The Lung Cancer Prediction Model "Stress Test": Assessment of Models' Performance in a High-Risk Prospective Pulmonary Nodule Cohort.

BACKGROUND: Pulmonary nodules represent a growing health care burden because of delayed diagnosis of malignant lesions and overtesting for benign processes. Clinical prediction models were developed to inform physician assessment of pretest probability of nodule malignancy but have not been validated in a high-risk cohort of nodules for which biopsy was ultimately performed. RESEARCH QUESTION: Do guideline-recommended prediction models sufficiently discriminate between benign and malignant nodules when applied to cases referred for biopsy by navigational bronchoscopy? STUDY DESIGN AND METHODS: We assembled a prospective cohort of 322 indeterminate pulmonary nodules in 282 patients referred to a tertiary medical center for diagnostic navigational bronchoscopy between 2017 and 2019. We calculated the probability of malignancy for each nodule using the Brock model, Mayo Clinic model, and Veterans Affairs (VA) model. On a subset of 168 patients who also had PET-CT scans before biopsy, we also calculated the probability of malignancy using the Herder model. The performance of the models was evaluated by calculating the area under the receiver operating characteristic curves (AUCs) for each model. RESULTS: The study cohort contained 185 malignant and 137 benign nodules (57% prevalence of malignancy). The malignant and benign cohorts were similar in terms of size, with a median longest diameter for benign and malignant nodules of 15 and 16 mm, respectively. The Brock model, Mayo Clinic model, and VA model showed similar performance in the entire cohort (Brock AUC, 0.70; 95% CI, 0.64-0.76; Mayo Clinic AUC, 0.70; 95% CI, 0.64-0.76; VA AUC, 0.67; 95% CI, 0.62-0.74). For 168 nodules with available PET-CT scans, the Herder model had an AUC of 0.77 (95% CI, 0.68-0.85). INTERPRETATION: Currently available clinical models provide insufficient discrimination between benign and malignant nodules in the common clinical scenario in which a patient is being referred for biopsy, especially when PET-CT scan information is not available.

Assessing the clinical utility of biomarkers using the intervention probability curve (IPC).

BACKGROUND: Assessing the clinical utility of biomarkers is a critical step before clinical implementation. The reclassification of patients across clinically relevant subgroups is considered one of the best methods to estimate clinical utility. However, there are important limitations with this methodology. We recently proposed the intervention probability curve (IPC) which models the likelihood that a provider will choose an intervention as a continuous function of the probability, or risk, of disease. OBJECTIVE: To assess the potential impact of a new biomarker for lung cancer using the IPC. METHODS: The IPC derived from the National Lung Screening Trial was used to assess the potential clinical utility of a biomarker for suspected lung cancer. The summary statistics of the change in likelihood of intervention over the population can be interpreted as the expected clinical impact of the added biomarker. RESULTS: The IPC analysis of the novel biomarker estimated that 8% of the benign nodules could avoid an invasive procedure while the cancer nodules would largely remain unchanged (0.1%). We showed the benefits of this approach compared to traditional reclassification methods based on thresholds. CONCLUSIONS: The IPC methodology can be a valuable tool for assessing biomarkers prior to clinical implementation.

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.

Cancer-associated fibroblasts in early-stage lung adenocarcinoma correlate with tumor aggressiveness.

Lung adenocarcinoma (LUAD) is the predominant type of lung cancer in the U.S. and exhibits a broad variety of behaviors ranging from indolent to aggressive. Identification of the biological determinants of LUAD behavior at early stages can improve existing diagnostic and treatment strategies. Extracellular matrix (ECM) remodeling and cancer-associated fibroblasts play a crucial role in the regulation of cancer aggressiveness and there is a growing need to investigate their role in the determination of LUAD behavior at early stages. We analyzed tissue samples isolated from patients with LUAD at early stages and used imaging-based biomarkers to predict LUAD behavior. Single-cell RNA sequencing and histological assessment showed that aggressive LUADs are characterized by a decreased number of ADH1B+ CAFs in comparison to indolent tumors. ADH1B+ CAF enrichment is associated with distinct ECM and immune cell signatures in early-stage LUADs. Also, we found a positive correlation between the gene expression of ADH1B+ CAF markers in early-stage LUADs and better survival. We performed TCGA dataset analysis to validate our findings. Identified associations can be used for the development of the predictive model of LUAD aggressiveness and novel therapeutic approaches.

