The importance of the regimen of screening in maximizing the benefit and minimizing the harms

China lung cancer screening (CLUS) version 2.0 with new techniques implemented: Artificial intelligence, circulating molecular biomarkers and autofluorescence bronchoscopy

OBJECTIVE

The present study, CLUS version 2.0, was conducted to evaluate the performance of new techniques in improving the implementation of lung cancer screening and to validate the efficacy of LDCT in reducing lung cancer-specific mortality in a high-risk Chinese population.

METHODS

From July 2018 to February 2019, high-risk participants from six screening centers in Shanghai were enrolled in our study. Artificial intelligence, circulating molecular biomarkers and autofluorescencebronchoscopy were applied during screening.

RESULTS

A total of 5087 eligible high-risk participants were enrolled in the study; 4490 individuals were invited, and 4395 participants (97.9%) finally underwent LDCT detection. Positive screening results were observed in 857 (19.5%) participants. Solid nodules represented 53.6% of all positive results, while multiple nodules were the most common location type (26.8%). Up to December 2020, 77 participants received lung resection or biopsy, including 70 lung cancers, 2 mediastinal tumors, 1 tracheobronchial tumor, 1 malignant pleural mesothelioma and 3 benign nodules. Lung cancer patients accounted for 1.6% of all the screened participants, and 91.4% were in the early stage (stage 0-1).

CONCLUSIONS

LDCT screening can detect a high proportion of early-stage lung cancer patients in a Chinese high-risk population. The utilization of new techniques would be conducive to improving the implementation of LDCT screening.

Association of Rurality With Annual Repeat Lung Cancer Screening in the Veterans Health Administration

PURPOSE

Lung cancer causes the largest number of cancer-related deaths in the United States. Lung cancer incidence rates, mortality rates, and rates of advanced stage disease are higher among those who live in rural areas. Known disparities in lung cancer outcomes between rural and nonrural populations may be in part because of barriers faced by rural populations. The authors tested the hypothesis that among Veterans who receive initial lung cancer screening, rural Veterans would be less likely to complete annual repeat screening than nonrural Veterans.

METHODS

A retrospective cohort study was conducted of 10 Veterans Affairs medical centers from 2015 to 2019. Rural and nonrural Veterans undergoing lung cancer screening were identified. Rural status was defined using the rural-urban commuting area codes. The primary outcome was annual repeat lung cancer screening in the 9- to 15-month window (primary analysis) and 31-day to 18-month window (sensitivity analysis) after the first documented lung cancer screening. To examine rurality as a predictor of annual repeat lung cancer screening, multivariable logistic regression models were used.

RESULTS

In the final analytic sample of 11,402 Veterans, annual repeat lung cancer screening occurred in 27.7% of rural Veterans (641 of 2,316) and 31.8% of nonrural Veterans (2,891 of 9,086) (adjusted odds ratio: 0.86; 95% confidence interval: 0.73-1.03). Similar results were seen in the sensitivity analysis, with 41.6% of rural Veterans (963 of 2,316) versus 45.2% of nonrural Veterans (4,110 of 9,086) (adjusted odds ratio: 0.88; 95% confidence interval: 0.73-1.04) having annual repeat screening in the expanded 31-day to 18-month window.

CONCLUSIONS

Among a national cohort of Veterans, rural residence was associated with numerically lower odds of annual repeat lung cancer screening than nonrural residence. Continued, intentional outreach efforts to increase annual repeat lung cancer screening among rural Veterans may offer an opportunity to decrease deaths from lung cancer.

Assessing the predictive accuracy of lung cancer, metastases, and benign lesions using an artificial intelligence-driven computer aided diagnosis system

Background

Artificial intelligence (AI) products have been widely used for the clinical detection of primary lung tumors. However, their performance and accuracy in risk prediction for metastases or benign lesions remain underexplored. This study evaluated the accuracy of an AI-driven commercial computer-aided detection (CAD) product (InferRead CT Lung Research, ICLR) in malignancy risk prediction using a real-world database.

Methods

This retrospective study assessed 486 consecutive resected lung lesions, including 320 adenocarcinomas, 40 other malignancies, 55 metastases, and 71 benign lesions, from September 2015 to November 2018. The malignancy risk probability of each lesion was obtained using the ICLR software based on a 3D convolutional neural network (CNN) with DenseNet architecture as a backbone (without clinical data). Two resident doctors independently graded each lesion using patient clinical history. One doctor (R1) has 3 years of chest radiology experience, and the other doctor (R2) has 3 years of general radiology experience. Cochran's Q test was used to assess the performances of the AI compared to the radiologists.

Results

The accuracy of malignancy-risk prediction using the ICLR for adenocarcinomas, other malignancies, metastases, and benign lesions was 93.4% (299/320), 95.0% (38/40), 50.9% (28/55), and 40.8% (29/71), respectively. The accuracy was significantly higher in adenocarcinomas and other malignancies compared to metastases and benign lesions (all P<0.05). The overall accuracy of risk prediction for R1 was 93.6% (455/486) and 87.4% for R2 (425/486), both of which were higher than the 81.1% accuracy obtained with the ICLR (394/486) (R1 vs. ICLR: P<0.001; R2 vs. ICLR: P=0.001), especially in assessing the risk of metastases (P<0.05). R1 performed better than R2 at risk prediction (P=0.001).

