Impact of histopathological subtypes on invasive lung adenocarcinoma: from epidemiology to tumour microenvironment to therapeutic strategies

Purpose: The aims of this study were to combine CT images with Ki-67 expression to distinguish various subtypes of lung adenocarcinoma and to pre-operatively predict the Ki-67 expression level based on CT radiomic features.Methods: Data from 215 patients with 237 pathologically proven lung adenocarcinoma lesions who underwent CT and immunohistochemical Ki-67 from January 2019 to April 2021 were retrospectively analyzed. The receiver operating curve (ROC) identified the Ki-67 cut-off value for differentiating subtypes of lung adenocarcinoma. A chi-square test or t-test analyzed the differences in the CT images between the negative expression group (n = 132) and the positive expression group (n = 105), and then the risk factors affecting the expression level of Ki-67 were evaluated. Patients were randomly divided into a training dataset (n = 165) and a validation dataset (n = 72) in a ratio of 7:3. A total of 1,316 quantitative radiomic features were extracted from the Analysis Kinetics (A.K.) software. Radiomic feature selection and radiomic classifier were generated through a least absolute shrinkage and selection operator (LASSO) regression and logistic regression analysis model. The predictive capacity of the radiomic classifiers for the Ki-67 levels was investigated through the ROC curves in the training and testing groups.Results: The cut-off value of the Ki-67 to distinguish subtypes of lung adenocarcinoma was 5%. A comparison of clinical data and imaging features between the two groups showed that histopathological subtypes and air bronchograms could be used as risk factors to evaluate the expression of Ki-67 in lung adenocarcinoma (p = 0.005, p = 0.045, respectively). Through radiomic feature selection, eight top-class features constructed the radiomic model to pre-operatively predict the expression of Ki-67, and the area under the ROC curves of the training group and the testing group were 0.871 and 0.8, respectively.Conclusion: Ki-67 expression level with a cut-off value of 5% could be used to differentiate non-invasive lung adenocarcinomas from invasive lung adenocarcinomas. It is feasible and reliable to pre-operatively predict the expression level of Ki-67 in lung adenocarcinomas based on CT radiomic features, as a non-invasive biomarker to predict the degree of malignant invasion of lung adenocarcinoma, and to evaluate the prognosis of the tumor.

Purpose: To investigate the correlation between 18F-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) metabolic parameters and clinicopathological factors in pathological subtypes of invasive lung adenocarcinoma and prognosis.Patients and Methods: Metabolic parameters and clinicopathological factors from 176 consecutive patients with invasive lung adenocarcinoma between August 2008 and August 2016 who underwent 18F-FDG PET/CT examination were retrospectively analyzed. Invasive lung adenocarcinoma was divided into five pathological subtypes:lepidic predominant adenocarcinoma (LPA), acinar predominant adenocarcinoma (APA), papillary predominant adenocarcinoma (PPA), solid predominant adenocarcinoma (SPA), and micropapillary predominant adenocarcinoma (MPA). The differences in metabolic parameters [maximal standard uptake value (SUVmax), mean standard uptake value (SUVmean), total lesion glycolysis (TLG), and metabolic tumor volume (MTV)] and tumor diameter for different pathological subtypes were analyzed. Patients were divided into two groups according to their prognosis: good prognosis group (LPA, APA, PPA) and poor prognosis group (SPA, MPA). Logistic regression was used to filter predictors and construct a predictive model, and areas under the receiver operating curve (AUC) were calculated. Cox regression analysis was performed on prognostic factors.Results: 82 (46.6%) females and 94 (53.4%) males of patients with invasive lung adenocarcinoma were enrolled in this study. Metabolic parameters and tumor diameter of different pathological subtype had statistically significant (P < 0.05). The predictive model constructed using independent predictors (Distant metastasis, Ki-67, and SUVmax) had good classification performance for both groups. The AUC for SUVmax was 0.694 and combined with clinicopathological factors were 0.745. Cox regression analysis revealed that Stage, TTF-1, MTV, and pathological subtype were independent risk factors for patient prognosis. The hazard ratio (HR) of the poor prognosis group was 1.948 (95% CI 1.042–3.641) times the good prognosis group. The mean survival times of good and poor prognosis group were 50.2621 (95% CI 47.818–52.706) and 35.8214 (95% CI 27.483–44.159) months, respectively, while the median survival time was 47.00 (95% CI 45.000–50.000) and 31.50 (95% CI 23.000–49.000) months, respectively.Conclusion: PET/CT metabolic parameters combined with clinicopathological factors had good classification performance for the different pathological subtypes, which may provide a reference for treatment strategies and prognosis evaluation of patients.