Tumoral Densities of T-Cells and Mast Cells Are Associated With Recurrence in Early-Stage Lung Adenocarcinoma.

Introduction: Lung cancer is the deadliest cancer in the United States and worldwide, and lung adenocarcinoma (LUAD) is the most prevalent histologic subtype in the United States. LUAD exhibits a wide range of aggressiveness and risk of recurrence, but the biological underpinnings of this behavior are poorly understood. Past studies have focused on the biological characteristics of the tumor itself, but the ability of the immune response to contain tumor growth represents an alternative or complementary hypothesis. Emerging technologies enable us to investigate the spatial distribution of specific cell types within the tumor nest and characterize this immune response. This study aimed to investigate the association between immune cell density within the primary tumor and recurrence-free survival (RFS) in stage I and II LUAD. Methods: This study is a prospective collection with retrospective evaluation. A total of 100 patients with surgically resected LUAD and at least 5-year follow-ups, including 69 stage I and 31 stages II tumors, were enrolled. Multiplexed immunohistochemistry panels for immune markers were used for measurement. Results: Cox regression models adjusted for sex and EGFR mutation status revealed that the risk of recurrence was reduced by 50% for the unit of one interquartile range (IQR) change in the tumoral T-cell (adjusted hazard ratio per IQR increase = 0.50, 95% confidence interval: 0.27-0.93) and decreased by 64% in mast cell density (adjusted hazard ratio per IQR increase = 0.36, confidence interval: 0.15-0.84). The analyses were reported without the type I error correction for the multiple types of immune cell testing. Conclusions: Analysis of the density of immune cells within the tumor and surrounding stroma reveals an association between the density of T-cells and RFS and between mast cells and RFS in early-stage LUAD. This preliminary result is a limited study with a small sample size and a lack of an independent validation set.

Integrated Multi-omics Analysis of Early Lung Adenocarcinoma Links Tumor Biological Features with Predicted Indolence or Aggressiveness.

Lung adenocarcinoma (LUAD) is a heterogeneous group of tumors associated with different survival rates, even when detected at an early stage. Here, we aim to investigate the biological determinants of early LUAD indolence or aggressiveness using radiomics as a surrogate of behavior. We present a set of 92 patients with LUAD with data collected across different methodologies. Patients were risk-stratified using the CT-based Score Indicative of Lung cancer Aggression (SILA) tool (0 = least aggressive, 1 = most aggressive). We grouped the patients as indolent (x ≤ 0.4, n = 14), intermediate (0.4 > x ≤ 0.6, n = 27), and aggressive (0.6 > x ≤ 1, n = 52). Using Cytometry by time of flight (CyTOF), we identified subpopulations with high HLA-DR expression that were associated with indolent behavior. In the RNA sequencing (RNA-seq) dataset, pathways related to immune response were associated with indolent behavior, while pathways associated with cell cycle and proliferation were associated with aggressive behavior. We extracted quantitative radiomics features from the CT scans of the patients. Integrating these datasets, we identified four feature signatures and four patient clusters that were associated with survival. Using single-cell RNA-seq, we found that indolent tumors had significantly more T cells and less B cells than aggressive tumors, and that the latter had a higher abundance of regulatory T cells and Th cells. In conclusion, we were able to uncover a correspondence between radiomics and tumor biology, which could improve the discrimination between indolent and aggressive LUAD tumors, enhance our knowledge in the biology of these tumors, and offer novel and personalized avenues for intervention. Significance: This study provides a comprehensive profiling of LUAD indolence and aggressiveness at the biological bulk and single-cell levels, as well as at the clinical and radiomics levels. This hypothesis generating study uncovers several potential future research avenues. It also highlights the importance and power of data integration to improve our systemic understanding of LUAD and to help reduce the gap between basic science research and clinical practice.

Update on Biomarkers for the Stratification of Indeterminate Pulmonary Nodules.

Lung cancer is the leading cause of cancer-related deaths. Early detection and diagnosis are critical, as survival decreases with advanced stages. Approximately 1.6 million nodules are incidentally detected every year on chest CT scan images in the United States. This number of nodules identified is likely much larger after accounting for screening-detected nodules. Most of these nodules, whether incidentally or screening detected, are benign. Despite this, many patients undergo unnecessary invasive procedures to rule out cancer because our current stratification approaches are suboptimal, particularly for intermediate probability nodules. Thus, noninvasive strategies are urgently needed. Biomarkers have been developed to assist through the continuum of lung cancer care and include blood protein-based biomarkers, liquid biopsies, quantitative imaging analysis (radiomics), exhaled volatile organic compounds, and bronchial or nasal epithelium genomic classifiers, among others. Although many biomarkers have been developed, few have been integrated into clinical practice as they lack clinical utility studies showing improved patient-centered outcomes. Rapid technologic advances and large network collaborative efforts will continue to drive the discovery and validation of many novel biomarkers. Ultimately, however, randomized clinical utility studies showing improved patient outcomes will be required to bring biomarkers into clinical practice.

