A Model Predicting Lymph Node Status for Patients with Clinical Stage T1aN0-2M0 Nonsmall Cell Lung Cancer

Predictability and Utility of Contrast-Enhanced CT on Occult Lymph Node Metastasis for Patients with Clinical Stage IA-IIA Lung Adenocarcinoma: A Double-Center Study

RATIONALE AND OBJECTIVES

With the advantage of minimizing damage and preserving more functional lung tissue, limited surgery is considered depend on the lymph node (LN) involvement situation. However, occult lymph node metastasis (OLM) may be ignored by limited surgery and become a risk factor for local recurrence after surgical resection. The aim of this study was to assess the risk factors for OLM based on computed tomography enhanced image in patients with clinical lung adenocarcinoma (ADC).

MATERIALS AND METHODS

From January 2016 to July 2022, 707 patients with clinical stage IA-IIA ADC underwent lobectomy with systematic LN dissection and were divided into training and validation group based on different institution. Univariate analysis followed by multivariable logistic regression were performed to estimate different risk factors of OLM. A predictive model was established with visual nomogram and external validation, and evaluated in terms of accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC).

RESULTS

Fifty-nine patients were diagnosed with OLM (11.9%), and four independent predictors of LN involvement were identified: larger consolidation diameter (odds ratio [OR], 2.35, 95% confidence interval [CI]: 1.06, 5.22, p = 0.013), bronchovascular bundle thickening (OR, 1.99, 95% CI: 1.00, 3.95, p = 0.049), lobulation (OR, 2.92, 95% CI: 1.22, 6.99, p = 0.016) and obstructive change (OR, 1.69, 95% CI: 1.17, 6.16, p = 0.020). The model showed good calibration (Hosmer-Lemeshow goodness-of-fit, p = 0.816) with an AUC of 0.821 (95% CI: 0.775, 0.853). For the validation group, the AUC was 0.788 (95% CI: 0.732, 0.806).

CONCLUSION

Our predictive model can non-invasively assess the risk of OLM in patients with clinical stage IA-IIA ADC, enable surgeons perform an individualized prediction preoperatively, and assist the clinical decision-making procedure.

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.

DeepCUBIT: Predicting Lymphovascular Invasion or Pathological Lymph Node Involvement of Clinical T1 Stage Non-Small Cell Lung Cancer on Chest CT Scan Using Deep Cubical Nodule Transfer Learning Algorithm

The prediction of lymphovascular invasion (LVI) or pathological nodal involvement of tumor cells is critical for successful treatment in early stage non-small cell lung cancer (NSCLC). We developed and validated a Deep Cubical Nodule Transfer Learning Algorithm (DeepCUBIT) using transfer learning and 3D Convolutional Neural Network (CNN) to predict LVI or pathological nodal involvement on chest CT images. A total of 695 preoperative CT images of resected NSCLC with tumor size of less than or equal to 3 cm from 2008 to 2015 were used to train and validate the DeepCUBIT model using five-fold cross-validation method. We also used tumor size and consolidation to tumor ratio (C/T ratio) to build a support vector machine (SVM) classifier. Two-hundred and fifty-four out of 695 samples (36.5%) had LVI or nodal involvement. An integrated model (3D CNN + Tumor size + C/T ratio) showed sensitivity of 31.8%, specificity of 89.8%, accuracy of 76.4%, and AUC of 0.759 on external validation cohort. Three single SVM models, using 3D CNN (DeepCUBIT), tumor size or C/T ratio, showed AUCs of 0.717, 0.630 and 0.683, respectively on external validation cohort. DeepCUBIT showed the best single model compared to the models using only C/T ratio or tumor size. In addition, the DeepCUBIT model could significantly identify the prognosis of resected NSCLC patients even in stage I. DeepCUBIT using transfer learning and 3D CNN can accurately predict LVI or nodal involvement in cT1 size NSCLC on CT images. Thus, it can provide a more accurate selection of candidates who will benefit from limited surgery without increasing the risk of recurrence.

Evidence for Expanding Invasive Mediastinal Staging for Peripheral T1 Lung Tumors

BACKGROUND

Guidelines recommend invasive mediastinal staging for patients with non-small cell lung cancer and a "central" tumor. However, there is no consensus definition for central location. As such, the decision to perform invasive staging largely remains on an empirical foundation.

RESEARCH QUESTION

Should patients with peripheral T1 lung tumors undergo invasive mediastinal staging?

STUDY DESIGN AND METHODS

All participants with a screen-detected cancer with a solid component between 8 and 30 mm were identified from the National Lung Screening Trial. After translation of CT data, cancer location was identified and the X, Y, Z coordinates were determined as well as distance from the main carina. A multivariable logistic regression model was constructed to evaluate for predictors associated with lymph node metastasis.

RESULTS

Three hundred thirty-two participants were identified, of which 69 had lymph node involvement (20.8%). Of those with lymph node metastasis, 39.1% were N2. There was no difference in rate of lymph node metastasis based on tumor size (OR, 1.03; P = .248). There was also no statistical difference in rate of lymph node metastasis based on location, either by distance from the carina (OR, 0.99; P = .156) or tumor coordinates (X: P = .180; Y: P = .311; Z: P = .292). When adjusted for age, sex, histology, and smoking history, there was no change in the magnitude of the risk, and tests of significance were not altered.