BackgroundThis study evaluated programmed cell death-ligand 1 (PD-L1) expression from pre-invasive adenocarcinoma to invasive lung adenocarcinoma, aimed to investigate the potential association of PD-L1 pathway with lung adenocarcinoma early evolution.MethodsWe evaluated PD-L1 expression in 1123 resected lung specimens of adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA) and invasive adenocarcinoma (IAC) of stage IA1–IA3. PD-L1 expression was defined based on the proportion of stained tumor cells using the tumor proportion score: < 1% (negative), ≥ 1% (positive) and ≥ 50% (strongly positive). Correlations between PD-L1 expression and T stage, pathological subtype, adenocarcinoma grade, spread through air space (STAS), vascular invasion, lymphatic invasion and driven genes were analyzed.ResultsThere was almost no PD-L1 expression in AIS or MIA. However, PD-L1 expression was correlated with invasiveness of lung adenocarcinoma. The percentages of PD-L1 positive in IA1–IA3 were 7.22%, 11.29%, and 14.20%, respectively. The strongly positive rates of PD-L1 were 0.38%, 1.64%, and 3.70% in IA1–IA3, respectively. PD-L1 expression and positive rate were also associated with poor pathological subtype and poor biological behavior, such as adenocarcinoma Grade 3, micropapillary or solid dominant subtype, STAS and vascular invasion. Finally, PD-L1 positive rate seems also corrected with driven gene ALK, ROS-1 and KRAS.ConclusionsPD-L1 expression was positively correlated with the emergence of invasiveness and poor pathological subtype or biological behavior of early-stage lung adenocarcinoma. PD-L1 pathway may be involved in the early evolution of lung adenocarcinoma from AIS to IAC.

Background: The Lung adenocarcinoma, a subtype of non-small cell lung cancer, exhibits diverse histopathological patterns, impacting prognosis and therapeutic outcomes. Objective: This study explores the correlation between smoking habits and the prevalence of different histopathological subtypes in invasive lung adenocarcinoma (IAC). Methods: A single-center, cross-sectional study included 140 patients with surgically treated, histopathological verified lung adenocarcinoma. The patients were classified based on the World Health Organization’s (WHO) histopathological patterns, and smoking status data were collected from medical records. Descriptive and inferential statistical analyses were performed using SPSS software. Results: The predominant histopathological subtypes were acinar (47.9%) and solid (30.7%) IAC. Smokers constituted 84.3% of the patients, with a majority (61.7%) consuming more than 20 cigarettes per day. A weak, statistically significant correlation was found between histopathological patterns and smoking habits among smokers (rho=0.054; p=0.04). Acinar IAC was more common in those consuming up to 20 cigarettes daily, while the solid pattern predominated in those smoking more than 20 cigarettes (rho=0.189; p=0.04). No significant correlation was observed with the duration of smoking history. Conclusion: The study reveals a predictive relationship between smoking habits, including the number of cigarettes consumed, and the histopathological pattern of IAC in resected specimens. Acinar and solid subtypes were more prevalent, with distinct associations to smoking behaviors. Understanding these relationships can contribute to personalized treatment approaches and further research on lung adenocarcinoma.

