Factors associated with nodal metastasis in 2-centimeter or less non-small cell lung cancer

Importance of Lymph Node Evaluation in ≤2-cm Pure-Solid Non-Small Cell Lung Cancer

BACKGROUND

The prevalence of lymph node (LN) metastasis in small-sized lung cancer varies depending on the tumor size and proportion of ground-glass opacity. We investigated occult LN metastasis and prognosis in patients with small-sized non-small cell lung cancer (NSCLC), mainly focusing on the pure-solid tumor.

METHODS

We retrospectively reviewed patients with ≤2-cm clinical N0 NSCLC who underwent lung resection with curative intent from 2003 to 2017. Among them we analyzed patients who also underwent adequate complete systematic LN dissection. Pathologic results and disease-free survival of the radiologically mixed ground-glass nodule (mGGN) and pure-solid nodule (PSN) groups were analyzed.

RESULTS

Of 1329 patients analyzed, 591 had mGGNs and PSNs. As tumor size increased, patients in the mGGN group showed no difference in LN metastasis: ≤1 cm, 2.27%; 1.0 to 1.5 cm, 2.19%; and 1.5 to 2.0 cm, 2.18% (P = .999). However the PSN group showed a significant difference in LN metastasis as the tumor size increased: ≤1 cm, 2.67%; 1.0 to 1.5 cm, 12.46%; and 1.5 to 2.0 cm, 21.31% (P < .001). In the multivariate analysis tumor size was a significant predictor of nodal metastasis in the PSN group but not in the mGGN group. In terms of 5-year disease-free survival, the mGGN group showed a better prognosis than the PSN group (94.4% vs 71.2%, P < .001).

CONCLUSIONS

We need to conduct a thorough LN dissection during surgery for small-sized NSCLC, especially for pure-solid tumors ≥ 1 cm.

The role of adenocarcinoma subtypes and immunohistochemistry in predicting lymph node metastasis in early invasive lung adenocarcinoma

BACKGROUND

Identifying lymph node metastasis areas during surgery for early invasive lung adenocarcinoma remains challenging. The aim of this study was to develop a nomogram mathematical model before the end of surgery for predicting lymph node metastasis in patients with early invasive lung adenocarcinoma.

METHODS

In this study, we included patients with invasive lung adenocarcinoma measuring ≤ 2 cm who underwent pulmonary resection with definite pathology at Qilu Hospital of Shandong University from January 2020 to January 2022. Preoperative biomarker results, clinical features, and computed tomography characteristics were collected. The enrolled patients were randomized into a training cohort and a validation cohort in a 7:3 ratio. The training cohort was used to construct the predictive model, while the validation cohort was used to test the model independently. Univariate and multivariate logistic regression analyses were performed to identify independent risk factors. The prediction model and nomogram were established based on the independent risk factors. Recipient operating characteristic (ROC) curves were used to assess the discrimination ability of the model. Calibration capability was assessed using the Hosmer-Lemeshow test and calibration curves. The clinical utility of the nomogram was assessed using decision curve analysis (DCA).

RESULTS

The overall incidence of lymph node metastasis was 13.23% (61/461). Six indicators were finally determined to be independently associated with lymph node metastasis. These six indicators were: age (P < 0.001), serum amyloid (SA) (P = 0.008); carcinoma antigen 125 (CA125) (P = 0. 042); mucus composition (P = 0.003); novel aspartic proteinase of the pepsin family A (Napsin A) (P = 0.007); and cytokeratin 5/6 (CK5/6) (P = 0.042). The area under the ROC curve (AUC) was 0.843 (95% CI: 0.779-0.908) in the training cohort and 0.838 (95% CI: 0.748-0.927) in the validation cohort. the P-value of the Hosmer-Lemeshow test was 0.0613 in the training cohort and 0.8628 in the validation cohort. the bias of the training cohort corrected C-index was 0.8444 and the bias-corrected C-index for the validation cohort was 0.8375. demonstrating that the prediction model has good discriminative power and good calibration.

CONCLUSIONS

The column line graphs created showed excellent discrimination and calibration to predict lymph node status in patients with ≤ 2 cm invasive lung adenocarcinoma. In addition, the predictive model has predictive potential before the end of surgery and can inform clinical decision making.

Development of the semi-dry dot-blot method for intraoperative detecting micropapillary component in lung adenocarcinoma based on proteomics analysis

BACKGROUND

Micropapillary (MIP) component was a major concern in determining surgical strategy in lung adenocarcinoma (LUAD). We sought to develop a novel method for detecting MIP component during surgery.

