Pulmonary nodules and CT screening: the past, present and future

Which is a real valuable screening tool for lung cancer and measure thoracic diseases, chest radiography or low-dose computed tomography?: A review on the current status of Japan and other countries

Chest radiography (CR) has been used as a screening tool for lung cancer and the use of low-dose computed tomography (LDCT) is not recommended in Japan. We need to reconsider whether CR really contributes to the early detection of lung cancer. In addition, we have not well discussed about other major thoracic disease detection by CR and LDCT compared with lung cancer despite of its high frequency. We review the usefulness of CR and LDCT as veridical screening tools for lung cancer and other thoracic diseases. In the case of lung cancer, many studies showed that LDCT has capability of early detection and improving outcomes compared with CR. Recent large randomized trial also supports former results. In the case of chronic obstructive pulmonary disease (COPD), LDCT contributes to early detection and leads to the implementation of smoking cessation treatments. In the case of pulmonary infections, LDCT can reveal tiny inflammatory changes that are not observed on CR, though many of these cases improve spontaneously. Therefore, LDCT screening for pulmonary infections may be less useful. CR screening is more suitable for the detection of pulmonary infections. In the case of cardiovascular disease (CVD), CR may be a better screening tool for detecting cardiomegaly, whereas LDCT may be a more useful tool for detecting vascular changes. Therefore, the current status of thoracic disease screening is that LDCT may be a better screening tool for detecting lung cancer, COPD, and vascular changes. CR may be a suitable screening tool for pulmonary infections and cardiomegaly.

Classification of Pulmonary Nodules in 2-[18F]FDG PET/CT Images with a 3D Convolutional Neural Network

Purpose

2-[18F]FDG PET/CT plays an important role in the management of pulmonary nodules. Convolutional neural networks (CNNs) automatically learn features from images and have the potential to improve the discrimination between malignant and benign pulmonary nodules. The purpose of this study was to develop and validate a CNN model for classification of pulmonary nodules from 2-[18F]FDG PET images.

Methods

One hundred thirteen participants were retrospectively selected. One nodule per participant. The 2-[18F]FDG PET images were preprocessed and annotated with the reference standard. The deep learning experiment entailed random data splitting in five sets. A test set was held out for evaluation of the final model. Four-fold cross-validation was performed from the remaining sets for training and evaluating a set of candidate models and for selecting the final model. Models of three types of 3D CNNs architectures were trained from random weight initialization (Stacked 3D CNN, VGG-like and Inception-v2-like models) both in original and augmented datasets. Transfer learning, from ImageNet with ResNet-50, was also used.

Results

The final model (Stacked 3D CNN model) obtained an area under the ROC curve of 0.8385 (95% CI: 0.6455-1.0000) in the test set. The model had a sensibility of 80.00%, a specificity of 69.23% and an accuracy of 73.91%, in the test set, for an optimised decision threshold that assigns a higher cost to false negatives.

Conclusion

A 3D CNN model was effective at distinguishing benign from malignant pulmonary nodules in 2-[18F]FDG PET images.

Supplementary Information

The online version contains supplementary material available at 10.1007/s13139-023-00821-6.

Prediction of positive pulmonary nodules based on machine learning algorithm combined with central carbon metabolism data

BACKGROUND

Lung cancer causes a huge disease burden, and early detection of positive pulmonary nodules (PPNs) as an early sign of lung cancer is extremely important for effective intervention. It is necessary to develop PPNs risk recognizer based on machine learning algorithm combined with central carbon metabolomics.

METHODS

The study included 2248 participants at high risk for lung cancer from the Ma'anshan Community Lung Cancer Screening cohort. The Least Absolute Shrinkage and Selection Operator (LASSO) was used to screen 18 central carbon-related metabolites in plasma, recursive feature elimination (RFE) was used to select all 42 features, followed by five machine learning algorithms for model development. The performance of the model was evaluated using area under the receiver operator characteristic curve (AUC), accuracy, precision, recall, and F1 scores. In addition, SHapley Additive exPlanations (SHAP) was performed to assess the interpretability of the final selected model and to gain insight into the impact of features on the predicted results.

RESULTS

Finally, the two prediction models based on the random forest (RF) algorithm performed best, with AUC values of 0.87 and 0.83, respectively, better than other models. We found that homogentisic acid, fumaric acid, maleic acid, hippuric acid, gluconic acid, and succinic acid played a significant role in both PPNs prediction model and NPNs vs PPNs model, while 2-oxadipic acid only played a role in the former model and phosphopyruvate only played a role in the NPNs vs PPNs model. This model demonstrates the potential of central carbon metabolism for PPNs risk prediction and identification.

CONCLUSION

We developed a series of predictive models for PPNs, which can help in the early detection of PPNs and thus reduce the risk of lung cancer.

