Survival of patients with stage I lung cancer detected on CT screening

Unsupervised lung CT image registration via stochastic decomposition of deformation fields

We address the problem of lung CT image registration, which underpins various diagnoses and treatments for lung diseases. The main crux of the problem is the large deformation that the lungs undergo during respiration. This physiological process imposes several challenges from a learning point of view. In this paper, we propose a novel training scheme, called stochastic decomposition, which enables deep networks to effectively learn such a difficult deformation field during lung CT image registration. The key idea is to stochastically decompose the deformation field, and supervise the registration by synthetic data that have the corresponding appearance discrepancy. The stochastic decomposition allows for revealing all possible decompositions of the deformation field. At the learning level, these decompositions can be seen as a prior to reduce the ill-posedness of the registration yielding to boost the performance. We demonstrate the effectiveness of our framework on Lung CT data. We show, through extensive numerical and visual results, that our technique outperforms existing methods.

Exhaled VOC detection in lung cancer screening: a comprehensive meta-analysis

BACKGROUND

Lung cancer (LC), characterized by high incidence and mortality rates, presents a significant challenge in oncology. Despite advancements in treatments, early detection remains crucial for improving patient outcomes. The accuracy of screening for LC by detecting volatile organic compounds (VOCs) in exhaled breath remains to be determined.

METHODS

Our systematic review, following PRISMA guidelines and analyzing data from 25 studies up to October 1, 2023, evaluates the effectiveness of different techniques in detecting VOCs. We registered the review protocol with PROSPERO and performed a systematic search in PubMed, EMBASE and Web of Science. Reviewers screened the studies' titles/abstracts and full texts, and used QUADAS-2 tool for quality assessment. Then performed meta-analysis by adopting a bivariate model for sensitivity and specificity.

RESULTS

This study explores the potential of VOCs in exhaled breath as biomarkers for LC screening, offering a non-invasive alternative to traditional methods. In all studies, exhaled VOCs discriminated LC from controls. The meta-analysis indicates an integrated sensitivity and specificity of 85% and 86%, respectively, with an AUC of 0.93 for VOC detection. We also conducted a systematic analysis of the source of the substance with the highest frequency of occurrence in the tested compounds. Despite the promising results, variability in study quality and methodological challenges highlight the need for further research.

CONCLUSION

This review emphasizes the potential of VOC analysis as a cost-effective, non-invasive screening tool for early LC detection, which could significantly improve patient management and survival rates.

Assessing the efficiency of eligibility criteria for low-dose computed tomography lung screening in China according to current guidelines

BACKGROUND

Evidence from observational studies indicates that lung cancer screening (LCS) guidelines with high rates of lung cancer (LC) underdiagnosis, and although current screening guidelines have been updated and eligibility criteria for screening have been expanded, there are no studies comparing the efficiency of LCS guidelines in Chinese population.

METHODS

Between 2005 and 2022, 31,394 asymptomatic individuals were screened using low-dose computed tomography (LDCT) at our institution. Demographic data and relevant LC risk factors were collected. The efficiency of the LCS for each guideline criteria was expressed as the efficiency ratio (ER). The inclusion rates, eligibility rates, LC detection rates, and ER based on the different eligibility criteria of the four guidelines were comparatively analyzed. The four guidelines were as follows: China guideline for the screening and early detection of lung cancer (CGSL), the National Comprehensive Cancer Network (NCCN), the United States Preventive Services Task Force (USPSTF), and International Early Lung Cancer Action Program (I-ELCAP).

RESULTS

Of 31,394 participants, 298 (155 women, 143 men) were diagnosed with LC. For CGSL, NCCN, USPSTF, and I-ELCAP guidelines, the eligibility rates for guidelines were 13.92%, 6.97%, 6.81%, and 53.46%; ERe for eligibility criteria were 1.46%, 1.64%, 1.51%, and 1.13%, respectively; and for the inclusion rates, they were 19.0%, 9.5%, 9.3%, and 73.0%, respectively. LCs which met the screening criteria of CGSL, NCCN, USPSTF, and I-ELCAP guidelines were 29.2%, 16.4%, 14.8%, and 86.6%, respectively. The age and smoking criteria for CGSL were stricter, hence resulting in lower rates of LC meeting the screening criteria. The CGSL, NCCN, and USPSTF guidelines showed the highest underdiagnosis in the 45-49 age group (17.4%), while the I-ELCAP guideline displayed the highest missed diagnosis rate (3.0%) in the 35-39 age group. Males and females significantly differed in eligibility based on the criteria of the four guidelines (P < 0.001).

CONCLUSIONS

The I-ELCAP guideline has the highest eligibility rate for both males and females. But its actual efficiency ratio for those deemed eligible by the guideline was the lowest. Whereas the NCCN guideline has the highest ERe value for those deemed eligible by the guideline.

Incidental diagnosis of lung cancer on chest CT scan performed for suspected or documented COVID-19 infection

CONTEXT

Recent studies have shown a benefit of chest computed tomography (CT scan) in lung cancer screening. The COVID-19 pandemic has led to many chest CT scan performed on a large population. The objective of this study was to describe the incidence and characteristics of lung cancer detected on chest CT scan, outside the framework of a clinical trial, for a suspected or documented COVID-19 infection.

METHODS

We conducted a multicenter study, carried out from the analysis of data from the prospective COVID-19 database of the Clinical Data Warehouse of the Greater Paris University Hospitals (AP-HP). We identified the patients who had been diagnosed with a lung cancer, due to a chest CT scan done for a suspected or confirmed COVID-19 infection. The study period was limited to the first two epidemic lockdowns: (03/01/20 - 05/31/20) and (10/10/20 - 11/30/20).

RESULTS

Over the study period, 24 390 patients had at least one chest CT scan. Among them, 72 lung cancer diagnoses were made (incidence 0.30 %; median age 67.4 years old, 50.0 % current smokers, 55.6 % adenocarcinoma). Half of the lung cancer patients (n = 36) did not meet the National Lung Screening Trial inclusion criteria. Twenty-six patients (36.1 %) were diagnosed at an early stage, 25 (34.7 %) of whom received radical curative treatment. Twenty-six patients died during the follow-up (36.1 %) but none in early stages. The median overall survival in lung cancer patients was 693 days [532 - NA].

CONCLUSIONS

A large-scale chest CT scan strategy for suspected or documented COVID-19 infection has allowed a significant proportion of early-stage lung cancer diagnosis, all of which have benefited from curative treatment.

Timeliness of surgery for early-stage lung cancer: Patient factors and predictors

Objectives

Time-to-treatment initiation is an important consideration for patients undergoing thoracic surgery for early-stage lung cancer because delays have the potential to adversely affect outcomes. This study seeks to quantify time-to-treatment initiation for patients with clinical stage I lung cancer, explore patient factors and predictors that lead to an increased time-to-treatment initiation, and compare surgeon perception of appropriate time-to-treatment initiation to the results.

Methods

Time-to-treatment initiation was determined for patients enrolled in the Mount Sinai Initiative for Early Lung Cancer Research on Treatment study who underwent surgical resection for clinical stage I lung cancer between March 2016 and December 2021. The following dates were determined: (1) date of first suspicious radiologic imaging, (2) date of first biopsy, and (3) date of surgery. A total of 15 thoracic surgeons who participated in the Mount Sinai Initiative for Early Lung Cancer Research on Treatment were assessed on their perception on time-to-treatment initiation.

Results

For 638 patients, median time from first suspicious imaging findings to biopsy was 40 days, biopsy to surgery was 37 days, and suspicious imaging to surgery was 84 days. Significant factors that resulted in longer time-to-treatment initiation in the multivariate analysis were African American or Black race (P = .005), vascular disease (P = .01), and median household income less than $75,000 (P = .04). Although the surgeon's perception was that the average time from biopsy to surgery was 28 days, it was longer for 63.5% of participants; surgeon perception of maximum time between diagnosis and surgery was 84 days and longer for 28.7% of participants.

Conclusions

Patient factors such as race, income, and comorbidities were found to have differences in time-to-treatment initiation. Delays to surgery exceeded the expectations of thoracic surgeons.

Global Burden of Lung Cancer Attributable to Household Fine Particulate Matter Pollution in 204 Countries and Territories, 1990 to 2019

INTRODUCTION

Household particulate matter (PM) air pollution is substantially associated with lung cancer. Nevertheless, the global burden of lung cancer attributable to household PM2.5 is still uncertain.

METHODS

In this study, data from the Global Burden and Disease Study 2019 are used to thoroughly assess the burden of lung cancer associated with household PM2.5.

