Outstanding negative prediction performance of solid pulmonary nodule volume AI for ultra-LDCT baseline lung cancer screening risk stratification 

Objective: To evaluate performance of AI as a standalone reader in ultra-low-dose CT lung cancer baseline screening, and compare it to that of experienced radiologists. Methods: 283 participants who underwent a baseline ultra-LDCT scan in Moscow Lung Cancer Screening, between February 2017–2018, and had at least one solid lung nodule, were included. Volumetric nodule measurements were performed by five experienced blinded radiologists, and independently assessed using an AI lung cancer screening prototype (AVIEW LCS, v1.0.34, Coreline Soft, Co. ltd, Seoul, Korea) to automatically detect, measure, and classify solid nodules. Discrepancies were stratified into two groups: positive misclassification (PM); nodule classified by the reader as a NELSON plus /EUPS-indeterminate/positive nodule, which at the reference consensus read was < 100 mm3, and negative-misclassification (NM); nodule classified as a NELSON-plus /EUPS-negative nodule, which at consensus read was ≥ 100 mm3. Results: 1149 nodules with a solid component were detected, of which 878 were classified as solid nodules. For the largest solid nodule per participant (n = 283); 61 [21.6 %; 53 PM, 8 NM] discrepancies were reported for AI as a standalone reader, compared to 43 [15.1 %; 22 PM, 21 NM], 36 [12.7 %; 25 PM, 11 NM], 29 [10.2 %; 25 PM, 4 NM], 28 [9.9 %; 6 PM, 22 NM], and 50 [17.7 %; 15 PM, 35 NM] discrepancies for readers 1, 2, 3, 4, and 5 respectively.
Conclusion: Our results suggest that through the use of AI as an impartial reader in baseline lung cancer screening, negative-misclassification results could exceed that of four out of five experienced radiologists, and radiologists’ workload could be drastically diminished by up to 86.7%.

Design and Rationale of the HANSE Study: A Holistic German Lung Cancer Screening Trial Using Low-Dose Computed Tomography

Despite the high prevalence and mortality of lung cancer and proven effectiveness of low-dose computed tomography (LDCT) to reduce mortality, Germany still lacks a national screening program. The German Institute for Quality and Efficiency in Health Care (IQWiG) and the Federal Office for Radiation Protection (BfS) both published positive scientific evaluations recommending a quality-controlled national screening program. IQWiG underlined the importance of a clear risk definition, integrated smoking cessation programs, and quality assurance, highlighting the necessity of procedural optimization.

In the HANSE study, former and current smokers aged 55-79 years are assessed for their lung cancer risk by the NELSON and PLCOM2012 risk scores. 5000 high-risk participants, defined as PLCOM2012 6-year risk ≥ 1.58 % or fulfilling NELSON risk inclusion criteria, will be screened by LDCT at baseline and after 12 months. Lung nodules are analyzed by a modified Lung-RADS 1.1 score of the HANSE study, and values of emphysema and coronary calcium are determined and randomly reported to the participants. 7100 low-risk participants serve as a control. All patients are followed-up for up to 10 years. The sensitivity and specificity of the two risk assessments and LDCT screening, effects of the randomized LDCT reporting, efficiency of lung nodule management, and several other factors are assessed to analyze the success and quality of the holistic screening program. The HANSE study is designed as a holistic lung cancer screening study in northern Germany to answer pressing questions for a successful implementation of an effective German lung cancer screening program.

• HANSE is designed to address pressing questions for the implementation of lung cancer screening in Germany.
• HANSE compares NELSON and PLCOM2012 risk assessments for optimal definition of the high-risk group.
• HANSE integrates cardiac calcium and pulmonary emphysema scoring in a holistic screening approach.