Comparing Lung Cancer Screening Strategies in a Nationally Representative US Population Using Transportability Methods for the National Lung Cancer Screening Trial.

Importance: The National Lung Screening Trial (NLST) found that screening for lung cancer with low-dose computed tomography (CT) reduced lung cancer-specific and all-cause mortality compared with chest radiography. It is uncertain whether these results apply to a nationally representative target population. Objective: To extend inferences about the effects of lung cancer screening strategies from the NLST to a nationally representative target population of NLST-eligible US adults. Design, Setting, and Participants: This comparative effectiveness study included NLST data from US adults at 33 participating centers enrolled between August 2002 and April 2004 with follow-up through 2009 along with National Health Interview Survey (NHIS) cross-sectional household interview survey data from 2010. Eligible participants were adults aged 55 to 74 years, and were current or former smokers with at least 30 pack-years of smoking (former smokers were required to have quit within the last 15 years). Transportability analyses combined baseline covariate, treatment, and outcome data from the NLST with covariate data from the NHIS and reweighted the trial data to the target population. Data were analyzed from March 2020 to May 2023. Interventions: Low-dose CT or chest radiography screening with a screening assessment at baseline, then yearly for 2 more years. Main Outcomes and Measures: For the outcomes of lung-cancer specific and all-cause death, mortality rates, rate differences, and ratios were calculated at a median (25th percentile and 75th percentile) follow-up of 5.5 (5.2-5.9) years for lung cancer-specific mortality and 6.5 (6.1-6.9) years for all-cause mortality. Results: The transportability analysis included 51 274 NLST participants and 685 NHIS participants representing the target population (of approximately 5 700 000 individuals after survey-weighting). Compared with the target population, NLST participants were younger (median [25th percentile and 75th percentile] age, 60 [57 to 65] years vs 63 [58 to 67] years), had fewer comorbidities (eg, heart disease, 6551 of 51 274 [12.8%] vs 1 025 951 of 5 739 532 [17.9%]), and were more educated (bachelor's degree or higher, 16 349 of 51 274 [31.9%] vs 859 812 of 5 739 532 [15.0%]). In the target population, for lung cancer-specific mortality, the estimated relative rate reduction was 18% (95% CI, 1% to 33%) and the estimated absolute rate reduction with low-dose CT vs chest radiography was 71 deaths per 100 000 person-years (95% CI, 4 to 138 deaths per 100 000 person-years); for all-cause mortality the estimated relative rate reduction was 6% (95% CI, -2% to 12%). In the NLST, for lung cancer-specific mortality, the estimated relative rate reduction was 21% (95% CI, 9% to 32%) and the estimated absolute rate reduction was 67 deaths per 100 000 person-years (95% CI, 27 to 106 deaths per 100 000 person-years); for all-cause mortality, the estimated relative rate reduction was 7% (95% CI, 0% to 12%). Conclusions and Relevance: Estimates of the comparative effectiveness of low-dose CT screening compared with chest radiography in a nationally representative target population were similar to those from unweighted NLST analyses, particularly on the relative scale. Increased uncertainty around effect estimates for the target population reflects large differences in the observed characteristics of trial participants and the target population.

Expanding Role of Advanced Image Analysis in CT-detected Indeterminate Pulmonary Nodules and Early Lung Cancer Characterization.

The implementation of low-dose chest CT for lung screening presents a crucial opportunity to advance lung cancer care through early detection and interception. In addition, millions of pulmonary nodules are incidentally detected annually in the United States, increasing the opportunity for early lung cancer diagnosis. Yet, realization of the full potential of these opportunities is dependent on the ability to accurately analyze image data for purposes of nodule classification and early lung cancer characterization. This review presents an overview of traditional image analysis approaches in chest CT using semantic characterization as well as more recent advances in the technology and application of machine learning models using CT-derived radiomic features and deep learning architectures to characterize lung nodules and early cancers. Methodological challenges currently faced in translating these decision aids to clinical practice, as well as the technical obstacles of heterogeneous imaging parameters, optimal feature selection, choice of model, and the need for well-annotated image data sets for the purposes of training and validation, will be reviewed, with a view toward the ultimate incorporation of these potentially powerful decision aids into routine clinical practice.

