Recommendations for optimal use of imaging studies to clinically stage mediastinal lymph nodes in non-small-cell lung cancer patients

PET/CT based cross-modal deep learning signature to predict occult nodal metastasis in lung cancer

Occult nodal metastasis (ONM) plays a significant role in comprehensive treatments of non-small cell lung cancer (NSCLC). This study aims to develop a deep learning signature based on positron emission tomography/computed tomography to predict ONM of clinical stage N0 NSCLC. An internal cohort (n = 1911) is included to construct the deep learning nodal metastasis signature (DLNMS). Subsequently, an external cohort (n = 355) and a prospective cohort (n = 999) are utilized to fully validate the predictive performances of the DLNMS. Here, we show areas under the receiver operating characteristic curve of the DLNMS for occult N1 prediction are 0.958, 0.879 and 0.914 in the validation set, external cohort and prospective cohort, respectively, and for occult N2 prediction are 0.942, 0.875 and 0.919, respectively, which are significantly better than the single-modal deep learning models, clinical model and physicians. This study demonstrates that the DLNMS harbors the potential to predict ONM of clinical stage N0 NSCLC.

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.

Lung cancer with PET/CT-defined occult nodal metastasis yields favourable prognosis and benefits from adjuvant therapy: a multicentre study

PURPOSE

To investigate the surgical prognosis and efficacy of adjuvant therapy in non-small cell lung cancer (NSCLC) with occult lymph node metastasis (ONM) defined by positron emission tomography/computed tomography (PET/CT).

METHODS

A total of 3537 NSCLC patients receiving surgical resection were included in this study. The prognosis between patients with ONM and evident nodal metastasis, ONM patients with and without adjuvant therapy was compared, respectively.

RESULTS

ONM was associated with significantly better prognosis than evident nodal metastasis whether for patients with N1 (5-year OS: 56.8% versus 52.3%, adjusted p value = 0.267; 5-year RFS: 44.7% versus 33.2%, adjusted p value = 0.031) or N2 metastasis (5-year OS: 42.8% versus 32.3%, adjusted p value = 0.010; 5-year RFS: 31.3% versus 21.6%, adjusted p value = 0.025). In ONM population, patients receiving adjuvant therapy yielded better prognosis comparing to those without adjuvant therapy (5-year OS: 50.1% versus 33.5%, adjusted p value < 0.001; 5-year RFS: 38.4% versus 22.1%, adjusted p value < 0.001).

CONCLUSIONS

ONM defined by PET/CT identifies a unique clinical subtype of lung cancer, ONM is a favorable prognostic factor whether for pathological N1 or N2 NSCLC and adjuvant therapy could provide additional survival benefits for ONM patients.

Deep Learning for Prediction of N2 Metastasis and Survival for Clinical Stage I Non-Small Cell Lung Cancer

Background Preoperative mediastinal staging is crucial for the optimal management of clinical stage I non-small cell lung cancer (NSCLC). Purpose To develop a deep learning signature for N2 metastasis prediction and prognosis stratification in clinical stage I NSCLC. Materials and Methods In this retrospective study conducted from May 2020 to October 2020 in a population with clinical stage I NSCLC, an internal cohort was adopted to establish a deep learning signature. Subsequently, the predictive efficacy and biologic basis of the proposed signature were investigated in an external cohort. A multicenter diagnostic trial (registration number: ChiCTR2000041310) was also performed to evaluate its clinical utility. Finally, on the basis of the N2 risk scores, the instructive significance of the signature in prognostic stratification was explored. The diagnostic efficiency was quantified with the area under the receiver operating characteristic curve (AUC), and the survival outcomes were assessed using the Cox proportional hazards model. Results A total of 3096 patients (mean age ± standard deviation, 60 years ± 9; 1703 men) were included in the study. The proposed signature achieved AUCs of 0.82, 0.81, and 0.81 in an internal test set (n = 266), external test cohort (n = 133), and prospective test cohort (n = 300), respectively. In addition, higher deep learning scores were associated with a lower frequency of EGFR mutation (P = .04), higher rate of ALK fusion (P = .02), and more activation of pathways of tumor proliferation (P < .001). Furthermore, in the internal test set and external cohort, higher deep learning scores were predictive of poorer overall survival (adjusted hazard ratio, 2.9; 95% CI: 1.2, 6.9; P = .02) and recurrence-free survival (adjusted hazard ratio, 3.2; 95% CI: 1.4, 7.4; P = .007). Conclusion The deep learning signature could accurately predict N2 disease and stratify prognosis in clinical stage I non-small cell lung cancer. © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Park and Lee in this issue.

