Diagnostic value of endobronchial ultrasound image features: A specialized review

Diagnostic modalities in the mediastinum and the role of bronchoscopy in mediastinal assessment: a narrative review

Background and Objective

Diagnosis of pathology in the mediastinum has proven quite challenging, given the wide variability of both benign and malignant diseases that affect a diverse array of structures. This complexity has led to the development of many different non-invasive and invasive diagnostic modalities. Historically, diagnosis of the mediastinum has relied on different imaging modalities such as chest X-ray, computed tomography (CT), magnetic resonance imaging, and positron emission topography. Once a suspicious lesion was identified with one of these techniques, the gold standard for diagnosis was mediastinoscopy for diagnosis and staging of disease. More recently, many minimally invasive techniques such as CT-guided biopsy, endobronchial ultrasound with transbronchial needle aspiration, and endoscopic ultrasound with fine needle aspiration have revolutionized the diagnosis of the mediastinum. This review provides a comprehensive analysis of all the modalities available for diagnosing mediastinal disease with an emphasis on bronchoscopic techniques.

Methods

Literature search was performed via the PubMed database. We included all types of articles and study designs, including original research, meta-analyses, reviews, and abstracts.

Key Content and Findings

Minimally invasive techniques such as endobronchial ultrasound-transbronchial needle aspiration (EBUS-TBNA) and endoscopic ultrasound-fine needle aspiration (EUS-FNA) have demonstrated high diagnostic yield and low complication rate and have made a significant difference in the time to diagnosis and lives of patients. There continues to be innovation in the field of bronchoscopy with the development of new technologies such as confocal laser endomicroscopy, optical coherence tomography, and artificial intelligence.

Conclusions

Bronchoscopy is and will continue to be an integral modality in minimally invasive diagnosis of the mediastinum.

The Impact of Balloon Use during Endobronchial Ultrasound: A Randomized Pilot Study

INTRODUCTION

During endobronchial ultrasound transbronchial needle aspiration (EBUS-TBNA), a saline-filled balloon placed over the tip of the bronchoscope is used to improve coupling of the ultrasound transducer to the airway wall. However, it is unknown whether it objectively improves image quality or affects procedural outcomes. Our aim was to establish whether the use of a balloon during EBUS impacts image quality, diagnostic yield, procedure duration or complications.

METHODS

A pilot randomized control trial of patients undergoing EBUS-TBNA of mediastinal lymph nodes was performed at a single academic center. Patients were randomized to use a saline-filled balloon (versus no balloon use) during EBUS-TBNA of the right lower paratracheal lymph node (station 4R). The EBUS videos were recorded and scored on a 4-point Likert scale by three blinded external reviewers. The primary outcome of this study was ultrasound image quality. Secondary outcomes included diagnostic yield, procedure duration, and complications.

RESULTS

Forty-six patients were randomized. In the balloon group, 61% of patients had an image quality score of "excellent" or "good," compared to 47% in the no balloon group (p = 0.009). There was no significant difference in diagnostic yield, procedure duration, or complications between the groups.

CONCLUSION

Inflation of the balloon during EBUS-TBNA at the right lower paratracheal lymph node improves ultrasound image quality but does not impact diagnostic yield, procedure duration, or safety. This study provides a framework for additional studies with complete nodal assessment to determine if balloon use has a clinically meaningful benefit to procedural outcomes.

Quantitative evaluation of endobronchial ultrasound elastography in the diagnosis of benign and malignant mediastinal and hilar lymph nodes

OBJECTIVE

To compare the diagnostic value of different quantitative methods of endobronchial ultrasound elastography in benign and malignant mediastinal and hilar lymph nodes.

METHODS

This retrospective study included patients who underwent endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA) for mediastinal and hilar lymph node enlargement in our hospital between January 2019 and August 2022. We compared different quantitative elastography parameters [red area ratio (RAR, lymph node red area/lymph node area), green area ratio (GAR, lymph node green area/lymph node area), blue area ratio (SAR, lymph node blue area/lymph node area), mixed area ratio (MAR, lymph node green area/lymph node area), blue-green lymph node area/lymph node area), strain rate ratio (SR), strain rate in the target lymph node (LPA), ratio of blue area to total lymph node area outside the center of the target lymph node (PAR), and average grey value (MGV)], in order to find the best quantitative evaluation method.

