[Prediction of Lymph Node Metastasis of Mixed Ground-glass Nodules 
Based on Clinical Imaging Information].

BACKGROUND: Previous studies have shown that lymph node metastasis only occurs in some mixed ground-glass nodules (mGGNs) which the pathological results were invasive adenocarcinoma (IAC). However, the presence of lymph node metastasis leads to the upgrading of tumor-node-metastasis (TNM) stage and worse prognosis of the patients, so it is important to perform the necessary evaluation before surgery to guide the operation method of lymph node. The aim of this study was to find suitable clinical and radiological indicators to distinguish whether mGGNs with pathology as IAC is accompanied by lymph node metastasis, and to construct a prediction model for lymph node metastasis. METHODS: From January 2014 to October 2019, the patients with resected IAC appearing as mGGNs in computed tomography (CT) scan were reviewed. All the lesions were divided into two groups (with lymph node metastasis or not) according to their lymph node status. Lasso regression model analysis by applying R software was used to evaluate the relationship between clinical and radiological parameters and lymph node metastasis of mGGNs. RESULTS: A total of 883 mGGNs patients were enroled in this study, among which, 12 (1.36%) showed lymph node metastasis. Lasso regression model analysis of clinical imaging information in mGGNs with lymph node metastasis showed that previous history of malignancy, mean density, mean density of solid components, burr sign and percentage of solid components were informative. Prediction model for lymph node metastasis in mGGNs was developed based on the results of Lasso regression model with area under curve=0.899. CONCLUSIONS: Clinical information combined with CT imaging information can predict lymph node metastasis in mGGNs.

Artificial-intelligence-based computed tomography histogram analysis predicting tumor invasiveness of lung adenocarcinomas manifesting as radiological part-solid nodules.

Background: Tumor invasiveness plays a key role in determining surgical strategy and patient prognosis in clinical practice. The study aimed to explore artificial-intelligence-based computed tomography (CT) histogram indicators significantly related to the invasion status of lung adenocarcinoma appearing as part-solid nodules (PSNs), and to construct radiomics models for prediction of tumor invasiveness. Methods: We identified surgically resected lung adenocarcinomas manifesting as PSNs in Peking University People's Hospital from January 2014 to October 2019. Tumors were categorized as adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA), and invasive adenocarcinoma (IAC) by comprehensive pathological assessment. The whole cohort was randomly assigned into a training (70%, n=832) and a validation cohort (30%, n=356) to establish and validate the prediction model. An artificial-intelligence-based algorithm (InferRead CT Lung) was applied to extract CT histogram parameters for each pulmonary nodule. For feature selection, multivariate regression models were built to identify factors associated with tumor invasiveness. Logistic regression classifier was used for radiomics model building. The predictive performance of the model was then evaluated by ROC and calibration curves. Results: In total, 299 AIS/MIAs and 889 IACs were included. In the training cohort, multivariate logistic regression analysis demonstrated that age [odds ratio (OR), 1.020; 95% CI, 1.004-1.037; p=0.017], smoking history (OR, 1.846; 95% CI, 1.058-3.221; p=0.031), solid mean density (OR, 1.014; 95% CI, 1.004-1.024; p=0.008], solid volume (OR, 5.858; 95% CI, 1.259-27.247; p = 0.037), pleural retraction sign (OR, 3.179; 95% CI, 1.057-9.559; p = 0.039), variance (OR, 0.570; 95% CI, 0.399-0.813; p=0.002), and entropy (OR, 4.606; 95% CI, 2.750-7.717; p<0.001) were independent predictors for IAC. The areas under the curve (AUCs) in the training and validation cohorts indicated a better discriminative ability of the histogram model (AUC=0.892) compared with the clinical model (AUC=0.852) and integrated model (AUC=0.886). Conclusion: We developed an AI-based histogram model, which could reliably predict tumor invasiveness in lung adenocarcinoma manifesting as PSNs. This finding would provide promising value in guiding the precision management of PSNs in the daily practice.

Long-term follow-up of persistent pulmonary subsolid nodules: Natural course of pure, heterogeneous, and real part-solid ground-glass nodules.