Parameterized Gompertz-Guided Morphological AutoEncoder for Predicting Pulmonary Nodule Growth

The growth rate of pulmonary nodules is a critical clue to the cancerous diagnosis. It is essential to monitor their dynamic progressions during pulmonary nodule management. To facilitate the prosperity of research on nodule growth prediction, we organized and published a temporal dataset called NLSTt with consecutive computed tomography (CT) scans. Based on the self-built dataset, we develop a visual learner to predict the growth for the following CT scan qualitatively and further propose a model to predict the growth rate of pulmonary nodules quantitatively, so that better diagnosis can be achieved with the help of our predicted results. To this end, in this work, we propose a parameterized Gempertz-guided morphological autoencoder (GM-AE) to generate any future-time-span high-quality visual appearances of pulmonary nodules from the baseline CT scan. Specifically, we parameterize a popular mathematical model for tumor growth kinetics, Gompertz, to predict future masses and volumes of pulmonary nodules. Then, we exploit the expected growth rate on the mass and volume to guide decoders generating future shape and texture of pulmonary nodules. We introduce two branches in an autoencoder to encourage shape-aware and textural-aware representation learning and integrate the generated shape into the textural-aware branch to simulate the future morphology of pulmonary nodules. We conduct extensive experiments on the self-built NLSTt dataset to demonstrate the superiority of our GM-AE to its competitive counterparts. Experiment results also reveal the learnable Gompertz function enjoys promising descriptive power in accounting for inter-subject variability of the growth rate for pulmonary nodules. Besides, we evaluate our GM-AE model on an in-house dataset to validate its generalizability and practicality. We make its code publicly available along with the published NLSTt dataset.

A combined non-enhanced CT radiomics and clinical variable machine learning model for differentiating benign and malignant sub-centimeter pulmonary solid nodules

BACKGROUND

Radiomics has been used to predict pulmonary nodule (PN) malignancy. However, most of the studies focused on pulmonary ground-glass nodules. The use of computed tomography (CT) radiomics in pulmonary solid nodules, particularly sub-centimeter solid nodules, is rare.

PURPOSE

This study aims to develop a radiomics model based on non-enhanced CT images that can distinguish between benign and malignant sub-centimeter pulmonary solid nodules (SPSNs, <1 cm).

METHODS

The clinical and CT data of 180 SPSNs confirmed by pathology were analyzed retrospectively. All SPSNs were divided into two groups: training set (n = 144) and testing set (n = 36). From non-enhanced chest CT images, over 1000 radiomics features were extracted. Radiomics feature selection was performed using the analysis of variance and principal component analysis. The selected radiomics features were fed into a support vector machine (SVM) to develop a radiomics model. The clinical and CT characteristics were used to develop a clinical model. Associating non-enhanced CT radiomics features with clinical factors were used to develop a combined model using SVM. The performance was evaluated using the area under the receiver-operating characteristic curve (AUC).

RESULTS

The radiomics model performed well in distinguishing between benign and malignant SPSNs, with an AUC of 0.913 (95% confidence interval [CI], 0.862-0.954) in the training set and an AUC of 0.877 (95% CI, 0.817-0.924) in the testing set. The combined model outperformed the clinical and radiomics models with an AUC of 0.940 (95% CI, 0.906-0.969) in the training set and an AUC of 0.903 (95% CI, 0.857-0.944) in the testing set.

CONCLUSIONS

Radiomics features based on non-enhanced CT images can be used to differentiate SPSNs. The combined model, which included radiomics and clinical factors, had the best discrimination power between benign and malignant SPSNs.

Impact of CT screening in lung cancer: Scientific evidence and literature review

The treatment of lung cancer has improved significantly in recent years however, lung cancer remains as a leading cause of cancer-related mortality worldwide. Lung cancer screening has been explored, over the past several decades, as a means of reducing lung cancer mortality, to identify asymptomatic disease when it is potentially curable. The National Lung Screening Trial (NLST) established that low-dose computed tomography (LDCT) scans of the chest can be instrumental in reducing lung cancer mortality but the criteria for screening implemented in this trial may not be equitably sensitive across racial and sex subpopulations. Furthermore, the high false detection rate reported in this trial has raised concerns regarding overdiagnosis with LDCT alone. The aim of this review is to summarize the history of lung cancer screening trials, limitations of lung cancer screening, the impact of alternative risk prediction models in reducing disparities, and the use of biomarkers in conjunction with imaging to improve diagnostic authenticity.

Evaluation of chest radiography and low-dose computed tomography as valuable screening tools for thoracic diseases

BACKGROUND

Recent studies have shown that low-dose computed tomography (LDCT) is effective for the early detection of lung cancer. However, the utility of chest radiography (CR) and LDCT for other thoracic diseases has not been as well investigated as it has been for lung cancer. This study aimed to clarify the usefulness of the veridical method in the screening of various thoracic diseases.

METHODS

Among individuals who had received general health checkups over a 10-year period, those who had undergone both CR and LDCT were selected for analysis. The present study included 4317 individuals (3146 men and 1171 women). We investigated cases in which abnormal opacity was detected on CR and/or LDCT.

RESULTS

A total of 47 and 124 cases had abnormal opacity on CR and LDCT, respectively. Among these, 41 cases in which the abnormal opacity was identified by both methods contained 20 treated cases. Six cases had abnormalities only on CR, and none of the cases required further treatment. Eighty-three cases were identified using LDCT alone. Of these, many cases, especially those over the age of 50 years, were diagnosed with thoracic tumors and chronic obstructive pulmonary disease, which required early treatment. In contrast, many cases of pulmonary infections have improved spontaneously, without any treatment.

