering implementation of CT screening in a general population. The ImaLife (Imaging in Lifelines) study, embedded in the Lifelines study, is designed to establish the reference values of the imaging biomarkers for the big three diseases in a well-defined general population aged 45 years and older. In total, 12,000 participants will undergo CACS and chest acquisitions with latest CT technology. The estimated percentage of individuals with lung nodules needing further workup is around 1–2%. Given the around 10% prevalence of COPD and CAD in the general population, the expected number of COPD and CAD is around 1000 each. So far, nearly 4000 participants have been included. The ImaLife study will allow differentiation between normal aging of the pulmonary and cardiovascular system and early stages of the big three diseases based on low-dose CT imaging. This information can be finally integrated into personalized precision health strategies in the general population.
Although exponential growth is assumed for lung cancer, this has never been quantified in vivo. Aim of this study was to evaluate and quantify growth patterns of lung cancers detected in the Dutch-Belgian low-dose computed tomography (CT) lung cancer screening trial (NELSON), in order to elucidate the development and progression of early lung cancer. Solid lung nodules found at ≥3 CT examinations before lung cancer diagnosis were included. Lung cancer volume (V) growth curves were fitted with a single exponential, expressed as V=V1 exp(t/τ), with t time from baseline (days), V1 estimated baseline volume (mm3), and τ estimated time constant. The R2 coefficient of determination was used to evaluate goodness of fit. Overall volume-doubling time for the individual lung cancer is given by τ*log(2). Forty-seven lung cancers in 46 participants were included. Forty participants were male (87.0%); mean age was 61.7 years (standard deviation, 6.2 years). Median nodule size at baseline was 99.5mm3 (IQR: 46.8-261.8mm3). Nodules were followed for a median of 770 days (inter-quartile range: 383-1102 days) before lung cancer diagnosis. One cancer (2.1%) was diagnosed after six CT examinations, six cancers (12.8%) were diagnosed after five CTs, 14 (29.8%) after four CTs, and 26 cancers (55.3%) after three CTs. Lung cancer growth could be described by an exponential function with excellent goodness of fit (R2 0.98). Median overall volume-doubling time was 348 days (inter-quartile range: 222-492 days). This study based on CT lung cancer screening provides in vivo evidence that growth of cancerous small-to-intermediate sized lung nodules detected at low-dose CT lung cancer screening can be described by an exponential function such as volume-doubling time.