The Liquid Biopsy Consortium: Challenges and opportunities for early cancer detection and monitoring.

The emerging field of liquid biopsy stands at the forefront of novel diagnostic strategies for cancer and other diseases. Liquid biopsy allows minimally invasive molecular characterization of cancers for diagnosis, patient stratification to therapy, and longitudinal monitoring. Liquid biopsy strategies include detection and monitoring of circulating tumor cells, cell-free DNA, and extracellular vesicles. In this review, we address the current understanding and the role of existing liquid-biopsy-based modalities in cancer diagnostics and monitoring. We specifically focus on the technical and clinical challenges associated with liquid biopsy and biomarker development being addressed by the Liquid Biopsy Consortium, established through the National Cancer Institute. The Liquid Biopsy Consortium has developed new methods/assays and validated existing methods/technologies to capture and characterize tumor-derived circulating cargo, as well as addressed existing challenges and provided recommendations for advancing biomarker assays.

Comprehensive tissue deconvolution of cell-free DNA by deep learning for disease diagnosis and monitoring.

Plasma cell-free DNA (cfDNA) is a noninvasive biomarker for cell death of all organs. Deciphering the tissue origin of cfDNA can reveal abnormal cell death because of diseases, which has great clinical potential in disease detection and monitoring. Despite the great promise, the sensitive and accurate quantification of tissue-derived cfDNA remains challenging to existing methods due to the limited characterization of tissue methylation and the reliance on unsupervised methods. To fully exploit the clinical potential of tissue-derived cfDNA, here we present one of the largest comprehensive and high-resolution methylation atlas based on 521 noncancer tissue samples spanning 29 major types of human tissues. We systematically identified fragment-level tissue-specific methylation patterns and extensively validated them in orthogonal datasets. Based on the rich tissue methylation atlas, we develop the first supervised tissue deconvolution approach, a deep-learning-powered model, cfSort, for sensitive and accurate tissue deconvolution in cfDNA. On the benchmarking data, cfSort showed superior sensitivity and accuracy compared to the existing methods. We further demonstrated the clinical utilities of cfSort with two potential applications: aiding disease diagnosis and monitoring treatment side effects. The tissue-derived cfDNA fraction estimated from cfSort reflected the clinical outcomes of the patients. In summary, the tissue methylation atlas and cfSort enhanced the performance of tissue deconvolution in cfDNA, thus facilitating cfDNA-based disease detection and longitudinal treatment monitoring.

Single-Cell Characterization of Pulmonary Nodules Implicates Suppression of Immunosurveillance across Early Stages of Lung Adenocarcinoma.

A greater understanding of molecular, cellular, and immunological changes during the early stages of lung adenocarcinoma development could improve diagnostic and therapeutic approaches in patients with pulmonary nodules at risk for lung cancer. To elucidate the immunopathogenesis of early lung tumorigenesis, we evaluated surgically resected pulmonary nodules representing the spectrum of early lung adenocarcinoma as well as associated normal lung tissues using single-cell RNA sequencing and validated the results by flow cytometry and multiplex immunofluorescence (MIF). Single-cell transcriptomics revealed a significant decrease in gene expression associated with cytolytic activities of tumor-infiltrating natural killer and natural killer T cells. This was accompanied by a reduction in effector T cells and an increase of CD4+ regulatory T cells (Treg) in subsolid nodules. An independent set of resected pulmonary nodules consisting of both adenocarcinomas and associated premalignant lesions corroborated the early increment of Tregs in premalignant lesions compared with the associated normal lung tissues by MIF. Gene expression analysis indicated that cancer-associated alveolar type 2 cells and fibroblasts may contribute to the deregulation of the extracellular matrix, potentially affecting immune infiltration in subsolid nodules through ligand-receptor interactions. These findings suggest that there is a suppression of immune surveillance across the spectrum of early-stage lung adenocarcinoma. SIGNIFICANCE: Analysis of a spectrum of subsolid pulmonary nodules by single-cell RNA sequencing provides insights into the immune regulation and cell-cell interactions in the tumor microenvironment during early lung tumor development.

Factors Associated With Nonadherence to Lung Cancer Screening Across Multiple Screening Time Points.