BACKGROUND: Previous studies have suggested the applicability of three classifications of subsolid nodules (SSNs). However, few studies have unraveled the natural history of the three types of SSNs. METHODS: A retrospective study from two medical centers between November 2007 and November 2017 was conducted to explore the long-term follow-up results of three different types of SSNs, which were divided into pure ground-glass nodules (pGGNs), heterogeneous ground-glass nodules (hGGNs), and real part-solid nodules (rPSNs). RESULTS: A total of 306 consecutive patients, including 361 SSNs with long-term follow-up, were reviewed. The median growth times of pGGNs, hGGNs, and rPSNs were 7.7, 6.0, and 2.0 years, respectively. For pGGNs, the median period of development into rPSNs was 4.6 years, while that of hGGNs was 1.8 years, and the time from pGGNs to hGGNs was 3.1 years (p < 0.05). In SSNs with an initial lung window consolidation tumor ratio (LW-CTR) >0.5 and mediastinum window (MW)-CTR >0.2, all cases with growth were identified within 5 years. Meanwhile, in SSNs whose LW-CTR and MW-CTR were 0, it took over 5 years to detect nodular growth. Pathologically, 90.6% of initial SSNs with LW-CTR >0 were invasive carcinomas (invasive adenocarcinoma and micro-invasive adenocarcinoma). Among patients with rPSNs in the initial state, 100.0% of the final pathological results were invasive carcinoma. Cox regression showed that age (p = 0.038), initial maximal diameter (p < 0.001), and LW-CTR (p = 0.002) were independent risk factors for SSN growth. CONCLUSIONS: pGGNs, hGGNs, and rPSNs have significantly different natural histories. Age, initial nodule diameter, and LW-CTR are important risk factors for SSN growth.

Lung adenocarcinoma manifesting as subsolid nodule potentially represents tumour in the equilibrium phase of immunoediting.

Lung adenocarcinomas manifesting as subsolid nodules (SSN-LUADs) possess distinct dormant behaviour. This study was designed to compare the immune landscapes of normal lungs (nLungs), SSN-LUADs and LUADs manifesting as solid nodules (SN-LUADs) so as to better understand the status of anti-tumour immunity in SSN-LUADs. Mass cytometry by time-of-flight analysis was performed on 299, 570 single cells from nLung, SSN-LUAD and SN-LUAD tissues. The immune cells were identified by phenotype, and the percentages of different immune cell subclusters were compared between SSN-LUADs, SN-LUADs and nLungs. Elevated percentage of CD8+ T cells were identified in SSN-LUADs compared with in nLungs and SN-LUADs. Elevated CD56bright NK cells and decreased CD56dim NK cells were identified in both SSN-LUADs and SN-LUADs compared with in nLungs. The immune landscape of SSN-LUAD fits the theory of equilibrium phase of immunoediting, thus functional adaptive anti-tumour immunity but impaired innate anti-tumour immunity potentially contributes to the maintaining of its dormant behaviour.

AI-based chest CT semantic segmentation algorithm enables semi-automated lung cancer surgery planning by recognizing anatomical variants of pulmonary vessels.

Background: The recognition of anatomical variants is essential in preoperative planning for lung cancer surgery. Although three-dimensional (3-D) reconstruction provided an intuitive demonstration of the anatomical structure, the recognition process remains fully manual. To render a semiautomated approach for surgery planning, we developed an artificial intelligence (AI)-based chest CT semantic segmentation algorithm that recognizes pulmonary vessels on lobular or segmental levels. Hereby, we present a retrospective validation of the algorithm comparing surgeons' performance. Methods: The semantic segmentation algorithm to be validated was trained on non-contrast CT scans from a single center. A retrospective pilot study was performed. An independent validation dataset was constituted by an arbitrary selection from patients who underwent lobectomy or segmentectomy in three institutions during Apr. 2020 to Jun. 2021. The golden standard of anatomical variants of each enrolled case was obtained via expert surgeons' judgments based on chest CT, 3-D reconstruction, and surgical observation. The performance of the algorithm is compared against the performance of two junior thoracic surgery attendings based on chest CT. Results: A total of 27 cases were included in this study. The overall case-wise accuracy of the AI model was 82.8% in pulmonary vessels compared to 78.8% and 77.0% for the two surgeons, respectively. Segmental artery accuracy was 79.7%, 73.6%, and 72.7%; lobular vein accuracy was 96.3%, 96.3%, and 92.6% by the AI model and two surgeons, respectively. No statistical significance was found. In subgroup analysis, the anatomic structure-wise analysis of the AI algorithm showed a significant difference in accuracies between different lobes (p = 0.012). Higher AI accuracy in the right-upper lobe (RUL) and left-lower lobe (LLL) arteries was shown. A trend of better performance in non-contrast CT was also detected. Most recognition errors by the algorithm were the misclassification of LA1+2 and LA3. Radiological parameters did not exhibit a significant impact on the performance of both AI and surgeons. Conclusion: The semantic segmentation algorithm achieves the recognition of the segmental pulmonary artery and the lobular pulmonary vein. The performance of the model approximates that of junior thoracic surgery attendings. Our work provides a novel semiautomated surgery planning approach that is potentially beneficial to lung cancer patients.

