A novel, stepwise approach combining conventional and endobronchial ultrasound needle aspiration for mediastinal lymph node sampling

Endobronchial Ultrasound-Based Support Vector Machine Model for Differentiating between Benign and Malignant Mediastinal and Hilar Lymph Nodes

INTRODUCTION

The aim of the study was to establish an ultrasonographic radiomics machine learning model based on endobronchial ultrasound (EBUS) to assist in diagnosing benign and malignant mediastinal and hilar lymph nodes (LNs).

METHODS

The clinical and ultrasonographic image data of 197 patients were retrospectively analyzed. The radiomics features extracted by EBUS-based radiomics were analyzed by the least absolute shrinkage and selection operator. Then, we used a support vector machine (SVM) algorithm to establish an EBUS-based radiomics model. A total of 205 lesions were randomly divided into training (n = 143) and validation (n = 62) groups. The diagnostic efficiency was evaluated by receiver operating characteristic (ROC) curve analysis.

RESULTS

A total of 13 stable radiomics features with non-zero coefficients were selected. The SVM model exhibited promising performance in both groups. In the training group, the SVM model achieved an ROC area under the curve (AUC) of 0.892 (95% CI: 0.885-0.899), with an accuracy of 85.3%, sensitivity of 93.2%, and specificity of 79.8%. In the validation group, the SVM model had an ROC AUC of 0.906 (95% CI: 0.890-0.923), an accuracy of 74.2%, a sensitivity of 70.3%, and a specificity of 74.1%.

CONCLUSION

The EBUS-based radiomics model can be used to differentiate mediastinal and hilar benign and malignant LNs. The SVM model demonstrated excellent potential as a diagnostic tool in clinical practice.

Detection of short stature homeobox 2 and RAS-associated domain family 1 subtype A DNA methylation in interventional pulmonology

One of the most important aspects of interventional pulmonology is to obtain tissue or liquid samples of the chest to diagnose a respiratory disease; however, it is still possible to obtain insufficient tissue or cytologic specimens. Indeed, methylation detection is an effective method by which to establish a diagnosis. This review focuses on the clinical application of short stature homeobox 2 and RAS-associated domain family 1 subtype A DNA methylation detection in interventional pulmonology, including bronchoscopic fluid biopsy, transbronchial needle aspiration, and pleural effusion.

Accuracy of endoscopic ultrasound-guided needle aspiration specimens for molecular diagnosis of non-small-cell lung carcinoma

BACKGROUND

Endoscopic ultrasonography-guided fine-needle aspiration (EUS-FNA) and endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA) are highly sensitive for diagnosing and staging lung cancer. In recent years, targeted therapy has shown great significance in the treatment of non-small cell lung carcinoma (NSCLC). Using these minimally invasive techniques to obtain specimens for molecular testing will provide patients with a more convenient diagnostic approach.

AIM

To evaluate the feasibility and accuracy of tissue samples obtained using EUS-FNA and EBUS-TBNA for molecular diagnosis of NSCLC.

METHODS

A total of 83 patients with NSCLC underwent molecular testing using tissues obtained from EUS-FNA or EBUS-TBNA at the Tianjin Medical University Cancer Hospital from January 2017 to June 2019. All enrolled patients underwent chest computed tomography or positron emission tomography/computed tomography prior to puncture. We detected abnormal expression of EGFR, KRAS, MET, HER2, ROS1 and anaplastic lymphoma kinase protein. Two patients failed to complete molecular testing due to insufficient tumor tissue. The clinical features, puncture records, molecular testing results and targeted treatment in the remaining 81 patients were summarized.

RESULTS

In a total of 99 tissue samples obtained from 83 patients, molecular testing was successfully completed in 93 samples with a sample adequacy ratio of 93.9% (93/99). Biopsy samples from two patients failed to provide test results due to insufficient tumor tissue. In the remaining 81 patients, 62 cases (76.5%) were found to have adenocarcinoma, 11 cases (13.6%) had squamous cell carcinoma, 3 cases (3.7%) had adenosquamous carcinoma and 5 cases (6.2%) had NSCLC-not otherwise specified. The results of molecular testing showed EGFR mutations in 21 cases (25.9%), KRAS mutations in 9 cases (11.1%), ROS-1 rearrangement in 1 case (1.2%) and anaplastic lymphoma kinase-positive in 5 cases (6.2%). Twenty-four patients with positive results received targeted therapy. The total effectiveness rate of targeted therapy was 66.7% (16/24), and the disease control rate was 83.3% (20/24).

CONCLUSION

Tissue samples obtained by EUS-FNA or EBUS-TBNA are feasible for the molecular diagnosis of NSCLC and can provide reliable evidence for clinical diagnosis and treatment.

Radiomics model for distinguishing tuberculosis and lung cancer on computed tomography scans

BACKGROUND

Pulmonary tuberculosis (TB) and lung cancer (LC) are common diseases with a high incidence and similar symptoms, which may be misdiagnosed by radiologists, thus delaying the best treatment opportunity for patients.

AIM

To develop and validate radiomics methods for distinguishing pulmonary TB from LC based on computed tomography (CT) images.

METHODS

We enrolled 478 patients (January 2012 to October 2018), who underwent preoperative CT screening. Radiomics features were extracted and selected from the CT data to establish a logistic regression model. A radiomics nomogram model was constructed, with the receiver operating characteristic, decision and calibration curves plotted to evaluate the discriminative performance.

