Novel CT-Derived Radiomic Biomarkers for Lung Nodule Characterization in the Screening Population
Abstract
Recent data from the National Lung Screening Trial (NLST) suggest that annual low-dose chest CT (LDCT) scans in patients who smoke leads to early detection of lung cancer and improves survival. CMS/Medicare has consequently approved CT scans for lung cancer screening. The Department of Veterans Affairs (VA) and military population is at an increased risk of developing lung cancer compared to the general population because of higher smoking rates and increased likelihood of exposure to other carcinogens during their military service. The VA system cares for some 6.7 million mostly older male Veterans each year, many of whom have long smoking histories. In a recent study, investigators from eight VA centers across the United States screened more than 2,000 Veterans over 2 years using criteria from the NLST, but with a cohort that trended older and tended to have smoked more. Among the 2,106 Veterans screened, a total of 1,257 (59.7%) had nodules, of which 1,184 (56.2%) required tracking. Nearly all of the positive results were negative for cancer, producing a false-positive rate of 97.5% for human-based interpretation. The demonstration project showed that developing and implementing a comprehensive lung cancer screening program “is a complex and challenging undertaking, and that most patients will have findings that require follow-up; however, few patients will have early-stage lung cancers.” Unfortunately, many of the nodules identified by human readers as “indeterminate” or “suspicious” triggered additional surgical interventions (~$5K to $25K/patient) and imaging exams. More than 30% of pulmonary nodules that are identified as suspicious on a CT scan and are biopsied or resected are identified as benign. This suggests that ~$600M is being spent annually in the United States in unnecessary and invasive surgical procedures. As a result, there is an urgent need for better image-based decision support tools for improving lung cancer screening programs at medical centers. Principal Investigator Dr. Anant Madabhushi and his team have developed novel computerized image analysis and pattern recognition tools for improved discrimination of cancerous versus non-cancerous nodules on routine screening chest CT scans. A significant breakthrough has been the development of a novel imaging marker, called “vessel tortuosity,” for quantitatively characterizing the architectural complexity in the vasculature of a lung nodule on chest CT scans, with the result that measurements of vessel tortuosity in benign long nodules have been shown to be significantly different from those in malignant lung nodules. Additionally, our group has identified other highly predictive computer-extracted image features from routine LDCT scans that aim to capture (1) subtle textural patterns of the microarchitecture within and immediately outside the nodule and (2) subtle three-dimensional (3D) shape patterns of the nodule and the nodule interface. In a validation set of N=145 patients, each of these imaging markers has been independently shown to have an area under the receiver operating characteristic curve (AUC) ranging from 77 to 87% in distinguishing malignant from benign nodules. In contrast, on this cohort, an expert chest radiologist and pulmonologist had maximum AUCs of 69 to 72%. More interestingly, on this cohort, combining machine-based interpretations with human readers resulted in an improvement of 30% in the AUC value for the human readers. Building on our current impressive results, in this study, we propose to continue optimizing our computerized decision support technology (Lung Imaging based Risk Score [LunIRiS]) to assign a risk score of malignancy to a nodule on LDCT scans. In Aim 1, we will identify the best combination of intranodule and perinodule texture, 3D shape, margin sharpness, and vessel tortuosity measurements for constructing the LunIRiS software program by employing a cohort of over N=300 patients. In Aim 2
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Oct 29, 2018
- Source ID
- W81XWH1810440
Entities
People
- Anant Madabhushi
Organizations
- Case Western Reserve University
- United States Army