CONCLUSION

These results revealed that LDCT allowed early detection of thoracic tumors and chronic obstructive pulmonary disease, especially in individuals over the age of 50 years. CR is still a useful imaging modality for other thoracic diseases, especially in individuals under the age of 49 years.

[Pulmonary nodules and pneumonia : A diagnostic guideline]

Hintergrund

Das konventionelle Röntgenbild zählt zu den am häufigsten durchgeführten radiologischen Untersuchungen. Seine Interpretation gehört zu den Grundkenntnissen jedes Radiologen.

Fragestellung

Ziel dieses Artikels ist es, häufige Zeichen und Muster der Pneumonie sowie Merkmale von Pseudoläsionen im konventionellen Röntgenbild zu erkennen und einen diagnostischen Leitfaden für junge Radiologen zu schaffen.

Methoden

Analyse aktueller Studien und Daten sowie eine Übersicht der häufigsten Zeichen und Muster im konventionellen Röntgenbild.

Ergebnisse

Die Kenntnis über häufige Zeichen und Muster im Röntgenbild bietet eine Hilfestellung in der Diagnostik und kann hinweisend für die Ursache einer Infektion sein. Häufig sind diese Zeichen jedoch unspezifisch und sollten daher immer in klinische Korrelation gesetzt werden. In der Detektion und Beurteilung von pulmonalen Rundherden gewinnt die Computertomographie (CT) durch ihre deutlich höhere Sensitivität in der Primärdiagnostik immer mehr an Bedeutung.

Schlussfolgerung

Das konventionelle Röntgenbild bildet weiterhin eine führende Rolle in der Primärdiagnostik; der Radiologe sollte jedoch die Limitationen des konventionellen Bildes kennen.

Improved differentiation between primary lung cancer and pulmonary metastasis by combining dual-energy CT-derived biomarkers with conventional CT attenuation

OBJECTIVES

To assess the clinical utility of dual-energy CT (DE-CT)-derived iodine concentration (IC) and effective Z (Z^eff) in addition to conventional CT attenuation (HU) for the discrimination between primary lung cancer (LC) and pulmonary metastases (PM) from different primary malignancies.

METHODS

DE-CT scans of 79 patients with LC (3 histopathologic subgroups) and 89 patients with PM (5 histopathologic subgroups) were evaluated. Quantitative IC, Z^eff, and conventional HU values were extracted and normalized to the thoracic aorta. Differences between groups were assessed by pairwise Welch's t test. Correlation and linear regression analyses were used to examine the relationship of imaging parameters in LC and PM. Diagnostic accuracy was measured by the area under receiver operator characteristic curve (AUC) and validated based on resampling methods.

RESULTS

Significant differences between subgroups of LC and PMs were noted for all imaging parameters, with the highest number of significant pairs for IC. In univariate analysis, only IC was a significant diagnostic feature for discriminating LC from PM (p = 0.03). All quantitative imaging parameters correlated significantly (p < 0.0001, respectively), with the highest correlation between IC and Z^eff (r = 0.91), followed by IC and HU (r = 0.76) and Z^eff and HU (r = 0.73). Diagnostic models combining IC or Z^eff with HU (IC+HU: AUC = 0.73; Z^eff+HU: AUC = 0.69; IC+Z^eff+HU: AUC = 0.73) were not significantly different and outperformed individual parameters (IC: AUC = 0.57; Z^eff: AUC = 0.57; HU: AUC = 0.55) in diagnostic accuracy (p < 0.05, respectively).

CONCLUSION

DE-CT-derived IC or Z^eff and conventional HU represent complementary imaging parameters, which, if used in combination, may improve the differentiation between LC and PM.

KEY POINTS

• Individual quantitative imaging parameters derived from DE-CT (iodine concentration, effective Z) and conventional CT (HU) provide complementary diagnostic information for the differentiation of primary lung cancer and pulmonary metastases. • A combination of conventional HU and DE-CT parameters enhances the diagnostic utility of individual parameters.

The development and validation of a radiomic nomogram for the preoperative prediction of lung adenocarcinoma

Background

Accurate diagnosis of early lung cancer from small pulmonary nodules (SPN) is challenging in clinical setting. We aimed to develop a radiomic nomogram to differentiate lung adenocarcinoma from benign SPN.

Methods

This retrospective study included a total of 210 pathologically confirmed SPN (≤ 10 mm) from 197 patients, which were randomly divided into a training dataset (n = 147; malignant nodules, n = 94) and a validation dataset (n = 63; malignant nodules, n = 39). Radiomic features were extracted from the cancerous volumes of interest on contrast-enhanced CT images. The least absolute shrinkage and selection operator (LASSO) regression was used for data dimension reduction, feature selection, and radiomic signature building. Using multivariable logistic regression analysis, a radiomic nomogram was developed incorporating the radiomic signature and the conventional CT signs observed by radiologists. Discrimination and calibration of the radiomic nomogram were evaluated.