RESULTS

A total of 244 patients (346 lymph nodes) were included in this study. All quantitative elastography parameters were statistically significant for the differentiation of benign and malignant lesions except the average grey value of the target lymph nodes. The area under the receiver operating characteristic curve of SAR was 0.872 (95% confidence interval: 0.83-0.91), the cutoff value was 0.409, and the sensitivity, specificity, positive and negative predictive values were 85.4%, 78.0%, 80.4%, and 83.4%, respectively.

CONCLUSION

Compared with other types of quantitative analysis, SAR has a higher predictive significance for benign and malignant lymph nodes.

Role of invasive mediastinal nodal staging in survival outcomes of patients with non-small cell lung cancer and without radiologic lymph node metastasis: a retrospective cohort study

Background

Lung cancer diagnostic guidelines advocate for invasive mediastinal nodal staging (IMNS), but the survival benefits of this approach in patients with non-small cell lung cancer (NSCLC) without radiologic evidence of lymph node metastasis (rN0) remain uncertain. We aimed to investigate the impact of IMNS in patients with rN0 NSCLC by comparing the long-term survival between patients who underwent IMNS and those who did not (non-IMNS).

Methods

In this retrospective cohort study, we included patients with NSCLC but without radiologic evidence of lymph node metastasis from the Registry for Thoracic Cancer Surgery and the clinical data warehouse at the Samsung Medical Centre, Republic of Korea between January 2, 2008 and December 31, 2016. We compared the 5-year overall survival (OS) rate as the primary outcome after propensity score matching between the IMNS and non-IMNS groups. The age, sex, performance statue, tumor size, centrality, solidity, lung function, FDG uptake in PET-CT, and histological examination of the tumor before surgery were matched.

Findings

A total of 4545 patients (887 in the IMNS group and 3658 in the non-IMNS group) who received curative treatment for NSCLC were included in this study. By the mediastinal node dissection, the overall incidence of unforeseen mediastinal node metastasis (N2) was 7.2% (317/4378 patients). Despite the IMNS, 67% of pathological N2 was missed (61/91 patients with unforeseen N2). Based on propensity score matching, 866 patients each for the IMNS and non-IMNS groups were assigned. There was no significant difference in 5-year OS and recurrence-free survival (RFS) between two groups: 5-year OS was 73.9% (95% confidence interval, CI: 71%-77%) for IMNS and 71.7% (95% CI: 68.6%-74.9%; p = 0.23), for non-IMNS (hazard ratio, HR 0.90, 95% CI: 0.77-1.07), while 5-year RFS was 64.7% (95% CI: 61.5%-68.2%) and 67.5% (95% CI: 64.3%-70.9%; p = 0.35 (HR 1.08, 95% CI: 0.92-1.27), respectively. Moreover, the timing and locations of recurrence were similar in both groups.

Interpretation

IMNS might not be required before surgery for patients with NSCLC without LN suspicious of metastasis. Further randomised trials are required to validate the findings of the present study.

Funding

None.

A risk-scoring model based on endobronchial ultrasound multimodal imaging for predicting metastatic lymph nodes in lung cancer patients

Background and Objectives

Endobronchial ultrasound (EBUS) imaging is a valuable tool for predicting lymph node (LN) metastasis in lung cancer patients. This study aimed to develop a risk-scoring model based on EBUS multimodal imaging (grayscale, Doppler mode, elastography) to predict LN metastasis in lung cancer patients.

Patients and Methods

This retrospective study analyzed 350 metastatic LNs in 314 patients with lung cancer and 124 reactive LNs in 96 patients with nonspecific inflammation. The sonographic findings were compared with the final pathology results and clinical follow-up. Univariate and multivariate logistic regression analyses were performed to evaluate the independent risk factors of metastatic LNs. According to the β coefficients of corresponding indicators in logistic regression analysis, a risk-scoring model was established. Receiver operating characteristic curve was applied to evaluate the predictive capability of model.

