Predicting pathological lymph node status in clinical stage IA peripheral lung adenocarcinoma

Dual-Region Computed Tomography Radiomics-Based Machine Learning Predicts Subcarinal Lymph Node Metastasis in Patients with Non-small Cell Lung Cancer

BACKGROUND

Noninvasively and accurately predicting subcarinal lymph node metastasis (SLNM) for patients with non-small cell lung cancer (NSCLC) remains challenging. This study was designed to develop and validate a tumor and subcarinal lymph nodes (tumor-SLNs) dual-region computed tomography (CT) radiomics model for predicting SLNM in NSCLC.

METHODS

This retrospective study included NSCLC patients who underwent lung resection and SLNs dissection between January 2017 and December 2020. The radiomic features of the tumor and SLNs were extracted from preoperative CT, respectively. Ninety machine learning (ML) models were developed based on tumor region, SLNs region, and tumor-SLNs dual-region. The model performance was assessed by the area under the curve (AUC) and validated internally by fivefold cross-validation.

RESULTS

In total, 202 patients were included in this study. ML models based on dual-region radiomics showed good performance for SLNM prediction, with a median AUC of 0.794 (range, 0.686-0.880), which was superior to those of models based on tumor region (median AUC, 0.746; range, 0.630-0.811) and SLNs region (median AUC, 0.700; range, 0.610-0.842). The ML model, which is developed by using the naive Bayes algorithm and dual-region features, had the highest AUC of 0.880 (range of cross-validation, 0.825-0.937) among all ML models. The optimal logistic regression model was inferior to the optimal ML model for predicting SLNM, with an AUC of 0.727.

CONCLUSIONS

The CT radiomics showed the potential for accurately predicting SLNM in NSCLC patients. The ML model with dual-region radiomic features has better performance than the logistic regression or single-region models.

An accurate prediction of negative lymph node metastasis with consideration of glucose metabolism in early-stage non-small cell lung cancer

OBJECTIVE

We aimed to identify risk factors in lymph node metastasis in early-stage non-small cell lung cancer (NSCLC) and predict lymph node metastasis.

METHODS

A total of 416 patients with clinical stage IA2-3 NSCLC who underwent lobectomy and lymph node dissection between July 2016 and December 2020 at National Cancer Center Hospital East were included. Multivariable logistic regression was performed to develop a model for predicting lymph node metastasis. Leave-one-out cross-validation was performed to evaluate the developing prediction model, and sensitivity, specificity, and concordance statistics were calculated to evaluate its diagnostic performance.

RESULTS

The formula for calculating the probability of pathological lymph node metastasis included SUVmax of the primary tumor and serum CEA level. The concordance statistics was 0.7452. When the cutoff value associated with the risk of incorrectly predicting pathological lymph node metastasis was 7.2%, the diagnostic sensitivity and specificity for predicting metastasis were 96.4% and 38.6%, respectively.

CONCLUSIONS

We created a prediction model for lymph node metastasis in NSCLC by combining the SUVmax of the primary tumor and serum CEA levels, which showed a particularly strong association. This model is clinically useful as it successfully predicts negative lymph node metastasis in patients with clinical stage IA2-3 NSCLC.

Risk profiles and a concise prediction model for lymph node metastasis in patients with lung adenocarcinoma

BACKGROUND

Lung cancer is the second most commonly diagnosed cancer and ranks the first in mortality. Pathological lymph node status(pN) of lung cancer affects the treatment strategy after surgery while systematic lymph node dissection(SLND) is always unsatisfied.

METHODS

We reviewed the clinicopathological features of 2,696 patients with LUAD and one single lesion ≤ 5 cm who underwent SLND in addition to lung resection at the Sun Yat-Sen University Cancer Center. The relationship between the pN status and all other clinicopathological features was assessed. All participants were stochastically divided into development and validation cohorts; the former was used to establish a logistic regression model based on selected factors from stepwise backward algorithm to predict pN status. C-statistics, accuracy, sensitivity, and specificity were calculated for both cohorts to test the model performance.