INTERPRETATION

Our data indicate a high rate of N2 metastasis among T1 tumors and no significant relationship between tumor diameter or location. This suggests that patients with small, peripheral lung cancers may benefit from invasive mediastinal staging.

Preoperative assessment of lymph node metastasis in Colon Cancer patients using machine learning: a pilot study

BACKGROUND

Preoperative detection of lymph node (LN) metastasis is critical for planning treatments in colon cancer (CC). The clinical diagnostic criteria based on the size of the LNs are not sensitive to determine metastasis using CT images. In this retrospective study, we investigated the potential value of CT texture features to diagnose LN metastasis using preoperative CT data and patient characteristics by developing quantitative prediction models.

METHODS

A total of 390 CC patients, undergone surgical resection, were enrolled in this monocentric study. 390 histologically validated LNs were collected from patients and randomly separated into training (312 patients, 155 metastatic and 157 normal LNs) and test cohorts (78 patients, 39 metastatic and 39 normal LNs). Six patient characteristics and 146 quantitative CT imaging features were analyzed and key variables were determined using either exhaustive search or least absolute shrinkage algorithm. Two kernel-based support vector machine classifiers (patient-characteristic model and radiomic-derived model), generated with 10-fold cross-validation, were compared with the clinical model that utilizes long-axis diameter for diagnosis of metastatic LN. The performance of the models was evaluated on the test cohort by computing accuracy, sensitivity, specificity, and area under the receiver operating curve (AUC).

RESULTS

The clinical model had an overall diagnostic accuracy of 64.87%; specifically, accuracy of 65.38% and 62.82%, sensitivity of 83.87% and 84.62%, and specificity of 47.13% and 41.03% for training and test cohorts, respectively. The patient-demographic model obtained accuracy of 67.31% and 73.08%, the sensitivity of 62.58% and 69.23%, and specificity of 71.97% and 76.23% for training and test cohorts, respectively. Besides, the radiomic-derived model resulted in an accuracy of 81.09% and 79.49%, sensitivity of 83.87% and 74.36%, and specificity of 78.34% and 84.62% for training and test cohorts, respectively. Furthermore, the diagnostic performance of the radiomic-derived model was significantly higher than clinical and patient-demographic models (p < 0.02) according to the DeLong method.

CONCLUSIONS

The texture of the LNs provided characteristic information about the histological status of the LNs. The radiomic-derived model leveraging LN texture provides better preoperative diagnostic accuracy for the detection of metastatic LNs compared to the clinically accepted diagnostic criteria and patient-demographic model.

Preoperative Risk Assessment of Lymph Node Metastasis in cT1 Lung Cancer: A Retrospective Study from Eastern China

Background

Lymph node status of clinical T1 (diameter ≤ 3 cm) lung cancer largely affects the treatment strategies in the clinic. In order to assess lymph node status before operation, we aim to develop a noninvasive predictive model using preoperative clinical information.

Methods

We retrospectively reviewed 924 patients (development group) and 380 patients (validation group) of clinical T1 lung cancer. Univariate analysis followed by polytomous logistic regression was performed to estimate different risk factors of lymph node metastasis between N1 and N2 diseases. A predictive model of N2 metastasis was established with dichotomous logistic regression, externally validated and compared with previous models.

Results

Consolidation size and clinical N stage based on CT were two common independent risk factors for both N1 and N2 metastases, with different odds ratios. For N2 metastasis, we identified five independent predictors by dichotomous logistic regression: peripheral location, larger consolidation size, lymph node enlargement on CT, no smoking history, and higher levels of serum CEA. The model showed good calibration and discrimination ability in the development data, with the reasonable Hosmer-Lemeshow test (p = 0.839) and the area under the ROC being 0.931 (95% CI: 0.906-0.955). When externally validated, the model showed a great negative predictive value of 97.6% and the AUC of our model was better than other models.

Conclusion

In this study, we analyzed risk factors for both N1 and N2 metastases and built a predictive model to evaluate possibilities of N2 metastasis of clinical T1 lung cancers before the surgery. Our model will help to select patients with low probability of N2 metastasis and assist in clinical decision to further management.

Young age increases risk for lymph node positivity but decreases risk for non-small cell lung cancer death

Non-small cell lung cancer (NSCLC) prognosis and risk of lymph node positivity (LN+) are reference points for reasonable treatments. The aim of the current study was to investigate the effect of age on LN+ and NSCLC death. Data from the Surveillance, Epidemiology, and End Results (SEER) registry were used to identify 82,253 patients with NSCLC diagnosed between 1988 and 2008. All the patients underwent standard lung cancer surgery with lymph node examination. Demographic and clinicopathological parameters were extracted and compared among each age group. Impact of age on LN+ and NSCLC death was evaluated by the Cochran-Armitage trend test and logistic univariate and multivariate analyses for all T stages. Overall, 22,711 (27.60%) patients of the entirety had lymph node metastasis and 28,968 (35.22%) patients died of NSCLC within 5 years. With the increase in age, LN+ rates decreased regardless of T stages (P<0.001), whereas NSCLC-specific mortality increased in stages T1-T3 (P<0.001). Controlling other covariates in multivariable logistic regression, age remained an independent risk factor for LN+ in all T stages (P<0.05) and in stages T1-T3 (P<0.05). Our SEER analysis demonstrated a higher rate of LN+ and lower mortality in younger patients with NSCLC, after accounting for other covariates.