Importance: Screening with low-dose computed tomography (CT) has been shown to reduce mortality from lung cancer in randomized clinical trials in which the rate of adherence to follow-up recommendations was over 90%; however, adherence to Lung Computed Tomography Screening Reporting & Data System (Lung-RADS) recommendations has been low in practice. Identifying patients who are at risk of being nonadherent to screening recommendations may enable personalized outreach to improve overall screening adherence. Objective: To identify factors associated with patient nonadherence to Lung-RADS recommendations across multiple screening time points. Design, Setting, and Participants: This cohort study was conducted at a single US academic medical center across 10 geographically distributed sites where lung cancer screening is offered. The study enrolled individuals who underwent low-dose CT screening for lung cancer between July 31, 2013, and November 30, 2021. Exposures: Low-dose CT screening for lung cancer. Main Outcomes and Measures: The main outcome was nonadherence to follow-up recommendations for lung cancer screening, defined as failing to complete a recommended or more invasive follow-up examination (ie, diagnostic dose CT, positron emission tomography-CT, or tissue sampling vs low-dose CT) within 15 months (Lung-RADS score, 1 or 2), 9 months (Lung-RADS score, 3), 5 months (Lung-RADS score, 4A), or 3 months (Lung-RADS score, 4B/X). Multivariable logistic regression was used to identify factors associated with patient nonadherence to baseline Lung-RADS recommendations. A generalized estimating equations model was used to assess whether the pattern of longitudinal Lung-RADS scores was associated with patient nonadherence over time. Results: Among 1979 included patients, 1111 (56.1%) were aged 65 years or older at baseline screening (mean [SD] age, 65.3 [6.6] years), and 1176 (59.4%) were male. The odds of being nonadherent were lower among patients with a baseline Lung-RADS score of 1 or 2 vs 3 (adjusted odds ratio [AOR], 0.35; 95% CI, 0.25-0.50), 4A (AOR, 0.21; 95% CI, 0.13-0.33), or 4B/X, (AOR, 0.10; 95% CI, 0.05-0.19); with a postgraduate vs college degree (AOR, 0.70; 95% CI, 0.53-0.92); with a family history of lung cancer vs no family history (AOR, 0.74; 95% CI, 0.59-0.93); with a high age-adjusted Charlson Comorbidity Index score (≥4) vs a low score (0 or 1) (AOR, 0.67; 95% CI, 0.46-0.98); in the high vs low income category (AOR, 0.79; 95% CI, 0.65-0.98); and referred by physicians from pulmonary or thoracic-related departments vs another department (AOR, 0.56; 95% CI, 0.44-0.73). Among 830 eligible patients who had completed at least 2 screening examinations, the adjusted odds of being nonadherent to Lung-RADS recommendations at the following screening were increased in patients with consecutive Lung-RADS scores of 1 to 2 (AOR, 1.38; 95% CI, 1.12-1.69). Conclusions and Relevance: In this retrospective cohort study, patients with consecutive negative lung cancer screening results were more likely to be nonadherent with follow-up recommendations. These individuals are potential candidates for tailored outreach to improve adherence to recommended annual lung cancer screening.

Bronchial gene expression alterations associated with radiological bronchiectasis.

OBJECTIVES: Discovering airway gene expression alterations associated with radiological bronchiectasis may improve the understanding of the pathobiology of early-stage bronchiectasis. METHODS: Presence of radiological bronchiectasis in 173 individuals without a clinical diagnosis of bronchiectasis was evaluated. Bronchial brushings from these individuals were transcriptomically profiled and analysed. Single-cell deconvolution was performed to estimate changes in cellular landscape that may be associated with early disease progression. RESULTS: 20 participants have widespread radiological bronchiectasis (three or more lobes). Transcriptomic analysis reflects biological processes associated with bronchiectasis including decreased expression of genes involved in cell adhesion and increased expression of genes involved in inflammatory pathways (655 genes, false discovery rate <0.1, log2 fold-change >0.25). Deconvolution analysis suggests that radiological bronchiectasis is associated with an increased proportion of ciliated and deuterosomal cells, and a decreased proportion of basal cells. Gene expression patterns separated participants into three clusters: normal, intermediate and bronchiectatic. The bronchiectatic cluster was enriched by participants with more lobes of radiological bronchiectasis (p<0.0001), more symptoms (p=0.002), higher SERPINA1 mutation rates (p=0.03) and higher computed tomography derived bronchiectasis scores (p<0.0001). CONCLUSIONS: Genes involved in cell adhesion, Wnt signalling, ciliogenesis and interferon-γ pathways had altered expression in the bronchus of participants with widespread radiological bronchiectasis, possibly associated with decreased basal and increased ciliated cells. This gene expression pattern is not only highly enriched among individuals with radiological bronchiectasis, but also associated with airway-related symptoms in those without discernible radiological bronchiectasis, suggesting that it reflects a bronchiectasis-associated, but non-bronchiectasis-specific lung pathophysiological process.