RESULTS

Radiomics features extracted from lesions with 4 mm radial dilation distances outside the lesion showed the best discriminative performance. The radiomics nomogram model exhibited good discrimination, with an area under the curve of 0.914 (sensitivity = 0.890, specificity = 0.796) in the training cohort, and 0.900 (sensitivity = 0.788, specificity = 0.907) in the validation cohort. The decision curve analysis revealed that the constructed nomogram had clinical usefulness.

CONCLUSION

These proposed radiomic methods can be used as a noninvasive tool for differentiation of TB and LC based on preoperative CT data.

Cost-effectiveness of endoscopic mediastinal staging

Lung cancer is the first cause of cancer-related mortality. Mediastinal staging has a main role in the definition of the therapeutic strategy in early-stage and locally-advanced non-small cell lung cancer (NSCLC). Non-invasive mediastinal staging with CT or PET imaging has relatively limited accuracy, and nodal biopsy may be required to reach adequate staging results. In the last two decades endoscopic techniques have been increasingly used in the field of mediastinal staging thanks to a reduced invasiveness and to the possibility of obtaining a more thorough assessment in comparison with surgical techniques. However, the ideal staging strategy is still a matter for debate, particularly considering the cost-effectiveness of the different approaches. Complication-rate, costs, impact on quality of life, time delay to treatment and survival of the different staging techniques still have to be analyzed in detail. Other issues to be discussed are the optimal combination of staging approaches and the influence of factors as the prevalence of nodal disease on the cost-effectiveness of the different methods. Future issues of invasive staging concern the possibility of extending the definition of nodal status to N1 intrapulmonary nodes, in the light of the development of new oncological and surgical therapeutic approaches.

Is FDG-PET/CT used correctly in the combined approach for nodal staging in NSCLC patients?

Background

The most widely accepted approach nowadays in nodal staging of non-small cell lung cancer (NSCLC) is the combined use of 18-Fluorodeoxyglucose-positron emission tomography/computed tomography (FDG-PET/CT) and endobronchial ultrasound-transbronchial needle aspiration (EBUS-TBNA). However, this approach may not be sufficient, especially for early stages.

Aims

Our aim was to assess whether more satisfactory results can be obtained with standardized uptake value maximum lymph node/standardized uptake value mean mediastinal blood pool (SUVmax LN/SUVmean MBP), SUVmax LN/Primary tumor, or a novel cut-off value to SUVmax in this special group.

Subjects and Methods

Patients with diagnosed NSCLC and underwent FDG-PET/CT were reviewed retrospectively. 168 LNs of 52 early stage NSCLC patients were evaluated. The LNs identified in surgery/pathology reports were found in the FDG-PET/CT images. Anatomic and metabolic parameters were measured. Statistical analysis was performed by using of MedCalc Statistical Software.

Results

Regardless of LNs size; sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of SUVmax >2.5 were 91.5%, 65.9%, 58.2%, and 95.1%, respectively. Optimum cut-off value of SUVmax was >4.0. Sensitivity, specificity, PPV, and NPV were found as 81.0%, 90.0%, 81.0%, and 90.0% respectively. Optimum cut-off value of SUVmax LN/SUVmean MBP was >1.71. Sensitivity, specificity, PPV, and NPV were found as 94.7%, 80.0%, 71.1%, and 96.7%, respectively. Optimum cut-off value of SUVmax LN/Primary tumor was >0.28. Sensitivity, specificity, PPV, and NPV were found as 81.1%, 85.1%, 72.9% and 90.1%, respectively.

Conclusion

SUVmax LN/SUVmean MBP >1.71 has higher PPV than currently used, with similar NPV and sensitivity. This can provide increase in the accuracy of combined approach. In this way, faster nodal staging/treatment decisions, cost savings for healthcare system and time saving of medical professionals can be obtained.

Diagnosis and Detection of Sarcoidosis. An Official American Thoracic Society Clinical Practice Guideline

Background: The diagnosis of sarcoidosis is not standardized but is based on three major criteria: a compatible clinical presentation, finding nonnecrotizing granulomatous inflammation in one or more tissue samples, and the exclusion of alternative causes of granulomatous disease. There are no universally accepted measures to determine if each diagnostic criterion has been satisfied; therefore, the diagnosis of sarcoidosis is never fully secure.

Methods: Systematic reviews and, when appropriate, meta-analyses were performed to summarize the best available evidence. The evidence was appraised using the Grading of Recommendations, Assessment, Development, and Evaluation approach and then discussed by a multidisciplinary panel. Recommendations for or against various diagnostic tests were formulated and graded after the expert panel weighed desirable and undesirable consequences, certainty of estimates, feasibility, and acceptability.

Results: The clinical presentation, histopathology, and exclusion of alternative diagnoses were summarized. On the basis of the available evidence, the expert committee made 1 strong recommendation for baseline serum calcium testing, 13 conditional recommendations, and 1 best practice statement. All evidence was very low quality.

Conclusions: The panel used systematic reviews of the evidence to inform clinical recommendations in favor of or against various diagnostic tests in patients with suspected or known sarcoidosis. The evidence and recommendations should be revisited as new evidence becomes available.