CT-Based Deep-Learning Model for Spread-Through-Air-Spaces Prediction in Ground Glass-Predominant Lung Adenocarcinoma

STAS: New explorations and challenges for thoracic surgeons

Spread through air spaces (STAS) represents a relatively novel concept in the pathology of lung cancer, and it specifically refers to the dissemination of tumour cells into the parenchymal air spaces adjacent to the primary tumour. In 2015, the World Health Organization (WHO) classified STAS as a new invasive form of lung adenocarcinoma (LUAD). Many studies investigated the role of STAS and revealed its association with the prognosis of LUAD and its influence on the outcomes of other malignant pulmonary neoplasms. Additionally, the underlying mechanisms and predictive models of STAS have received considerable attention in recent years. This paper provides a comprehensive overview of the research advancements and prospects of STAS by examining it from multiple perspectives.

A PET/CT-based 3D deep learning model for predicting spread through air spaces in stage I lung adenocarcinoma

PURPOSE

This study evaluates a three-dimensional (3D) deep learning (DL) model based on fluorine-18 fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) for predicting the preoperative status of spread through air spaces (STAS) in patients with clinical stage I lung adenocarcinoma (LUAD).

METHODS

A retrospective analysis of 162 patients with stage I LUAD was conducted, splitting data into training and test sets (4:1). Six 3D DL models were developed, and the top-performing PET and CT models (ResNet50) were fused for optimal prediction. The model's clinical utility was assessed through a two-stage reader study.

RESULTS

The fused PET/CT model achieved an area under the curve (AUC) of 0.956 (95% CI 0.9230-0.9881) in the training set and 0.889 (95% CI 0.7624-1.0000) in the test set. Compared to three physicians, the model demonstrated superior sensitivity and specificity. After the artificial intelligence (AI) assistance's participation, the diagnostic accuracy of the physicians improved during their subsequent reading session.

CONCLUSION

Our DL model demonstrates potential as a resource to aid physicians in predicting STAS status and preoperative treatment planning for stage I LUAD, though prospective validation is required.

A CT-based deep learning model for preoperative prediction of spread through air spaces in clinical stage I lung adenocarcinoma

Objective

To develop and validate a deep learning signature for noninvasive prediction of spread through air spaces (STAS) in clinical stage I lung adenocarcinoma and compare its predictive performance with conventional clinical-semantic model.

Methods

A total of 513 patients with pathologically-confirmed stage I lung adenocarcinoma were retrospectively enrolled and were divided into training cohort (n = 386) and independent validation cohort (n = 127) according to different center. Clinicopathological data were collected and CT semantic features were evaluated. Multivariate logistic regression analyses were conducted to construct a clinical-semantic model predictive of STAS. The Swin Transformer architecture was adopted to develop a deep learning signature predictive of STAS. Model performance was assessed using area under the receiver operating characteristic curve (AUC), sensitivity, specificity, positive and negative predictive value, and calibration curve. AUC comparisons were performed by the DeLong test.

Results

The proposed deep learning signature achieved an AUC of 0.869 (95% CI: 0.831, 0.901) in training cohort and 0.837 (95% CI: 0.831, 0.901) in validation cohort, surpassing clinical-semantic model both in training and validation cohort (all P<0.01). Calibration curves demonstrated good agreement between STAS predicted probabilities using deep learning signature and actual observed probabilities in both cohorts. The inclusion of all clinical-semantic risk predictors failed to show an incremental value with respect to deep learning signature.

Conclusions

The proposed deep learning signature based on Swin Transformer achieved a promising performance in predicting STAS in clinical stage I lung adenocarcinoma, thereby offering information in directing surgical strategy and facilitating adjuvant therapeutic scheduling.

Research hotspots and trends in lung cancer STAS: a bibliometric and visualization analysis

Purpose

This study employed the R software bibliometrix and the visualization tools CiteSpace and VOSviewer to conduct a bibliometric analysis of literature on lung cancer spread through air spaces (STAS) published since 2015.

Methods

On September 1, 2024, a computer-based search was performed in the Web of Science (WOS) Core Collection dataset for literature on lung cancer STAS published between January 1, 2015, and August 31, 2024. VOSviewer was used to visually analyze countries, institutions, authors, co-cited authors, and keywords, while CiteSpace was utilized to analyze institutional centrality, references, keyword bursts, and co-citation literature. Descriptive analysis tables were created using Excel 2021.

Results

A total of 243 articles were included from the WOS, with a significant increase in annual publications observed since 2018. China, Kadota K, and Fudan University were leading countries, authors, and institutions by publication volume. The top three authors by co-citation count were Kadota K, Chen C, and Adusumilli PS. The journal with the highest publication volume was Lung Cancer, with the most influential journal among the top 10 being the Journal of Thoracic Oncology. The most frequently cited reference was "Lobectomy Is Associated with Better Outcomes than Sublobar Resection in Spread through Air Spaces (STAS)-Positive T1 Lung Adenocarcinoma: A Propensity Score-Matched Analysis." Keyword clustering categorized the research into four main areas: pathological studies of lung cancer STAS, biological mechanisms, prognostic assessment, and imaging analysis. Current research hotspots include deep learning, lung squamous cell carcinoma, and air spaces STAS.

