Invasive Lung Adenocarcinoma Research Articles

Predictive value of SUVmax in visceral pleural invasive lung adenocarcinoma with different diameters.

This study aimed to investigate predictive visceral pleural invasion (VPI) occurrence value of the maximum standardized uptake value (SUVmax) in patients with lung adenocarcinoma (LA). A total of 388 LA patients were divided into D1ab, D1c, D1, D2, D2a, D2b, D3, and all patient groups based on their tumor diameter (D). Patients were also classified into negative VPI (VPI-n) and positive VPI (VPI-p) groups according to VPI presence. SUVmax of patients was measured with 18F-fluorodeoxyglucose (FDG) by PET/computed tomography (18F-PET/CT). Receiver operating characteristic (ROC) analysis and the area under curve (AUC) of SUVmax were applied to determine optimal cut-off value for predicting VPI occurrence. There were significant differences in SUVmax between VPI-n and VPI-p groups ( P < 0.05) at the same tumor diameter. SUVmax cut-off value and sensitivity (Se,%) of VPI occurrence in each group were following: D1ab was 3.79 [AUC = 0.764, P < 0.001], Se86.11%; D1c was 5.47 (AUC = 0.706, P < 0.001), Se 93.75%; D1 was 5.49 (AUC = 0.731, P < 0.001), Se 79.76%; D2 was 7.36 (AUC = 0.726, P < 0.001), Se81.67%. All patient group was 7.26 (AUC = 0.735, P < 0.001), Se74.19%. In LA patients with the same diameter, SUVmax of the VPI-p group was significantly higher than that of the VPI-n group. The cut-off value of SUVmax for predicting VPI of T1 stage, T1 substages, and T2 stage LA could be determined through ROC curve. SUVmax measurement by PET/CT scan in stratified tumor size is helpful for predicting VPI occurrences of the physician.

Differences in serum cytokine levels distinguish between clinically noninvasive lung adenocarcinoma and invasive lung adenocarcinoma: A cross-sectional study.

Lung cancer incidence and mortality remain high and are now the leading cause of cancer-related death. Lung adenocarcinoma (LUAD) is one of the main histological subtypes of lung cancer. Previous studies have shown the role of inflammation in the development of lung cancer, but the relationship between cytokines and LUAD is still unclear. To further differentiate and explore the association of cytokines with the risk of non-invasive and invasive LUAD, we studied and assessed serum cytokine levels in patients with two types of LUAD. A cohort study of 90 non-invasive LUAD and 90 invasive LUAD was retrospectively included, and the clinical characteristics were recorded in detail. The differences in the levels of 12 serum cytokines (IFN-α, IFN-γ, IL-10, IL-12P70, IL-17A, IL-1β, IL-2, IL-4, IL-5, IL-6, IL-8, and TNF-α) between the two groups of patients with LUAD were analyzed and evaluated. And we evaluated the clinical value of cytokine differential diagnosis of invasive LUAD based on receiver operating characteristics (ROC) curves. The mean age of the patients was 56.6 years, and the proportions of males and females were 38.9% and 61.1%, respectively. IFN-α, IL-1β, IL-2, IL-6, TNF-α, IL-4, and IL-8 were significantly increased in patients with invasive LUAD compared with the non-invasive LUAD group. Further research found that smoking is an important factor, with changes in the four cytokines IL-1β, IL-6, IL-8, and TNF-α being significantly higher in the smoking group of patients with invasive LUAD. It can be seen from the area under the curve that IL-1β and IL-2 have a significant differential diagnosis. We observed differences in preoperative serum cytokine levels between patients with invasive and non-invasive LUAD, which may serve as potential serum biomarkers for clinical differential diagnosis and disease progression assessment.

Efficacy of thoracoscopic segmentectomy versus lobectomy in the treatment of early invasive lung adenocarcinoma: a propensity score matching study.