BackgroundAdenocarcinoma in situ (AIS) is a pre-invasive lesion in the lung and a subtype of lung adenocarcinoma. The patients with AIS can be cured by resecting the lesion completely. In contrast, the patients with invasive lung adenocarcinoma have very poor 5-year survival rate. AIS can develop into invasive lung adenocarcinoma. The investigation and comparison of AIS and invasive lung adenocarcinoma at the genomic level can deepen our understanding of the mechanisms underlying lung cancer development.ResultsIn this study, we identified 61 lung adenocarcinoma (LUAD) invasive-specific differentially expressed genes, including nine long non-coding RNAs (lncRNAs) based on RNA sequencing techniques (RNA-seq) data from normal, AIS, and invasive tissue samples. These genes displayed concordant differential expression (DE) patterns in the independent stage III LUAD tissues obtained from The Cancer Genome Atlas (TCGA) RNA-seq dataset. For individual invasive-specific genes, we constructed subnetworks using the Genetic Algorithm (GA) based on protein-protein interactions, protein-DNA interactions and lncRNA regulations. A total of 19 core subnetworks that consisted of invasive-specific genes and at least one putative lung cancer driver gene were identified by our study. Functional analysis of the core subnetworks revealed their enrichment in known pathways and biological progresses responsible for tumor growth and invasion, including the VEGF signaling pathway and the negative regulation of cell growth.ConclusionsOur comparison analysis of invasive cases, normal and AIS uncovered critical genes that involved in the LUAD invasion progression. Furthermore, the GA-based network method revealed gene clusters that may function in the pathways contributing to tumor invasion. The interactions between differentially expressed genes and putative driver genes identified through the network analysis can offer new targets for preventing the cancer invasion and potentially increase the survival rate for cancer patients.

The aim of this study was to analyze the influence of non-predominant micropapillary pattern in small sized invasive lung adenocarcinoma. A total of 986 lung adenocarcinoma patients with tumor size ≤3 cm were identified and classified according to the IALSC/ATS/ERS classification. Emphasis was placed on the impact of non-predominant micropapillary pattern on disease-free survival (DFS) and overall survival (OS). The relationship between lung adenocarcinoma subtype and lymph node involvement, EGFR mutation and KRAS mutation was also evaluated. A nomogram was developed to predict the probability of 3- and 5-year OS for these patients. The concordance index and calibration plot were used to validate this model. Among all 986 patients, the percentages of lymph node involvement were: 58.1, 50.0, 33.5, 21.4, 21.1, 10.9, 0, and 0% for micropapillary predominant, solid predominant, acinar predominant, papillary predominant, invasive mucinous adenocarcinoma (IMA), lepidic predominant, minimally invasive adenocarcinoma (MIA), adenocarcinoma in situ (AIS), respectively. The frequency of EGFR mutation in the cases of lepidic predominant, acinar predominant, MIA, micropapillary predominant, papillary predominant, solid predominant, IMA, and AIS were 51.1, 45.2, 44.4, 36.8, 29.3, 26.8, 8.3, and 0%, respectively. A non-predominant micropapillary pattern was observed in 344 (38.4%) invasive adenocarcinoma (IAC), and its presence predicted a poorer DFS (median: 56.0 months vs. 66.0 months, P <0.001) and OS (median: 61.0 months vs. 70.0 months, P <0.001). After propensity score matching, non-predominant micropapillary pattern retained its unfavorable effect on DFS (P = 0.007) and OS (P = 0.001). Multivariate analysis showed that non-predominant micropapillary pattern was identified as an independent prognostic factor for DFS (P = 0.003) and OS (P <0.001) in IAC. The nomogram showed good calibration and reliable discrimination ability (C-index = 0.775) to evaluated the 3- and 5-year OS. This retrospective analysis of patients with small sized IAC suggests the value of non-predominant micropapillary pattern to predict poor prognosis. A reliable nomogram model was constructed to provide personalized survival predictions.

This study investigated the application value and imaging features of multi-detector CT (MDCT) in the treatment of lung adenocarcinoma with ground glass nodules (GGN). The medical data of 168 patients with pulmonary GGN in Shengli Oilfield Central Hospital from January 2013 to June 2015 were analyzed. Patients with microinvasive adenocarcinoma and invasive adenocarcinoma were included in group A (invasive lung adenocarcinoma, n=98), while patients with atypical adenomatous hyperplasia and adenocarcinoma in situ were included in group B (pre-invasive lung adenocarcinoma, n=70). The imaging features of MDCT were compared. ROC curves of the size of nidus and the size of solid component were drawn for the diagnosis of invasive lung adenocarcinoma. Logistic multivariate regression analysis was used to analyze the risk factors that affected invasive lung adenocarcinoma. There were significant differences in nidus, burr, and lobes of the patients between groups A and B. The size of nidus and the size of solid component of the patients in group A were significantly higher than those of the patients in group B. The AUCs of the size of the nidus and the size of the solid component of the invasive lung adenocarcinoma were 0.891 and 0.902, respectively. The AUC of the combined diagnosis was 0.984. Size of the nidus, size of the solid component, nature of the lesion, burr, and lobes were all risk factors for invasive lung adenocarcinoma. In patients with GGN, size of the nidus and size of the solid component can be used as excellent diagnostic parameters for invasive lung adenocarcinoma, and nidus size (≥9.8 mm), size of the solid component (≥0.9 mm), the mixed GGN nature of the nidus, burr and lobes can distinguish invasive lung adenocarcinoma and pre-invasive lesions.