Conclusions

The accuracy of the ICLR for risk prediction is very high for primary lung cancers but poor for metastases and benign lesions.

Early detection of lung cancer in Czech high-risk asymptomatic individuals (ELEGANCE): A study protocol

BACKGROUND

Lung cancer screening in high-risk population increases the proportion of patients diagnosed at a resectable stage.

AIMS

To optimize the selection criteria and quality indicators for lung cancer screening by low-dose CT (LDCT) in the Czech population of high-risk individuals. To compare the influence of screening on the stage of lung cancer at the time of the diagnosis with the stage distribution in an unscreened population. To estimate the impact on life-years lost according to the stage-specific cancer survival and stage distribution in the screened population. To calculate the cost-effectiveness of the screening program.

METHODS

Based on the evidence from large national trials - the National Lung Screening Trial in the USA (NLST), the NELSON study, the recent recommendations of the Fleischner society, the American College of Radiology, and I-ELCAP action group, we developed a protocol for a single-arm prospective study in the Czech Republic for the screening of high-risk asymptomatic individuals. The study commenced in August 2020.

RESULTS

The inclusion criteria are: age 55 to 74 years; smoking: ≥30 pack-years; smoker or ex-smoker <15 years; performance status (0-1). The screening timepoints are at baseline and 1 year. The LDCT acquisition has a target CTDIvol ≤0.5mGy and effective dose ≤0.2mSv for a standard-size patient. The interpretation of findings is primarily based on nodule volumetry, volume doubling time (and related risk of malignancy). The management includes follow-up LDCT, contrast enhanced CT, PET/CT, tissue sampling. The primary outcome is the number of cancers detected at a resectable stage, secondary outcomes include the average cost per diagnosis of lung cancer, the number, cost, complications of secondary examinations, and the number of potentially important secondary findings.

CONCLUSIONS

A study protocol for early detection of lung cancer in Czech high-risk asymptomatic individuals (ELEGANCE) study using LDCT has been described.

Strategic Initiatives for Veterans with Lung Cancer

Background

Lung cancer is a leading cause of cancer-related mortality among veterans-as well as the US population-despite veterans' access to advanced medical technologies within the Veterans Health Administration (VHA). To improve outcomes, the VHA launched 3 lung cancer treatment initiatives in 2016 and 2017.

Observations

This article summarizes the VHA lung cancer initiatives and discusses future programs aimed to improve care for veterans. The US Department of Veterans Affairs (VA) Partnership to Increase Access to Lung Screening aims to reduce lung cancer mortality among veterans at risk by increasing access to low-dose computed tomography lung screening scans. The VALOR study is a randomized phase 3 clinical trial that evaluates optimal treatment for participants with operable early stage non-small cell lung cancer (NSCLC). This trial plans to enroll veterans with stage I NSCLC who will be randomly assigned to treatment with either surgical lobectomy or stereotactic body radiation therapy. Researchers will follow each participant for at least 5 years to evaluate which treatment, if either, results in a higher overall survival rate. The VA Radiation Oncology Quality Surveillance program compares treatment of veterans with lung cancer in the VHA with quality standards recommended by nationally recognized experts in lung cancer care.

Conclusions

The VHA continues to prioritize resources to improve and assure optimal outcomes for veterans with lung cancer. Future efforts include creating a national network of lung cancer centers of excellence to ensure that treatment decisions for veterans with lung cancer are based on all available molecular information, including data on pharmacogenomic profiles.

Estimation of the tumor size at cure threshold among aggressive non-small cell lung cancers (NSCLCs): evidence from the surveillance, epidemiology, and end results (SEER) program and the national lung screening trial (NLST)

The National Lung Screening Trial (NLST) demonstrated that non-small cell lung cancer (NSCLC) mortality can be reduced by a program of annual CT screening in high-risk individuals. However, CT screening regimens and adherence vary, potentially impacting the lung cancer mortality benefit. We defined the NSCLC cure threshold as the maximum tumor size at which a given NSCLC would be curable due to early detection. We obtained data from 518,234 NSCLCs documented in the U.S. SEER cancer registry between 1988 and 2012 and 1769 NSCLCs detected in the NLST. We demonstrated mathematically that the distribution function governing the cure threshold for the most aggressive NSCLCs, G(x|Φ = 1), was embedded in the probability function governing detection of SEER-documented NSCLCs. We determined the resulting probability functions governing detection over a range of G(x|Φ = 1) scenarios and compared them with their expected functional forms. We constructed a simulation framework to determine the cure threshold models most consistent with tumor sizes and outcomes documented in SEER and the NLST. Whereas the median tumor size for lethal NSCLCs documented in SEER is 43 mm (males) and 40 mm (females), a simulation model in which the median cure threshold for the most aggressive NSCLCs is 10 mm (males) and 15 mm (females) best fit the SEER and NLST data. The majority of NSCLCs in the NLST were treated at sizes greater than our median cure threshold estimates. New technology is needed to better distinguish and treat the most aggressive NSCLCs when they are small (i.e., 5-15 mm).