This study aimed to investigate and analyze the clinical application value of thoracoscopic segmentectomy and lobectomy in patients with invasive pulmonary adenocarcinoma. 286 patients with invasive pulmonary adenocarcinoma who underwent segmentectomy or lobectomy at the First Hospital of Jiaxing City from January 2018 to June 2020 were retrospectively analyzed. Patients were divided into a thoracoscopic segmentectomy group(n=97) and a lobectomy group (n=189). Patients were compared after obtaining 1:1 propensity score-matched cohorts. Outcome indicators included surgery-related indicators, immune-inflammation-related indicators, postoperative complications, recurrence, and metastasis. After 1:1 propensity score matching, 93 patients were included in each group. We found that the volume of intraoperative blood loss in the segmentectomy group was significantly less than in the lobectomy group (P=0.014). The duration of postoperative drainage (P = 0.005) and hospitalization (P=0.002) in the segmentectomy group were significantly shorter than in the lobectomy group. In terms of immunoinflammatory response, compared with the lobectomy group, white blood cells, neutrophils, SII, and NLR in the segmentectomy group were significantly lower than in the lobectomy group (P< 0.05). The recurrence-free survival (RFS) rates in the segmentectomy and lobectomy were 80.5% and 88.2% at 1 year and 35.1% and 52.6% at 3 years, respectively, and the difference was statistically significant (P<0.05). The segmentectomy group achieved similar outcomes to the lobectomy group at 1 year and 3 years (P > 0.05). Multivariate COX regression analysis showed that CAR was an independent risk factor for RFS in patients undergoing invasive adenocarcinoma surgery. Compared with lobectomy, thoracoscopic segmentectomy can effectively reduce the postoperative inflammatory response in patients with early invasive lung adenocarcinoma and promote patient recovery. Although segmentectomy is associated with a higher recurrence rate in the short term for patients with early invasive lung adenocarcinoma, the associated survival rate is similar to the lobectomy group. Segmentectomy should be considered in the treatment of early invasive lung adenocarcinoma. Meanwhile, postoperative CAR represents an independent risk factor for early postoperative recurrence in patients with IAC.

Integration analysis using bioinformatics and experimental validation on the clinical and biological significance of TSLP in cancers

Thymic stromal lymphopoietin (TSLP) has significantly impacted the development and progression of various neoplastic disorders. To comprehensively evaluate the diverse significance of TSLP in malignant tumors, we first integrative analyze the TSLP expression level in paired and unpaired pan-cancer tissue and cell line, compared against the normal tissue. The correlation between TSLP expression, molecular subtypes, immune subtypes, diagnostic value, and prognostic value in pan-cancer was also investigated. We then explored the impact of TSLP expression on multifaced immune cell infiltration and subsequent clinical outcomes in lung adenocarcinoma (LUAD) patients. and conducted cellular experiments to functionally examine the effect of TSLP on cell proliferation, apoptosis, cell cycle, migration, and invasion in LUAD. The anti-neoplastic mechanism of TSLP was further investigated by qRT-PCR and western blotting. Our findings reveal that TSLP expression is abnormally low in various cancers compared to normal tissue and is associated with different molecular and immune subtypes of cancers. Moreover, ROC and survival analysis results suggest that TSLP expression is correlated with the diagnostic, prognostic, clinical features, and immune cells of LUAD patients. Cell experiments showed that overexpression of TSLP elicited a significant reduction in LUAD cell viability, promoted cell apoptosis, impeded cell cycle progression in the G2/M phase, and inhibited cell migration and invasion. In addition, TSLP inhibited LUAD progression through the JAK1/STAT3 signaling pathway. Therefore, targeting TSLP shows potential as a therapeutic strategy for pan-cancer, particularly for LUAD, and as a biomarker for predicting the prognosis of this malignancy.

A nomogram for predicting invasiveness of lung adenocarcinoma manifesting as pure ground-glass nodules: incorporating subjective CT signs and histogram parameters based on artificial intelligence.