RESULTS

The number of deaths and disability-adjusted life-years (DALYs) attributable to household PM2.5 was found to be 0.08 million and 1.94 million, respectively in 2019. Nevertheless, the burden of lung cancer attributable to household PM2.5 decreased from 1990 to 2019. At the sociodemographic index (SDI) district level, the middle SDI region had the most number of lung cancer deaths and DALYs attributable to household PM2.5. Moreover, the burden of lung cancer was mainly distributed in low-SDI regions, such as Sub-Saharan Africa. Conversely, in high-SDI regions, the age-standardized mortality rate and age-standardized DALY rate of lung cancer attributable to household PM2.5 exhibit the most rapid declines. The burden of lung cancer attributable to household PM2.5 is heavier for men than for women. The sex difference is more obvious in the elderly.

CONCLUSIONS

The prevalence of lung cancer attributable to household PM2.5 has exhibited a declining trend from 1990 to 2019 owing to a concurrent decline in household PM2.5 exposure.

Impact of OLD/Emphysema in LC Mortality Risk in Screening Programs: An Analysis of NLST and P-IELCAP

INTRODUCTION

The impact of obstructive lung disease (OLD) and emphysema on lung cancer (LC) mortality in patients undergoing LC screening is controversial.

METHODS

Patients with spirometry and LC diagnosed within the first three rounds of screening were selected from the National Lung Screening Trial (NLST) and from the Pamplona International Early Lung Cancer Detection Program (P-IELCAP). Medical and demographic data, tumor characteristics, comorbidities and presence of emphysema were collected. The effect of OLD and emphysema on the risk of overall survival was assessed using unadjusted and adjusted Cox models, competing risk regression analysis, and propensity score matching.

RESULTS

Data from 353 patients with LC, including 291 with OLD and/or emphysema and 62 with neither, were analyzed. The median age was 67.3 years-old and 56.1% met OLD criteria, predominantly mild (1: 28.3%, 2: 65.2%). Emphysema was present in 69.4% of the patients. Patients with OLD and/or emphysema had worse survival on univariate analysis (HR: 1.40; 95% CI: 0.86-2.31; p=0.179). However, after adjusting for LC stage, age, and sex, the HR was 1.02 (95% CI: 0.61-1.70; p=0.952). Specific LC survival between both groups showed an adjusted HR of 0.90 (95% CI: 0.47-1.72; p=0.76). Propensity score matching found no statistically significant difference in overall survival (HR: 1.03; 95% CI: 0.59-1.9; p=0.929).

CONCLUSION

The survival of LC patients diagnosed in the context of screening is not negatively impacted by the coexistence of mild OLD and/or emphysema.

A novel microRNA miR-4433a-3p as a potential diagnostic biomarker for lung adenocarcinoma

Background

Lung adenocarcinoma is one of the leading causes of cancer-related deaths because of the lack of early specific clinical indicators. MicroRNAs (miRNAs) have become the focus in lung cancer diagnosis. Further studies are required to explore miRNA expression in the serum of lung adenocarcinoma patients and their correlation with therapy and analyse specific messenger RNA targets to improve the specificity and sensitivity of early diagnosis.

Methods

The Toray 3D-Gene miRNA array was used to compare the expression levels of various miRNAs in the sera of patients with lung adenocarcinoma and healthy volunteers. Highly expressed miRNAs were selected for further analysis. To verify the screening results, serum and pleural fluid samples were analysed using qRT-PCR. Serum levels of the miRNAs and their correlation with the clinical information of patients with lung adenocarcinoma were analysed. The functions of miRNAs were further analysed using the Kyoto Encyclopedia of Gene and Genomes and Gene Ontology databases.

Results

Microarray analysis identified 60 and 50 miRNAs with upregulated and downregulated expressions, respectively, in the serum of patients with lung adenocarcinoma compared to those in healthy individuals. Using qRT-qPCR to detection of miRNAs expression in the serum or pleural effusion of patients with early and advanced lung adenocarcinoma, we found that miR-4433a-3p could be used as a diagnostic marker and therapeutic evaluation indicator for lung adenocarcinoma. Serum of miR-4433a-3p levels significantly correlated with the clinical stage. miR-4433a-3p may be more suitable than other tumour markers for the early diagnosis and evaluation of therapeutic effects in lung adenocarcinoma. miR-4433a-3p may affect tumour growth and metastasis by acting on target genes (PIK3CD, UBE2J2, ICMT, PRDM16 and others) and regulating tumour-related signalling pathways (MAPK signal pathway, Ras signalling pathway and others).

Conclusion

miR-4433a-3p may serve as a biomarker for the early diagnosis of lung adenocarcinoma and monitoring of therapeutic effects.

Tumor Location Is an Independent Prognostic Factor in Completely Resected Pathological Stage I Non-Small Cell Lung Cancer: A Multicenter Retrospective Study

Previous studies suggested that the location of the primary tumor in non-small cell lung cancer (NSCLC) is associated with clinical features and prognosis, but results are conflicting. The purpose of this study was to explore tumor location as an independent risk factor of survival for patients with completely resected pathological stage I NSCLC. This was a multicenter retrospective study conducted in Taiwan. Included patients were diagnosed with stage I NSCLC and had undergone primary tumor resection. Variables including tumor location, pathological stage, histological differentiation, and International Association for the Study of Lung Cancer (IASLC) grade were evaluated for predictive ability for disease-free survival (DFS) and overall survival (OS). A total of 208 patients were included, with 123 (59.1%) patients having a primary tumor in the upper and middle lobes. The median duration of follow-up for survivors was 60.5 months. Compared to patients with IASLC Grade 3 disease, patients with Grade 1 disease had significantly longer DFS. Tumor location and IASLC grade were independent predictors for OS in multivariate analysis. Specifically, patients with NSCLC in the lower lobe and patients who are histologically classified as IASLC Grade 3 may have poorer prognosis and require greater attention to improve outcomes.

Lipidomics reveals new lipid-based lung adenocarcinoma early diagnosis model

Lung adenocarcinoma (LUAD) continues to pose a significant mortality risk with a lack of dependable biomarkers for early noninvasive cancer detection. Here, we find that aberrant lipid metabolism is significantly enriched in lung cancer cells. Further, we identified four signature lipids highly associated with LUAD and developed a lipid signature-based scoring model (LSRscore). Evaluation of LSRscore in a discovery cohort reveals a robust predictive capability for LUAD (AUC: 0.972), a result further validated in an independent cohort (AUC: 0.92). We highlight one lipid signature biomarker, PE(18:0/18:1), consistently exhibiting altered levels both in cancer tissue and in plasma of LUAD patients, demonstrating significant predictive power for early-stage LUAD. Transcriptome analysis reveals an association between increased PE(18:0/18:1) levels and dysregulated glycerophospholipid metabolism, which consistently displays strong prognostic value across two LUAD cohorts. The combined utility of LSRscore and PE(18:0/18:1) holds promise for early-stage diagnosis and prognosis of LUAD.

Long-term Survival After Lung Cancer Resection in the National Lung Screening Trial

BACKGROUND

This study sought to evaluate the long-term survival and causes of death after surgery among patients with pathologic stage IA non-small cell lung cancer (NSCLC) in the National Lung Screening Trial (NLST).

METHODS

Patients who underwent surgery and who had a diagnosis of pathologic stage IA NSCLC in the NLST were identified for analysis. The 5- and 10-year overall survival and lung cancer-specific survival, stratified by operation type, were evaluated. Among patients who underwent lobectomy, the causes of death and the cumulative incidence of lung cancer death were assessed.

RESULTS

A total of 380 patients (n = 329, 86.6% lobectomy; n = 20, 5.3% segmentectomy; n = 31, 8.1% wedge resection) met inclusion criteria. Median follow-up time from the date of surgery was 7.8 years (interquartile range, 4.8-10.7 years). The 10-year overall survival rate was 58.3% (95% CI, 52.4%-63.8%) for lobectomy, 59.9% (95% CI, 33.2%-78.8%) for segmentectomy, and 45.2% (95% CI, 20.8%-66.9%) for wedge resection. The 10-year lung cancer-specific survival rate was 74.3% (95% CI, 68.6%-79.1%) for lobectomy, 81.3% (95% CI, 51.3%-93.8%) for segmentectomy, and 84.8% (95% CI, 64.0%-94.1%) for wedge resection. Lung cancer was the leading cause of death, accounting for 55.8% of deaths after lobectomy. The 10-year cumulative incidence of lung cancer death after lobectomy was 22.5% (95% CI, 18.3%-27.1%).

CONCLUSIONS

The 10-year overall survival rate after lobectomy among patients with pathologic stage IA NSCLC in the NLST was 58%. Lung cancer was the leading cause of death, accounting for more than 55% of deaths.