Results

Multivariate analysis showed that short axis >10 mm, distinct margin, absence of central hilar structure, presence of necrosis, nonhilar vascularity, and elastography score 4 to 5 were independent predictors of metastatic LNs. Both short axis and margin were scored 1 point, and the rest of independent predictors were scored 2 points. The combination of 3 EBUS modes had the highest area under the receiver operating characteristic and accuracy of 0.884 (95% confidence interval, 0.846-0.922) and 87.55%, respectively. The risk stratification was as follows: 0 to 2 points, malignancy rate of 11.11%, low suspicion; 3 to 10 points, malignancy rate of 86.77%, high suspicion.

Conclusions

The risk-scoring model based on EBUS multimodal imaging can effectively evaluate metastatic LNs in lung cancer patients to support clinical decision making.

A Nomogram to Predict Benign/Malignant Mediastinal Lymph Nodes Based on EBUS Sonographic Features

Background

Endobronchial ultrasound (EBUS) sonographic features help identify benign/malignant lymph nodes while conducting transbronchial needle aspiration (TBNA). This study aims to identify risk factors for malignancy based on EBUS sonographic features and to estimate the risk of malignancy in lymph nodes by constructing a nomogram.

Methods

1082 lymph nodes from 625 patients were randomly enrolled in training (n = 760) and validation (n = 322) sets. The subgroup of EBUS-TBNA postoperative negative lymph nodes (n = 317) was randomly enrolled in a training (n = 224) set and a validation (n = 93) set. Logistic regression analysis was used to identify the EBUS features of malignant lymph nodes. A nomogram was formulated using the EBUS features in the training set and later validated in the validation set.

Results

Multivariate analysis revealed that long-axis, short-axis, echogenicity, fusion, and central hilar structure (CHS) were the independent predictors of malignant lymph nodes. Based on these risk factors, a nomogram was constructed. Both the training and validation sets of 5 EBUS features nomogram showed good discrimination, with area under the curve values of 0.880 (sensitivity = 0.829 and specificity = 0.807) and 0.905 (sensitivity = 0.819 and specificity = 0.857). Subgroup multivariate analysis revealed that long-axis, echogenicity, and CHS were the independent predictors of malignancy outcomes of EBUS-TBNA postoperative negative lymph nodes. Based on these risk factors, a nomogram was constructed. Both the training and validation sets of 3 EBUS features nomogram showed good discrimination, with the area under the curve values of 0.890 (sensitivity = 0.882 and specificity = 0.786) and 0.834 (sensitivity = 0.930 and specificity = 0.636).

Conclusions

Our novel scoring system based on two nomograms can be utilized to predict malignant lymph nodes.

Ultrasound in the Study of Thoracic Diseases: Innovative Aspects

Thoracic ultrasound (TU) has rapidly gained popularity over the past 10 years. This is in part because ultrasound equipment is available in many settings, more training programmes are educating trainees in this technique, and ultrasound can be done rapidly without exposure to radiation. The aim of this review is to present the most interesting and innovative aspects of the use of TU in the study of thoracic diseases. In pleural diseases, TU has been a real revolution. It helps to differentiate between different types of pleural effusions, guides the performance of pleural biopsies when necessary and is more cost-effective under these conditions, and assists in the decision to remove thoracic drainage after talc pleurodesis. With the advent of COVID19, the use of TU has increased for the study of lung involvement. Nowadays it helps in the diagnosis of pneumonias, tumours and interstitial diseases, and its use is becoming more and more widespread in the Pneumology ward. In recent years, TU guided biopsies have been shown to be highly cost-effective, with other advantages such as the absence of radiation and the possibility of being performed at bedside. The use of contrast in ultrasound to increase the cost-effectiveness of these biopsies is very promising. In the study of the mediastinum and peripheral pulmonary nodules, the introduction of echobronchoscopy has brought about a radical change. It is a fully established technique in the study of lung cancer patients. The introduction of elastography may help to further improve its cost-effectiveness. In critically-ill patients, diaphragmatic ultrasound helps in the assessment of withdrawal of mechanical ventilation, and is now an indispensable tool in the management of these patients. In neuromuscular patients, ultrasound is a good predictor of impaired lung function. Currently, in Neuromuscular Disease Units, TU is an indispensable tool. Ultrasound study of the intercostal musculature is also effective in the study of respiratory function, and is widely used in Respiratory Rehabilitation. In Intermediate Care Units, thoracic ultrasound is indispensable for patient management. In these units there are ultrasound protocols for the management of patients with acute dyspnoea that have proven to be very effective.