To construct a nomogram based on subjective CT signs and artificial intelligence (AI) histogram parameters to identify invasiveness of lung adenocarcinoma presenting as pure ground-glass nodules (pGGNs) and to evaluate its diagnostic performance. 187 patients with 228 pGGNs confirmed by postoperative pathology were collected retrospectively and divided into pre-invasive group [atypical adenomatous hyperplasia (AAH) and adenocarcinoma in situ (AIS)] and invasive group [minimally invasive adenocarcinoma (MIA) and invasive adenocarcinoma (IAC)]. All pGGNs were randomly assigned to training cohort (n = 160) and validation cohort (n = 68). Nomogram was developed using subjective CT signs and AI-based histogram parameters by logistic regression analysis. The diagnostic performance was evaluated by receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis (DCA) curve. The nomogram was constructed with nodule shape, 3D mean diameter, maximum CT value, and skewness. It showed better discriminative power in differentiating invasive lesions from pre-invasive lesions with area under curve (AUC) of 0.849 (95% CI 0.790-0.909) in the training cohort and 0.831 (95% CI 0.729-0.934) in the validation cohort, which performed better than nodule shape (AUC 0.675, 95% CI 0.609-0.741), 3D mean diameter (AUC 0.762, 95% CI 0.688-0.835), maximum CT value (AUC 0.794, 95% CI 0.727-0.862), or skewness (AUC 0.594, 95% CI 0.506-0.682) alone in training cohort (for all, P < 0.05). For pulmonary pGGNs, the nomogram based on subjective CT signs and AI histogram parameters had a good predictive ability to discriminate invasive lung adenocarcinoma from pre-invasive lung adenocarcinoma, and it has the potential to improve diagnostic efficiency and to help the patient management.

Spatial downregulation of CD74 signatures may drive invasive component development in part-solid lung adenocarcinoma

Pulmonary nodules with part-solid imaging features manifest during the progression from preinvasive to invasive lung adenocarcinoma. To define the spatial composition and evolutionary trajectories of early-stage lung adenocarcinoma, we combined spatial transcriptomics (ST) and pathological annotations from 20 part-solid nodules (PSNs), four of which were matched with single-cell RNA sequencing. Two malignant cell populations (MC1 and MC2) were identified, and a linear evolutionary relationship was observed. Compared to MC2, the pre-existing malignant MC1 exhibited a lower metastatic signature, corresponding to the preinvasive component (lepidic) on pathology and the ground glass component on PSN imaging. Higher immune infiltration was observed among MC1 regions in ST profiles, and further analysis revealed that macrophages may be involved in this process through the CD74 axis. This work provides deeper insights into the evolutionary process and spatial immune cell composition behind PSNs and highlights the mechanisms of immune escape behind this adenocarcinoma trajectory.

Development and validation of 18F-FDG PET/CT radiomics-based nomogram to predict visceral pleural invasion in solid lung adenocarcinoma.

This study aimed to establish a radiomics model based on 18F-FDG PET/CT images to predict visceral pleural invasion (VPI) of solid lung adenocarcinoma preoperatively. We retrospectively enrolled 165 solid lung adenocarcinoma patients confirmed by histopathology with 18F-FDG PET/CT images. Patients were divided into training and validation at a ratio of 0.7. To find significant VPI predictors, we collected clinicopathological information and metabolic parameters measured from PET/CT images. Three-dimensional (3D) radiomics features were extracted from each PET and CT volume of interest (VOI). Receiver operating characteristic (ROC) curve was performed to determine the performance of the model. Accuracy, sensitivity, specificity and area under curve (AUC) were calculated. Finally, their performance was evaluated by concordance index (C-index) and decision curve analysis (DCA) in training and validation cohorts. 165 patients were divided into training cohort (n = 116) and validation cohort (n = 49). Multivariate analysis showed that histology grade, maximum standardized uptake value (SUVmax), distance from the lesion to the pleura (DLP) and the radiomics features had statistically significant differences between patients with and without VPI (P < 0.05). A nomogram was developed based on the logistic regression method. The accuracy of ROC curve analysis of this model was 75.86% in the training cohort (AUC: 0.867; C-index: 0.867; sensitivity: 0.694; specificity: 0.889) and the accuracy rate in validation cohort was 71.55% (AUC: 0.889; C-index: 0.819; sensitivity: 0.654; specificity: 0.739). A PET/CT-based radiomics model was developed with SUVmax, histology grade, DLP, and radiomics features. It can be easily used for individualized VPI prediction.