METHODS

Differentially expressed proteins between MIP-positive and MIP-negative LUAD were identified through proteomics analysis. The semi-dry dot-blot (SDB) method which visualises the targeted protein was developed to detect MIP component.

RESULTS

Cellular retinoic acid-binding protein 2 (CRABP2) was significantly upregulated in MIP-positive LUAD (P < 0.001), and the high CRABP2 expression zone showed spatial consistency with MIP component. CRABP2 expression was also associated with decreased recurrence-free survival (P < 0.001). In the prospective cohort, the accuracy and sensitivity of detecting MIP component using SDB method by visualising CRABP2 were 82.2% and 72.7%, which were comparable to these of pathologist. Pathologist with the aid of SDB method would improve greatly in diagnostic accuracy (86.4%) and sensitivity (78.2%). In patients with minor MIP component (≤5%), the sensitivity of SDB method (63.6%) was significantly higher than pathologist (45.4%).

CONCLUSIONS

Intraoperative examination of CRABP2 using SDB method to detect MIP component reached comparable performance to pathologist, and SDB method had notable superiority than pathologist in detecting minor MIP component.

Efficacy of radiomics model based on the concept of gross tumor volume and clinical target volume in predicting occult lymph node metastasis in non-small cell lung cancer

Objective

This study aimed to establish a predictive model for occult lymph node metastasis (LNM) in patients with clinical stage I-A non-small cell lung cancer (NSCLC) based on contrast-enhanced CT.

Methods

A total of 598 patients with stage I-IIA NSCLC from different hospitals were randomized into the training and validation group. The "Radiomics" tool kit of AccuContour software was employed to extract the radiomics features of GTV and CTV from chest-enhanced CT arterial phase pictures. Then, the least absolute shrinkage and selection operator (LASSO) regression analysis was applied to reduce the number of variables and develop GTV, CTV, and GTV+CTV models for predicting occult lymph node metastasis (LNM).

Results

Eight optimal radiomics features related to occult LNM were finally identified. The receiver operating characteristic (ROC) curves of the three models showed good predictive effects. The area under the curve (AUC) value of GTV, CTV, and GTV+CTV model in the training group was 0.845, 0.843, and 0.869, respectively. Similarly, the corresponding AUC values in the validation group were 0.821, 0.812, and 0.906. The combined GTV+CTV model exhibited a better predictive performance in the training and validation group by the Delong test (p<0.05). Moreover, the decision curve showed that the combined GTV+CTV predictive model was superior to the GTV or CTV model.

Conclusion

The radiomics prediction models based on GTV and CTV can predict occult LNM in patients with clinical stage I-IIA NSCLC preoperatively, and the combined GTV+CTV model is the optimal strategy for clinical application.

Preoperative CT-Based Radiomics Combined With Nodule Type to Predict the Micropapillary Pattern in Lung Adenocarcinoma of Size 2 cm or Less: A Multicenter Study

Purpose

To construct an optimal radiomics model for preoperative prediction micropapillary pattern (MPP) in adenocarcinoma (ADC) of size ≤ 2 cm, nodule type was used for stratification to construct two radiomics models based on high-resolution computed tomography (HRCT) images.

Materials and Methods

We retrospectively analyzed patients with pathologically confirmed ADC of size ≤ 2 cm who presented to three hospitals. Patients presenting to the hospital with the greater number of patients were included in the training set (n = 2386) and those presenting to the other two hospitals were included in the external validation set (n = 119). HRCT images were used for delineation of region of interest of tumor and extraction of radiomics features; dimensionality reduction was performed for the features. Nodule type was used to stratify the data and the random forest method was used to construct two models for preoperative prediction MPP in ADC of size ≤ 2 cm. Model 1 included all nodule types and model 2 included only solid nodules. The receiver operating characteristic curve was used to assess the prediction performance of the two models and independent validation was used to assess its generalizability.

Results

Both models predicted ADC with MPP preoperatively. The area under the curve (AUC) of prediction performance of models 1 and 2 were 0.91 and 0.78, respectively. The prediction performance of model 2 was lower than that of model 1. The AUCs in the external validation set were 0.81 and 0.72, respectively. The DeLong test showed statistically significant differences between the training and validation sets in model 1 (p = 0.0296) with weak generalizability. There was no statistically significant difference between the training and validation sets in model 2 (p = 0.2865) with some generalizability.