Longitudinal lung cancer prediction convolutional neural network model improves the classification of indeterminate pulmonary nodules.

A deep learning model (LCP CNN) for the stratification of indeterminate pulmonary nodules (IPNs) demonstrated better discrimination than commonly used clinical prediction models. However, the LCP CNN score is based on a single timepoint that ignores longitudinal information when prior imaging studies are available. Clinically, IPNs are often followed over time and temporal trends in nodule size or morphology inform management. In this study we investigated whether the change in LCP CNN scores over time was different between benign and malignant nodules. This study used a prospective-specimen collection, retrospective-blinded-evaluation (PRoBE) design. Subjects with incidentally or screening detected IPNs 6-30 mm in diameter with at least 3 consecutive CT scans prior to diagnosis (slice thickness ≤ 1.5 mm) with the same nodule present were included. Disease outcome was adjudicated by biopsy-proven malignancy, biopsy-proven benign disease and absence of growth on at least 2-year imaging follow-up. Lung nodules were analyzed using the Optellum LCP CNN model. Investigators performing image analysis were blinded to all clinical data. The LCP CNN score was determined for 48 benign and 32 malignant nodules. There was no significant difference in the initial LCP CNN score between benign and malignant nodules. Overall, the LCP CNN scores of benign nodules remained relatively stable over time while that of malignant nodules continued to increase over time. The difference in these two trends was statistically significant. We also developed a joint model that incorporates longitudinal LCP CNN scores to predict future probability of cancer. Malignant and benign nodules appear to have distinctive trends in LCP CNN score over time. This suggests that longitudinal modeling may improve radiomic prediction of lung cancer over current models. Additional studies are needed to validate these early findings.

Improving lung cancer diagnosis with cancer, fungal, and imaging biomarkers.

OBJECTIVE: Indeterminate pulmonary nodules (IPNs) represent a significant diagnostic burden in health care. We aimed to compare a combination clinical prediction model (Mayo Clinic model), fungal (histoplasmosis serology), imaging (computed tomography [CT] radiomics), and cancer (high-sensitivity cytokeratin fraction 21; hsCYFRA 21-1) biomarker approach to a validated prediction model in diagnosing lung cancer. METHODS: A prospective specimen collection, retrospective blinded evaluation study was performed in 3 independent cohorts with 6- to 30-mm IPNs (n = 281). Serum histoplasmosis immunoglobulin G and immunoglobulin M antibodies and hsCYFRA 21-1 levels were measured and a validated CT radiomic score was calculated. Multivariable logistic regression models were estimated with Mayo Clinic model variables, histoplasmosis antibody levels, CT radiomic score, and hsCYFRA 21-1. Diagnostic performance of the combination model was compared with that of the Mayo Clinic model. Bias-corrected clinical net reclassification index (cNRI) was used to estimate the clinical utility of a combination biomarker approach. RESULTS: A total of 281 patients were included (111 from a histoplasmosis-endemic region). The combination biomarker model including the Mayo Clinic model score, histoplasmosis antibody levels, radiomics, and hsCYFRA 21-1 level showed improved diagnostic accuracy for IPNs compared with the Mayo Clinic model alone with an area under the receiver operating characteristics curve of 0.80 (95% CI, 0.76-0.84) versus 0.72 (95% CI, 0.66-0.78). Use of this combination model correctly reclassified intermediate risk IPNs into low- or high-risk category (cNRI benign = 0.11 and cNRI malignant = 0.16). CONCLUSIONS: The addition of cancer, fungal, and imaging biomarkers improves the diagnostic accuracy for IPNs. Integrating a combination biomarker approach into the diagnostic algorithm of IPNs might decrease unnecessary invasive testing of benign nodules and reduce time to diagnosis for cancer.

Improving Lung Cancer Diagnosis with CT Radiomics and Serum Histoplasmosis Testing.