EGFR co-mutation is associated with the risk of recurrence in invasive lung adenocarcinoma with the micropapillary component

BackgroundInvasive lung adenocarcinoma (LUAD) patients with the micropapillary (MPP) component tend to have extremely poor prognosis. To optimize clinical outcomes, a better understanding of specific concurrent gene alterations and their impact on the prognosis of patients with the MPP component is necessary. MethodA total of 621 Chinese patients with surgically resected invasive LUAD who underwent genetic testing for lung cancer were enrolled in this retrospective study. The genomic profiling of major lung cancer-related genes based on next-generation sequencing (NGS) was carried out on formalin-fixed paraffin-embedded tumor samples. ResultAmong 621 patients with invasive LUAD, 154 (24.8%, 154/621) had the MPP component. We found that PIK3CA (4.5% vs 1.3%), KRAS (9.1% vs 4.7%), and ROS1 (2.6% vs 0.4%) were more frequent in patients with the MPP component than those without the MPP component (P < 0.05). The co-mutation occurred in 66 patients (10.6%, 66/621), of which 19 patients with the MPP component. Most of them were EGFR co-mutations (89.5%, 17/19), including EGFR and PIK3CA, EGFR and ERBB2, and other types. Patients with the MPP component who harbored EGFR co-mutations showed significantly worse recurrence-free survival (RFS) than single EGFR mutation (median RFS 20.1 vs 30.5 months; hazard ratio [HR]: 8.008; 95% confidence interval [CI]: 1.322–48.508). ConclusionsPatients with the MPP component harbored the co-mutation of driver genes had a higher risk of recurrence after surgery, especially in patients with EGFR co-mutation. EGFR co-mutation was a significant prognostic factor for RFS in patients with the MPP component.

ABCA3, a tumor suppressor gene, inhibits the proliferation, migration and invasion of lung adenocarcinoma by regulating the epithelial‑mesenchymal transition process.

Lung adenocarcinoma (LUAD) is one of the most common types of lung cancer, which affects the life and health of patients. The role of ATP-binding cassette subfamily A member 3 (ABCA3) in the occurrence and development of LUAD is unclear; therefore, ABCA3 expression in LUAD and other tumors was analyzed in the present study. In addition, ABCA3 expression in patients with LUAD and their survival were analyzed using a public database. ABCA3 co-expressed genes were identified and their enriched pathways were analyzed. Furthermore, ABCA3 expression was knocked down in LUAD cell lines. The proliferation, invasion and migration of cells, and the process of epithelial-mesenchymal transition (EMT), were studied through cytological and molecular biology experiments. Compared with that in normal lung tissues, ABCA3 expression was significantly reduced in tumor tissues. Patients with low ABCA3 expression had a markedly worse overall survival compared with those with high ABCA3 expression. Notably, abnormal ABCA3 expression has been observed in a variety of tumors. Subsequently, multiple pathophysiological pathways enriched by ABCA3 and its co-expressed genes were explored. Furthermore, the malignant behavior of tumor cells was enhanced when ABCA3 expression was knocked down, and the EMT process was activated after ABCA3 expression was knocked down. In conclusion, as a tumor suppressor gene, ABCA3 serves a protective role in the development of tumors, and may have a potential role in clinical applications, and thus, is worthy of further study.

Dual-energy CT-based radiomics for predicting invasiveness of lung adenocarcinoma appearing as ground-glass nodules.

To explore the value of radiomics based on Dual-energy CT (DECT) for discriminating preinvasive or MIA from IA appearing as GGNs before surgery. The retrospective study included 92 patients with lung adenocarcinoma comprising 30 IA and 62 preinvasive-MIA, which were further divided into a training (n=64) and a test set (n=28). Clinical and radiographic features along with quantitative parameters were recorded. Radiomics features were derived from virtual monoenergetic images (VMI), including 50kev and 150kev images. Intraclass correlation coefficients (ICCs), Pearson's correlation analysis and least absolute shrinkage and selection operator (LASSO) penalized logistic regression were conducted to eliminate unstable and redundant features. The performance of the models was evaluated by area under the curve (AUC) and the clinical utility was assessed using decision curve analysis (DCA). The DECT-based radiomics model performed well with an AUC of 0.957 and 0.865 in the training and test set. The clinical-DECT model, comprising sex, age, tumor size, density, smoking, alcohol, effective atomic number, and normalized iodine concentration, had an AUC of 0.929 in the training and 0.719 in the test set. In addition, the radiomics model revealed a higher AUC value and a greater net benefit to patients than the clinical-DECT model. DECT-based radiomics features were valuable in predicting the invasiveness of GGNs, yielding a better predictive performance than the clinical-DECT model.