Perspective on Management of Low-Dose Computed Tomography Findings on Low-Dose Computed Tomography Examinations for Lung Cancer Screening. From the International Association for the Study of Lung Cancer Early Detection and Screening Committee

Lung cancer screening using low-dose computed tomography (LDCT) carefully implemented has been found to reduce deaths from lung cancer. Optimal management starts with selection of eligibility criteria, counseling of screenees, smoking cessation, selection of the regimen of screening which specifies the imaging protocol, and workup of LDCT findings. Coordination of clinical, radiologic, and interventional teams and ultimately treatment of diagnosed lung cancers under screening determine the benefit of LDCT screening. Ethical considerations of who should be eligible for LDCT screening programs are important to provide the benefit to as many people at risk of lung cancer as possible. Unanticipated diseases identified on LDCT may offer important benefits through early detection of leading global causes of death, such as cardiovascular diseases and chronic obstructive pulmonary disease, as the latter may result from conditions such as emphysema and bronchiectasis, which can be identified early on LDCT. This report identifies the key components of the regimen of LDCT screening for lung cancer which include the need for a management system to provide data for continuous updating of the regimen and provides quality assurance assessment of actual screenings. Multidisciplinary clinical management is needed to maximize the benefit of early detection, diagnosis, and treatment of lung cancer. Different regimens have been evolving throughout the world as the resources and needs may be different, for countries with limited resources. Sharing of results, further knowledge, and incorporation of technologic advances will continue to accelerate worldwide improvements in the diagnostic and treatment approaches.

Artificial intelligence in lung cancer screening: Detection, classification, prediction, and prognosis

BACKGROUND

The exceptional capabilities of artificial intelligence (AI) in extracting image information and processing complex models have led to its recognition across various medical fields. With the continuous evolution of AI technologies based on deep learning, particularly the advent of convolutional neural networks (CNNs), AI presents an expanded horizon of applications in lung cancer screening, including lung segmentation, nodule detection, false-positive reduction, nodule classification, and prognosis.

METHODOLOGY

This review initially analyzes the current status of AI technologies. It then explores the applications of AI in lung cancer screening, including lung segmentation, nodule detection, and classification, and assesses the potential of AI in enhancing the sensitivity of nodule detection and reducing false-positive rates. Finally, it addresses the challenges and future directions of AI in lung cancer screening.

RESULTS

AI holds substantial prospects in lung cancer screening. It demonstrates significant potential in improving nodule detection sensitivity, reducing false-positive rates, and classifying nodules, while also showing value in predicting nodule growth and pathological/genetic typing.

CONCLUSIONS

AI offers a promising supportive approach to lung cancer screening, presenting considerable potential in enhancing nodule detection sensitivity, reducing false-positive rates, and classifying nodules. However, the universality and interpretability of AI results need further enhancement. Future research should focus on the large-scale validation of new deep learning-based algorithms and multi-center studies to improve the efficacy of AI in lung cancer screening.

Lung cancer screening in Brazil: recommendations from the Brazilian Society of Thoracic Surgery, Brazilian Thoracic Association, and Brazilian College of Radiology and Diagnostic Imaging

Although lung cancer (LC) is one of the most common and lethal tumors, only 15% of patients are diagnosed at an early stage. Smoking is still responsible for more than 85% of cases. Lung cancer screening (LCS) with low-dose CT (LDCT) reduces LC-related mortality by 20%, and that reduction reaches 38% when LCS by LDCT is combined with smoking cessation. In the last decade, a number of countries have adopted population-based LCS as a public health recommendation. Albeit still incipient, discussion on this topic in Brazil is becoming increasingly broad and necessary. With the aim of increasing knowledge and stimulating debate on LCS, the Brazilian Society of Thoracic Surgery, the Brazilian Thoracic Association, and the Brazilian College of Radiology and Diagnostic Imaging convened a panel of experts to prepare recommendations for LCS in Brazil. The recommendations presented here were based on a narrative review of the literature, with an emphasis on large population-based studies, systematic reviews, and the recommendations of international guidelines, and were developed after extensive discussion by the panel of experts. The following topics were reviewed: reasons for screening; general considerations about smoking; epidemiology of LC; eligibility criteria; incidental findings; granulomatous lesions; probabilistic models; minimum requirements for LDCT; volumetric acquisition; risks of screening; minimum structure and role of the multidisciplinary team; practice according to the Lung CT Screening Reporting and Data System; costs versus benefits of screening; and future perspectives for LCS.

Potential Role of Lymphocyte CD44 in Determining Treatment Selection Between Stereotactic Body Radiation Therapy and Surgery for Early-Stage Non-Small Cell Lung Cancer

PURPOSE

Stereotactic body radiation therapy (SBRT) versus surgery for operable early-stage non-small cell lung cancer (ES-NSCLC) remains highly debated. Herein, we used spatial proteomics to identify whether any molecular biomarker(s) associate with the efficacy of either modality, in efforts to optimize treatment selection between surgery and SBRT for this population.

METHODS AND MATERIALS

We evaluated biopsy tissue samples from 44 patients with ES-NSCLC treated with first-line SBRT (cohort 1) by GeoMx Digital Spatial Profiling (DSP) with a panel of 70 proteins in 5 spatial molecular compartments: tumor (panCK+), leukocyte (CD45+), lymphocyte (CD3+), macrophage (CD68+), and stroma (α-SMA+). To validate the findings in cohort 1, biopsy samples from 52 patients with ES-NSCLC who received SBRT (cohort 2) and 62 patients with ES-NSCLC who underwent surgery (cohort 3) were collected and analyzed by multiplex immunofluorescence (mIF).

RESULTS

In cohort 1, higher CD44 expression in the lymphocyte compartment was associated with poorer recurrence-free survival (RFS) (DSP: P < .001; mIF: P < .001) and higher recurrence rate (DSP: P = .001; mIF: P = .004). mIF data from cohort 2 validated these findings (P < .05 for all). From cohort 3, higher lymphocyte CD44 predicted higher RFS after surgery (P = .003). Intermodality comparisons demonstrated that SBRT was associated with significantly higher RFS over surgery in CD44-low patients (P < .001), but surgery was superior to SBRT in CD44-high cases (P = .016).

CONCLUSIONS

Lymphocyte CD44 may not only be a predictor of SBRT efficacy in this population but also an important biomarker (pending validation by large prospective data) that could better sharpen selection for SBRT versus surgery in ES-NSCLC.

Lung adenocarcinoma: selection of surgical approaches in solid adenocarcinoma from the viewpoint of clinicopathologic features and tumor microenvironmental heterogeneity

Introduction

Solid adenocarcinoma represents a notably aggressive subtype of lung adenocarcinoma. Amidst the prevailing inclination towards conservative surgical interventions for diminutive lung cancer lesions, the critical evaluation of this subtype's malignancy and heterogeneity stands as imperative for the formulation of surgical approaches and the prognostication of long-term patient survival.

Methods

A retrospective dataset, encompassing 2406 instances of non-solid adenocarcinoma (comprising lepidic, acinar, and papillary adenocarcinoma) and 326 instances of solid adenocarcinoma, was analyzed to ascertain the risk factors concomitant with diverse histological variants of lung adenocarcinoma. Concurrently, RNA-sequencing data delineating explicit pathological subtypes were extracted from 261 cases in the TCGA database and 188 cases in the OncoSG database. This data served to illuminate the heterogeneity across lung adenocarcinoma (LUAD) specimens characterized by differential histological features.

Results

Solid adenocarcinoma is associated with an elevated incidence of pleural invasion, microscopic vessel invasion, and lymph node metastasis, relative to other subtypes of lung adenocarcinoma. Furthermore, the tumor microenvironment (TME) in solid pattern adenocarcinoma displayed suboptimal oxygenation and acidic conditions, concomitant with augmented tumor cell proliferation and invasion capacities. Energy and metabolic activities were significantly upregulated in tumor cells of the solid pattern subtype. This subtype manifested robust immune tolerance and capabilities for immune evasion.

Conclusion

This present investigation identifies multiple potential metrics for evaluating the invasive propensity, metastatic likelihood, and immune resistance of solid pattern adenocarcinoma. These insights may prove instrumental in devising surgical interventions that are tailored to patients diagnosed with disparate histological subtypes of LUAD, thereby offering valuable directional guidance.

Robust explanation supervision for false positive reduction in pulmonary nodule detection

BACKGROUND

Lung cancer is the deadliest and second most common cancer in the United States due to the lack of symptoms for early diagnosis. Pulmonary nodules are small abnormal regions that can be potentially correlated to the occurrence of lung cancer. Early detection of these nodules is critical because it can significantly improve the patient's survival rates. Thoracic thin-sliced computed tomography (CT) scanning has emerged as a widely used method for diagnosing and prognosis lung abnormalities.