CT-based radiomics signature for the stratification of N2 disease risk in clinical stage I lung adenocarcinoma

Background

Risk stratification of N2 disease is vital for selecting candidates to receive invasive mediastinal staging modalities. In this study, we aimed to stratify the risk of N2 metastasis in clinical stage I lung adenocarcinoma using radiomics analysis.

Methods

Two datasets of patients with clinical stage I lung adenocarcinoma who underwent lung resection were included (training dataset, 880; validation dataset, 322). Using PyRadiomics, 1,078 computed tomography (CT)-based radiomics features were extracted after semi-automated lung nodule segmentation. In order to predict N2 status, a radiomics signature was constructed after selecting the optimal radiomics feature subset by sequentially applying minimum-redundancy-maximum-relevance and least absolute shrinkage and selection operator (LASSO) techniques. Its performance was validated in the validation dataset.

Results

The incidences of N2 metastasis were 8.4% and 7.1% in the training and validation datasets, respectively. Unsupervised cluster analysis revealed that radiomics features significantly correlated with lymph node status and pathological subtypes. For N2 disease prediction, five radiomics features were selected to establish the radiomics signature, which showed a significantly better predictive performance than clinical factors (P<0.001). The area under the receiver operating characteristic curve was 0.81 (0.77-0.86) and 0.69 (0.63-0.75) for radiomics signature and clinical factors, respectively, in the training dataset, and 0.82 (0.71-0.92) and 0.64 (0.52-0.75), respectively, in the validation dataset.

Conclusions

The established CT-based radiomics signature could stratify the risk of N2 metastasis in clinical stage I lung adenocarcinoma, thus assisting clinicians in making patient-specific mediastinal staging strategy.

18F-fluorodeoxyglucose positron emission tomography/computed tomography in the evaluation of clinically node-negative non-small cell lung cancer

One in four non-small cell lung cancer (NSCLC) patients are diagnosed at an early-stage. Following the results of the National Lung Screening Trial that demonstrated a survival benefit for low-dose computed tomography screening in high-risk patients, the incidence of early-stage NSCLC is expected to increase. Use of 18F-fluorodeoxyglucose positron emission tomography/computed tomography during initial diagnosis of these early-stage lesions has been increasing. Traditionally, positron emission tomography/computed tomography scans have been utilized for mediastinal nodal staging and to rule out distant metastases in suspected early-stage NSCLC. In clinically node-negative NSCLC, the use of sublobar resection and selective lymph node dissection has been increasing as a therapeutic option. The higher rate of locoregional recurrences after limited resection and the significant incidence of occult lymph node metastases underscores the need to further stratify clinically node-negative NSCLC in order to select patients for limited resection versus lobectomy with complete mediastinal lymph node dissection. In this report, we review the published data, and discuss the significance and potential role of 18F-fluorodeoxyglucose positron emission tomography/computed tomography evaluation for clinically node-negative NSCLC. Consequently, the literature review demonstrates that maximum standardized uptake value is a predictive factor for occult nodal metastasis with an accuracy of 55-77%. In addition, maximum standardized uptake value is a predictor for worse overall, as well as disease-free, survival.

Mediastinoscopy: trends and practice patterns in the United States

OBJECTIVES

Historically, mediastinoscopy has been the gold standard for the staging of lung cancer. A practice gap exists as the result of a variation in knowledge concerning current trends and practice patterns of mediastinoscopy usage. In addition, there are regional variations in practice-based learning and patient care. Lessons learned during surgeries performed on patients with lung cancer and other advances such as positron emission tomography and endobronchial ultrasound could be universally applied to improve surgeons' management of patient care. The purpose of this study was to assess contemporary practices in the staging of lung cancer.