Computed Tomography and 18F-Fluorodeoxyglucose-Positron Emission Tomography/Computed Tomography Imaging Biomarkers of Lung Invasive Non-mucinous Adenocarcinoma: Prediction of Grade 3 Tumour Based on World Health Organization Grading System

AimsTo evaluate computed tomography (CT) and 18F-fluorodeoxyglucose-positron emission tomography/computed tomography (18F-FDG-PET/CT) findings of invasive non-mucinous adenocarcinoma (INMA) of the lung as a predictor of histological tumour grade according to 2021 World Health Organization (WHO) classification. Materials and methodsThis retrospective study included consecutive patients with surgically resected INMA who underwent both preoperative CT and 18F-FDG-PET/CT. A three-tiered tumour grade was performed based on the fifth edition of the WHO classification of lung tumours. CT imaging features and the maximum standardised uptake value (SUVmax) were compared among the three tumour grades. ResultsIn total, 214 patients with INMA (median age 70 years; interquartile range 65–76 years; 123 men) were histologically categorised: 36 (17%) as grade 1, 102 (48%) as grade 2 and 76 (35%) as grade 3. Pure solid appearance was more frequent in grade 3 (83%) than in grades 1 (0%) and 2 (26%) (P < 0.001). The SUVmax of the entire tumour was higher in grade 3 than in grades 1 and 2 (P < 0.001). Multivariable analysis revealed that pure solid appearance (odds ratio = 94.0; P < 0.001), round/oval shape (odds ratio = 4.01; P = 0.001), spiculation (odds ratio = 2.13; P = 0.04), air bronchogram (odds ratio = 0.40; P = 0.03) and SUVmax (odds ratio = 1.45; P < 0.001) were significant predictors for grade 3 INMAs. ConclusionPure solid appearance, round/oval shape, spiculation, absence of air bronchogram and high SUVmax were associated with grade 3 INMAs. CT and 18F-FDG-PET/CT were potentially useful non-invasive imaging methods to predict the histological grade of INMAs.

Multi-dimensional radiomics analysis to predict visceral pleural invasion in lung adenocarcinoma of ≤3 cm maximum diameter

To explore the value of radiomics analysis in preoperatively predicting visceral pleural invasion (VPI) of lung adenocarcinoma (LAC) with ≤3 cm maximum diameter and to compare the performance of two-dimensional (2D) and three-dimensional (3D) computed tomography (CT) radiomics models. A total of 391 LAC patients were enrolled retrospectively, of whom 142 were VPI (+) and 249 were VPI (-). Radiomics features were extracted from 2D and 3D regions of interest (ROIs) of tumours in CT images. 2D and 3D radiomics models were developed combining the optimal radiomics features by using the logistic regression machine-learning method and radiomics scores (rad-scores) were calculated. Nomograms were constructed by integrating independent risk factors and rad-scores. The performance of each model was evaluated by using the receiver operator characteristic (ROC) curve, decision curve analysis (DCA), clinical impact curve (CIC), and calculating the area under the curve (AUC). There was no difference in the VPI prediction between 2D and 3D radiomics models (training group: 2D AUC=0.835, 3D AUC=0.836, p=0.896; validation group: 2D AUC=0.803, 3D AUC=0.794, p=0.567). The 2D and 3D nomograms performed similarly regarding discrimination (training group: 2D AUC=0.867, 3D AUC=0.862, p=0.409, validation group: 2D AUC=0.835, 3D AUC=0.827, p=0.558), and outperformed their corresponding radiomics models and the clinical model. DCA and CIC revealed that the 2D nomogram had slightly better clinical utility. The 2D radiomics model has a similar discrimination capability compared with the 3D radiomics model. The 2D nomogram performs slightly better for individual VPI prediction in LAC.