PURPOSE

The standard clinical workflow of detecting pulmonary nodules relies on radiologists to analyze CT images to assess the risk factors of cancerous nodules. However, this approach can be error-prone due to the various nodule formation causes, such as pollutants and infections. Deep learning (DL) algorithms have recently demonstrated remarkable success in medical image classification and segmentation. As an ever more important assistant to radiologists in nodule detection, it is imperative ensure the DL algorithm and radiologist to better understand the decisions from each other. This study aims to develop a framework integrating explainable AI methods to achieve accurate pulmonary nodule detection.

METHODS

A robust and explainable detection (RXD) framework is proposed, focusing on reducing false positives in pulmonary nodule detection. Its implementation is based on an explanation supervision method, which uses nodule contours of radiologists as supervision signals to force the model to learn nodule morphologies, enabling improved learning ability on small dataset, and enable small dataset learning ability. In addition, two imputation methods are applied to the nodule region annotations to reduce the noise within human annotations and allow the model to have robust attributions that meet human expectations. The 480, 265, and 265 CT image sets from the public Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) dataset are used for training, validation, and testing.

RESULTS

Using only 10, 30, 50, and 100 training samples sequentially, our method constantly improves the classification performance and explanation quality of baseline in terms of Area Under the Curve (AUC) and Intersection over Union (IoU). In particular, our framework with a learnable imputation kernel improves IoU from baseline by 24.0% to 80.0%. A pre-defined Gaussian imputation kernel achieves an even greater improvement, from 38.4% to 118.8% from baseline. Compared to the baseline trained on 100 samples, our method shows less drop in AUC when trained on fewer samples. A comprehensive comparison of interpretability shows that our method aligns better with expert opinions.

CONCLUSIONS

A pulmonary nodule detection framework was demonstrated using public thoracic CT image datasets. The framework integrates the robust explanation supervision (RES) technique to ensure the performance of nodule classification and morphology. The method can reduce the workload of radiologists and enable them to focus on the diagnosis and prognosis of the potential cancerous pulmonary nodules at the early stage to improve the outcomes for lung cancer patients.

Factors influencing the intention for lung cancer screening in high-risk populations for lung cancer

Objective

Utilizing low-dose computed tomography for lung cancer screening has proven effective in reducing lung cancer mortality among high-risk individuals. This study aimed to investigate the health beliefs, knowledge of lung cancer, and cancer prevention behaviors in adults at high risk for lung cancer, with the goal of identifying predictors influencing their intention to undergo lung cancer screening.

Methods

The study utilized a descriptive cross-sectional design. Online questionnaires, including assessments of lung cancer screening health beliefs, knowledge of lung cancer, cancer prevention behaviors, intention to undergo lung cancer screening, and participant characteristics, were distributed to 186 individuals at high risk of lung cancer through a survey link. The data collection period spanned from April 26 to May 3, 2023. Analytical procedures encompassed descriptive statistics, independent t-test, one-way ANOVA, Pearson's correlations, and hierarchical multiple regression.

Results

The mean score for the intention to undergo lung cancer screening in our study was 3.66 out of 5. The regression model explaining the intention to undergo lung cancer screening accounted for 34.7% of the variance. Significant factors identified included stress level (β = 0.20, P = 0.002), perceived risk (β = 0.13, P = 0.040), self-efficacy (β = 0.35, P < 0.001), and engagement in cancer prevention behavior (β = 0.26, P < 0.001).

Conclusions

Healthcare providers should implement psychological interventions and provide education about cancer screening for high-risk individuals, aiming to enhance their perceived risk and self-efficacy, thus promoting a higher likelihood of undergoing screening.

An artificial intelligence-assisted diagnostic system for the prediction of benignity and malignancy of pulmonary nodules and its practical value for patients with different clinical characteristics

Objectives

This study aimed to explore the value of an artificial intelligence (AI)-assisted diagnostic system in the prediction of pulmonary nodules.

Methods

The AI system was able to make predictions of benign or malignant nodules. 260 cases of solitary pulmonary nodules (SPNs) were divided into 173 malignant cases and 87 benign cases based on the surgical pathological diagnosis. A stratified data analysis was applied to compare the diagnostic effectiveness of the AI system to distinguish between the subgroups with different clinical characteristics.

Results

The accuracy of AI system in judging benignity and malignancy of the nodules was 75.77% (p < 0.05). We created an ROC curve by calculating the true positive rate (TPR) and the false positive rate (FPR) at different threshold values, and the AUC was 0.755. Results of the stratified analysis were as follows. (1) By nodule position: the AUC was 0.677, 0.758, 0.744, 0.982, and 0.725, respectively, for the nodules in the left upper lobe, left lower lobe, right upper lobe, right middle lobe, and right lower lobe. (2) By nodule size: the AUC was 0.778, 0.771, and 0.686, respectively, for the nodules measuring 5-10, 10-20, and 20-30 mm in diameter. (3) The predictive accuracy was higher for the subsolid pulmonary nodules than for the solid ones (80.54 vs. 66.67%).

Conclusion

The AI system can be applied to assist in the prediction of benign and malignant pulmonary nodules. It can provide a valuable reference, especially for the diagnosis of subsolid nodules and small nodules measuring 5-10 mm in diameter.

Impact of systemic inflammatory markers in patients with ALK-positive non-small cell lung cancer treated with crizotinib

OBJECTIVES

To evaluate the prognostic utility of inflammation-based prognostic scores in patients with ALK-positive metastatic or non-resectable non-small-cell lung cancer (NSCLC) treated with crizotinib.

PATIENTS AND METHODS

A total of 82 patients with ALK-positive metastatic or non-resectable NSCLC who received ALK TKI crizotinib were included. Pre-treatment modified Glasgow prognostic score (mGPS), prognostic nutritional index (PNI), and systemic immune-inflammation index (SII) were calculated. Multivariable logistic regression and Cox proportional hazards models were used to assess the impact of pretreatment mGPS, PNI, and SII on overall survival (OS), progression-free survival (PFS), and objective response rate (ORR).

RESULTS

The ORR was 77.2%, while 1-year OS and PFS rates were 95.0% and 93.5%, respectively. The univariate analysis revealed significantly higher 1-year PFS (89.4 vs. 64.4%, p=0.043) and OS (92.0 vs. 83.3%, p=0.01) rates in patients with low (<934.7) vs. high (≥934.7) SII scores. Multivariate analysis revealed that PNI ≥0.09 was a significant determinant of poorer 1-year OS rates (hazard ratio [HR]: 2.46, 95% confidence interval [CI] 0.88-4.85, p=0.035). No significant difference was observed in survival rates according to gender, age, smoking status, prior lines of therapy, or mGPS scores, while higher mGPS scores (odds ratio [OR]: 0.1, 95%CI 0.16-1.04; p=0.009) and higher PNI scores (OR: 0.16, 95% CI 0.02-0.55; p=0.035) were associated with poorer ORR.

CONCLUSION

Our findings indicate the prognostic significance of PNI and SII in terms of survival outcome and the impact of mGPS and PNI on treatment response in patients with ALK-positive NSCLC treated with crizotinib.

Lung Cancer Screening: The European Perspective

Several randomized and observational studies on lung cancer screening held in Europe significantly contributed to the knowledge on low-dose computed tomography screening targets in high-risk individuals with smoking history and older than 50 years. In particular, steps forward have been made in the field of risk modeling, screening interval, diagnostic protocol with volumetry, optimization, overdiagnosis estimation, oncological outcome, oncological risk due to radiation exposure, recruitment, and communication strategy.

Historical Perspective on Lung Cancer Screening

Lung cancer represents a large burden on society with a staggering incidence and mortality rate that has steadily increased until recently. The impetus to design an effective screening program for the deadliest cancer in the United States and worldwide began in 1950. It has taken more than 50 years of numerous clinical trials and continued persistence to arrive at the development of modern-day screening program. As the program continues to grow, it is important for clinicians to understand its evolution, track outcomes, and continually assess the impact and bias of screening on the medical, social, and economic systems.