Effect of a disposable endoscope precleaning kit in the cleaning procedure of gastrointestinal endoscope: A multi-center observational study

BACKGROUND

Precleaning is a key step in endoscopic reprocessing.

AIM

To develop an effective and economic endoscope cleaning method by using a disposable endoscope bedside precleaning kit.

METHODS

Altogether, 228 used gastrointestinal endoscopes were selected from five high-volume endoscopy units and precleaned by a traditional precleaning bucket (group T) or a disposable endoscope bedside precleaning kit (group D). Each group was further subdivided based on the replacement frequency of the cleaning solution, which was replaced every time in subgroups T1 and D1 and every several times in subgroups Ts and Ds. The adenosine triphosphate (ATP) level and residual proteins were measured three times: Before and after precleaning and after manual cleaning.

RESULTS

After precleaning, the precleaning kit significantly reduced the ATP levels (P = 0.034) and has a more stable ATP clearance rate than the traditional precleaning bucket. The precleaning kit also saved a quarter of the cost of enzymatic detergent used during the precleaning process. After manual cleaning, the ATP levels were also significantly lower in the precleaning kit group than in the traditional precleaning bucket group (P < 0.05). Meanwhile, the number of uses of the cleaning solution (up to four times) has no significant impact on the cleaning effect (P > 0.05).

CONCLUSION

Considering its economic cost and cleaning effect, the use of a disposable endoscope bedside precleaning kit can be an optimal option in the precleaning stage with the cleaning solution being replaced several times in the manual cleaning stage.

PET-CT SUVmax and Endobronchial Ultrasound Features for Prediction of Malignancy: A Prospective Study

INTRODUCTION

Accurate and early staging of lung cancer has a critical impact on its prognosis. EBUS-TBNA is often the procedure of choice for mediastinal staging. Comprehension of the likelihood of malignancy of each lymph node (LN) can assist puncture decision-making during EBUS and offer insight of the procedure expected diagnostic yield.

METHODS

Prospective analysis of mediastinal LN of patients undergoing EBUS-TBNA from April 2021 to May 2022. The relationship between PET-CT SUVmax levels, EBUS features, and malignancy on LN was investigated. For statistical analysis, patients were assigned to 3 groups: suspected malignancy (diagnosis and/or staging), confirmed malignancy (staging) or suspected benign disease.

RESULTS

A total of 363 LN from 132 patients (71% male, mean 62 years old) were analyzed. Among those with suspected benign disease, no LN puncture resulted in a diagnosis of malignancy. PET-CT SUVmax and short axis size were independent factors for malignancy in LN of patients who underwent EBUS for suspected (p < .001 and p = .047, respectively) or confirmed malignancy (p < .001 and p < .001, respectively). All malignant LN presented SUVmax≥1.85 (≥2.85 for staging EBUS cases) and/or short axis size ≥4.28mm. Vascularized LN were more often malignant in either those with suspected (p = .087) or confirmed (p = .095) malignancy, although not statistically significant. LN that were simultaneously vascularized and lacked central hilar structure were also more commonly malignant (p = .013).

CONCLUSION

LN that has higher SUVmax and are larger should be prioritized for puncture, followed by those vascularized and lacking central hilar structure. In staging EBUS cases, a systematic sampling (N3-N2-N1) is required and must precede any malignancy yield rationale.