Single-cell profiling reveals the trajectory of FOLR2-expressing tumor-associated macrophages to regulatory T cells in the progression of lung adenocarcinoma

An immunosuppressive microenvironment enriched with regulatory CD4+ T lymphocytes (Tregs) facilitates the progression of lung adenocarcinoma (LUAD). This study aims to investigate the cellular mechanism underlying the formation of the immunosuppressive microenvironment in LUAD. LUAD samples (n = 12) and normal lung samples (n = 3) were obtained from patients with different pathological stages of LUAD. Single-cell RNA sequencing was performed to classify cellular components and analyze the transcriptomes, including transcription factors/targets and chemokine ligands/receptors, followed by bioinformatics study such as pseudotime analysis. Myeloid cells and T cells were the most abundant cell types in tumors and normal lung tissues, while tumor-associated macrophage-folate receptor 2 (TAM-FOLR2) and CD4+ nuclear receptor subfamily 4 group A member 3 (NR4A3) exhibited sharp increases in invasive adenocarcinoma (IA). The enrichment of TAM-FOLR2 in IA might result from alveolar resident macrophage-resistin (ARM-RETN) transformation and recruitment of dendritic cells (DCs) and other TAMs, as evidenced by temporal trajectories and differential expression profiles of chemokine ligands/receptors versus those in the early stages of tumors. High expression of CCL17/19/22 was observed in IA as well as in DCs, along with the strong interaction of TAM-FOLR2 with DCs. The results of pseudotime analysis suggested that CD4+NR4A3 might potentially convert to CD4+FOXP3, further supported by the high expression of NR4A3 target genes in CD4+FOXP3 cells. This study provides a single-cell transcriptome atlas from preinvasive to invasive LUAD and reveals a potential ARM-RETN/TAM-FOLR2/DCs/CD4+NR4A3/CD4+FOXP3 trajectory in shaping the immune suppressive microenvironment along the pathogenesis of LUAD.

Prognostic value of cancer-associated fibroblasts-related genes in lung adenocarcinoma.

The incidence of lung adenocarcinoma is in the forefront of malignant tumors in the world. The purpose of this study was to investigate the role of cancer-associated fibroblast-related genes (CAFRGs) in the occurrence, diagnosis and development of lung adenocarcinoma. RNA data and corresponding clinical information of lung adenocarcinoma patients were acquired from The Cancer Genome Atlas (TCGA) database. Consensus clustering was performed to identify different molecular subgroups. The tumor immune states of different subgroups were determined by Estimation of STromal and Immune cells in MAlignant Tumor tissues using Expression data (ESTIMATE; https://bioinformatics.mdanderson.org/estimate/index.html), microenvironment cell populations (MCP)-counter (which can reliably quantify the abundance of eight immune cell populations and two stromal cell populations), and single sample gene set enrichment analysis (ssGSEA) analyses. In order to elucidate the potential mechanism of CAFRGs, functional enrichment analysis including gene ontology (GO), Kyoto Encyclopedia of Genes and Genome (KEGG), and GSEA analysis were performed on the differentially expressed genes (DEGs). Least absolute shrinkage and selection operator (LASSO) algorithm and multivariate Cox regression analysis were used to construct the prognostic risk model, which was verified by lung adenocarcinoma data from Gene Expression Omnibus (GEO) dataset GSE37745. This study identified two molecular subgroups with significant differences in survival. High immunoscore and immune cell infiltration were more common in the subgroup with better prognosis. GO and KEGG analysis showed that DEGs between the two different subgroups were mainly concentrated in the mitotic cell cycle, cell proliferation, vascular development, and humoral immune response, adaptive immune-related pathways. GSEA analysis indicated that RNA degradation and P53 signaling pathway might be related to the increased invasiveness of lung adenocarcinoma. Risk models based on CAFRGs have demonstrated potent potential for predicting lung adenocarcinoma survival and have been validated in validation cohorts. The nomogram combined with risk model and clinical characteristics can predict the prognosis of patients with lung adenocarcinoma. The expression of CAFRGs is related to tumor immune microenvironment (TIME) of lung adenocarcinoma patients, and can predict the prognosis of lung adenocarcinoma patients.

Invasiveness identification in pure ground-glass nodules: exploring the generalizability of radiomics based on external validation and stress testing.