Invasive mucinous lung adenocarcinoma (IMA) is a subtype of lung adenocarcinoma with a strong invasive ability. IMA frequently carries "undruggable" KRAS mutations, highlighting the need for new molecular targets and therapies. Nuclear receptor HNF4α is abnormally enriched in IMA, but the potential of HNF4α to be a therapeutic target for IMA remains unknown. Here, we report that P2 promoter-driven HNF4α expression promotes IMA growth and metastasis. Mechanistically, HNF4α transactivated lncRNA BC200, which acted as a scaffold for mRNA binding protein FMR1. BC200 promoted the ability of FMR1 to bind and regulate stability of cancer-related mRNAs and HNF4α mRNA, forming a positive feedback circuit. Mycophenolic acid, the active metabolite of FDA-approved drug mycophenolate mofetil, was identified as an HNF4α antagonist exhibiting anti-IMA activities in vitro and in vivo. This study reveals the role of a HNF4α-BC200-FMR1-positive feedback loop in promoting mRNA stability during IMA progression and metastasis, providing a targeted therapeutic strategy for IMA. SIGNIFICANCE: Growth and metastatic progression of invasive mucinous lung adenocarcinoma can be restricted by targeting HNF4α, a critical regulator of a BC200-FMR1-mRNA stability axis.

背景与目的肺癌是国内外致死率最高的恶性肿瘤，肺结节的精确检测是降低肺癌死亡率的关键。人工智能辅助诊断系统在肺结节检测、良恶性鉴别和浸润亚型诊断等领域发展迅速，对其效能进行验证是促进其应用于临床的前提。本研究旨在评估人工智能辅助诊断系统预测肺结节早期肺腺癌浸润亚型的效能。方法回顾性分析2016年1月1日-2021年12月31日期间兰州大学第二医院收治的223例肺结节早期肺腺癌患者的临床资料，将早期肺腺癌分为浸润性腺癌组(n=170)和非浸润性腺癌组(n=53)，其中非浸润性腺癌组又分为微浸润性腺癌组(n=31)和浸润前病变组(n=22)。比较各组的恶性概率和影像特征等信息，分析其对早期肺腺癌浸润亚型的预测能力，并对人工智能辅助诊断早期肺腺癌浸润亚型定性诊断的结果与术后病理进行一致性分析。结果早期肺腺癌不同浸润亚型肺结节的平均CT值(P < 0.001)、直径(P < 0.001)、体积(P < 0.001)、恶性概率(P < 0.001)、胸膜凹陷征(P < 0.001)、分叶征(P < 0.001)、毛刺征(P < 0.001)差异均有统计学意义; 随着早期肺腺癌不同浸润亚型浸润性增加，各组参数显性征象比例也逐渐升高; 在二分类问题上，人工智能辅助诊断系统定性诊断早期肺腺癌浸润亚型的敏感性、特异性及曲线下面积(area under the curve, AUC)分别为81.76%、92.45%和0.871; 在三分类问题上，人工智能辅助诊断系统定性诊断早期肺腺癌浸润亚型的准确率、召回率、F1分数及AUC分别为83.86%、85.03%、76.46%和0.879。结论该人工智能辅助诊断系统对肺结节早期肺腺癌浸润亚型具有一定的预测价值，随着算法的优化和数据的完善或可为患者个体化治疗提供指导。