Results

The radiomic signature consisting of five radiomic features achieved an AUC of 0.853 (95% confidence interval [CI]: 0.735–0.970), accuracy of 81.0%, sensitivity of 82.9%, and specificity of 77.3%. The two conventional CT signs achieved an AUC of 0.833 (95% CI: 0.707–0.958), accuracy of 65.1%, sensitivity of 53.7%, and specificity of 86.4%. The radiomic nomogram incorporating the radiomic signature and conventional CT signs showed an improved AUC of 0.857 (95% CI: 0.723–0.991), accuracy of 84.1%, sensitivity of 85.4%, and specificity of 81.8%. The radiomic nomogram had good calibration power.

Conclusion

The radiomic nomogram might has the potential to be used as a non-invasive tool for individual prediction of SPN preoperatively. It might facilitate decision-making and improve the management of SPN in the clinical setting.

Evaluating Lung Cancer Screening Across Diverse Healthcare Systems: A Process Model from the Lung PROSPR Consortium

Numerous organizations, including the United States Preventive Services Task Force, recommend annual lung cancer screening (LCS) with low-dose CT for high risk adults who meet specific criteria. Despite recommendations and national coverage for screening eligible adults through the Centers for Medicare and Medicaid Services, LCS uptake in the United States remains low (<4%). In recognition of the need to improve and understand LCS across the population, as part of the larger Population-based Research to Optimize the Screening PRocess (PROSPR) consortium, the NCI (Bethesda, MD) funded the Lung PROSPR Research Consortium consisting of five diverse healthcare systems in Colorado, Hawaii, Michigan, Pennsylvania, and Wisconsin. Using various methods and data sources, the center aims to examine utilization and outcomes of LCS across diverse populations, and assess how variations in the implementation of LCS programs shape outcomes across the screening process. This commentary presents the PROSPR LCS process model, which outlines the interrelated steps needed to complete the screening process from risk assessment to treatment. In addition to guiding planned projects within the Lung PROSPR Research Consortium, this model provides insights on the complex steps needed to implement, evaluate, and improve LCS outcomes in community practice.

Computed Tomography-Based Radiomic Features for Diagnosis of Indeterminate Small Pulmonary Nodules

OBJECTIVE

This study aimed to determine the potential of radiomic features extracted from preoperative computed tomography to discriminate malignant from benign indeterminate small (≤10 mm) pulmonary nodules.

METHODS

A total of 197 patients with 210 nodules who underwent surgical resections between January 2011 and March 2017 were analyzed. Three hundred eighty-five radiomic features were extracted from the computed tomographic images. Feature selection and data dimension reduction were performed using the Kruskal-Wallis test, Spearman correlation analysis, and principal component analysis. The random forest was used for radiomic signature building. The receiver operating characteristic curve analysis was used to evaluate the model performance.

RESULTS

Fifteen principal component features were selected for modeling. The area under the curve, sensitivity, specificity, and accuracy of the prediction model were 0.877 (95% confidence interval [CI], 0.795-0.959), 81.8% (95% CI, 72.0%-90.9%), 77.4% (95% CI, 63.9%-89.3%), and 80.0% (95% CI, 72.0%-86.7%) in the validation cohort, respectively.

CONCLUSIONS

Computed tomography-based radiomic features showed good discriminative power for benign and malignant indeterminate small pulmonary nodules.

Common mental disorders in Taiwanese consumers of commercial low-dose computed tomography lung cancer screening: Comparison with a nationally representative sample

BACKGROUND/PURPOSE

We examined the prevalence of probable common mental disorders (CMDs) in commercial low-dose computed tomography (LDCT) lung cancer screening consumers relative to the general population and to determine the correlates of probable CMDs among screening participants.

METHODS

Commercial LDCT lung cancer screening consumers (N = 1323) were compared with a nationally representative sample from the Taiwan Social Change Survey (TSCS) (N = 2034). Respondents scoring ≥3 on the Chinese Health Questionnaire were classified as having a probable CMD. Logistic regression was used to investigate differences between the two groups and correlates of probable CMDs among LDCT lung cancer screening participants.

RESULTS

The prevalence of probable CMDs was higher among LDCT lung cancer screening participants (25.47%) than among TSCS adults (21.56%). Compared with the TSCS sample, the screening participants had a higher probability of CMDs (OR = 1.40, 95% CI = 1.13-1.73), higher education levels (OR = 7.95, 95% CI = 6.00-10.53), and a history of drinking (OR = 11.85, 95% CI = 9.45-14.85) or betel-quid use (OR = 5.43, 95% CI = 3.98-7.42) but were less likely to smoke (OR = 0.52, 95% CI = 0.40-0.68). Among the screening participants, being female (OR = 1.37, 95% CI = 1.02-1.84) and a current smoker (OR = 1.74, 1.19-2.54) and living near ≥2 smoking family members (OR = 2.30, 95% CI 1.57-3.38) were associated with an increased likelihood of having CMDs.

CONCLUSION

Commercial LDCT lung cancer screening users may have a positive association with probable CMDs compared to the general population. Screening programs should consider including criteria and providing psychoeducation to improve the physical and mental outcomes of participants.