Conclusion

Nodule type is an important factor that affects the performance of radiomics predictor model for MPP with ADC of size ≤ 2 cm. The radiomics prediction model constructed based on solid nodules alone, can be used to evaluate MPP and may contribute to proper surgical planning in patients with ADC of size ≤ 2 cm.

Which will carry more weight when CTR > 0.5, solid component size, CTR, tumor size or SUVmax?

BACKGROUND

This study was conducted to explore the clinical significance of the maximum standard uptake value (SUVmax) in the clinical stage IA lung adenocarcinoma with tumor size ≤ 2 cm and consolidation to tumor ratio (CTR) > 0.5.

METHODS

We retrospectively reviewed non-small cell lung cancer patients who underwent surgeries between January 2014 and March 2017. Clinical stage IA lung adenocarcinoma patients with tumor of size ≤ 2 cm and CTR > 0.5 were enrolled. The patients were divided into two groups: part-solid and pure-solid based on whether CTR = 1.0 or not. Nodules with any amount of solid or micropapillary components were regarded as the high-risk subtype. Time-dependent ROC curve was used to determine the best cut-off value. Finally, we analyzed the relationship between SUVmax, high-risk subtypes, node metastasis and 5-year relapse-free survival and overall survival.

RESULTS

Totally, 270 patients were included. The distribution of pathological subtypes (p < 0.001), SUVmax (p < 0.001), and pathological N stage (p < 0.001) were different between the two groups. Multivariable analysis indicated that SUVmax could predict high-risk subtypes in cases of part-solid nodules (p < 0.001) and both high-risk subtypes (p = 0.022) and node metastasis (p < 0.001) in cases of pure-solid ones. SUVmax ≥ 2.6 and SUVmax ≥ 5.1 were strongly associated with 5-year relapse-free survival (p < 0.001) and 5-year overall survival (p < 0.001) among all the patients, respectively.

CONCLUSION

Part-solid nodules with 0.5 < CTR < 1 and pure-solid nodules in lung adenocarcinoma show different clinicopathological characteristics, especially in SUVmax. SUVmax is significantly associated with high-risk subtypes, node metastasis, 5-year relapse-free survival and overall survival.

Radiomics-guided deep neural networks stratify lung adenocarcinoma prognosis from CT scans

Deep learning (DL) is a breakthrough technology for medical imaging with high sample size requirements and interpretability issues. Using a pretrained DL model through a radiomics-guided approach, we propose a methodology for stratifying the prognosis of lung adenocarcinomas based on pretreatment CT. Our approach allows us to apply DL with smaller sample size requirements and enhanced interpretability. Baseline radiomics and DL models for the prognosis of lung adenocarcinomas were developed and tested using local (n = 617) cohort. The DL models were further tested in an external validation (n = 70) cohort. The local cohort was divided into training and test cohorts. A radiomics risk score (RRS) was developed using Cox-LASSO. Three pretrained DL networks derived from natural images were used to extract the DL features. The features were further guided using radiomics by retaining those DL features whose correlations with the radiomics features were high and Bonferroni-corrected p-values were low. The retained DL features were subject to a Cox-LASSO when constructing DL risk scores (DRS). The risk groups stratified by the RRS and DRS showed a significant difference in training, testing, and validation cohorts. The DL features were interpreted using existing radiomics features, and the texture features explained the DL features well.

Clinicopathological models for predicting lymph node metastasis in patients with early-stage lung adenocarcinoma: the application of machine learning algorithms

Background

Lymph node metastasis (LNM) status can be a critical decisive factor for clinical management of lung cancer. Accurately evaluating the risk of LNM during or after the surgery can be helpful for making clinical decisions. This study aims to incorporate clinicopathological characteristics to develop reliable machine learning (ML)-based models for predicting LNM in patients with early-stage lung adenocarcinoma.

Methods

A total of 709 lung adenocarcinoma patients with tumor size ≤2 cm were enrolled for analysis and modeling by multiple ML algorithms. The receiver operating characteristic (ROC) curve and decision curve were used for evaluating model’s predictive performance and clinical usefulness. Feature selection based on potential models was performed to identify most-contributed predictive factors.

Results

LNM occurred in 11.3% (80/709) of patients with lung adenocarcinoma. Most models reached high areas under the ROC curve (AUCs) >0.9. In the decision curve, all models performed better than the treat-all and treat-none lines. The random forest classifier (RFC) model, with a minimal number of five variables introduced (including carcinoembryonic antigen, solid component, micropapillary component, lymphovascular invasion and pleural invasion), was identified as the optimal model for predicting LNM, because of its excellent performance in both ROC and decision curves.

