Ehab Billatos

Abstract Rationale Patients with indeterminate pulmonary nodules (IPNs) at risk of cancer undergo high rates of invasive, costly, and morbid procedures. Objectives To train and externally validate a risk prediction model that combined clinical, blood, and imaging biomarkers to improve the noninvasive management of IPNs. Methods In this prospectively collected, retrospective blinded evaluation study, probability of cancer was calculated for 456 patient nodules using the Mayo Clinic model, and patients were categorized into low-, intermediate-, and high-risk groups. A combined biomarker model (CBM) including clinical variables, serum high sensitivity CYFRA 21-1 level, and a radiomic signature was trained in cohort 1 (n = 170) and validated in cohorts 2–4 (total n = 286). All patients were pooled to recalibrate the model for clinical implementation. The clinical utility of the CBM compared with current clinical care was evaluated in 2 cohorts. Measurements and Main Results The CBM provided improved diagnostic accuracy over the Mayo Clinic model with an improvement in area under the curve of 0.124 (95% bootstrap confidence interval, 0.091–0.156; P < 2 × 10−16). Applying 10% and 70% risk thresholds resulted in a bias-corrected clinical reclassification index for cases and control subjects of 0.15 and 0.12, respectively. A clinical utility analysis of patient medical records estimated that a CBM-guided strategy would have reduced invasive procedures from 62.9% to 50.6% in the intermediate-risk benign population and shortened the median time to diagnosis of cancer from 60 to 21 days in intermediate-risk cancers. Conclusions Integration of clinical, blood, and image biomarkers improves noninvasive diagnosis of patients with IPNs, potentially reducing the rate of unnecessary invasive procedures while shortening the time to diagnosis.

Somatic mutations are a hallmark of tumorigenesis and may be useful for non-invasive diagnosis of cancer. We analyzed whole-genome sequencing data from 2,511 individuals in the Pan-Cancer Analysis of Whole Genomes (PCAWG) study as well as 489 individuals from four prospective cohorts and found distinct regional mutation type-specific frequencies in tissue and cell-free DNA from patients with cancer that were associated with replication timing and other chromatin features. A machine-learning model using genome-wide mutational profiles combined with other features and followed by CT imaging detected >90% of patients with lung cancer, including those with stage I and II disease. The fixed model was validated in an independent cohort, detected patients with cancer earlier than standard approaches and could be used to monitor response to therapy. This approach lays the groundwork for non-invasive cancer detection using genome-wide mutation features that may facilitate cancer screening and monitoring.

Lung cancer is one of the deadliest forms of cancers and is often diagnosed by performing biopsies with the use of a bronchoscope. However, this diagnostic procedure is limited in ability to explore deep into the periphery of the lung where cancer can remain undetected. In this study, we present design, modeling, fabrication, and testing of a one degree of freedom soft robot with integrated diagnostic and interventional capabilities as well as vision sensing. The robot can be deployed through the working channel of commercial bronchoscopes or used as a stand-alone system as it integrates a micro camera to provide vision sensing and controls to the periphery of the lung. The small diameter (2.4 mm) of the device allows navigation in branches deeper in the lung, where current devices have limited reachability. We have performed mechanical characterizations of the robotic platform, including blocked force, maximum bending angle, maximum angular velocity, and workspace, and assessed its performance in in vitro and ex vivo experiments. We have developed a computer vision algorithm, and validated it in in vitro conditions, to autonomously align the robot to a selected branch of the lung and aid the clinician (by means of a graphical user interface) during navigation tasks and to perform robot-assisted stabilization in front of a lesion, with automated tracking and alignment.

Abstract Lung cancer remains the leading cause of cancer-related death due to its advanced stage at diagnosis. Early detection of lung cancer can be improved by better defining who should be screened radiographically and determining which imaging-detected pulmonary nodules are malignant. Gene expression biomarkers measured in normal-appearing airway epithelium provide an opportunity to use lung cancer–associated molecular changes in this tissue for early detection of lung cancer. Molecular changes in the airway may result from an etiologic field of injury and/or field cancerization. The etiologic field of injury reflects the aberrant physiologic response to carcinogen exposure that creates a susceptible microenvironment for cancer initiation. In contrast, field cancerization reflects effects of “first-hit” mutations in a clone of cells from which the tumor ultimately arises or the effects of the tumor on the surrounding tissue. These fields might have value both for assessing lung cancer risk and diagnosis. Cancer-associated gene expression changes in the bronchial airway have recently been used to develop and validate a 23-gene classifier that improves the diagnostic yield of bronchoscopy for lung cancer among intermediate-risk patients. Recent studies have demonstrated that these lung cancer–related gene expression changes extend to nasal epithelial cells that can be sampled noninvasively. While the bronchial gene expression biomarker is being adopted clinically, further work is necessary to explore the potential clinical utility of gene expression profiling in the nasal epithelium for lung cancer diagnosis, lung cancer risk assessment, and precision medicine for lung cancer treatment and chemoprevention. Clin Cancer Res; 24(13); 2984–92. ©2018 AACR.