CLINICAL TRIAL REGISTRATION

Purely observational studies (those in which the assignment of the medical intervention is not at the discretion of the investigator) do not require registration.

Effect of a New Model-Based Reconstruction Algorithm for Evaluating Early Peripheral Lung Cancer With Submillisievert Chest Computed Tomography

OBJECTIVE

The aim of this study was to compare a new model-based iterative reconstruction algorithm with either spatial and density resolution balance (MBIRSTND) or spatial resolution preference (MBIRRP20) with the adaptive statistical iterative reconstruction (ASIR) in evaluating early small peripheral lung cancer (SPLC) with submillisievert chest computed tomography (CT).

METHODS

Low-contrast and spatial resolutions were assessed in a phantom and with 30 pathologically confirmed SPLC patients. Images were reconstructed using 40% ASIR, MBIRSTND, and MBIRRP20. Computed tomography value and image noise were measured by placing the regions of interest on back muscle and subcutaneous fat at 3 levels. Two radiologists used a 4-point scale (1, worst, and 4, best) to rate subjective image quality in 3 aspects: image noise, nodule imaging signs, and nodule internal clarity.

RESULTS

The phantom study revealed an improved detectability of low-contrast targets and small objects for MBIRSTND and MBIRRP20 compared with ASIR. The effective dose for patient scans was 0.88 ± 0.83 mSv. There was no significant difference in CT value between the 3 reconstructions (P > 0.05), but MBIRSTND and MBIRRP20 significantly reduced image noise compared with ASIR (P < 0.05): 15.69 ± 1.83 HU and 29.97 ± 3.84 HU versus 51.06 ± 11.02 HU in the back muscle, and 15.96 ± 3.07 HU and 27.37 ± 3.88 HU versus 38.04 ± 8.87 HU in subcutaneous fat, respectively. Among the 3 reconstructions, MBIRSTND was the best in reducing image noise and identifying the internal compositions of cancer nodules, and MBIRRP20 was the best in analyzing the internal and external signs of pulmonary nodules.

CONCLUSIONS

Submillisievert chest CT reconstructed with MBIRSTND and MBIRRP20 provides superior images for the detailed analyses of SPLC compared with ASIR.

IILS: Intelligent imaging layout system for automatic imaging report standardization and intra-interdisciplinary clinical workflow optimization

Background

To achieve imaging report standardization and improve the quality and efficiency of the intra-interdisciplinary clinical workflow, we proposed an intelligent imaging layout system (IILS) for a clinical decision support system-based ubiquitous healthcare service, which is a lung nodule management system using medical images.

Methods

We created a lung IILS based on deep learning for imaging report standardization and workflow optimization for the identification of nodules. Our IILS utilized a deep learning plus adaptive auto layout tool, which trained and tested a neural network with imaging data from all the main CT manufacturers from 11,205 patients. Model performance was evaluated by the receiver operating characteristic curve (ROC) and calculating the corresponding area under the curve (AUC). The clinical application value for our IILS was assessed by a comprehensive comparison of multiple aspects.

Findings

Our IILS is clinically applicable due to the consistency with nodules detected by IILS, with its highest consistency of 0·94 and an AUC of 90·6% for malignant pulmonary nodules versus benign nodules with a sensitivity of 76·5% and specificity of 89·1%. Applying this IILS to a dataset of chest CT images, we demonstrate performance comparable to that of human experts in providing a better layout and aiding in diagnosis in 100% valid images and nodule display. The IILS was superior to the traditional manual system in performance, such as reducing the number of clicks from 14·45 ± 0·38 to 2, time consumed from 16·87 ± 0·38 s to 6·92 ± 0·10 s, number of invalid images from 7·06 ± 0·24 to 0, and missing lung nodules from 46·8% to 0%.

Interpretation

This IILS might achieve imaging report standardization, and improve the clinical workflow therefore opening a new window for clinical application of artificial intelligence.

Fund

The National Natural Science Foundation of China.

Implementation planning for lung cancer screening in China

Lung cancer is the leading cause of cancer-related deaths in China, with over 690 000 lung cancer deaths estimated in 2018. The mortality has increased about five-fold from the mid-1970s to the 2000s. Lung cancer low-dose computerized tomography (LDCT) screening in smokers was shown to improve survival in the US National Lung Screening Trial, and more recently in the European NELSON trial. However, although the predominant risk factor, smoking contributes to a lower fraction of lung cancers in China than in the UK and USA. Therefore, it is necessary to establish Chinese-specific screening strategies. There have been 23 associated programmes completed or still ongoing in China since the 1980s, mainly after 2000; and one has recently been planned. Generally, their entry criteria are not smoking-stringent. Most of the Chinese programmes have reported preliminary results only, which demonstrated a different high-risk subpopulation of lung cancer in China. Evidence concerning LDCT screening implementation is based on results of randomized controlled trials outside China. LDCT screening programmes combining tobacco control would produce more benefits. Population recruitment (e.g. risk-based selection), screening protocol, nodule management and cost-effectiveness are discussed in detail. In China, the high-risk subpopulation eligible for lung cancer screening has not as yet been confirmed, as all the risk parameters have not as yet been determined. Although evidence on best practice for implementation of lung cancer screening has been accumulating in other countries, further research in China is urgently required, as China is now facing a lung cancer epidemic.

