Current Controversies in Cardiothoracic Imaging: Low-dose Computerized Tomographic Overdiagnosis of Lung Cancer is Substantial; Its Consequences are Underappreciated-Point

Monitoring non-small cell lung cancer progression and treatment response through hyaluronic acid in sputum

We evaluated whether hyaluronan (HA) levels in the sputum could be used as a noninvasive tool to predict progressive disease and treatment response, as detected in a computed tomography scan in non-small cell lung cancer (NSCLC) patients. Sputum samples were collected from 84 patients with histological confirmation of NSCLC, 33 of which were in early-stage and 51 in advanced-stage disease. Patients received systemic chemotherapy (CT) after surgery (n=36), combined CT and immunotherapy (IO) (n=15), or targeted therapy for driver mutation and disease relapse (N=4). The primary end-point was to compare sputum HA levels in two different concentrations of hypertonic saline solution with overall survival (OS) and the secondary and exploratory end-points were radiologic responses to treatment and patient outcome. Higher concentrations of HA in the sputum were significantly associated to factors related to tumor stage, phenotype, response to treatment, and outcome. In the early stage, patients with lower sputum HA levels before treatment achieved a complete tumor response after systemic CT with better progression-free survival (PFS) than those with high HA levels. We also examined the importance of the sputum HA concentration and tumor response in the 51 patients who developed metastatic disease and received CT+IO. Patients with low levels of sputum HA showed a complete tumor response in the computed tomography scan and stable disease after CT+IO treatment, as well as a better PFS than those receiving CT alone. HA levels in sputum of NSCLC patients may serve as a candidate biomarker to detect progressive disease and monitor treatment response in computed tomography scans.

Artificial intelligence for detection and characterization of pulmonary nodules in lung cancer CT screening: ready for practice?

Lung cancer computed tomography (CT) screening trials using low-dose CT have repeatedly demonstrated a reduction in the number of lung cancer deaths in the screening group compared to a control group. With various countries currently considering the implementation of lung cancer screening, recurring discussion points are, among others, the potentially high false positive rates, cost-effectiveness, and the availability of radiologists for scan interpretation. Artificial intelligence (AI) has the potential to increase the efficiency of lung cancer screening. We discuss the performance levels of AI algorithms for various tasks related to the interpretation of lung screening CT scans, how they compare to human experts, and how AI and humans may complement each other. We discuss how AI may be used in the lung cancer CT screening workflow according to the current evidence and describe the additional research that will be required before AI can take a more prominent role in the analysis of lung screening CT scans.

Machine Learning/Deep Neuronal Network: Routine Application in Chest Computed Tomography and Workflow Considerations

The constantly increasing number of computed tomography (CT) examinations poses major challenges for radiologists. In this article, the additional benefits and potential of an artificial intelligence (AI) analysis platform for chest CT examinations in routine clinical practice will be examined. Specific application examples include AI-based, fully automatic lung segmentation with emphysema quantification, aortic measurements, detection of pulmonary nodules, and bone mineral density measurement. This contribution aims to appraise this AI-based application for value-added diagnosis during routine chest CT examinations and explore future development perspectives.

Non-invasive exploration of metabolic profile of lung cancer with Magnetic Resonance Spectroscopy and Mass Spectrometry

BACKGROUND

Lung cancer is a major cause of global morbidity and mortality. Current low dose CT screening is invasive and its role remains contentious. There are no known biomarkers to monitor treatment response, detect disease recurrence and patient selection for adjuvant treatment after curative surgical resection. Hence there is an urgent need to explore non-conventional and non-invasive tools to develop novel biomarkers to improve the outcome of this lethal cancer.

METHODS

This is an ongoing exploratory and translational study involving collection of bio fluids from 50 patients with early stage non-small cell lung cancer before and after surgical resection. The primary objective is to identify cancer specific metabolome in body fluids - sputum, exhaled breath condensate, blood and urine of the patients with early stage non-small cell lung cancer using Magnetic Resonance Spectroscopy and Mass Spectroscopy.

CONCLUSION

The trajectory of change in metabolic profile of body fluids before and after surgical resection may have potential clinical applications in lung cancer screening, as biomarkers for disease recurrence and exploration of novel targets for therapeutic intervention.