This study aimed to apply external validation and stress tests to evaluate the generalizability of radiomics models built using various machine-learning methods for identifying the invasiveness of lung adenocarcinomas manifesting as pure ground-glass nodules (pGGNs). This retrospective study enrolled 495 patients (514 pGGNs) confirmed as lung adenocarcinomas by postoperative pathology from three centers. All nodules were included in the primary cohort (randomly divided into training and test cohorts), two external validation cohorts, and two stress test cohorts. Six machine-learning radiomics models were constructed in the training cohort using the optimal features. Performance of radiomics models and clinical models were compared in primary cohort and external validation cohorts. The stress tests included stratified performance evaluation and shifted performance evaluation and contrastive evaluation under three single-condition modification settings. The predictive performance was validated by area under curve (AUC) of receiver operating characteristic (ROC). Of the six radiomics models, the best logistic regression (LR) model was able to maintain high differential diagnostic capability (AUC: 0.849 ± 0.049) and good stability (relative standard deviation, 5.719%), but it showed poorer performance (AUC= 0.835) than the clinical model (AUC= 0.862) in the external validation cohort E1. The stress tests suggested LR model had no significant difference in performance between subgroups after stratification and had good consistency in the predictions before and after the three transformations (Kappa = 0.960, 0.840, and 0.933, respectively; p < 0.05, all). The rigorous testing procedure facilitates the selection of high-performance radiomics models with good clinical generalizability.

Development of a novel combined nomogram integrating deep-learning-assisted CT texture and clinical–radiological features to predict the invasiveness of clinical stage IA part-solid lung adenocarcinoma: a multicentre study

To develop a novel combined nomogram based on deep-learning-assisted computed tomography (CT) texture (DL-TA) and clinical-radiological features for the preoperative prediction of invasiveness in patients with clinical stage IA lung adenocarcinoma manifesting as part-solid nodules (PSNs). This study was conducted from January 2015 to October 2021 at three centres: 355 patients with 355 PSN lung adenocarcinomas who underwent surgical resection were included and classified into the training (n=222) and validation (n=133) cohorts. PSN segmentation on CT images was performed automatically with a commercial deep-learning algorithm, and CT texture features were extracted. The least absolute shrinkage and selection operator was used for feature selection and transformed into a DL-TA score. The combined nomogram that incorporated the DL-TA score and identified clinical-radiological features was developed for the prediction of pathological invasiveness of the PSNs and validated in terms of discrimination and calibration. The present study generated a combined nomogram for predicting the invasiveness of PSNs that included age, consolidation-to-tumour ratio, smoking status, and DL-TA score, with a C-index of 0.851 (95% confidence interval: 0.826-0.877) for the training cohort and 0.854 (95% confidence interval: 0.817-0.891) for the validation cohort, indicating good discrimination. Furthermore, the model had a Brier score of 0.153 for the training cohort and 0.135 for the validation cohort, indicating good calibration. The developed combined nomogram consisting of the DL-TA score and clinical-radiological features and has the potential to predict the individual risk for the invasiveness of stage IA PSN lung adenocarcinomas.

An ensemble deep learning model for risk stratification of invasive lung adenocarcinoma using thin-slice CT

Lung cancer screening using computed tomography (CT) has increased the detection rate of small pulmonary nodules and early-stage lung adenocarcinoma. It would be clinically meaningful to accurate assessment of the nodule histology by CT scans with advanced deep learning algorithms. However, recent studies mainly focus on predicting benign and malignant nodules, lacking of model for the risk stratification of invasive adenocarcinoma. We propose an ensemble multi-view 3D convolutional neural network (EMV-3D-CNN) model to study the risk stratification of lung adenocarcinoma. We include 1075 lung nodules (≤30 mm and ≥4 mm) with preoperative thin-section CT scans and definite pathology confirmed by surgery. Our model achieves a state-of-art performance of 91.3% and 92.9% AUC for diagnosis of benign/malignant and pre-invasive/invasive nodules, respectively. Importantly, our model outperforms senior doctors in risk stratification of invasive adenocarcinoma with 77.6% accuracy [i.e., Grades 1, 2, 3]). It provides detailed predictive histological information for the surgical management of pulmonary nodules. Finally, for user-friendly access, the proposed model is implemented as a web-based system (https://seeyourlung.com.cn).

Deep learning-based diagnosis of histopathological patterns for invasive non-mucinous lung adenocarcinoma using semantic segmentation

ObjectivesThe application of artificial intelligence (AI) to the field of pathology has facilitated the development of digital pathology, hence, making AI-assisted diagnosis possible. Due to the variety of lung cancers...