MR Volumetry of Lung Nodules: A Pilot Study

Introduction: Computed tomography (CT) is currently the reference modality for the detection and follow-up of pulmonary nodules. While 2D measurements are commonly used in clinical practice to assess growth, increasingly 3D volume measurements are being recommended. The goal of this pilot study was to evaluate preliminarily the capabilities of 3D MRI using ultra-short echo time for lung nodule volumetry, as it would provide a radiation-free modality for this task. Material and Methods: Artificial nodules were manufactured out of Agar and measured using an ultra-short echo time MRI sequence. CT data were also acquired as a reference. Image segmentation was carried out using an algorithm based on signal intensity thresholding (SIT). For comparison purposes, we also performed manual slice by slice segmentation. Volumes obtained with MRI and CT were compared. Finally, the volumetry of a lung nodule was evaluated in one human subject in comparison with CT. Results: Using the SIT technique, minimal bias was observed between CT and MRI across the entire range of volumes (2%) with limits of agreement below 14%. Comparison of manually segmented MRI and CT resulted in a larger bias (8%) and wider limits of agreement (-23% to 40%). In vivo, nodule volume differed of <16% between modalities with the SIT technique. Conclusion: This pilot study showed very good concordance between CT and UTE-MRI to quantify lung nodule volumes, in both a phantom and human setting. Our results enhance the potential of MRI to quantify pulmonary nodule volume with similar performance to CT.

The clinical significance of indeterminate pulmonary nodules in melanoma patients at baseline and during follow-up chest CT

Objective

This study aims to determine an appropriate timeline to monitor indeterminate pulmonary nodules (IPN) in melanoma patients to confirm metastatic origin.

Materials and Methods

588 clinically non-metastatic melanoma patients underwent curative intent surgery during 3 years. Patients with baseline chest CT and at least one follow-up (FU) CT were retrospectively analyzed to assess for IPN. Patients with definitely benign nodules, metastases and non-melanoma malignancies were excluded. Change in volume from first to FU CT, initial diameter (D1) and volume (V1), distance from pleura, peripheral and perifissural location, density and clinical stage were evaluated. Nodules were volumetrically measured on CTs and were considered metastases if they increased in size between two CTs or if increase was accompanied by multiple new nodules or extrapulmonary metastases.

Results

148 patients were included. Two out of 243 baseline IPN detected in 70 patients, increased significantly in volume in 3 and 5 months and were proven metastases. During FU, 86% of 40 interval IPN detected in 28 patients, were proven metastases. Interval nodule (p < 0.0001, HR:243,CI:[57.32,1033.74]), 3-month volume change (OR:1.023,CI:[1.014,1.033]), V1 (OR:1.006,CI:[1.003,1.009]), D1 (OR:1.424,CI:[1.23,1.648]), distance from pleura (OR:1.03,CI:[1.003,1.059]), and combined stage IIC + III (OR:11.29,CI:[1.514,84.174]), were associated with increased risk for metastasis. 43%, 72% and 94% of patients with IPN were confirmed with metastases in the first FU CT at 3, 6 and 12 months respectively.

Conclusion

Baseline IPN are most likely benign, while interval IPN are high risk for metastasis. Absence of volume increase of IPN within 6 months excluded metastasis in most patients.

Computer-Aided Detection of Pulmonary Nodules in Computed Tomography Using ClearReadCT

This study evaluates the accuracy of a computer-aided detection (CAD) application for pulmonary nodular lesions (PNL) in computed tomography (CT) scans, the ClearReadCT (Riverain Technologies). The study was retrospective for 106 biopsied PNLs from 100 patients. Seventy-five scans were Contrast-Enhanced (CECT) and 25 received no enhancer (NECT). Axial reconstructions in soft-tissue and lung kernel were applied at three different slice thicknesses, 0.75 mm (CECT/NECT n = 25/6), 1.5 mm (n = 18/9) and 3.0 mm (n = 43/18). We questioned the effect of (1) enhancer, (2) kernel and (3) slice thickness on the CAD performance. Our main findings are: (1) Vessel suppression is effective and specific in both NECT and CECT. (2) Contrast enhancement significantly increased the CAD sensitivity from 60% in NECT to 80% in CECT, P = 0.025 Fischer's exact test. (3) The CAD sensitivity was 84% in 3 mm slices compared to 68% in 0.75 mm slices, P > 0.2 Fischer's exact test. (4) Small lesions of low attenuation were detected with higher sensitivity. (5) Lung kernel reconstructions increased the false positive rate without affecting the sensitivity (P > 0.05 McNemar's test). In conclusion, ClearReadCT showed an optimized sensitivity of 84% and a positive predictive value of 67% in enhanced lung scans with thick, soft kernel reconstructions. NECT, thin slices and lung kernel reconstruction were associated with inferior performance.