Stepwise evolutionary genomics of early-stage lung adenocarcinoma manifesting as pure, heterogeneous and part-solid ground-glass nodules.

BACKGROUND: This study was designed to unravel the genomic landscape and evolution of early-stage subsolid lung adenocarcinomas (SSN-LUADs) manifesting as pure ground-glass nodules (pGGNs), heterogeneous ground-glass nodules (HGGNs) and part-solid nodules (PSNs). METHODS: Samples subjected to either broad-panel next-generation sequencing (NGS) or whole-exome sequencing (WES) were included. Clinicopathologic and genomic features were compared among pGGN, HGGN and PSN, while tumour evolutionary trajectories and mutational signatures were evaluated in the entire cohort. RESULTS: In total, 247 SSN-LUAD samples subjected to broad-panel NGS and 125 to WES were identified. Compared with PSNs, HGGNs had significantly lower tumour mutation count (P < 0.001), genomic alteration count (P < 0.001), and intra-tumour heterogeneity (P = 0.005). Statistically significant upward trends were observed in alterations involving driver mutations and oncogenic pathways from pGGNs to HGGNs to PSNs. EGFR mutation was proved to be a key early event in the progression of SSN-LUADs, with subsequently two evolutionary trajectories involving either RBM10 or TP53 mutation in the cancer-evolution models. CONCLUSIONS: This study provided evidence for unravelling the previously unknown genomic underpinnings associated with SSN-LUAD evolution from pGGN to HGGN to PSN, proving that HGGN was an intermediate SSN form between pGGN and PSN genetically.

Total nodule number as an independent prognostic factor in resected stage III non-small cell lung cancer: a deep learning-powered study.

Background: Almost every patient with lung cancer has multiple pulmonary nodules; however, the significance of nodule multiplicity in locally advanced non-small cell lung cancer (NSCLC) remains unclear. Methods: We identified patients who had undergone surgical resection for stage I-III NSCLC at the Peking University People's Hospital from 2005 to 2018 for whom preoperative chest computed tomography (CT) scans were available. Deep learning-based artificial intelligence (AI) algorithms using convolutional neural networks (CNN) were applied to detect and classify pulmonary nodules (PNs). Maximally selected log-rank statistics were used to determine the optimal cutoff value of the total nodule number (TNN) for predicting survival. Results: A total of 33,410 PNs were detected by AI among the 2,126 participants. The median TNN detected per person was 12 [interquartile range (IQR) 7-20]. It was revealed that AI-detected TNN (analyzed as a continuous variable) was an independent prognostic factor for both recurrence-free survival (RFS) [hazard ratio (HR) 1.012, 95% confidence interval (CI): 1.002 to 1.022, P=0.021] and overall survival (OS) (HR 1.013, 95% CI: 1.002 to 1.025, P=0.021) in multivariate analyses of the stage III cohort. In contrast, AI-detected TNN was not significantly associated with survival in the stage I and II cohorts. In a survival tree analysis, rather than using traditional IIIA and IIIB classifications, the model grouped cases according to AI-detected TNN (lower vs. higher: log-rank P<0.001), which led to a more effective determination of survival rates in the stage III cohort. Conclusions: The AI-detected TNN is significantly associated with survival rates in patients with surgically resected stage III NSCLC. A lower TNN detected on preoperative CT scans indicates a better prognosis for patients who have undergone complete surgical resection.

Disparate genomic characteristics of patients with early-stage lung adenocarcinoma manifesting as radiological subsolid or solid lesions.