Cost-effective methylome sequencing of cell-free DNA for accurately detecting and locating cancer.

Early cancer detection by cell-free DNA faces multiple challenges: low fraction of tumor cell-free DNA, molecular heterogeneity of cancer, and sample sizes that are not sufficient to reflect diverse patient populations. Here, we develop a cancer detection approach to address these challenges. It consists of an assay, cfMethyl-Seq, for cost-effective sequencing of the cell-free DNA methylome (with > 12-fold enrichment over whole genome bisulfite sequencing in CpG islands), and a computational method to extract methylation information and diagnose patients. Applying our approach to 408 colon, liver, lung, and stomach cancer patients and controls, at 97.9% specificity we achieve 80.7% and 74.5% sensitivity in detecting all-stage and early-stage cancer, and 89.1% and 85.0% accuracy for locating tissue-of-origin of all-stage and early-stage cancer, respectively. Our approach cost-effectively retains methylome profiles of cancer abnormalities, allowing us to learn new features and expand to other cancer types as training cohorts grow.

Patient Adherence to Lung CT Screening Reporting & Data System-Recommended Screening Intervals in the United States: A Systematic Review and Meta-Analysis.

Lung cancer screening (LCS) is effective in reducing mortality, particularly when patients adhere to follow-up recommendations standardized by the Lung CT Screening Reporting & Data System (Lung-RADS). Nevertheless, patient adherence to recommended intervals varies, potentially diminishing benefit from screening. We conducted a systematic review and meta-analysis of patient adherence to Lung-RADS-recommended screening intervals. We systematically searched MEDLINE, EMBASE, Web of Science, the Cochrane Central Register of Controlled Trials, and major radiology and oncology conference archives between April 28, 2014, and December 17, 2020. Eligible studies mentioned patient adherence to the recommendations of Lung-RADS. The review protocol was registered with PROSPERO (CRD42020189326). We identified 24 eligible studies for qualitative summary, of which 21 were suitable for meta-analysis. The pooled adherence rate was 57% (95% confidence interval: 46%-69%) for defined adherence (e.g., an annual incidence screen was performed within 15 mo) among 6689 patients and 65% (95% confidence interval: 55%-75%) for anytime adherence among 5085 patients. Large heterogeneity in adherence rates between studies was observed (I2 = 99% for defined adherence, I2 = 98% for anytime adherence). Heterogeneous adherence rates were associated with Lung-RADS scores, with significantly higher adherence rates among Lung-RADS 3 to 4 than Lung-RADS 1 to 2 (p < 0.05). Patient adherence to Lung-RADS-recommended screening intervals is suboptimal across clinical LCS programs in the United States, especially among patients with results of Lung-RADS categories 1 to 2. To improve adherence rates, future research may focus on implementing tailored interventions after identifying barriers to LCS. We also propose a minimum standardized set of data elements for future pooled analyses of LCS adherence on the basis of our findings.

Capturing Demographic, Health-Related, and Psychosocial Variables in a Standardized Manner: Towards Improving Cancer Screening Adherence.