Current Practice in the Management of Pulmonary Nodules Detected on Computed Tomography Chest Scans

Lung cancer is associated with high mortality. It can present as one or more pulmonary nodules identified on computed tomography (CT) chest scans. The National Lung Screening Trial has shown that the use of low-dose CT chest screening can reduce deaths due to lung cancer. High adherence to appropriate follow-up of positive results, including imaging or interventional approaches, is an important aspect of pulmonary nodule management. Our study is one of the first to evaluate the current practice in managing pulmonary nodules and to explore potential causes for nonadherence to follow-up. This is a retrospective analysis at St. Paul's Hospital, a tertiary healthcare center in Vancouver, British Columbia, Canada. We first identified CT chest scans between January 1 to June 30, 2014, that demonstrated one or more pulmonary nodules equal to or greater than 6 mm in diameter. We then looked for evidence of interventional (surgical resection or biopsy, or bronchoscopy for transbronchial biopsy and cytology) and radiological follow-up of the pulmonary nodule by searching on the province-wide CareConnect eHealth Viewer patient database. A total of 1614 CT reports were analyzed and 139 (8.6%) had a positive finding. Out of the 97 patients who received follow-up, 54.6% (N = 53) was referred for a repeat CT chest scan and 36.1% (N = 35) and 9.3% (N = 9) were referred for interventional biopsy and surgical resection, respectively. In our study, 30.2% (N = 42) of the patients with pulmonary nodules were nonadherent to follow-up. Despite the radiologist's recommendation for follow-up within a certain time interval, only 36% had repeat imaging in a timely manner. Our findings reflect the current practice in the management of pulmonary nodules and suggest that there is a need for improvement at our academic center. Adherence to follow-up is important for the potentially near-future implementation of lung cancer screening.

Recognising Lung Cancer in Primary Care

Significant advances in the management of both early and advanced stage lung cancer have not yet led to the scale of improved outcomes which have been achieved in other cancers over the last 40 years. Diagnosis of lung cancer at the earliest stage of disease is strongly associated with improved survival. Therefore, although recent advances in oncology may herald breakthroughs in effective treatment, achieving early diagnosis will remain crucial to obtaining optimal outcomes. This is challenging, as most lung cancer symptoms are non-specific or are common respiratory symptoms which usually represent benign disease. Identification of patients at risk of lung cancer who require further investigation is an important responsibility for general practitioners (GPs). Diagnosis has historically relied upon plain chest X-ray (CXR), organised in response to symptoms. The sensitivity of this modality, however, compares unfavourably with that of computed tomography (CT). In some jurisdictions screening high-risk individuals with low dose CT (LDCT) is now recommended. However uptake remains low and the eligibility for screening programmes is restricted. Therefore, even if screening is widely adopted, most patients will continue to be diagnosed after presenting with symptoms. Achieving early diagnosis requires GPs to maintain an appropriate level of suspicion and readiness to investigate in high-risk patients or those with non-resolving symptoms. This article discusses the early detection of lung cancer from a primary care perspective. We outline risk factors and epidemiology, the role of screening and offer guidance on the recognition of symptomatic presentation and the investigation and referral of suspected lung cancer.

A Gene Expression Classifier from Whole Blood Distinguishes Benign from Malignant Lung Nodules Detected by Low-Dose CT

Low-dose CT (LDCT) is widely accepted as the preferred method for detecting pulmonary nodules. However, the determination of whether a nodule is benign or malignant involves either repeated scans or invasive procedures that sample the lung tissue. Noninvasive methods to assess these nodules are needed to reduce unnecessary invasive tests. In this study, we have developed a pulmonary nodule classifier (PNC) using RNA from whole blood collected in RNA-stabilizing PAXgene tubes that addresses this need. Samples were prospectively collected from high-risk and incidental subjects with a positive lung CT scan. A total of 821 samples from 5 clinical sites were analyzed. Malignant samples were predominantly stage 1 by pathologic diagnosis and 97% of the benign samples were confirmed by 4 years of follow-up. A panel of diagnostic biomarkers was selected from a subset of the samples assayed on Illumina microarrays that achieved a ROC-AUC of 0.847 on independent validation. The microarray data were then used to design a biomarker panel of 559 gene probes to be validated on the clinically tested NanoString nCounter platform. RNA from 583 patients was used to assess and refine the NanoString PNC (nPNC), which was then validated on 158 independent samples (ROC-AUC = 0.825). The nPNC outperformed three clinical algorithms in discriminating malignant from benign pulmonary nodules ranging from 6-20 mm using just 41 diagnostic biomarkers. Overall, this platform provides an accurate, noninvasive method for the diagnosis of pulmonary nodules in patients with non-small cell lung cancer. SIGNIFICANCE: These findings describe a minimally invasive and clinically practical pulmonary nodule classifier that has good diagnostic ability at distinguishing benign from malignant pulmonary nodules.

CNN models discriminating between pulmonary micro-nodules and non-nodules from CT images

Background

Early and automatic detection of pulmonary nodules from CT lung screening is the prerequisite for precise management of lung cancer. However, a large number of false positives appear in order to increase the sensitivity, especially for detecting micro-nodules (diameter < 3 mm), which increases the radiologists’ workload and causes unnecessary anxiety for the patients. To decrease the false positive rate, we propose to use CNN models to discriminate between pulmonary micro-nodules and non-nodules from CT image patches.

