Lung-PNet: An Automated Deep Learning Model for the Diagnosis of Invasive Adenocarcinoma in Pure Ground-Glass Nodules on Chest CT

Knowledge mapping analysis of ground glass nodules: a bibliometric analysis from 2013 to 2023

Background

In recent years, the widespread use of computed tomography (CT) in early lung cancer screening has led to an increase in the detection rate of lung ground glass nodules (GGNs). The persistence of GGNs, which may indicate early lung adenocarcinoma, has been a focus of attention for scholars in the field of lung cancer prevention and treatment in recent years. Despite the rapid development of research into GGNs, there is a lack of intuitive content and trend analyses in this field, as well as a lack of detailed elaboration on possible research hotspots. The objective of this study was to conduct a comprehensive analysis of the knowledge structure and research hotspots of lung ground glass nodules over the past decade, employing bibliometric methods.

Method

The Web of Science Core Collection (WoSCC) database was searched for relevant ground-glass lung nodule literature published from 2013-2023. Bibliometric analyses were performed using VOSviewer, CiteSpace, and the R package "bibliometrix".

Results

A total of 2,218 articles from 75 countries and 2,274 institutions were included in this study. The number of publications related to GGNs has been high in recent years. The United States has led in GGNs-related research. Radiology has one of the highest visibilities as a selected journal and co-cited journal. Jin Mo Goo has published the most articles. Travis WD has been cited the most frequently. The main topics of research in this field are Lung Cancer, CT, and Deep Learning, which have been identified as long-term research hotspots. The GGNs-related marker is a major research trend in this field.

Conclusion

This study represents the inaugural bibliometric analysis of applied research on ground-glass lung nodules utilizing three established bibliometric software. The bibliometric analysis of this study elucidates the prevailing research themes and trends in the field of GGNs over the past decade. It also furnishes pertinent recommendations for researchers to provide objective descriptions and comprehensive guidance for future related research.

Combined model integrating deep learning, radiomics, and clinical data to classify lung nodules at chest CT

OBJECTIVES

The study aimed to develop a combined model that integrates deep learning (DL), radiomics, and clinical data to classify lung nodules into benign or malignant categories, and to further classify lung nodules into different pathological subtypes and Lung Imaging Reporting and Data System (Lung-RADS) scores.

MATERIALS AND METHODS

The proposed model was trained, validated, and tested using three datasets: one public dataset, the Lung Nodule Analysis 2016 (LUNA16) Grand challenge dataset (n = 1004), and two private datasets, the Lung Nodule Received Operation (LNOP) dataset (n = 1027) and the Lung Nodule in Health Examination (LNHE) dataset (n = 1525). The proposed model used a stacked ensemble model by employing a machine learning (ML) approach with an AutoGluon-Tabular classifier. The input variables were modified 3D convolutional neural network (CNN) features, radiomics features, and clinical features. Three classification tasks were performed: Task 1: Classification of lung nodules into benign or malignant in the LUNA16 dataset; Task 2: Classification of lung nodules into different pathological subtypes; and Task 3: Classification of Lung-RADS score. Classification performance was determined based on accuracy, recall, precision, and F1-score. Ten-fold cross-validation was applied to each task.

RESULTS

The proposed model achieved high accuracy in classifying lung nodules into benign or malignant categories in LUNA 16 with an accuracy of 92.8%, as well as in classifying lung nodules into different pathological subtypes with an F1-score of 75.5% and Lung-RADS scores with an F1-score of 80.4%.

CONCLUSION

Our proposed model provides an accurate classification of lung nodules based on the benign/malignant, different pathological subtypes, and Lung-RADS system.