RESULTS

Nerve tract infiltration (NTI), visceral pleural infiltration (PI), lymphovascular infiltration (LVI), right upper lobe (RUL), low differentiated component, tumor size, micropapillary component, lepidic component, and micropapillary predominance were included in the final model. Model performance in the development and validation cohorts was as follows: 0.861 (95% CI: 0.842-0.883) and 0.840 (95% CI: 0.804-0.876) for the C-statistics and 0.803 (95% CI: 0.784-0.821) and 0.785 (95% CI: 0.755-0.814) for accuracy, and 0.754 (95% CI: 0.706-0.798) and 0.686 (95% CI: 0.607-0.757) for sensitivity and 0.814 (95% CI: 0.794-0.833) and 0.811 (95% CI: 0.778-0.841) for specificity, respectively.

CONCLUSION

Our study showed an easy and credible tool with good performance in predicting pN in patients with LUAD with a single tumor ≤ 5.0 cm without SLND and it is valuable to adjust the treatment strategy.

Development and validation of a deep learning signature for predicting lymph node metastasis in lung adenocarcinoma: comparison with radiomics signature and clinical-semantic model

OBJECTIVE

To develop and validate a deep learning (DL) signature for predicting lymph node (LN) metastasis in patients with lung adenocarcinoma.

METHODS

A total of 612 patients with pathologically-confirmed lung adenocarcinoma were retrospectively enrolled and were randomly divided into training cohort (n = 489) and internal validation cohort (n = 123). Besides, 108 patients were enrolled and constituted an independent test cohort (n = 108). Patients' clinical characteristics and CT semantic features were collected. The radiomics features were derived from contrast-enhanced CT images. The clinical-semantic model and radiomics signature were built to predict LN metastasis. Furthermore, Swin Transformer was adopted to develop a DL signature predictive of LN metastasis. Model performance was evaluated by area under the receiver operating characteristic curve (AUC), sensitivity, specificity, calibration curve, and decision curve analysis. The comparisons of AUC were conducted by the DeLong test.

RESULTS

The proposed DL signature yielded an AUC of 0.948-0.961 across all three cohorts, significantly superior to both clinical-semantic model and radiomics signature (all p < 0.05). The calibration curves show that DL signature predicted probabilities fit well the actual observed probabilities of LN metastasis. DL signature gained a higher net benefit than both clinical-semantic model and radiomics signature. The incorporation of radiomics signature or clinical-semantic risk predictors failed to reveal an incremental value over the DL signature.

CONCLUSIONS

The proposed DL signature based on Swin Transformer achieved a promising performance in predicting LN metastasis and could confer important information in noninvasive mediastinal LN staging and individualized therapeutic options.

KEY POINTS

• Accurate prediction for lymph node metastasis is crucial to formulate individualized therapeutic options for patients with lung adenocarcinoma. • The deep learning signature yielded an AUC of 0.948-0.961 across all three cohorts in predicting lymph node metastasis, superior to both radiomics signature and clinical-semantic model. • The incorporation of radiomics signature or clinical-semantic risk predictors into deep learning signature failed to reveal an incremental value over deep learning signature.

Tumour-pleura relationship on CT is a risk factor for occult lymph node metastasis in peripheral clinical stage IA solid adenocarcinoma

OBJECTIVES

To investigate whether the tumour-pleura relationship on computed tomography (CT) is a risk factor for occult lymph node metastasis (OLNM) in peripheral clinical stage IA solid adenocarcinoma.

METHODS

A total of 232 patients were included in the study. The tumour-pleura relationship was divided into four types: type 1, the tumour was unrelated to the pleura; type 2, the tumour was not in contact with the pleura, and one or more linear or striated pleural tags were visible; type 3, the tumour was not in contact with the pleura, and one or more linear or striated pleural tags with soft tissue component at the pleural end were visible; and type 4, the tumour was in contact with the pleura. Univariate and multivariate logistic regression analyses were used to identify the predictive factors, including the tumour-pleura relationship, clinical factors, conventional CT findings, and pathology-reported visceral pleural invasion, for OLNM.