A total of 1039 stage I-III invasive lung adenocarcinoma including 186 solid subtype patients who have undergone radical resection were assessed for clincopathlogic characteristics, status of common driver mutations, pattern of recurrence, recurrence-free survival (RFS), overall survival (OS), post-recurrence survival (PRS) and predictive value for adjuvant chemotherapy and EGFR tyrosine kinase inhibitors (TKIs). Solid predominant adenocarcinomas were more likely to have initial distant recurrences than non-solid subtype invasive adenocarcinomas (P = 0.018). In univariate analysis, solid predominant adenocarcinoma patients had significantly worse RFS (P < 0.001), OS (P < 0.001) and PRS (P = 0.010). Multivariate analysis adjusting for clinicopathologic variables and mutational status showed that solid subtype was an independent poor prognostic factor (odds ratio = 1.876, 95% confidence interval: 1.291–3.158; P = 0.003) and an independent negative predictor for stage II-III patients undergoing adjuvant chemotherapy (odds ratio = 2.020, 95% confidence interval: 1.291–3.158; P = 0.002). In EGFR-mutated solid predominant lung adenocarcinoma patients who experienced disease recurrence, the response rate to EGFR TKIs was only 37.5%. In radically resected invasive lung adenocarcinoma, solid subtype was an independent poor prognostic factor and negative predictor for adjuvant chemotherapy.

This study aims to develop a CT-based hybrid deep learning network to predict pathological subtypes of early-stage lung adenocarcinoma by integrating residual network (ResNet) with Vision Transformer (ViT).A total of 1411 pathologically confirmed ground-glass nodules (GGNs) retrospectively collected from two centers were used as internal and external validation sets for model development. 3D ResNet and ViT were applied to investigate two deep learning frameworks to classify three subtypes of lung adenocarcinoma namely invasive adenocarcinoma (IAC), minimally invasive adenocarcinoma and adenocarcinoma in situ, respectively. To further improve the model performance, four Res-TransNet based models were proposed by integrating ResNet and ViT with different ensemble learning strategies. Two classification tasks involving predicting IAC from Non-IAC (Task1) and classifying three subtypes (Task2) were designed and conducted in this study.For Task 1, the optimal Res-TransNet model yielded area under the receiver operating characteristic curve (AUC) values of 0.986 and 0.933 on internal and external validation sets, which were significantly higher than that of ResNet and ViT models (p < 0.05). For Task 2, the optimal fusion model generated the accuracy and weighted F1 score of 68.3% and 66.1% on the external validation set.The experimental results demonstrate that Res-TransNet can significantly increase the classification performance compared with the two basic models and have the potential to assist radiologists in precision diagnosis.

Objective: To explore the value of quantitative parameters of artificial intelligence (AI) and computed tomography (CT) signs in identifying pathological subtypes of lung adenocarcinoma appearing as ground-glass nodules (GGNs). Methods: CT images of 224 GGNs from 210 individuals were collected retrospectively and classified into atypical adenomatous hyperplasia (AAH)/adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA), and invasive adenocarcinoma (IAC) groups. AI was used to identify GGNs and to obtain quantitative parameters, and CT signs were recognized manually. The mixed predictive model based on logistic multivariate regression was built and evaluated. Results: Of the 224 GGNs, 55, 93, and 76 were AAH/AIS, MIA, and IAC, respectively. In terms of AI parameters, from AAH/AIS to MIA, and IAC, there was a gradual increase in two-dimensional mean diameter, three-dimensional mean diameter, mean CT value, maximum CT value, and volume of GGNs (all P<0.0001). Except for the CT signs of the location, and the tumor–lung interface, there were significant differences among the three groups in the density, shape, vacuolar signs, air bronchogram, lobulation, spiculation, pleural indentation, and vascular convergence signs (all P<0.05). The areas under the curve (AUC) of predictive model 1 for identifying the AAH/AIS and MIA and model 2 for identifying MIA and IAC were 0.779 and 0.918, respectively, which were greater than the quantitative parameters independently (all P<0.05). Conclusion: AI parameters are valuable for identifying subtypes of early lung adenocarcinoma and have improved diagnostic efficacy when combined with CT signs.