BACKGROUND: Indeterminate pulmonary nodules (IPN) are a diagnostic challenge in regions where pulmonary fungal disease and smoking prevalence are high. We aimed to determine the impact of a combined fungal and imaging biomarker approach compared with a validated prediction model (Mayo) to rule out benign disease and diagnose lung cancer. METHODS: Adults ages 40 to 90 years with 6-30 mm IPNs were included from four sites. Serum samples were tested for histoplasmosis IgG and IgM antibodies by enzyme immunoassay and a CT-based risk score was estimated from a validated radiomic model. Multivariable logistic regression models including Mayo score, radiomics score, and IgG and IgM histoplasmosis antibody levels were estimated. The areas under the ROC curves (AUC) of the models were compared among themselves and to Mayo. Bias-corrected clinical net reclassification index (cNRI) was estimated to assess clinical reclassification using a combined biomarker model. RESULTS: We included 327 patients; 157 from histoplasmosis-endemic regions. The combined biomarker model including radiomics, histoplasmosis serology, and Mayo score demonstrated improved diagnostic accuracy when endemic histoplasmosis was accounted for [AUC, 0.84; 95% confidence interval (CI), 0.79-0.88; P < 0.0001 compared with 0.73; 95% CI, 0.67-0.78 for Mayo]. The combined model demonstrated improved reclassification with cNRI of 0.18 among malignant nodules. CONCLUSIONS: Fungal and imaging biomarkers may improve diagnostic accuracy and meaningfully reclassify IPNs. The endemic prevalence of histoplasmosis and cancer impact model performance when using disease related biomarkers. IMPACT: Integrating a combined biomarker approach into the diagnostic algorithm of IPNs could decrease time to diagnosis.

Extending the value of routine lung screening CT with quantitative body composition assessment.

Certain body composition phenotypes, like sarcopenia, are well established as predictive markers for post-surgery complications and overall survival of lung cancer patients. However, their association with incidental lung cancer risk in the screening population is still unclear. We study the feasibility of body composition analysis using chest low dose computed tomography (LDCT). A two-stage fully automatic pipeline is developed to assess the cross-sectional area of body composition components including subcutaneous adipose tissue (SAT), muscle, visceral adipose tissue (VAT), and bone on T5, T8 and T10 vertebral levels. The pipeline is developed using 61 cases of the VerSe'20 dataset, 40 annotated cases of NLST, and 851 inhouse screening cases. On a test cohort consisting of 30 cases from the inhouse screening cohort (age 55 - 73, 50% female) and 42 cases of NLST (age 55 - 75, 59.5% female), the pipeline achieves a root mean square error (RMSE) of 7.25 mm (95% CI: [6.61, 7.85]) for the vertebral level identification and mean Dice similarity score (DSC) 0.99 ± 0.02, 0.96 ± 0.03, and 0.95 ± 0.04 for SAT, muscle, and VAT, respectively for body composition segmentation. The pipeline is generalized to the CT arm of the NLST dataset (25,205 subjects, 40.8% female, 1,056 lung cancer incidences). Time-to-event analysis for lung cancer incidence indicates inverse association between measured muscle cross-sectional area and incidental lung cancer risks (p < 0.001 female, p < 0.001 male). In conclusion, automatic body composition analysis using routine lung screening LDCT is feasible.

Assay Performance of a Label-Free, Solution-Phase CYFRA 21-1 Determination.

CYFRA 21.1, a cytokeratin fragment of epithelial origin, has long been a valuable blood-based biomarker. As with most biomarkers, the clinical diagnostic value of CYFRA 21.1 is dependent on the quantitative performance of the assay. Looking toward translation, it is shown here that a free-solution assay (FSA) coupled with a compensated interferometric reader (CIR) can be used to provide excellent analytical performance in quantifying CYFRA 21.1 in patient serum samples. This report focuses on the analytical performance of the high-sensitivity (hs)-CYFRA 21.1 assay in the context of quantifying the biomarker in two indeterminate pulmonary nodule (IPN) patient cohorts totaling 179 patients. Each of the ten assay calibrations consisted of 6 concentrations, each run as 7 replicates (e.g., 10 × 6 × 7 data points) and were performed on two different instruments by two different operators. Coefficients of variation (CVs) for the hs-CYFRA 21.1 analytical figures of merit, limit of quantification (LOQ) of ca. 60 pg/mL, B max, initial slope, probe-target binding affinity, and reproducibility of quantifying an unknown were found to range from 2.5 to 8.3%. Our results demonstrate the excellent performance of our FSA-CIR hs-CYFRA 21-1 assay and a proof of concept for potentially redefining the performance characteristics of this existing important candidate biomarker.