RESULTS

Type 3 and 4 tumour-pleura relationships were more likely to have visceral pleural invasion than type 1 and 2 tumour-pleura relationships (p < 0.001). Univariate and multivariate logistic regression analyses revealed that the type 3 or 4 tumour-pleura relationship (OR: 3.261, p = 0.026), carcinoembryonic antigen level (OR: 3.361, p = 0.006), cytokeratin 19 fragments level (OR: 2.539, p = 0.025), and mediastinal window tumour size (OR: 1.078, p = 0.020) were predictive factors for OLNM.

CONCLUSIONS

The type 3 or 4 tumour-pleura relationship is correlated with a greater risk of OLNM in peripheral clinical stage IA solid adenocarcinoma.

KEY POINTS

• The tumour-pleura relationship on CT is a risk factor for occult lymph node metastasis in peripheral clinical stage IA solid adenocarcinoma. • Other risk factors for OLNM include CEA level, CYFRA level, and mediastinal window tumour size. • Pathology-reported visceral pleural invasion is not a risk factor for OLNM.

Construction and Evaluation of a Preoperative Prediction Model for Lymph Node Metastasis of cIA Lung Adenocarcinoma Using Random Forest

Background

Lymph node metastasis (LNM) is the main route of metastasis in lung adenocarcinoma (LA), and preoperative prediction of LNM in early LA is key for accurate medical treatment. We aimed to establish a preoperative prediction model of LNM of early LA through clinical data mining to reduce unnecessary lymph node dissection, reduce surgical injury, and shorten the operation time.

Methods

We retrospectively collected imaging data and clinical features of 1121 patients with early LA who underwent video-assisted thoracic surgery at the First Hospital of China Medical University from 2004 to 2021. Logistic regression analysis was used to select variables and establish the preoperative diagnosis model using random forest classifier (RFC). The prediction results from the test set were used to evaluate the prediction performance of the model.

Results

Combining the results of logistic analysis and practical clinical application experience, nine clinical features were included. In the random forest classifier model, when the number of nodes was three and the n-tree value is 500, we obtained the best prediction model (accuracy = 0.9769), with a positive prediction rate of 90% and a negative prediction rate of 98.69%.

Conclusion

We established a preoperative prediction model for LNM of early LA using a machine learning random forest method combined with clinical and imaging features. More excellent predictors may be obtained by refining imaging features.

Prognostic influence of epidermal growth factor receptor mutation and radiological ground glass appearance in patients with early-stage lung adenocarcinoma

OBJECTIVES

The ADAURA demonstrated the efficacy of osimertinib as adjuvant therapy in patients with resected stage IB-IIIA adenocarcinoma harboring epidermal growth factor receptor (EGFR) mutations. However, it is controversial whether adjuvant therapy should be applied to all these patients because of their heterogeneities. This study aimed to examine the influence of GGO and EGFR mutations on the prognosis and to identify optimal targets for the development of perioperative therapy.

MATERIAL AND METHODS

Among the patients who underwent complete resection between 2003 and 2014 and had pathological stage IA3-IIA adenocarcinoma, 505 consecutive patients were examined for EGFR mutation status. The prognosis was analyzed among the clinicopathological factors including EGFR status and presence or absence of GGO.

RESULTS

Of the 489 patients, 193 (39.5%) showed EGFR mutations. The recurrence-free survival (RFS) and overall survival (OS) of the EGFR mutant were slightly better than those of the EGFR wild type. There was no difference in RFS and OS between EGFR mutant and wild type in patients with GGO; however, EGFR mutant showed better OS than EGFR wild type in patients without GGO. The presence of GGO was a strong independent prognostic predictor in OS and RFS, but EGFR mutations was not predictors. In patients without GGO, EGFR mutants showed slightly higher recurrence, especially with a hazard ratio of 1.427 in stage IB.

CONCLUSIONS

Adenocarcinoma with GGO show a very good prognosis, so may not require adjuvant therapy. It will be necessary to further develop perioperative therapy in patients with poor prognosis.