A 20-year Follow-up of the International Early Lung Cancer Action Program (I-ELCAP)

Background The low-dose CT (≤3 mGy) screening report of 1000 Early Lung Cancer Action Program (ELCAP) participants in 1999 led to the International ELCAP (I-ELCAP) collaboration, which enrolled 31 567 participants in annual low-dose CT screening between 1992 and 2005. In 2006, I-ELCAP investigators reported the 10-year lung cancer-specific survival of 80% for 484 participants diagnosed with a first primary lung cancer through annual screening, with a high frequency of clinical stage I lung cancer (85%). Purpose To update the cure rate by determining the 20-year lung cancer-specific survival of participants diagnosed with first primary lung cancer through annual low-dose CT screening in the expanded I-ELCAP cohort. Materials and Methods For participants enrolled in the HIPAA-compliant prospective I-ELCAP cohort between 1992 and 2022 and observed until December 30, 2022, Kaplan-Meier survival analysis was used to determine the 10- and 20-year lung cancer-specific survival of participants diagnosed with first primary lung cancer through annual low-dose CT screening. Eligible participants were aged at least 40 years and had current or former cigarette use or had never smoked but had been exposed to secondhand tobacco smoke. Results Among 89 404 I-ELCAP participants, 1257 (1.4%) were diagnosed with a first primary lung cancer (684 male, 573 female; median age, 66 years; IQR, 61-72), with a median smoking history of 43.0 pack-years (IQR, 29.0-60.0). Median follow-up duration was 105 months (IQR, 41-182). The frequency of clinical stage I at pretreatment CT was 81% (1017 of 1257). The 10-year lung cancer-specific survival of 1257 participants was 81% (95% CI: 79, 84) and the 20-year lung cancer-specific survival was 81% (95% CI: 78, 83), and it was 95% (95% CI: 91, 98) for 181 participants with pathologic T1aN0M0 lung cancer. Conclusion The 10-year lung cancer-specific survival of 80% reported in 2006 for I-ELCAP participants enrolled in annual low-dose CT screening and diagnosed with a first primary lung cancer has persisted, as shown by the updated 20-year lung cancer-specific survival for the expanded I-ELCAP cohort. © RSNA, 2023 See also the editorials by Grenier and by Sequist and Olazagasti in this issue.

Preliminary results from the EMoLung clinical study showing early lung cancer detection by the LC score

BACKGROUND

Lung cancer (LC) causes more deaths worldwide than any other cancer type. Despite advances in therapeutic strategies, the fatality rate of LC cases remains high (95%) since the majority of patients are diagnosed at late stages when patient prognosis is poor. Analysis of the International Association for the Study of Lung Cancer (IASLC) database indicates that early diagnosis is significantly associated with favorable outcome. However, since symptoms of LC at early stages are unspecific and resemble those of benign pathologies, current diagnostic approaches are mostly initiated at advanced LC stages.

METHODS

We developed a LC diagnosis test based on the analysis of distinct RNA isoforms expressed from the GATA6 and NKX2-1 gene loci, which are detected in exhaled breath condensates (EBCs). Levels of these transcript isoforms in EBCs were combined to calculate a diagnostic score (the LC score). In the present study, we aimed to confirm the applicability of the LC score for the diagnosis of early stage LC under clinical settings. Thus, we evaluated EBCs from patients with early stage, resectable non-small cell lung cancer (NSCLC), who were prospectively enrolled in the EMoLung study at three sites in Germany.

RESULTS

LC score-based classification of EBCs confirmed its performance under clinical conditions, achieving a sensitivity of 95.7%, 91.3% and 84.6% for LC detection at stages I, II and III, respectively.

CONCLUSIONS

The LC score is an accurate and non-invasive option for early LC diagnosis and a valuable complement to LC screening procedures based on computed tomography.

Prevalence, molecular markers, and outcome of bronchial squamous carcinoma in situ in high-risk subjects

Bronchial squamous carcinoma in situ (CIS) is a preinvasive lesion that is thought to precede invasive carcinoma. We conducted prospective autofluorescence and white light bronchoscopy trials between 1992 and 2016 to assess the prevalence, molecular markers, and outcome of individuals with CIS and other preneoplastic bronchial lesions. Biopsies were evaluated at multiple levels and selected biopsies were tested for aneuploidy and DNA sequenced for TP53 mutation. Thirty-one individuals with CIS were identified. Twenty-two cases of CIS occurred in association with concurrent invasive carcinomas. Seven of the invasive tumors were radiographically occult. In two cases, CIS spread from the focus of invasive carcinoma into contralateral lung lobes, forming secondary invasive tumors. In nine cases, CIS occurred as isolated lesions and one progressed to invasive squamous carcinoma at the same site 40 months after discovery. In a second case, CIS was a precursor of carcinoma at a separate site in a different lobe. In seven cases CIS regressed to a lower grade or disappeared. High level chromosomal aneusomy was often associated with TP53 mutation and with invasive carcinoma. CIS most often occurs in association with invasive squamous carcinoma and may extend along the airways into distant lobes. In rare cases, CIS may be observed to directly transform into invasive carcinoma. CIS may be indicative of invasive tumor at a separate distant site. Isolated CIS may regress. Molecular changes parallel histological changes in CIS and may be used to map clonal expansion in the airways.

Lung cancer screening using low-dose CT and FDG-PET in liver transplant recipients

To address the feasibility of implementing a lung cancer screening program in liver transplant recipients (LTR) targeted to detect early-stage lung cancer one hundred twenty-four LTR (89% male, 59.8+/-8.8 y old), who entered the lung cancer screening program at our hospital were reviewed. The results of the diagnostic algorithm using low-dose CT and F-18-fluorodeoxyglycose positron emission tomography (FDG-PET) were analyzed. Lung cancer was detected in 12 LTR (9.7%), most of which corresponded to the non-small cell subtype. Two of the 12 lung cancers were detected in the baseline study (prevalence of 1.6%), whereas 10 patients were diagnosed with lung cancer in the follow-up (incidence of 8.1%). Considering all cancers, 10 of 12 (83.3%) were diagnosed at stage I, one cancer was diagnosed at stage IIIA, and another one at stage IV. The sensitivity, specificity, diagnostic accuracy, and positive and negative predictive values of F-18-fluorodeoxyglycose positron emission tomography to detect malignancy in our cohort were 81.8%,100%, 99.3%, 100%, and 99.3%, respectively. A carefully followed multidisciplinary lung cancer screening algorithm in LTR that includes F-18-fluorodeoxyglycose positron emission tomography and low-dose CT allows lung cancer to be diagnosed at an early stage while reducing unnecessary invasive procedures.

The Usefulness of the Ratio of Antigen-Autoantibody Immune Complexes to Their Free Antigens in the Diagnosis of Non-Small Cell Lung Cancer

Autoantibodies against specific lung cancer-associated antigens have been suggested for the performance of lung cancer diagnosis. This study aimed to evaluate the diagnostic performance of the antigen-autoantibody immune complex (AIC) against its free antigens for CYFRA21-1, ProGRP, neutrophil gelatinase-associated lipocalin (NGAL), and neuron-specific enolase (NSE) in non-small cell lung cancer (NSCLC). In total, 85 patients with NSCLC and 120 healthy controls (HCs) were examined using a 9-guanine DNA chip method. The ratios of AICs to their antigens and the combinations of ratios consisting of two to four markers were calculated. The levels of AICs for CYFRA21-1, ProGRP, NGAL, and NSE were higher than those for their free antigens in all participants. The levels of each free antigens distinguished patients with NSCLC from the HCs. The ratios of the AIC to its antigen and seven combinations of two to four ratios were significantly higher in patients with NSCLC than in the HCs. Excellent diagnostic performance was observed for all combination ratios (C4-1), with 85.9% sensitivity and 86.7% specificity at a 3.51 cut-off. Higher sensitivity was observed in the early stages (0-I) and adenocarcinoma than in stages II-IV and other pathological types. Combining all ratios of AICs and their antigens for all four markers was useful when diagnosing NSCLC.

Artificial Intelligence in Lung Cancer Screening: The Future Is Now

Lung cancer has one of the worst morbidity and fatality rates of any malignant tumour. Most lung cancers are discovered in the middle and late stages of the disease, when treatment choices are limited, and patients' survival rate is low. The aim of lung cancer screening is the identification of lung malignancies in the early stage of the disease, when more options for effective treatments are available, to improve the patients' outcomes. The desire to improve the efficacy and efficiency of clinical care continues to drive multiple innovations into practice for better patient management, and in this context, artificial intelligence (AI) plays a key role. AI may have a role in each process of the lung cancer screening workflow. First, in the acquisition of low-dose computed tomography for screening programs, AI-based reconstruction allows a further dose reduction, while still maintaining an optimal image quality. AI can help the personalization of screening programs through risk stratification based on the collection and analysis of a huge amount of imaging and clinical data. A computer-aided detection (CAD) system provides automatic detection of potential lung nodules with high sensitivity, working as a concurrent or second reader and reducing the time needed for image interpretation. Once a nodule has been detected, it should be characterized as benign or malignant. Two AI-based approaches are available to perform this task: the first one is represented by automatic segmentation with a consequent assessment of the lesion size, volume, and densitometric features; the second consists of segmentation first, followed by radiomic features extraction to characterize the whole abnormalities providing the so-called "virtual biopsy". This narrative review aims to provide an overview of all possible AI applications in lung cancer screening.

