A practical and adaptive approach to lung cancer screening: a review of international evidence and position on CT lung cancer screening in the Singaporean population by the College of Radiologists Singapore

Characteristics of Singapore lung cancer patients who miss out on lung cancer screening recommendations

INTRODUCTION

The National Lung Screening Trial (NLST) identified individuals at high risk for lung cancer and showed that serial low-dose helical computed tomography could identify lung cancer at an earlier stage, leading to mortality reduction. However, there is little evidence regarding the effectiveness of the NLST criteria for the Asian population.

METHODS

We performed a retrospective audit in our hospital from January 2018 to December 2018, with the aim to describe the characteristics of patients diagnosed with lung cancer and to identify patients who would miss out on lung cancer screening when the NLST criteria was applied.

RESULTS

We found that only 38.1% of our cohort who were diagnosed with lung cancer met the NLST criteria strictly by age and smoking status. Patients who met the screening criteria would have derived significant benefits from it, as 85.4% of our patients had presented at an advanced stage and 54.6% died within 1 year. When the United States Preventive Services Task Force criteria was applied, it increased the sensitivity of lung cancer diagnosis to 58.7%. Only 15.5% of the female patients with lung cancer met the NLST criteria; their low smoking quantity was a significant contributing factor for exclusion.

CONCLUSION

The majority of Singapore patients diagnosed with lung cancer, especially females, would not have been identified with the NLST criteria. However, those who met the inclusion criteria would have benefited greatly from screening. Extending the screening age upper limit may yield benefits and improved sensitivity in the Singapore context.

The Effects of Artificial Intelligence Assistance on the Radiologists' Assessment of Lung Nodules on CT Scans: A Systematic Review

To reduce the number of missed or misdiagnosed lung nodules on CT scans by radiologists, many Artificial Intelligence (AI) algorithms have been developed. Some algorithms are currently being implemented in clinical practice, but the question is whether radiologists and patients really benefit from the use of these novel tools. This study aimed to review how AI assistance for lung nodule assessment on CT scans affects the performances of radiologists. We searched for studies that evaluated radiologists' performances in the detection or malignancy prediction of lung nodules with and without AI assistance. Concerning detection, radiologists achieved with AI assistance a higher sensitivity and AUC, while the specificity was slightly lower. Concerning malignancy prediction, radiologists achieved with AI assistance generally a higher sensitivity, specificity and AUC. The radiologists' workflows of using the AI assistance were often only described in limited detail in the papers. As recent studies showed improved performances of radiologists with AI assistance, AI assistance for lung nodule assessment holds great promise. To achieve added value of AI tools for lung nodule assessment in clinical practice, more research is required on the clinical validation of AI tools, impact on follow-up recommendations and ways of using AI tools.

Validation of low-dose lung cancer PET-CT protocol and PET image improvement using machine learning

PURPOSE

To conduct a simplified lesion-detection task of a low-dose (LD) PET-CT protocol for frequent lung screening using 30% of the effective PETCT dose and to investigate the feasibility of increasing clinical value of low-statistics scans using machine learning.

METHODS

We acquired 33 SD PET images, of which 13 had actual LD (ALD) PET, and simulated LD (SLD) PET images at seven different count levels from the SD PET scans. We employed image quality transfer (IQT), a machine learning algorithm that performs patch-regression to map parameters from low-quality to high-quality images. At each count level, patches extracted from 23 pairs of SD/SLD PET images were used to train three IQT models - global linear, single tree, and random forest regressions with cubic patch sizes of 3 and 5 voxels. The models were then used to estimate SD images from LD images at each count level for 10 unseen subjects. Lesion-detection task was carried out on matched lesion-present and lesion-absent images.

RESULTS

LD PET-CT protocol yielded lesion detectability with sensitivity of 0.98 and specificity of 1. Random forest algorithm with cubic patch size of 5 allowed further 11.7% reduction in the effective PETCT dose without compromising lesion detectability, but underestimated SUV by 30%.

CONCLUSION

LD PET-CT protocol was validated for lesion detection using ALD PET scans. Substantial image quality improvement or additional dose reduction while preserving clinical values can be achieved using machine learning methods though SUV quantification may be biased and adjustment of our research protocol is required for clinical use.