The Intervention Probability Curve: Modeling the Practical Application of Threshold-Guided Decision-Making, Evaluated in Lung, Prostate, and Ovarian Cancers.

BACKGROUND: Diagnostic prediction models are useful guides when considering lesions suspicious for cancer, as they provide a quantitative estimate of the probability that a lesion is malignant. However, the decision to intervene ultimately rests on patient and physician preferences. The appropriate intervention in many clinical situations is typically defined by clinically relevant, actionable subgroups based upon the probability of malignancy. However, the "all-or-nothing" approach of threshold-based decisions is in practice incorrect. METHODS: Here, we present a novel approach to understanding clinical decision-making, the intervention probability curve (IPC). The IPC models the likelihood that an intervention will be chosen as a continuous function of the probability of disease. We propose the cumulative distribution function as a suitable model. The IPC is explored using the National Lung Screening Trial and the Prostate Lung Colorectal and Ovarian Screening Trial datasets. RESULTS: Fitting the IPC results in a continuous curve as a function of pretest probability of cancer with high correlation (R2 > 0.97 for each) with fitted parameters closely aligned with professional society guidelines. CONCLUSIONS: The IPC allows analysis of intervention decisions in a continuous, rather than threshold-based, approach to further understand the role of biomarkers and risk models in clinical practice. IMPACT: We propose that consideration of IPCs will yield significant insights into the practical relevance of threshold-based management strategies and could provide a novel method to estimate the actual clinical utility of novel biomarkers.

The impact of the lung EDRN-CVC on Phase 1, 2, & 3 biomarker validation studies.

The Early Detection Research Network's (EDRN) purpose is to discover, develop and validate biomarkers and imaging methods to detect early-stage cancers or at-risk individuals. The EDRN is composed of sites that fall into four categories: Biomarker Developmental Laboratories (BDL), Biomarker Reference Laboratories (BRL), Clinical Validation Centers (CVC) and Data Management and Coordinating Centers. Each component has a crucial role to play within the mission of the EDRN. The primary role of the CVCs is to support biomarker developers through validation trials on promising biomarkers discovered by both EDRN and non-EDRN investigators. The second round of funding for the EDRN Lung CVC at Vanderbilt University Medical Center (VUMC) was funded in October 2016 and we intended to accomplish the three missions of the CVCs: To conduct innovative research on the validation of candidate biomarkers for early cancer detection and risk assessment of lung cancer in an observational study; to compare biomarker performance; and to serve as a resource center for collaborative research within the Network and partner with established EDRN BDLs and BRLs, new laboratories and industry partners. This report outlines the impact of the VUMC EDRN Lung CVC and describes the role in promoting and validating biological and imaging biomarkers.

Deep Multi-path Network Integrating Incomplete Biomarker and Chest CT Data for Evaluating Lung Cancer Risk.

Clinical data elements (CDEs) (e.g., age, smoking history), blood markers and chest computed tomography (CT) structural features have been regarded as effective means for assessing lung cancer risk. These independent variables can provide complementary information and we hypothesize that combining them will improve the prediction accuracy. In practice, not all patients have all these variables available. In this paper, we propose a new network design, termed as multi-path multi-modal missing network (M3Net), to integrate the multi-modal data (i.e., CDEs, biomarker and CT image) considering missing modality with multiple paths neural network. Each path learns discriminative features of one modality, and different modalities are fused in a second stage for an integrated prediction. The network can be trained end-to-end with both medical image features and CDEs/biomarkers, or make a prediction with single modality. We evaluate M3Net with datasets including three sites from the Consortium for Molecular and Cellular Characterization of Screen-Detected Lesions (MCL) project. Our method is cross validated within a cohort of 1291 subjects (383 subjects with complete CDEs/biomarkers and CT images), and externally validated with a cohort of 99 subjects (99 with complete CDEs/biomarkers and CT images). Both cross-validation and external-validation results show that combining multiple modality significantly improves the predicting performance of single modality. The results suggest that integrating subjects with missing either CDEs/biomarker or CT imaging features can contribute to the discriminatory power of our model (p < 0.05, bootstrap two-tailed test). In summary, the proposed M3Net framework provides an effective way to integrate image and non-image data in the context of missing information.