The present study aimed to investigate the association between epidermal growth factor receptor (EGFR)/Kirsten rat sarcoma viral oncogene homolog (KRAS) mutations, anaplastic lymphoma receptor tyrosine kinase (ALK) rearrangements and the morphological characteristics of lung adenocarcinoma (LAC), according to the International Association for the Study of Lung Cancer/American Thoracic Society/European Respiratory Society (IASLC/ATS/ERS) classification in a large group of patients with primary LAC. A total of 200 patients with invasive LAC who had undergone complete resections at the Beijing Chest Hospital (Beijing, China) were randomly selected. The morphology of the samples was reassessed in 5% increments by two pathologists, according to the IASLC/ATS/ERS scheme. EGFR and KRAS mutations were tested by direct DNA sequencing. ALK rearrangements were screened by immunohistochemistry on a Benchmark XT stainer. The data revealed that EGFR and KRAS mutations, and ALK rearrangements were identified in 46.0% (92/200), 9.0% (18/200) and 11.5% (23/200) of the patients, respectively. The EGFR/KRAS mutations and ALK rearrangements were mostly exclusive. However, 1 patient exhibited the coexistence of the EGFR (at exon 20) and KRAS (codon 12) mutations, and another patient exhibited the coexistence of the EGFR mutation (at exon 21) and the ALK gene fusion. EGFR mutations were indicated to be closely associated with the acinar predominant (43/77; 55.8%; P=0.030) and papillary predominant (26/49; 53.1%; P=0.006) subtypes. KRAS mutations were more commonly associated with the solid predominant subtype (9/52; 17.3%; P=0.023) and invasive mucinous LAC (5/10; 50.0%; P=0.004), and less commonly associated with the acinar predominant subtype (1/77; 1.3%; P=0.002). ALK rearrangements more commonly occurred in the solid predominant subtype compared with other subtypes (13/52; 25%; P=0.002), and less commonly occurred in the papillary predominant subtype (1/49; 2.0%; P=0.004). Tumors harboring ALK rearrangements were characterized by signet-ring cell (7/9; 77.8%; P<0.0001) and cribriform (7/12; 58.3%; P<0.0001) patterns. The association between the mutation status and histological subtype in LAC was distinct. The predominant subtype according to the IASLC/ATS/ERS classification provided important information for gene mutations and integrated clinical findings to improve the treatment of LAC patients.

Here we focus on the molecular characterization of clinically significant histological subtypes of early-stage lung adenocarcinoma (esLUAD), which is the most common histological subtype of lung cancer. Within lung adenocarcinoma, histology is heterogeneous and associated with tumor invasion and diverse clinical outcomes. We present a gene signature distinguishing invasive and non-invasive tumors among esLUAD. Using the gene signatures, we estimate an Invasiveness Score that is strongly associated with survival of esLUAD patients in multiple independent cohorts and with the invasiveness phenotype in lung cancer cell lines. Regulatory network analysis identifies aurora kinase as one of master regulators of the gene signature and the perturbation of aurora kinases in vitro and in a murine model of invasive lung adenocarcinoma reduces tumor invasion. Our study reveals aurora kinases as a therapeutic target for treatment of early-stage invasive lung adenocarcinoma.

Adenocarcinoma in situ (AIS) and minimally invasive adenocarcinoma (MIA) are assumed to be indolent lung adenocarcinoma with excellent prognosis. We aim to identify these lesions from invasive adenocarcinoma (IA) by a radiomics approach. This retrospective study was approved by institutional review board with a waiver of informed consent. Pathologically confirmed lung adenocarcinomas manifested as lung nodules less than 3 cm were retrospectively identified. In-house software was used to quantitatively extract 60 CT-based radiomics features quantifying nodule's volume, intensity and texture property through manual segmentation. In order to differentiate AIS/MIA from IA, least absolute shrinkage and selection operator (LASSO) logistic regression was used for feature selection and developing radiomics signatures. The predictive performance of the signature was evaluated via receiver operating curve (ROC) and calibration curve, and validated using an independent cohort. 402 eligible patients were included and divided into the primary cohort (n = 207) and the validation cohort (n = 195). Using the primary cohort, we developed a radiomics signature based on five radiomics features. The signature showed good discrimination between MIA/AIS and IA in both the primary and validation cohort, with AUCs of 0.95 (95% CI, 0.91-0.98) and 0.89 (95% CI, 0.84-0.93), respectively. Multivariate logistic analysis revealed that the signature (OR, 13.3; 95% CI, 6.2-28.5; p < 0.001) and gender (OR, 3.5; 95% CI, 1.2-10.9; p = 0.03) were independent predictors of indolent lung adenocarcinoma. The signature based on radiomics features helps to differentiate indolent from invasive lung adenocarcinoma, which might be useful in guiding the intervention choice for patients with pulmonary nodules. • Based on radiomics features, a signature is established to differentiate adenocarcinoma in situ and minimally invasive adenocarcinoma from invasive lung adenocarcinoma.