Effective lung cancer control: An unaccomplished challenge in cancer research

Lung cancer has always been a burden to the society since its non-effective early detection and poor survival status. Different imaging modalities such as computed tomography scan have been practiced for lung cancer detection. This review focuses on the importance of sputum cytology for early lung cancer detection and biomarkers effective in sputum samples. Published articles were discussed in light of the potential of sputum cytology for lung cancer early detection and risk assessment across high-risk groups. Recent developments in sample processing techniques have documented a clear potential to improve or refine diagnosis beyond that achieved with conventional sputum cytology examination. The diagnostic potential of sputum cytology may be exploited better through the standardization and automation of sputum preparation and analysis for application in routine laboratory practices and clinical trials. The challenging aspects in sputum cytology as well as sputum-based molecular markers are to ensure appropriate standardization and validation of the processing techniques.

A Lightweight and Robust Framework for Circulating Genetically Abnormal Cells (CACs) Identification Using 4-Color Fluorescence In Situ Hybridization (FISH) Image and Deep Refined Learning

Circulating genetically abnormal cells (CACs) constitute an important biomarker for cancer diagnosis and prognosis. This biomarker offers high safety, low cost, and high repeatability, which can serve as a key reference in clinical diagnosis. These cells are identified by counting fluorescence signals using 4-color fluorescence in situ hybridization (FISH) technology, which has a high level of stability, sensitivity, and specificity. However, there are some challenges in CACs identification, due to the difference in the morphology and intensity of staining signals. In this concern, we developed a deep learning network (FISH-Net) based on 4-color FISH image for CACs identification. Firstly, a lightweight object detection network based on the statistical information of signal size was designed to improve the clinical detection rate. Secondly, the rotated Gaussian heatmap with a covariance matrix was defined to standardize the staining signals with different morphologies. Then, the heatmap refinement model was proposed to solve the fluorescent noise interference of 4-color FISH image. Finally, an online repetitive training strategy was used to improve the model's feature extraction ability for hard samples (i.e., fracture signal, weak signal, and adjacent signals). The results showed that the precision was superior to 96%, and the sensitivity was higher than 98%, for fluorescent signal detection. Additionally, validation was performed using the clinical samples of 853 patients from 10 centers. The sensitivity was 97.18% (CI 96.72-97.64%) for CACs identification. The number of parameters of FISH-Net was 2.24 M, compared to 36.9 M for the popularly used lightweight network (YOLO-V7s). The detection speed was about 800 times greater than that of a pathologist. In summary, the proposed network was lightweight and robust for CACs identification. It could greatly increase the review accuracy, enhance the efficiency of reviewers, and reduce the review turnaround time during CACs identification.

Effect of stage shift and immunotherapy treatment on lung cancer survival outcomes

OBJECTIVES

Non-small-cell lung cancer mortality has declined at a faster rate than incidence due to multiple factors, including changes in smoking behaviour, early detection which shifts diagnosis, and novel therapies. Limited resources require that we quantify the contribution of early detection versus novel therapies in improving lung cancer survival outcomes.

METHODS

Non-small-cell lung cancer patients from the Surveillance, Epidemiology, and End Results-Medicare data were queried and divided into: (i) stage IV diagnosed in 2015 (n = 3774) and (ii) stage I-III diagnosed in 2010-2012 (n = 15 817). Multivariable Cox-proportional hazards models were performed to assess the independent association of immunotherapy or diagnosis at stage I/II versus III with survival.

RESULTS

Patients treated with immunotherapy had significantly better survival than those who did not (HRadj: 0.49, 95% confidence interval: 0.43-0.56), as did those diagnosed at stage I/II versus stage III (HRadj: 0.36, 95% confidence interval: 0.35-0.37). Patients on immunotherapy had a 10.7-month longer survival than those who were not. Stage I/II patients had an average survival benefit of 34 months, compared to stage III. If 25%% of stage IV patients not on immunotherapy received it, there would be a gain of 22 292 person-years survival per 100 000 diagnoses. A switch of only 25% from stage III to stage I/II would correspond to 70 833 person-years survival per 100 000 diagnoses.

CONCLUSIONS

In this cohort study, earlier stage at diagnosis contributed to life expectancy by almost 3 years, while gains from immunotherapy would contribute ½ year of survival. Given the relative affordability of early detection, risk reduction through increased screening should be optimized.

Cost-effectiveness of stereotactic body radiotherapy versus conventional fractionated radiotherapy for medically inoperable, early-stage non-small cell lung cancer

BACKGROUND

Stereotactic body radiotherapy (SBRT) is a novel radio-therapeutic technique that has recently emerged as standard-of-care treatment for medically inoperable, early-stage non-small cell lung cancer (NSCLC). In this study, we compared the cost-effectiveness of SBRT with that of conventional fractionated radiotherapy (CFRT) in patients with medically inoperable, early-stage NSCLC from the perspective of the Chinese health system.

METHODS

A Markov model was developed to describe health states of patients after treatment with SBRT and CFRT. The recurrence risks, treatment toxicities, and utilities inputs were obtained from the literature. The costs were based on listed prices and real-world evidence. A simulation was conducted to determine the post-treatment lifetime years. For each treatment, the total costs, quality-adjusted life-years (QALYs), and incremental cost-effectiveness ratios (ICERs) per QALY were calculated. Deterministic and probabilistic sensitivity analyses were performed to assess the uncertainty of the model parameters.

RESULTS

In the base case analysis, SBRT was associated with a mean cost of USD16,933 and 2.05 QALYs, whereas CFRT was associated with a mean cost of USD17,726 and 1.61 QALYs. SBRT is a more cost-effective strategy compared with CFRT for medically inoperable, early-stage NSCLC, with USD 1802 is saved for every incremental QALY. This result was validated by DSA and PSA, in which SBRT remained the most cost-effective option.

CONCLUSIONS

The findings suggested that, compared to CFRT, SBRT may be considered a more cost-effective strategy for medically inoperable, early-stage NSCLC.

Systematic Review of Lung Cancer Screening: Advancements and Strategies for Implementation

Lung cancer is the leading cause of cancer-related deaths in Europe, with low survival rates primarily due to late-stage diagnosis. Early detection can significantly improve survival rates, but lung cancer screening is not currently implemented in Italy. Many countries have implemented lung cancer screening programs for high-risk populations, with studies showing a reduction in mortality. This review aimed to identify key areas for establishing a lung cancer screening program in Italy. A literature search was conducted in October 2022, using the PubMed and Scopus databases. Items of interest included updated evidence, approaches used in other countries, enrollment and eligibility criteria, models, cost-effectiveness studies, and smoking cessation programs. A literature search yielded 61 scientific papers, highlighting the effectiveness of low-dose computed tomography (LDCT) screening in reducing mortality among high-risk populations. The National Lung Screening Trial (NLST) in the United States demonstrated a 20% reduction in lung cancer mortality with LDCT, and other trials confirmed its potential to reduce mortality by up to 39% and detect early-stage cancers. However, false-positive results and associated harm were concerns. Economic evaluations generally supported the cost-effectiveness of LDCT screening, especially when combined with smoking cessation interventions for individuals aged 55 to 75 with a significant smoking history. Implementing a screening program in Italy requires the careful consideration of optimal strategies, population selection, result management, and the integration of smoking cessation. Resource limitations and tailored interventions for subpopulations with low-risk perception and non-adherence rates should be addressed with multidisciplinary expertise.

Integrated models of blood protein and metabolite enhance the diagnostic accuracy for Non-Small Cell Lung Cancer

BACKGROUND

For early screening and diagnosis of non-small cell lung cancer (NSCLC), a robust model based on plasma proteomics and metabolomics is required for accurate and accessible non-invasive detection. Here we aim to combine TMT-LC-MS/MS and machine-learning algorithms to establish models with high specificity and sensitivity, and summarize a generalized model building scheme.

METHODS

TMT-LC-MS/MS was used to discover the differentially expressed proteins (DEPs) in the plasma of NSCLC patients. Plasma proteomics-guided metabolites were selected for clinical evaluation in 110 NSCLC patients who were going to receive therapies, 108 benign pulmonary diseases (BPD) patients, and 100 healthy controls (HC). The data were randomly split into training set and test set in a ratio of 80:20. Three supervised learning algorithms were applied to the training set for models fitting. The best performance models were evaluated with the test data set.