Methods

A total of 13,179 micro-nodules and 21,315 non-nodules marked by radiologists are extracted with three different patch sizes (16 × 16, 32 × 32 and 64 × 64) from LIDC/IDRI database and used in the experiments. Three CNN models with different depths (1, 2 or 4 convolutional layers) are designed; their performances are evaluated by the fivefold cross-validation in term of the accuracy, area under the curve (AUC), F-score and sensitivity. The network parameters are also optimized.

Results

It is found that the performance of the CNN models is greatly dependent on the patches size and the number of convolutional layers. The CNN model with two convolutional layers presented the best performance in case of 32 × 32 patches size, achieving an accuracy of 88.28%, an AUC of 0.87, a F-score of 83.45% and a sensitivity of 83.82%.

Conclusions

The CNN models with appropriate depth and size of image patches can effectively discriminate between pulmonary micro-nodules and non-nodules, and reduce the false positives and help manage lung cancer precisely.

Analysis of the clinicopathological characteristics and their trends among patients with lung cancer undergoing surgery in a tertiary cancer hospital of north China during 2000-2013

BACKGROUND

Lung cancer is the primary cause of death among all cancers in China. However, clinical and pathological features and trends among patients with lung cancer in mainland China are largely unknown. This study analyzed the clinicopathological characteristics and trends of patients newly diagnosed as lung cancer and underwent surgery in a tertiary cancer hospital of north China between 2000 and 2013.

METHODS

Data were collected retrospectively from medical records. Pathological diagnosis was confirmed by surgery or puncture, bronchoscopy, thoracoscopy, and sputum cytology.

RESULTS

This study included 3,733 patients with lung cancer (2,252 male and 1,481 female; male-to-female 1.52:1). An increase in the incidence of lung cancer was observed among women. The most frequently observed pathology types were adenocarcinoma (ADC, 63.41%), squamous cell carcinoma (SQ, 24.48%), and small cell carcinoma (SCC, 3.08%). There was a decrease in the proportion of SQ cases and increase in ADC cases. The proportion of male patients with SQ and female patients with ADC increased. Differences between men and women in the distribution of lesions according to pathology were as follows: ADC and SQ were present in 49.73% and 35.92% of male patients, respectively, and in 84.20% and 7.09% of female patients, respectively. Comparing the time period 2000-2006 and 2007-2013, there were no changes in the distribution of pathology among men, while the proportion of ADC and SQ cases among women increased from 74.43% to 85.90% and decreased from 15.07% to 5.71%, respectively.

CONCLUSIONS

The proportion of female patients with lung cancer who could undergo surgery increased significantly. The proportion of patients with SQ decreased while that of ADC increased, and the increase of ADC was mainly due to the increase in the number of female patients with ADC.

Localized thin-section CT with radiomics feature extraction and machine learning to classify early-detected pulmonary nodules from lung cancer screening

Lung cancer screening aims to detect small pulmonary nodules and decrease the mortality rate of those affected. However, studies from large-scale clinical trials of lung cancer screening have shown that the false-positive rate is high and positive predictive value is low. To address these problems, a technical approach is greatly needed for accurate malignancy differentiation among these early-detected nodules. We studied the clinical feasibility of an additional protocol of localized thin-section CT for further assessment on recalled patients from lung cancer screening tests. Our approach of localized thin-section CT was integrated with radiomics features extraction and machine learning classification which was supervised by pathological diagnosis. Localized thin-section CT images of 122 nodules were retrospectively reviewed and 374 radiomics features were extracted. In this study, 48 nodules were benign and 74 malignant. There were nine patients with multiple nodules and four with synchronous multiple malignant nodules. Different machine learning classifiers with a stratified ten-fold cross-validation were used and repeated 100 times to evaluate classification accuracy. Of the image features extracted from the thin-section CT images, 238 (64%) were useful in differentiating between benign and malignant nodules. These useful features include CT density (p  =  0.002 518), sigma (p  =  0.002 781), uniformity (p  =  0.032 41), and entropy (p  =  0.006 685). The highest classification accuracy was 79% by the logistic classifier. The performance metrics of this logistic classification model was 0.80 for the positive predictive value, 0.36 for the false-positive rate, and 0.80 for the area under the receiver operating characteristic curve. Our approach of direct risk classification supervised by the pathological diagnosis with localized thin-section CT and radiomics feature extraction may support clinical physicians in determining truly malignant nodules and therefore reduce problems in lung cancer screening.

Biomarker development in the precision medicine era: lung cancer as a case study

Precision medicine relies on validated biomarkers with which to better classify patients by their probable disease risk, prognosis and/or response to treatment. Although affordable 'omics'-based technology has enabled faster identification of putative biomarkers, the validation of biomarkers is still stymied by low statistical power and poor reproducibility of results. This Review summarizes the successes and challenges of using different types of molecule as biomarkers, using lung cancer as a key illustrative example. Efforts at the national level of several countries to tie molecular measurement of samples to patient data via electronic medical records are the future of precision medicine research.