INTRODUCTION: Early-stage lung adenocarcinoma (LUAD) manifesting as subsolid nodules (SSNs) exhibit more favorable prognosis than solid nodules (SNs). However, the genomic underpinnings behind their indolent tumor behavior remain largely unexplained. METHODS: We identified patients with stage I invasive LUAD who underwent complete surgical resection and broad-panel next-generation sequencing (NGS). Comparative genomic profiling was then performed by radiological subtype (SSNs vs. SNs) regarding the general genomic features, driver genes, oncogenic pathways, therapeutic actionability, and evolutionary trajectory. RESULTS: In total, 177 SSN-LUADs and 133 SN-LUADs were included. Compared with SNs, SSN-LUADs possessed lower somatic mutation count (P < 0.001), genomic alteration count (P = 0.002), and intra-tumor heterogeneity (P = 0.006). In terms of driver genes, SSNs harbored more EGFR mutation (77% vs. 62%), but had lower frequencies of genes such as TP53, ARID1A, PIK3CA, CDKN2A, and BRAF (FDR q < 0.1). Besides, RBM10 mutation was independently associated with SSN-LUADs in multivariate analysis (P = 0.033). Three oncogenic pathways (p53, cell cycle, PI3K) were altered with statistical significance in SNs, while only RNA splicing/processing pathway was significantly altered in SSNs (FDR q < 0.1). Also, SSNs had significantly lower number of pathway alterations (P < 0.001). Finally, SSNs and SNs showed distinct evolutionary trajectories regarding somatic mutations during early-stage LUAD progression. CONCLUSIONS: This study performed the first direct comparative genomic profiling in pathologic stage I invasive LUAD by radiological subtype, highlighting a less complex genomic architecture of SSNs, which might be the molecular interpretation of their indolent tumor behavior.

A fully automated noncontrast CT 3-D reconstruction algorithm enabled accurate anatomical demonstration for lung segmentectomy.

BACKGROUND: Three-dimensional reconstruction of chest computerized tomography (CT) excels in intuitively demonstrating anatomical patterns for pulmonary segmentectomy. However, current methods are labor-intensive and rely on contrast CT. We hereby present a novel fully automated reconstruction algorithm based on noncontrast CT and assess its performance both independently and in combination with surgeons. METHODS: A retrospective pilot study was performed. Patients between May 2020 to August 2020 who underwent segmentectomy in our single institution were enrolled. Noncontrast CTs were used for reconstruction. In the first part of the study, the accuracy of the demonstration of anatomical variants by either automated or manual reconstruction algorithm were compared to surgical observation, respectively. In the second part of the study, we tested the accuracy of the identification of anatomical variants by four independent attendees who reviewed 3-D reconstruction in combination with CT scans. RESULTS: A total of 20 cases were enrolled in this study. All segments were represented in this study with two left S1-3, two left S4 + 5, one left S6, five left basal segmentectomies, one right S1, three right S2, 1 right S2b + 3a, one right S3, two right S6 and two right basal segmentectomies. The median time consumption for the automated reconstruction was 280 (205-324) s. Accurate vessel and bronchial detection were achieved in 85% by the AI approach and 80% by Mimics, p = 1.00. The accuracy of vessel classification was 80 and 95% by AI and manual approaches, respectively, p = 0.34. In real-world application, the accuracy of the identification of anatomical variant by thoracic surgeons was 85% by AI+CT, and the median time consumption was 2 (1-3) min. CONCLUSIONS: The AI reconstruction algorithm overcame defects of traditional methods and is valuable in surgical planning for segmentectomy. With the AI reconstruction, surgeons may achieve high identification accuracy of anatomical patterns in a short time frame.

Multiomics Analysis Reveals Distinct Immunogenomic Features of Lung Cancer with Ground-Glass Opacity.

Rationale: Ground-glass opacity (GGO)-associated lung cancers are common and radiologically distinct clinical entities known to have an indolent clinical course and superior survival, implying a unique underlying biology. However, the molecular and immune characteristics of GGO-associated lung nodules have not been systemically studied. Objectives: To provide mechanistic insights for the treatment of these radiologically distinct clinical entities. Methods: We initiated a prospective cohort study to collect and characterize pulmonary nodules with GGO components (nonsolid and part-solid nodules) or without GGO components, as precisely quantified by using three-dimensional image reconstruction to delineate the molecular and immune features associated with GGO. Multiomics assessment conducted by using targeted gene panel sequencing, RNA sequencing, TCR (T-cell receptor) sequencing, and circulating tumor DNA detection was performed. Measurements and Main Results: GGO-associated lung cancers exhibited a lower tumor mutation burden than solid nodules. Transcriptomic analysis revealed a less active immune environment in GGO components and immune pathways, decreased expression of immune activation markers, and less infiltration of most immune-cell subsets, which was confirmed by using multiplex immunofluorescence. Furthermore, T-cell repertoire sequencing revealed lower T-cell expansion in GGO-associated lung cancers. HLA loss of heterozygosity was significantly less common in lung adenocarcinomas with GGO components than in those without. Circulating tumor DNA analysis suggested that the release of tumor DNA to the peripheral blood was correlated with the tumor size of non-GGO components. Conclusions: Compared with lung cancers presenting with solid lung nodules, GGO-associated lung cancers are characterized by a less active metabolism and a less active immune microenvironment, which may be the mechanisms underlying their indolent clinical course. Clinical trial registered with www.clinicaltrials.gov (NCT03320044).