METHODS

We queried the Society of Thoracic Surgeons National Database for data regarding mediastinoscopy usage, yield, and variation, both by year and region.

RESULTS

Cases with mediastinoscopy, as a percentage of all cases performed in the database, have significantly decreased from 14.6% in 2006 to 11.4% in 2010 (P < 0.001). The 5-year median rate of mediastinoscopy in lung cancer patients at 163 centers was 15.3% (interquartile range 5.2%-31.7%), indicating significant variation among centers. The overall median center rate also decreased over time from 21.4% (2006) to 10.0% (2010).

CONCLUSIONS

With advances in minimally invasive procedures and imaging, mediastinoscopy usage has declined significantly. Our findings are likely to be relevant to both clinical practice and practice guidelines.

Node/aorta and node/liver SUV ratios from (18)F-FDG PET/CT may improve the detection of occult mediastinal lymph node metastases in patients with non-small cell lung carcinoma

RATIONALE AND OBJECTIVES

Research suggests that the semiquantitative determination of nodal (18)F-fluorodeoxyglucose (FDG) uptake on positron emission tomography (PET)/computed tomography (CT) may be useful for the assessment of mediastinal metastases in patients with non-small-cell lung carcinoma (NSCLC). The aim of this study was to evaluate the diagnostic ability of using different standardized uptake value (SUV) parameters in the detection of ipsilateral mediastinal (N2) disease.

MATERIALS AND METHODS

A total of 102 patients newly diagnosed with non-small-cell lung carcinoma who underwent (18)F-FDG PET/CT before surgery and had not received prior therapy were retrospectively included. All patients underwent surgical resection of the primary tumor and mediastinal lymph node dissection. On a station-based analysis, different SUV parameters (eg, mediastinal lymph node SUV, node/aorta SUV ratio, and node/liver SUV ratio) were evaluated using the histopathologic results as the reference standard. The optimal cutoff value for each SUV parameter was determined with receiver-operating characteristic curve analysis.

RESULTS

The areas under the receiver-operating characteristic curves were 0.674, 0.693, and 0.715 for node SUV, node/aorta SUV ratio, and node/liver SUV ratio, respectively (P < .05). With cutoff values of 3.15, 1.37, and 1.02 for node SUV, node/aorta SUV ratio, and node/liver SUV ratio, respectively, the sensitivity of (18)F-FDG PET/CT for N2 staging was 57.1%, 85.7%, and 71.4%, and specificity was 74.2%, 50.5%, and 61.9%.

CONCLUSIONS

Compared to node SUV alone, the use of node/aorta and node/liver SUV ratios resulted in improved detection of N2 metastases. The two SUV parameters may potentially improve the diagnostic accuracy of (18)F-FDG PET/CT for the diagnosis of N2 disease in patients with non-small-cell lung carcinoma.

[Role of FDG-PET scanning in stage IIIAN2 non-small cell lung cancer]

Patients with clinical stage IIIAN2 non-small cell lung cancer (NSCLC) are a heterogeneous subgroup in term of prognosis and therapeutic management. The optimal management of this patient group is a major focus for thoracic oncology research and the concept of multimodality treatment has recently been introduced. This approach combines induction chemotherapy or radiochemotherapy followed by surgery in the case of mediastinal lymph node down-staging. positron emission tomography computed tomography with [18F]-fluorodesoxyglucose (FDG-PET) is a molecular and metabolic imaging modality which combines the metabolic data of PET with morphological data from CT. FDG-PET has become a standard in lung cancer management since the different indications listed in the standards, options and recommendations (SOR) of the FNCLCC. However, the potential specific importance of FDG-PET in IIIAN2 patients needs to be addressed further. In this setting, the authors' objective is to review the potential role of metabolic imaging in stage IIIAN2 NSCLC, taking into account new multimodality treatments. In stage IIIAN2, FDG-PET has performed better than morphoradiological imaging for baseline and postinduction lymph node staging, the identification of distant metastasis, and determining prognosis, as well as assessing the response to treatment.