Determining factors influencing patient participation in and adherence to cancer screening recommendations is key to successful cancer screening programs. However, the collection of variables necessary to anticipate patient behavior in cancer screening has not been systematically examined. Using lung cancer screening as a representative example, we conducted an exploratory analysis to characterize the current representations of 18 demographic, health-related, and psychosocial variables collected as part of a conceptual model to understand factors for lung cancer screening participation and adherence. Our analysis revealed a lack of standardization in controlled terminologies and common data elements for these variables. For example, only eight (44%) demographic and health-related variables were recorded consistently in the electronic health record. Multiple survey instruments could collect the remaining variables but were highly inconsistent in how variables were represented. This analysis suggests opportunities to establish standardized data formats for psychological, cognitive, social, and environmental variables to improve data collection.

Generalizability and Transportability of the National Lung Screening Trial Data: Extending Trial Results to Different Populations.

BACKGROUND: Randomized controlled trials (RCT) play a central role in evidence-based healthcare. However, the clinical and policy implications of implementing RCTs in clinical practice are difficult to predict as the studied population is often different from the target population where results are being applied. This study illustrates the concepts of generalizability and transportability, demonstrating their utility in interpreting results from the National Lung Screening Trial (NLST). METHODS: Using inverse-odds weighting, we demonstrate how generalizability and transportability techniques can be used to extrapolate treatment effect from (i) a subset of NLST to the entire NLST population and from (ii) the entire NLST to different target populations. RESULTS: Our generalizability analysis revealed that lung cancer mortality reduction by LDCT screening across the entire NLST [16% (95% confidence interval [CI]: 4-24)] could have been estimated using a smaller subset of NLST participants. Using transportability analysis, we showed that populations with a higher prevalence of females and current smokers had a greater reduction in lung cancer mortality with LDCT screening [e.g., 27% (95% CI, 11-37) for the population with 80% females and 80% current smokers] than those with lower prevalence of females and current smokers. CONCLUSIONS: This article illustrates how generalizability and transportability methods extend estimation of RCTs' utility beyond trial participants, to external populations of interest, including those that more closely mirror real-world populations. IMPACT: Generalizability and transportability approaches can be used to quantify treatment effects for populations of interest, which may be used to design future trials or adjust lung cancer screening eligibility criteria.

Using deep neural networks and interpretability methods to identify gene expression patterns that predict radiomic features and histology in non-small cell lung cancer.

Purpose: Integrative analysis combining diagnostic imaging and genomic information can uncover biological insights into lesions that are visible on radiologic images. We investigate techniques for interrogating a deep neural network trained to predict quantitative image (radiomic) features and histology from gene expression in non-small cell lung cancer (NSCLC). Approach: Using 262 training and 89 testing cases from two public datasets, deep feedforward neural networks were trained to predict the values of 101 computed tomography (CT) radiomic features and histology. A model interrogation method called gene masking was used to derive the learned associations between subsets of genes and a radiomic feature or histology class [adenocarcinoma (ADC), squamous cell, and other]. Results: Overall, neural networks outperformed other classifiers. In testing, neural networks classified histology with area under the receiver operating characteristic curves (AUCs) of 0.86 (ADC), 0.91 (squamous cell), and 0.71 (other). Classification performance of radiomics features ranged from 0.42 to 0.89 AUC. Gene masking analysis revealed new and previously reported associations. For example, hypoxia genes predicted histology ( > 0.90 AUC ). Previously published gene signatures for classifying histology were also predictive in our model ( > 0.80 AUC ). Gene sets related to the immune or cardiac systems and cell development processes were predictive ( > 0.70 AUC ) of several different radiomic features. AKT signaling, tumor necrosis factor, and Rho gene sets were each predictive of tumor textures. Conclusions: This work demonstrates neural networks' ability to map gene expressions to radiomic features and histology types in NSCLC and to interpret the models to identify predictive genes associated with each feature or type.

Guidelines for the Evaluation of Pulmonary Nodules Detected Incidentally or by Screening: A Survey of Radiologist Awareness, Agreement, and Adherence From the Watch the Spot Trial.