Quantitative analysis of endobronchial elastography combined with serum tumour markers of lung cancer in the diagnosis of benign and malignant mediastinal and hilar lymph nodes

Purpose: In malignant tumours, elastography and serum tumour markers have shown high diagnostic efficacy. Therefore, we aimed to quantitatively analyse the results of endobronchial elastography combined with serum tumour markers of lung cancer to accurately distinguish benign and malignant mediastinal and hilar lymph nodes. Methods: Data of patients who underwent endobronchial ultrasound-guided transbronchial needle aspiration for mediastinal lymph node enlargement in our hospital between January 2018 and August 2022 were retrospectively collected. The characteristics of quantitative elastography and serum tumour markers were evaluated. Results: We enrolled 197 patients (273 lymph nodes). In the differential diagnosis of benign and malignant mediastinal and hilar lymph nodes, the stiffness area ratio (SAR), strain ratio (SR), and strain rate in lymph nodes were significant, among which SAR had the highest diagnostic value (cut-off value, 0.409). The combination of the four tumour markers had a high diagnostic value (AUC, 0.886). Three types of quantitative elastography indices combined with serum tumour markers for lung cancer showed a higher diagnostic value (AUC, 0.930; sensitivity, 83.5%; specificity, 89.3%; positive predictive value, 88.1%; negative predictive value, 85%) (p < 0.05). In the differential diagnosis of pathological types of lung cancer, different quantitative elastography indicators and serum tumour markers for lung cancer have different diagnostic significance for the differential diagnosis of lung cancer pathological types. Conclusion: The quantitative analysis of endobronchial ultrasound elastography combined with tumour markers can improve the diagnosis rate of benign and malignant mediastinal and hilar lymph nodes, help guide the puncture of false negative lymph nodes, and reduce the misdiagnosis rate.

Endobronchial ultrasound sonographic characteristics of mediastinal lymph node in the evaluation of lung cancer

Endobronchial ultrasound (EBUS) and contrast-enhanced computed tomography (CECT) are essential components of lung cancer evaluation. Features of mediastinal lymph nodes on EBUS and CECT can help in predicting metastatic disease. Clinical, radiological, and EBUS data of patients with clinico-radiological suspicion of lung cancer who have undergone EBUS with no transbronchial needle aspiration (TBNA) or nonyielding EBUS-TBNA were retrospectively collected from medical records. EBUS features of lymph nodes for metastatic disease [size >1 cm, round shape, heterogeneous echotexture, indistinct margin, coagulation necrosis (CN), absence of central hilar structures (CHS), and grade II-III vascularity] were noted. CECT findings were noted from CECT films and reports to analyze and compare with EBUS findings. Scoring criteria of EBUS sonographic characteristics from previous studies for discriminating benign and malignant lymph nodes were also assessed for possible prediction. 31 patients [male: 18 (58.1%), female: 13 (41.9); age (mean ± standard deviation): 52.9±15.7 years] with CECT findings suggesting lung cancer were studied. EBUS showed mediastinal lymphadenopathy at 82 lymph node stations in 29 patients. Size >1 cm, round shape, heterogeneous echotexture, distinct margin, CN, absence of CHS and grade II-III vascularity at 33 (40%), 28 (34%), 31 (38%), 55 (67%), 3 (4%), 77 (94%), and 6 (7.3%) lymph nodes, respectively, were found. The malignant or benign status assigned to lymph nodes using different scoring criteria was highly discordant. Compared to EBUS, CECT revealed abnormal mediastinal lymph nodes in significantly fewer patients [21 (67.7%) versus 29 (93.5%), p=0.01] involving a lower number of lymph node stations (37 versus 82, p<0.001). Lymphadenopathy frequency at different LNS on EBUS and CECT showed a weak positive but significant correlation (r=0.356; p=0.0426). EBUS characteristics and related scores have limited accuracy in differentiating benign and malignant nodes. CECT underestimates lymphadenopathy in comparison to EBUS. A larger prospective study of EBUS features with cyto/histopathology correlation may elicit its clinical significance and help to create better and more composite scoring criteria.

Endobronchial ultrasound-guided transbronchial needle aspiration in patients with previously treated malignancies: diagnostic performance and predictive value

BACKGROUND

Endobronchial ultrasound-guided transbronchial needle aspiration is a minimally invasive and effective sampling approach for patients with mediastinal or hilar lymphadenopathy. Increased recognition of the ultrasonographic features revealed the value of its images in predicting mediastinal lymph node malignancy. However, its diagnostic validity and the predictive value of its ultrasonographic features have not been demonstrated well in patients after systemic anti-tumor therapy. This study aimed to evaluate the efficiency of endobronchial ultrasound-guided transbronchial needle aspiration in patients with suspicious lymph nodes after anti-tumor therapy.