Conclusions

The cost-efficient application of RFC model could precisely predict LNM during or after the operation of early-stage adenocarcinomas (sensitivity: 87.5%; specificity: 82.2%). Incorporating clinicopathological characteristics, it is feasible to predict LNM intraoperatively or postoperatively by ML algorithms.

[Pathological and Molecular Features of Lung Micropapillary Adenocarcinoma]

肺微乳头腺癌作为高级别肺腺癌，具频发转移、淋巴结浸润、复发率高和总体生存率低的临床特征。该亚型肿瘤中存在特征致癌因子通路的激活和肿瘤免疫微环境的建立。本文拟对近年来微乳头腺癌的病理学表现及分子学特征研究进展作一综述，旨在加深对微乳头型病变的认识，进而为制定特异性治疗策略奠定基础。

Predicting occult lymph node metastasis by nomogram in patients with lung adenocarcinoma ≤2 cm

Background: Previous researches had not proposed any prediction models for occult lymph node metastasis (OLNM). Considering the occurrence of OLNM and the importance of OLNM management, we aimed to develop a nomogram to predict OLNM of patients with lung adenocarcinoma ≤2 cm. Methods: Characteristics of patients with lung adenocarcinoma of ≤2 cm diameter at the Peking Union Medical College Hospital were retrospectively reviewed. Univariate and multivariate logistic regressions were performed. A nomogram model was developed. The concordance index (C-index) and calibration and decision curves were used to evaluate the predictive ability. Results: A total of 473 patients were enrolled, with an OLNM incidence of 7.4%. Four factors were selected as risk factors. The model had a C-index of 0.932. Calibration and decision curves were determined. Conclusion: Patients with pure ground-glass opacity (pGGO) or noninvasive adenocarcinoma have significantly lower risk of OLNM. SUV_max, CEA, micropapillary and solid component were identified as independent risk factors. The nomogram model was effective in predicting OLNM preoperatively.

Micropapillary pattern of stage IIIA-N2 lung adenocarcinoma is a prognostic factor after adjuvant chemoradiotherapy

Aim: This study aims to investigate the significance of a micropapillary pattern in stage IIIA-N₂ lung adenocarcinoma after adjuvant chemoradiotherapy. Patients & methods: A total of 257 patients with stage IIIA-N₂ lung adenocarcinoma were enrolled in this study. Patients were classified into three groups based on the proportion of micropapillary components: micropapillary negative, micropapillary minor component and micropapillary predominant component. Results: The micropapillary predominant group had the shortest median disease-free survival and overall survival times compared with the micropapillary minor component and micropapillary negative groups (median overall survival time: 54 months vs 64 months vs not reached; p = 0.004). Furthermore, the micropapillary pattern was an independent prognostic factor for disease-free survival and overall survival (p < 0.05). Conclusion: The micropapillary pattern of IIIA-N₂ lung adenocarcinoma is related to worse prognosis.

Preoperative Prediction of Lymph Node Metastasis in Patients With Early-T-Stage Non-small Cell Lung Cancer by Machine Learning Algorithms

Background: Lymph node metastasis (LNM) is difficult to precisely predict before surgery in patients with early-T-stage non-small cell lung cancer (NSCLC). This study aimed to develop machine learning (ML)-based predictive models for LNM.

Methods: Clinical characteristics and imaging features were retrospectively collected from 1,102 NSCLC ≤ 2 cm patients. A total of 23 variables were included to develop predictive models for LNM by multiple ML algorithms. The models were evaluated by the receiver operating characteristic (ROC) curve for predictive performance and decision curve analysis (DCA) for clinical values. A feature selection approach was used to identify optimal predictive factors.

Results: The areas under the ROC curve (AUCs) of the 8 models ranged from 0.784 to 0.899. Some ML-based models performed better than models using conventional statistical methods in both ROC curves and decision curves. The random forest classifier (RFC) model with 9 variables introduced was identified as the best predictive model. The feature selection indicated the top five predictors were tumor size, imaging density, carcinoembryonic antigen (CEA), maximal standardized uptake value (SUV_max), and age.

Conclusions: By incorporating clinical characteristics and radiographical features, it is feasible to develop ML-based models for the preoperative prediction of LNM in early-T-stage NSCLC, and the RFC model performed best.