RESULTS

Differential plasma proteomics and metabolic pathways analyses revealed that the majority of DEPs in NSCLC were enriched in the pathways of complement and coagulation cascades, cholesterol and bile acids metabolism. Moreover, 10 DEPs, 14 amino acids, 15 bile acids, as well as 6 classic tumor biomarkers in blood were quantified using clinically validated assays. Finally, we obtained a high-performance screening model using logistic regression algorithm with AUC of 0.96, sensitivity of 92%, and specificity of 89%, and a diagnostic model with AUC of 0.871, sensitivity of 86%, and specificity of 78%. In the test set, the screening model achieved accuracy of 90%, sensitivity of 91%, and specificity of 90%, and the diagnostic model achieved accuracy of 82%, sensitivity of 77%, and specificity of 86%.

CONCLUSIONS

Integrated analysis of DEPs, amino acid, and bile acid features based on plasma proteomics-guided metabolite profiling, together with classical tumor biomarkers, provided a much more accurate detection model for screening and differential diagnosis of NSCLC. In addition, this new mathematical modeling based on plasma proteomics-guided metabolite profiling will be used for evaluation of therapeutic efficacy and long-term recurrence prediction of NSCLC.

[Questions and Answers in Lung Cancer]

Over the past 2 decades, scientific evidence has strongly supported the use of low-radiation dose chest computed tomography (CT) as a screening technique for lung cancer. This approach has resulted in a significant reduction in mortality rates by enabling the detection of early-stage lung cancer amenable to potentially curative treatments. Regarding diagnosis, there are also novel methods under study, such as liquid biopsy, identification of the pulmonary microbiome, and the use of artificial intelligence techniques, which will play a key role in the near future. At present, there is a growing trend towards less invasive surgical procedures, such as segmentectomy, as an alternative to lobectomy. This procedure is based on 2 recent clinical trials conducted on peripheral tumors measuring less than 2 cm. Although these approaches have demonstrated comparable survival rates, there remains controversy due to uncertainties surrounding recurrence rates and functional capacity preservation. With regard to adjuvant therapy, immunotherapy, either as a monotherapy or in conjunction with chemotherapy, has shown encouraging results in resectable stages of locally advanced lung cancer, demonstrating complete pathologic responses and improved overall survival.After surgery treatment, despite the lack of solid evidence for long-term follow-up of these patients, clinical practice recommends periodic CT scans during the early years.In conclusion, there have been significant advances in lung cancer that have improved diagnostic techniques using new technologies and screening programs. Furthermore, the treatment of lung cancer is increasingly personalized, resulting in an improvement in the survival of patients.

Metabolic biomarkers in lung cancer screening and early diagnosis (Review)

Late diagnosis is one of the major contributing factors to the high mortality rate of lung cancer, which is now the leading cause of cancer-associated mortality worldwide. At present, low-dose CT (LDCT) screening in the high-risk population, in which lung cancer incidence is higher than that of the low-risk population is the predominant diagnostic strategy. Although this has efficiently reduced lung cancer mortality in large randomized trials, LDCT screening has high false-positive rates, resulting in excessive subsequent follow-up procedures and radiation exposure. Complementation of LDCT examination with biofluid-based biomarkers has been documented to increase efficacy, and this type of preliminary screening can potentially reduce potential radioactive damage to low-risk populations and the burden of hospital resources. Several molecular signatures based on components of the biofluid metabolome that can possibly discriminate patients with lung cancer from healthy individuals have been proposed over the past two decades. In the present review, advancements in currently available technologies in metabolomics were reviewed, with particular focus on their possible application in lung cancer screening and early detection.

Reliability and Validity of the Korean Version of Lung Cancer Screening Health Belief Scale

The purpose of this study was to verify the validity and reliability of the LCSHBS-K. This was a methodological study. The participants were adults aged between 50 and 74 years old, according to the selection criteria for lung cancer screening presented by the Comprehensive Cancer Network clinical practice guidelines in oncology recommendations. This study included 204 high-risk individuals who had not been diagnosed with lung cancer. The collected data were analyzed using the IBM SPSS Statistics software 26.0 version (IBM, New York, NY, USA). The reliability was analyzed by Cronbach's α for internal consistency, and the concurrent validity was analyzed by Pearson's correlation coefficients to identify the correlations with the health belief scale for Korean adults. To test the convergent validity, the average variance extracted (AVE) and composite reliability (CR) were calculated using confirmatory factor analysis. In addition, the model fit for a tool was CMIN (χ²/df), SRMR, RMSEA, GFI, and CFI as a comparative fit index. The discriminant validity was tested based on AVE > r². The average age of the participants was 55.49 (SD = 5.07), the average smoking history was 29.55 (SD = 8.12) years, and the average number of cigarettes smoked per day was 12.18 (SD = 7.77). The goodness of fit met the criteria with GFI = 0.81 (criteria > 0.9), CMIN = 1.69 (criteria < 2), SRMR = 0.06 (criteria < 0.08), RMSEA = 0.058 (criteria < 0.06), and CFI = 0.91 (criteria > 0.9). The LCSHBS-K showed a statistically significant positive correlation with the HBS (r = 0.32 (p < 0.001)). Cronbach's α was 0.80 for all the items in the LCSHBS-K. Therefore, the validity and reliability of the LCSHBS-K tool were confirmed. Based on the results of this study, the Korean version of the LCSHBS tool was found to be suitable for screening lung cancer in high-risk groups in Korea.

Comparison of Gray-scale Inversion to Improve Detection of Pulmonary Nodules on Chest X-rays Between Radiologists and a Deep Convolutional Neural Network

Detection of pulmonary nodules on chest x-rays is an important task for radiologists. Previous studies have shown improved detection rates using gray-scale inversion. The purpose of our study was to compare the efficacy of gray-scale inversion in improving the detection of pulmonary nodules on chest x-rays for radiologists and machine learning models (ML). We created a mixed dataset consisting of 60, 2-view (posteroanterior view - PA and lateral view) chest x-rays with computed tomography confirmed nodule(s) and 62 normal chest x-rays. Twenty percent of the cases were separated for a testing dataset (24 total images). Data augmentation through mirroring and transfer learning was used for the remaining cases (784 total images) for supervised training of 4 ML models (grayscale PA, grayscale lateral, gray-scale inversion PA, and gray-scale inversion lateral) on Google's cloud-based AutoML platform. Three cardiothoracic radiologists analyzed the complete 2-view dataset (n=120) and, for comparison to the ML, the single-view testing subsets (12 images each). Gray-scale inversion (area under the curve (AUC) 0.80, 95% confidence interval (CI) 0.75-0.85) did not improve diagnostic performance for radiologists compared to grayscale (AUC 0.84, 95% CI 0.79-0.88). Gray-scale inversion also did not improve diagnostic performance for the ML. The ML did demonstrate higher sensitivity and negative predictive value for grayscale PA (72.7% and 75.0%), grayscale lateral (63.6% and 66.6%), and gray-scale inversion lateral views (72.7% and 76.9%), comparing favorably to the radiologists (63.9% and 72.3%, 27.8% and 58.3%, 19.5% and 50.5% respectively). In the limited testing dataset, the ML did demonstrate higher sensitivity and negative predictive value for grayscale PA (72.7% and 75.0%), grayscale lateral (63.6% and 66.6%), and gray-scale inversion lateral views (72.7% and 76.9%), comparing favorably to the radiologists (63.9% and 72.3%, 27.8% and 58.3%, 19.5% and 50.5%, respectively). Further investigation of other post-processing algorithms to improve diagnostic performance of ML is warranted.

Metal Nanoparticles as Novel Agents for Lung Cancer Diagnosis and Therapy

Lung cancer is one of the most common malignancies worldwide and contributes to most cancer-related morbidity and mortality cases. During the past decades, the rapid development of nanotechnology has provided opportunities and challenges for lung cancer diagnosis and therapeutics. As one of the most extensively studied nanostructures, metal nanoparticles obtain higher satisfaction in biomedical applications associated with lung cancer. Metal nanoparticles have enhanced almost all major imaging strategies and proved great potential as sensor for detecting cancer-specific biomarkers. Moreover, metal nanoparticles could also improve therapeutic efficiency via better drug delivery, improved radiotherapy, enhanced gene silencing, and facilitated photo-driven treatment. Herein, the recently advanced metal nanoparticles applied in lung cancer therapy and diagnosis are summarized. Future perspective on the direction of metal-based nanomedicine is also discussed. Stimulating more research interests to promote the development of metal nanoparticles in lung cancer is devoted.

Sublobar resection versus lobectomy in the treatment of synchronous multiple primary lung cancer

OBJECTIVE

Although synchronous multiple primary lung cancers (sMPLCs) are common in clinical practice, the choice of surgical modalities for the main lesion is still at the stage of exploration. This study is designed to analyze the prognosis of sMPLCs and single primary lung cancers with similar tumor stages and to explore whether sublobar resection has a similar prognosis as lobectomy for sMPLCs.

