Solitary Pulmonary Nodule

BackgroundEach year, millions of pulmonary nodules are identified incidentally or through lung cancer screening, and many involve biopsy to distinguish cancer from benign processes. Both navigational bronchoscopy and computed tomography-guided transthoracic needle biopsy are commonly used in patients undergoing biopsies of peripheral pulmonary nodules, but the relative diagnostic accuracy of these two approaches is unclear.MethodsIn this multicenter, randomized, parallel-group, noninferiority trial, we assigned patients with an intermediate-risk or high-risk peripheral pulmonary nodule measuring 10 to 30 mm in diameter to undergo navigational bronchoscopy or transthoracic needle biopsy at seven centers across the United States. The primary outcome was diagnostic accuracy, which was defined as the percentage of patients with biopsies that showed a specific diagnosis (cancer or a specific benign condition) that was confirmed to be accurate through 12 months of clinical follow-up (nonferiority margin, 10 percentage points). Secondary outcomes included procedural complications such as the occurrence of pneumothorax.ResultsAmong the 234 patients included in the primary-outcome analysis (5 of whom were lost to follow-up), biopsy resulted in a specific diagnosis that was confirmed to be accurate through month 12 in 94 of 119 patients (79.0%) in the navigational bronchoscopy group and in 81 of 110 patients (73.6%) in the transthoracic needle biopsy group (absolute difference, 5.4 percentage points; 95% confidence interval, -6.5 to 17.2; P = 0.003 for noninferiority; P = 0.17 for superiority). Pneumothorax occurred in 4 of 121 patients (3.3%) in the navigational bronchoscopy group and in 32 of 113 patients (28.3%) in the transthoracic needle biopsy group and led to the placement of a chest tube, hospital admission, or both in 1 patient (0.8%) and 13 patients (11.5%), respectively.ConclusionsThe diagnostic accuracy of navigational bronchoscopy was noninferior to that of transthoracic needle biopsy among patients with peripheral pulmonary nodules measuring 10 to 30 mm. (Funded by Medtronic and others; VERITAS ClinicalTrials.gov number, NCT04250194.).

ObjectivesThe accurate detection and precise segmentation of lung nodules on computed tomography are key prerequisites for early diagnosis and appropriate treatment of lung cancer. This study was designed to compare detection and segmentation methods for pulmonary nodules using deep-learning techniques to fill methodological gaps and biases in the existing literature.MethodsThis study utilized a systematic review with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines, searching PubMed, Embase, Web of Science Core Collection, and the Cochrane Library databases up to May 10, 2023. The Quality Assessment of Diagnostic Accuracy Studies 2 criteria was used to assess the risk of bias and was adjusted with the Checklist for Artificial Intelligence in Medical Imaging. The study analyzed and extracted model performance, data sources, and task-focus information.ResultsAfter screening, we included nine studies meeting our inclusion criteria. These studies were published between 2019 and 2023 and predominantly used public datasets, with the Lung Image Database Consortium Image Collection and Image Database Resource Initiative and Lung Nodule Analysis 2016 being the most common. The studies focused on detection, segmentation, and other tasks, primarily utilizing Convolutional Neural Networks for model development. Performance evaluation covered multiple metrics, including sensitivity and the Dice coefficient.ConclusionsThis study highlights the potential power of deep learning in lung nodule detection and segmentation. It underscores the importance of standardized data processing, code and data sharing, the value of external test datasets, and the need to balance model complexity and efficiency in future research.Clinical relevance statementDeep learning demonstrates significant promise in autonomously detecting and segmenting pulmonary nodules. Future research should address methodological shortcomings and variability to enhance its clinical utility.Key pointsDeep learning shows potential in the detection and segmentation of pulmonary nodules. There are methodological gaps and biases present in the existing literature. Factors such as external validation and transparency affect the clinical application.

BackgroundEarly-stage lung adenocarcinoma that radiologically manifests as part-solid nodules, consisting of both ground-glass and solid components, has distinctive growth patterns and prognosis. The characteristics of the tumour microenvironment and transcriptional features of the malignant cells of different radiological phenotypes remain poorly understood.MethodsTwelve treatment-naive patients with radiological part-solid nodules were enrolled. After frozen pathology was confirmed as lung adenocarcinoma, two regions (ground-glass and solid) from each of the 12 part-solid nodules and 5 normal lung tissues from 5 of the12 patients were subjected to single-cell sequencing by 10x Genomics. We used Seurat v3.1.5 for data integration and analysis.ResultsWe comprehensively dissected the multicellular ecosystem of the ground-glass and solid components of part-solid nodules at the single-cell resolution. In tumours, these components had comparable proportions of malignant cells. However, the angiogenesis, epithelial-to-mesenchymal transition, KRAS, p53, and cell-cycle signalling pathways were significantly up-regulated in malignant cells within solid components compared to those within ground-glass components. For the tumour microenvironment, the relative abundance of myeloid and NK cells tended to be higher in solid components than in ground-glass components. Slight subtype composition differences existed between the ground-glass and solid components. The T/NK cell subsets' cytotoxic function and the macrophages' pro-inflammation function were suppressed in solid components. Moreover, pericytes in solid components had a stronger communication related to angiogenesis promotion with endothelial cells and tumour cells.ConclusionThe cellular landscape of ground-glass components is significantly different from that of normal tissue and similar to that of solid components. However, transcriptional differences exist in the vital signalling pathways of malignant and immune cells within these components.

Early detection of lung cancer through low-dose CT lung cancer screening in a high-risk population has proven to reduce lung cancer-specific mortality. Nodule management plays a pivotal role in early detection and further diagnostic approaches. The European Society of Thoracic Imaging (ESTI) has established a nodule management recommendation to improve the handling of pulmonary nodules detected during screening. For solid nodules, the primary method for assessing the likelihood of malignancy is to monitor nodule growth using volumetry software. For subsolid nodules, the aggressiveness is determined by measuring the solid part. The ESTI-recommendation enhances existing protocols but puts a stronger focus on lesion aggressiveness. The main goals are to minimise the overall number of follow-up examinations while preventing the risk of a major stage shift and reducing the risk of overtreatment. KEY POINTS: Question Assessment of nodule growth and management according to guidelines is essential in lung cancer screening. Findings Assessment of nodule aggressiveness defines follow-up in lung cancer screening. Clinical relevance The ESTI nodule management recommendation aims to reduce follow-up examinations while preventing major stage shift and overtreatment.