PURPOSE: The aim of this study was to examine radiologists' beliefs about existing guidelines for pulmonary nodule evaluation. METHODS: A self-administered survey was developed to ascertain awareness of, agreement with, and adherence to published guidelines, including those from the Fleischner Society and the Lung CT Screening Reporting and Data System (Lung-RADS™). Surveys were distributed to 514 radiologists at 13 health care systems that are participating in a large, pragmatic trial of pulmonary nodule evaluation. Prespecified comparisons were made among groups defined by type of health system, years of experience, reader volume, and study arm. RESULTS: The response rate was 26.3%. Respondents were most familiar with guidelines from Fleischner (94%) and Lung-RADS (71%). For both incidental and screening-detected nodules, self-reported adherence to preferred guidelines was very high (97% and 94%, respectively), and most respondents believed that the benefits of adherence outweigh the harms (81% and 74%, respectively). Underlying evidence was thought to be high in quality by 68% of respondents for screening-detected nodules and 41% for incidental nodules. Approximately 70% of respondents believed that the frequency of recommended follow-up was "just right" for both guidelines. Radiologists who practice in nonintegrated health care systems were more likely to believe that the evidence was high in quality (79.5% versus 57.1%) and that the benefits of adherence outweigh the harms (85.1% versus 67.5%). Low-volume readers had lower awareness and self-reported adherence than higher volume readers. CONCLUSIONS: Radiologists reported high levels of familiarity and agreement with and adherence to guidelines for pulmonary nodule evaluation, but many overestimated the quality of evidence in support of the recommendations.

EDICNet: An end-to-end detection and interpretable malignancy classification network for pulmonary nodules in computed tomography.

We present an interpretable end-to-end computer-aided detection and diagnosis tool for pulmonary nodules on computed tomography (CT) using deep learning-based methods. The proposed network consists of a nodule detector and a nodule malignancy classifier. We used RetinaNet to train a nodule detector using 7,607 slices containing 4,234 nodule annotations and validated it using 2,323 slices containing 1,454 nodule annotations drawn from the LIDC-IDRI dataset. The average precision for the nodule class in the validation set reached 0.24 at an intersection over union (IoU) of 0.5. The trained nodule detector was externally validated using a UCLA dataset. We then used a hierarchical semantic convolutional neural network (HSCNN) to classify whether a nodule was benign or malignant and generate semantic (radiologist-interpretable) features (e.g., mean diameter, consistency, margin), training the model on 149 cases with diagnostic CTs collected from the same UCLA dataset. A total of 149 nodule-centered patches from the UCLA dataset were used to train the HSCNN. Using 5-fold cross validation and data augmentation, the mean AUC and mean accuracy in the validation set for predicting nodule malignancy achieved 0.89 and 0.74, respectively. Meanwhile, the mean accuracy for predicting nodule mean diameter, consistency, and margin were 0.59, 0.74, and 0.75, respectively. We have developed an initial end-to-end pipeline that automatically detects nodules ≥ 5 mm on CT studies and labels identified nodules with radiologist-interpreted features automatically.

Correction to: Toward clinically usable CAD for lung cancer screening with computed tomography.

The original version of this article, published on 24 July 2014, unfortunately contained a mistake. In section "Discussion," a sentence was worded incorrectly.

Micronodules Detected on Computed Tomography During the National Lung Screening Trial: Prevalence and Relation to Positive Studies and Lung Cancer.