Conclusion

The current research on lung cancer STAS primarily focuses on pathological studies, biological mechanisms, prognostic assessments, and preoperative imaging model predictions. This study's findings provide new insights and directions for future research in this area.

Systematic review registration

https://www.crd.york.ac.uk/prospero/#myprospero, identifier 589442.

Habitat-based CT radiomics enhances the ability to predict spread through air spaces in stage T1 invasive lung adenocarcinoma

Introduction

Spread through air spaces (STAS) represents a novel invasive pattern in lung adenocarcinoma (LUAD) and is a risk factor for poor prognosis in stage T1 LUAD. This study aims to develop and validate a CT habitat imaging analysis model for predicting STAS in stage T1 invasive LUAD.

Methods

We retrospectively analyzed 217 patients with preoperative stage T1 invasive LUAD (115 STAS-positive and 102 STAS-negative cases, including 151 in the train set and 66 in the test set). Semi-automatic segmentation was performed on the regions of interest (ROIs) in all CT images, with an automatic 3mm expansion around the tumor, considering the intratumoral and peritumoral 3mm area. This area was divided into three sub-regions via K-means clustering, and 1197 radiomic features were extracted from each sub-region and the overall combined region. After dimension reduction through the Mann-Whitney U test, Pearson correlation analysis, and least absolute shrinkage and selection operator(LASSO), the best features for each sub-region and overall were selected. Models were then built using the selected radiomic features through the Adaptive Boosting (AdaBoost) and Multilayer Perceptron (MLP) classifiers. Four different models were established based on different sub-regions and the overall features. The performance of these models was evaluated through receiver operating characteristic curves (AUC) under the DeLong test, calibration curves via the Hosmer-Lemeshow test, and decision curve analysis to assess the performance of these features.

Results

In this study, we evaluated the predictive performance of AdaBoost and MLP classifiers on rad feature models across various subregions and the overall dataset. In the test set, the AdaBoost classifier achieved a maximum AUC of 0.871 in Habitat 3, whereas the MLP classifier demonstrated slightly superior performance with an AUC of 0.879. Both classifiers exhibited high efficiency in habitat 3, with the MLP algorithm showing enhanced model performance.

Conclusions

CT habitat imaging analysis for the preoperative prediction of STAS in stage T1 invasive LUAD shows satisfactory diagnostic performance, with the habitat3 model exhibiting the highest efficacy, reflecting tumor heterogeneity.

Deep Learning Analysis for Predicting Tumor Spread through Air Space in Early-Stage Lung Adenocarcinoma Pathology Images

The presence of spread through air spaces (STASs) in early-stage lung adenocarcinoma is a significant prognostic factor associated with disease recurrence and poor outcomes. Although current STAS detection methods rely on pathological examinations, the advent of artificial intelligence (AI) offers opportunities for automated histopathological image analysis. This study developed a deep learning (DL) model for STAS prediction and investigated the correlation between the prediction results and patient outcomes. To develop the DL-based STAS prediction model, 1053 digital pathology whole-slide images (WSIs) from the competition dataset were enrolled in the training set, and 227 WSIs from the National Taiwan University Hospital were enrolled for external validation. A YOLOv5-based framework comprising preprocessing, candidate detection, false-positive reduction, and patient-based prediction was proposed for STAS prediction. The model achieved an area under the curve (AUC) of 0.83 in predicting STAS presence, with 72% accuracy, 81% sensitivity, and 63% specificity. Additionally, the DL model demonstrated a prognostic value in disease-free survival compared to that of pathological evaluation. These findings suggest that DL-based STAS prediction could serve as an adjunctive screening tool and facilitate clinical decision-making in patients with early-stage lung adenocarcinoma.

Lung Cancer Surgery in Octogenarians: Implications and Advantages of Artificial Intelligence in the Preoperative Assessment

The general world population is aging and patients are often diagnosed with early-stage lung cancer at an advanced age. Several studies have shown that age is not itself a contraindication for lung cancer surgery, and therefore, more and more octogenarians with early-stage lung cancer are undergoing surgery with curative intent. However, octogenarians present some peculiarities that make surgical treatment more challenging, so an accurate preoperative selection is mandatory. In recent years, new artificial intelligence techniques have spread worldwide in the diagnosis, treatment, and therapy of lung cancer, with increasing clinical applications. However, there is still no evidence coming out from trials specifically designed to assess the potential of artificial intelligence in the preoperative evaluation of octogenarian patients. The aim of this narrative review is to investigate, through the analysis of the available international literature, the advantages and implications that these tools may have in the preoperative assessment of this particular category of frail patients. In fact, these tools could represent an important support in the decision-making process, especially in octogenarian patients in whom the diagnostic and therapeutic options are often questionable. However, these technologies are still developing, and a strict human-led process is mandatory.