METHODS

One-hundred forty-one cases of sMPLCs were selected, including the following: 65 cases underwent lobectomy for main lesions, and 76 cases underwent sublobar resection for main lesions. One thousand one hundred forty-four cases of single primary lung cancer were matched at 1:1 by propensity score matching. Then, the patients with sMPLCs were divided into a lobectomy group and a sublobar group according to the first tumor stage. Ninety-eight cases of patients with sMPLCs were matched. The short-term perioperative effect, 5-year disease-free survival (DFS) rate, and 5-year overall survival (OS) rate between the two groups were compared.

RESULTS

There was no significant difference in OS between sMPLCs and single primary lung cancer after lobectomy (77.1% vs. 77.2%, P = 0.157) and sublobar resection (98.7% vs. 90.7%, P = 0.309). There was no significant difference in OS (86.7% vs. 83.9%, P = 0.482) or DFS (67.6 vs. 87.7%, P = 0.324) between the lobectomy group and sublobar group with sMPLCs. The sublobar resection group obtained a lower incidence of postoperative complications (40.8% vs. 16.3%, P = 0.007) and shorter postoperative hospital stay (11.22 vs. 9.27, P = 0.049).

CONCLUSION

The prognosis of patients with sMPLCs generally depends on the main tumor state, which has no statistical difference regardless of sublobar resection or lobectomy, and the perioperative period of sublobar resection is safer than that of lobectomy.

Changes in mortality among patients with chronic obstructive pulmonary disease from the 1990s to the 2000s: a pooled analysis of two prospective cohort studies

OBJECTIVES

This study aimed to identify and investigate changes in the mortality of patients with chronic obstructive pulmonary disease (COPD) at the same institute from the 1990s to the 2000s. We hypothesised that the improvement in long-term mortality of COPD was achieved due to the development of pharmacological and non-pharmacological treatments.

DESIGN

This study was a retrospective analysis of two observational prospective cohort studies. One study enrolled subjects from 1995 to 1997 (the 1990s), and the other enrolled subjects from 2005 to 2009 (the 2000s).

SETTING

Two studies from a single centre, which was the same university hospital in Japan.

PARTICIPANTS

Patients with stable COPD.

PRIMARY AND SECONDARY OUTCOME MEASURES

We analysed all-cause mortality data from the pooled database. Subanalyses were conducted by stratifying subjects into two groups according to airflow limitation severity as severe/very severe (per cent predicted value of forced expiratory volume in 1 s (%FEV₁) <50%) or mild/moderate (%FEV₁≥50%).

RESULTS

In total, 280 male patients with COPD were enrolled. Patients in the 2000s (n=130) were significantly older (71.6 vs 68.7 years) and had milder disease (%FEV₁; 57.6% vs 47.1%) than those in the 1990s (n=150). Almost all severe/very severe patients in the 2000s received long-acting bronchodilators (LABDs), and they had a significantly lower risk of mortality than those in the 1990s according to Cox proportional regression analyses (OR=0.34, 95% CI 0.13-0.78), with a 48% reduction in 5-year mortality (from 31.0% to 16.1%). Moreover, any LABD use had a significantly positive impact on prognosis, even after adjustments for age, FEV₁, smoking status, dyspnoea, body size, oxygen therapy and study period.

CONCLUSIONS

Trends indicating a better prognosis for patients with COPD in the 2000s were observed. This improvement may be associated with the usage of LABDs.

Lung cancer screening

Randomised controlled trials, including the National Lung Screening Trial (NLST) and the NELSON trial, have shown reduced mortality with lung cancer screening with low-dose CT compared with chest radiography or no screening. Although research has provided clarity on key issues of lung cancer screening, uncertainty remains about aspects that might be critical to optimise clinical effectiveness and cost-effectiveness. This Review brings together current evidence on lung cancer screening, including an overview of clinical trials, considerations regarding the identification of individuals who benefit from lung cancer screening, management of screen-detected findings, smoking cessation interventions, cost-effectiveness, the role of artificial intelligence and biomarkers, and current challenges, solutions, and opportunities surrounding the implementation of lung cancer screening programmes from an international perspective. Further research into risk models for patient selection, personalised screening intervals, novel biomarkers, integrated cardiovascular disease and chronic obstructive pulmonary disease assessments, smoking cessation interventions, and artificial intelligence for lung nodule detection and risk stratification are key opportunities to increase the efficiency of lung cancer screening and ensure equity of access.

Lung nodules: sorting the wheat from the chaff

Pulmonary nodules are a common finding on CT scans of the chest. In the United Kingdom, management should follow British Thoracic Society Guidelines, which were published in 2015. This review covers key aspects of nodule management also looks at new and emerging evidence since then.

An improved 3-D attention CNN with hybrid loss and feature fusion for pulmonary nodule classification

BACKGROUND AND OBJECTIVE

Lung cancer has the highest cancer-related mortality worldwide, and lung nodule usually presents with no symptom. Low-dose computed tomography (LDCT) was an important tool for lung cancer detection and diagnosis. It provided a complete three-dimensional (3-D) chest image with a high resolution.Recently, convolutional neural network (CNN) had flourished and been proven the CNN-based computer-aided diagnosis (CADx) system could extract the features and help radiologists to make a preliminary diagnosis. Therefore, a 3-D ResNeXt-based CADx system was proposed to assist radiologists for diagnosis in this study.

METHODS

The proposed CADx system consists of image preprocessing and a 3-D CNN-based classification model for pulmonary nodule classification. First, the image preprocessing was executed to generate the normalized volumn of interest (VOI) only including nodule information and a few surrounding tissues. Then, the extracted VOI was forwarded to the 3-D nodule classification model. In the classification model, the RestNext was employed as the backbone and the attention scheme was embedded to focus on the important features. Moreover, a multi-level feature fusion network incorporating feature information of different scales was used to enhance the prediction accuracy of small malignant nodules. Finally, a hybrid loss based on channel optimization which make the network learn more detailed information was empolyed to replace a binary cross-entropy (BCE) loss.

RESULTS

In this research, there were a total of 880 low-dose CT images including 440 benign and 440 malignant nodules from the American National Lung Screening Trial (NLST) for system evaluation. The results showed that our system could achieve the accuracy of 85.3%, the sensitivity of 86.8%, the specificity of 83.9%, and the area-under-curve (AUC) value was 0.9042. It was confirmed that the designed system had a good diagnostic ability.

CONCLUSION

In this study, a CADx composed of the image preprocessing and a 3-D nodule classification model with attention scheme, feature fusion, and hybrid loss was proposed for pulmonary nodule classification in LDCT. The results indicated that the proposed CADx system had potential for achieving high performance in classifying lung nodules as benign and malignant.

Impact of Duration of Diagnostic Workup on Prognosis for Early Lung Cancer

INTRODUCTION

Growth assessment for pulmonary nodules is an important diagnostic tool; however, the impact on prognosis due to time delay for follow-up diagnostic scans needs to be considered.

METHODS

Using the data between 2003 and 2019 from the International Early Lung Cancer Action Program, a prospective cohort study, we determined the size-specific, 10-year Kaplan-Meier lung cancer (LC) survival rates as surrogates for cure rates. We estimated the change in LC diameter after delays of 90, 180, and 365 days using three representative LC volume doubling times (VDTs) of 60 (fast), 120 (moderate), and 240 (slow). We then estimated the decrease in the LC cure rate resulting from time between computed tomography scans to assess for growth during the diagnostic workup.

RESULTS

Using a regression model of the 10-year LC survival rates on LC diameter, the estimated LC cure rate of a 4.0 mm LC with fast (60-d) VDT is 96.0% (95% confidence interval [CI]: 95.2%-96.7%) initially, but it would decrease to 94.3% (95% CI: 93.2%-95.0%), 92.0% (95% CI: 90.5%-93.4%), and 83.6%(95% CI: 80.6%-86.6%) after delays of 90, 180, and 365 days, respectively. A 20.0-mm LC with the same VDTs has a lower LC cure rate of 79.9% (95% CI: 76.2%-83.5%) initially and decreases more rapidly to 71.5% (95% CI: 66.4%-76.7%), 59.8% (95% CI: 52.4%-67.1%), and 17.9% (95% CI: 3.0%-32.8%) after the same delays of 90, 180, and 365 days, respectively.

CONCLUSIONS

Time between scans required to measure growth of lung nodules affects prognosis with the effect being greater for fast growing and larger cancers. Quantifying the extent of change in prognosis is required to understand efficiencies of different management protocols.