METHODS

We retrospectively reviewed cases of endobronchial ultrasound-guided transbronchial needle aspiration performed between January 2019 and August 2021 at a single tertiary hospital center. Patients with suspected mediastinal or hilar lymph nodes within 5 years of systemic anti-tumor therapy were enrolled. Final diagnoses were determined by pathologic diagnoses of samples from transbronchial needle aspiration, surgery, or follow-up for at least 6 months. Ultrasonographic features were analyzed to assess the predictive value of malignant lymph nodes after treatment.

RESULTS

Overall, 168 lymph nodes of 138 patients were analyzed. Among 110 (65.5%) malignant lymph nodes, 75 originated from lung cancers; the other 35 were from other malignancies. No complications related to endobronchial ultrasound-guided transbronchial needle aspiration were observed. Of 58 negative results of transbronchial needle aspiration, 51 were proven to be true negatives; 7 were false. The overall sensitivity and the negative predictive value were 94.02% and 87.93%, respectively. Univariate and multivariate analysis revealed the absence of central hilar structure and short axis > 10 mm as independent predictive factors for malignancy.

CONCLUSIONS

Endobronchial ultrasound-guided transbronchial needle aspiration performs satisfactorily in diagnosing mediastinal and hilar lymphadenopathy even after anti-tumor treatment.

Combination of 18F-FDG PET/CT and convex probe endobronchial ultrasound elastography for intrathoracic malignant and benign lymph nodes prediction

Background

Positron emission tomography–computed tomography (PET/CT) and convex probe endobronchial ultrasound (CP-EBUS) elastography are important diagnostic methods in predicting intrathoracic lymph nodes (LNs) metastasis, but a joint analysis of the two examinations is still lacking. This study aimed to compare the diagnostic efficiency of the two methods and explore whether the combination can improve the diagnostic efficiency in differentiating intrathoracic benign LNs from malignant LNs.

Materials and Methods

LNs examined by EBUS-guided transbronchial needle aspiration (EBUS-TBNA) and PET/CT from March 2018 to June 2019 in Shanghai Chest Hospital were retrospectively analyzed as the model group. Four PET/CT parameters, namely, maximal standardized uptake value mean standardized uptake value (SUVmean), SUVmean, metabolic tumor volume (MTV), and tumor lesion glycolysis (TLG); four quantitative elastography indicators (stiff area ratio, mean hue value, RGB, and mean gray value); and the elastography grading score of targeted LNs were analyzed. A prediction model was constructed subsequently and the dataset from July to November 2019 was used to validate the diagnostic capability of the model.

Results

A total of 154 LNs from 135 patients and 53 LNs from 47 patients were enrolled in the model and validation groups, respectively. Mean hue value and grading score were independent malignancy predictors of elastography, as well as SUVmax and TLG of PET/CT. In model and validation groups, the combination of PET/CT and elastography demonstrated sensitivity, specificity, positive and negative predictive values, and accuracy for malignant LNs diagnosis of 85.87%, 88.71%, 91.86%, 80.88%, and 87.01%, and 94.44%, 76.47%, 89.47%, 86.67%, and 88.68%, respectively. Moreover, elastography had better diagnostic accuracies than PET/CT in both model and validation groups (85.71% vs. 79.22%, 86.79% vs. 75.47%).

Conclusion

EBUS elastography demonstrated better efficiency than PET/CT and the combination of the two methods had the best diagnostic efficacy in differentiating intrathoracic benign from malignant LNs, which may be helpful for clinical application.

Pulmonary Lesion Classification Framework Using the Weighted Ensemble Classification with Random Forest and CNN Models for EBUS Images

Lung cancer is a deadly disease with a high mortality rate. Endobronchial ultrasonography (EBUS) is one of the methods for detecting pulmonary lesions. Computer-aided diagnosis of pulmonary lesions from images can help radiologists to classify lesions; however, most of the existing methods need a large volume of data to give good results. Thus, this paper proposes a novel pulmonary lesion classification framework for EBUS images that works well with small datasets. The proposed framework integrates the statistical results from three classification models using the weighted ensemble classification. The three classification models include the radiomics feature and patient data-based model, the single-image-based model, and the multi-patch-based model. The radiomics features are combined with the patient data to be used as input data for the random forest, whereas the EBUS images are used as input data to the other two CNN models. The performance of the proposed framework was evaluated on a set of 200 EBUS images consisting of 124 malignant lesions and 76 benign lesions. The experimental results show that the accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and area under the curve are 95.00%, 100%, 86.67%, 92.59%, 100%, and 93.33%, respectively. This framework can significantly improve the pulmonary lesion classification.