Development and Validation of Machine Learning-based Model for the Prediction of Malignancy in Multiple Pulmonary Nodules: Analysis from Multicentric Cohorts.

PURPOSE: Nodule evaluation is challenging and critical to diagnose multiple pulmonary nodules (MPNs). We aimed to develop and validate a machine learning-based model to estimate the malignant probability of MPNs to guide decision-making. EXPERIMENTAL DESIGN: A boosted ensemble algorithm (XGBoost) was used to predict malignancy using the clinicoradiologic variables of 1,739 nodules from 520 patients with MPNs at a Chinese center. The model (PKU-M model) was trained using 10-fold cross-validation in which hyperparameters were selected and fine-tuned. The model was validated and compared with solitary pulmonary nodule (SPN) models, clinicians, and a computer-aided diagnosis (CADx) system in an independent transnational cohort and a prospective multicentric cohort. RESULTS: The PKU-M model showed excellent discrimination [area under the curve; AUC (95% confidence interval (95% CI)), 0.909 (0.854-0.946)] and calibration (Brier score, 0.122) in the development cohort. External validation (583 nodules) revealed that the AUC of the PKU-M model was 0.890 (0.859-0.916), higher than those of the Brock model [0.806 (0.771-0.838)], PKU model [0.780 (0.743-0.817)], Mayo model [0.739 (0.697-0.776)], and VA model [0.682 (0.640-0.722)]. Prospective comparison (200 nodules) showed that the AUC of the PKU-M model [0.871 (0.815-0.915)] was higher than that of surgeons [0.790 (0.711-0.852), 0.741 (0.662-0.804), and 0.727 (0.650-0.788)], radiologist [0.748 (0.671-0.814)], and the CADx system [0.757 (0.682-0.818)]. Furthermore, the model outperformed the clinicians with an increase of 14.3% in sensitivity and 7.8% in specificity. CONCLUSIONS: After its development using machine learning algorithms, validation using transnational multicentric cohorts, and prospective comparison with clinicians and the CADx system, this novel prediction model for MPNs presented solid performance as a convenient reference to help decision-making.

Genomic characterisation of pulmonary subsolid nodules: mutational landscape and radiological features.

BACKGROUND: Lung adenocarcinomas (LUADs) that display radiologically as subsolid nodules (SSNs) exhibit more indolent biological behaviour than solid LUADs. SSNs, commonly encompassing pre-invasive and invasive yet early-stage adenocarcinomas, can be categorised as pure ground-glass nodules and part-solid nodules. The genomic characteristics of SSNs remain poorly understood. METHODS: We subjected 154 SSN samples from 120 treatment-naïve Chinese patients to whole-exome sequencing. Clinical parameters and radiological features of these SSNs were collected. The genomic landscape of SSNs and differences from that of advanced-stage LUADs were defined. In addition, we investigated the intratumour heterogeneity and clonal relationship of multifocal SSNs and conducted radiogenomic analysis to link imaging and molecular characteristics of SSNs. Fisher's exact and Wilcoxon rank sum tests were used in the statistical analysis. RESULTS: The median somatic mutation rate across the SSN cohort was 1.12 mutations per Mb. Mutations in EGFR were the most prominent and significant variation, followed by those in RBM10, TP53, STK11 and KRAS. The differences between SSNs and advanced-stage LUADs at a genomic level were unravelled. Branched evolution and remarkable genomic heterogeneity were demonstrated in SSNs. Although multicentric origin was predominant, we also detected early metastatic events among multifocal SSNs. Using radiogenomic analysis, we found that higher ratios of solid components in SSNs were accompanied by significantly higher mutation frequencies in EGFR, TP53, RBM10 and ARID1B, suggesting that these genes play roles in the progression of LUADs. CONCLUSIONS: Our study provides the first comprehensive description of the mutational landscape and radiogenomic mapping of SSNs.