INTRODUCTION: In the National Lung Screening Trial (NLST) all cases with a 4-mm nodule (micronodule) and no other findings were classified as a negative study. The prevalence and malignant potential of micronodules in the NLST is evaluated to understand if this classification was appropriate. METHODS AND MATERIALS: In the NLST a total of 53,452 participants were enrolled with 26,722 undergoing low-dose computed tomography (CT) screening. To determine whether a micronodule developed into a lung cancer, a list from the NLST database of those participants who developed lung cancer and had a micronodule recorded was selected. The CT images of this subset were reviewed by experienced, fellowship-trained thoracic radiologists (R.F.M., C.C., P.M.B., and D.R.A.), all of whom participated as readers in the NLST. RESULTS: There were 26,722 participants who underwent CT in the NLST, of which 11,326 (42%) participants had at least one CT with a micronodule. Five thousand five hundred sixty (49%) of these participants had at least one positive CT examination, of which 409 (3.6%) subsequently were diagnosed with lung cancer. Of the 409 lung cancer cases with a micronodule recorded, there were 13 cases in which a micronodule developed into lung cancer. Considering the 13 cases, they represent 1.2% (13 of 1089) of the lung cancers diagnosed in the CT arm of the NLST and 0.11% (13 of 11,326) of the total micronodule cases. Additionally they represent 0.23% (13 of 5560) of the micronodule and at least one positive CT examination cases and 3.2% (13 of 409) of the micronodule cases diagnosed with lung cancer. The average size of the nodule at baseline (recorded as maximum diameter by perpendicular diameter) was 3.0 × 2.5 mm (ranges 2 x 4 mm and 2 x 4 mm) and at the positive CT the nodule was 11.1 × 8.6 mm (ranges, 6 x 20 mm and 5 x 14 mm); a difference of average change in size of 8.1 × 6.1 mm. The average number of days from first CT with a micronodule recorded to positive CT was 459 days (range, 338 - 723 days), the mean time from first CT with micronodule to lung cancer diagnosis was 617 days (range, 380 - 1140 days) and the mean time from positive CT to lung cancer diagnosis was 160 days (range, 18 - 417 days). Histologically, there was one small cell carcinoma and 12 non-small cell with stages of IA in 8 (62%), stage IB in 2 (15%), and 1 each stage IIIA, IIIB, and IV. The overall survival of NSCLC cases with a micronodule was not significantly different than the survival of the CT subset diagnosed with NSCL (p = 0.36). CONCLUSIONS: Micronodules are common among lung cancer-screened participants and are capable of developing into lung cancer; however, following micronodules by annual CT screening surveillance is appropriate and does not impact overall survival or outcome.

An Interpretable Deep Hierarchical Semantic Convolutional Neural Network for Lung Nodule Malignancy Classification.

While deep learning methods have demonstrated performance comparable to human readers in tasks such as computer-aided diagnosis, these models are difficult to interpret, do not incorporate prior domain knowledge, and are often considered as a "black-box." The lack of model interpretability hinders them from being fully understood by end users such as radiologists. In this paper, we present a novel interpretable deep hierarchical semantic convolutional neural network (HSCNN) to predict whether a given pulmonary nodule observed on a computed tomography (CT) scan is malignant. Our network provides two levels of output: 1) low-level semantic features; and 2) a high-level prediction of nodule malignancy. The low-level outputs reflect diagnostic features often reported by radiologists and serve to explain how the model interprets the images in an expert-interpretable manner. The information from these low-level outputs, along with the representations learned by the convolutional layers, are then combined and used to infer the high-level output. This unified architecture is trained by optimizing a global loss function including both low- and high-level tasks, thereby learning all the parameters within a joint framework. Our experimental results using the Lung Image Database Consortium (LIDC) show that the proposed method not only produces interpretable lung cancer predictions but also achieves significantly better results compared to using a 3D CNN alone.

The Immune Contexture Associates with the Genomic Landscape in Lung Adenomatous Premalignancy.

Epithelial cells in the field of lung injury can give rise to distinct premalignant lesions that may bear unique genetic aberrations. A subset of these lesions may escape immune surveillance and progress to invasive cancer; however, the mutational landscape that may predict progression has not been determined. Knowledge of premalignant lesion composition and the associated microenvironment is critical for understanding tumorigenesis and the development of effective preventive and interception strategies. To identify somatic mutations and the extent of immune cell infiltration in adenomatous premalignancy and associated lung adenocarcinomas, we sequenced exomes from 41 lung cancer resection specimens, including 89 premalignant atypical adenomatous hyperplasia lesions, 15 adenocarcinomas in situ, and 55 invasive adenocarcinomas and their adjacent normal lung tissues. We defined nonsynonymous somatic mutations occurring in both premalignancy and the associated tumor as progression-associated mutations whose predicted neoantigens were highly correlated with infiltration of CD8+ and CD4+ T cells as well as upregulation of PD-L1 in premalignant lesions, suggesting the presence of an adaptive immune response to these neoantigens. Each patient had a unique repertoire of somatic mutations and associated neoantigens. Collectively, these results provide evidence for mutational heterogeneity, pathway dysregulation, and immune recognition in pulmonary premalignancy.Significance: These findings identify progression-associated somatic mutations, oncogenic pathways, and association between the mutational landscape and adaptive immune responses in adenomatous premalignancy.See related commentary by Merrick, p. 4811.