Clinical characteristics and establishment of a 2-year-OS predictive model of EGFR mutation-positive patients with pleural invasion of lung adenocarcinoma.

To investigate the differences between lung adenocarcinoma with the pleural invasion that has EGFR (epidermal growth factor receptor) 19-del or 21L858R mutations in terms of clinical characteristics and outcomes. EGFR mutation-positive patients with pleural metastasis of lung adenocarcinoma diagnosed in the Department of Respiratory Medicine of Yuhuangding Hospital of Yantai City, Shandong Province, from January 2014 to January 2022 were selected. The clinical data of the patients were collected to retrospectively analyze whether the clinical characteristics and prognosis of patients with 19-del or 21L858R mutation subtype were different and analyze the impact of clinical characteristics on the prognosis of patients. The difference in clinical characteristics between the 2 groups was analyzed by SPSS, P < .05. There was statistical significance. Univariate and multivariate regression analysis was performed with R soft. To establish a 2-year overall survival predictive model for patients with EGFR gene 19-del and 21L858R mutations in patients with pleural invasion of lung adenomas and to provide predictive model maps. Receiver operating characteristic curve, calibration curve, and decision curve analysis were used to evaluate the value of the prediction model in this study. Of the 74 patients included, the 19-del mutation group had a higher incidence of pleural thickening (P = .023) and a lower Ki-67 level (P = .035). There was no difference in 2-year overall survival and progression-free survival between the 2 mutations. There were differences in pleural thickening and Ki-67 index between the 2 groups, but no differences in disease outcome between the 2 groups. The nomogram model established based on gender, treatment regimen, CEA, lymph node metastasis, and pleural changes is accurate and feasible.

LINC01117 inhibits invasion and migration of lung adenocarcinoma through influencing EMT process.

Studying the mechanism of action of LncRNAs in lung adenocarcinoma (LUAD) is of great importance for an in-depth understanding of the molecular mechanism of lung adeno carcinogenesis and development. The aim is to identify a long non-coding RNA LINC01117 that is specifically and highly expressed in LUAD cells and to investigate its biological functions and molecular mechanisms in LUAD cells, providing a new potential target for targeting LUAD therapy. This study used publicly available data downloaded from The Cancer Genome Atlas (TCGA) database. Construction of siRNA and overexpression plasmid-packed lentiviral constructs were used to knock down and increase the expression of LINC01117 in LUAD cells. The effect of LINC01117 on LUAD cell migration and invasion was verified by scratch assays and Transwell assays. Western blot assays were performed to verify the effect of knocking down LINC01117 expression on key proteins of the EMT process. The effect of overexpression and knockdown LINC01117 expression on key proteins of the EMT process and the nuclear and cytoplasmic distribution of YAP1, a key effector molecule of the Hippo pathway, was verified by Western blot assays. LINC01117 expression was upregulated in LUAD tissues and cell lines. Clinical correlation and prognostic analyses showed that LINC01117 was associated with poorer clinical features (staging and N classification) and poorer prognosis and could be analyzed as an independent prognostic factor. Cell migration and invasion were significantly inhibited in the knockdown group compared to the control group; in contrast, cell migration and invasion were promoted in the overexpression group. Overexpression of LINC01117 resulted in down-regulation of E-cadherin expression and increased expression levels of N-cadherin, vimentin, ZEB1, snail and slug; in contrast, knockdown of LINC01117 appeared to have the opposite effect. Furthermore, knockdown of LINC01117 increased the enrichment of YAP1 protein in the cytoplasm and reduced its level in the nucleus; overexpression of LINC01117 produced the opposite intracellular distribution results. LINC01117 was highly expressed in LUAD, and knockdown of LINC01117 significantly inhibited the migration and invasion of LUAD cells, while overexpression of LINC01117 significantly promoted the migration and invasion of LUAD cells, and affected the EMT process, and was able to alter the distribution of YAP1 in the nucleus and cytoplasm. This suggests that LINC01117 may regulate the activity of the Hippo pathway by altering the nuclear and cytoplasmic distribution of YAP1, which in turn induces the EMT process in lung adenocarcinoma cells and thus exerts a pro-cancer effect. It suggests that LINC01117 may play a key role in the occurrence and development of LUAD.