High SUVmax Is an Independent Predictor of Higher Diagnostic Accuracy of ROSE in EBUS-TBNA for Patients with NSCLC

Introduction: This study aimed to verify the predictors of the diagnostic accuracy of rapid on-site evaluation (ROSE) in endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA) among patients with non-small cell lung cancer (NSCLC). Methods: We retrospectively reviewed consecutive patients with NSCLC who underwent EBUS-TBNA for staging or diagnosis at our hospital from June 2016 to June 2018. The patients were divided into two groups—those with a correct diagnosis and an incorrect diagnosis after ROSE. Kaplan−Meier plots and log-rank tests were used to estimate outcomes. Results: A total of 84 patients underwent EBUS-TBNA for staging and diagnosis. Sixty patients with demonstrated malignant mediastinal lymph nodes were enrolled. In the univariate analysis, lymph nodes < 1.5 cm (HR = 3.667, p = 0.031) and a SUVmax > 5 (HR = 41, p = 0.001) were statistically significant for diagnostic accuracy of ROSE. In the multivariate Cox regression analysis, only a SUVmax > 5 (HR = 20.258, p = 0.016) was statistically significant. Conclusions: A SUVmax > 5 is an independent predictor of higher diagnostic accuracy of ROSE in EBUS-TBNA in patients with NSCLC with malignant mediastinal lymph nodes. Therefore, ROSE in patients with a SUVmax < 5 might not be reliable and requires further prudent assessment (more shots or repeated biopsies at mediastinal LNs) in clinical practice.

Automatic Image Selection Model Based on Machine Learning for Endobronchial Ultrasound Strain Elastography Videos

Background

Endoscopic ultrasound (EBUS) strain elastography can diagnose intrathoracic benign and malignant lymph nodes (LNs) by reflecting the relative stiffness of tissues. Due to strong subjectivity, it is difficult to give full play to the diagnostic efficiency of strain elastography. This study aims to use machine learning to automatically select high-quality and stable representative images from EBUS strain elastography videos.

Methods

LNs with qualified strain elastography videos from June 2019 to November 2019 were enrolled in the training and validation sets randomly at a quantity ratio of 3:1 to train an automatic image selection model using machine learning algorithm. The strain elastography videos in December 2019 were used as the test set, from which three representative images were selected for each LN by the model. Meanwhile, three experts and three trainees selected one representative image severally for each LN on the test set. Qualitative grading score and four quantitative methods were used to evaluate images above to assess the performance of the automatic image selection model.

Results

A total of 415 LNs were included in the training and validation sets and 91 LNs in the test set. Result of the qualitative grading score showed that there was no statistical difference between the three images selected by the machine learning model. Coefficient of variation (CV) values of the four quantitative methods in the machine learning group were all lower than the corresponding CV values in the expert and trainee groups, which demonstrated great stability of the machine learning model. Diagnostic performance analysis on the four quantitative methods showed that the diagnostic accuracies were range from 70.33% to 73.63% in the trainee group, 78.02% to 83.52% in the machine learning group, and 80.22% to 82.42% in the expert group. Moreover, there were no statistical differences in corresponding mean values of the four quantitative methods between the machine learning and expert groups (p >0.05).

Conclusion

The automatic image selection model established in this study can help select stable and high-quality representative images from EBUS strain elastography videos, which has great potential in the diagnosis of intrathoracic LNs.

Scoring model of convex probe endobronchial ultrasound multimodal imaging in differentiating benign and malignant lung lesions

Background

Convex probe endobronchial ultrasound images can reflect the morphology, blood flow status and stiffness of the lesions. Endobronchial ultrasound multimodal imaging has great value for the diagnosis of intrathoracic lymph nodes. This study aimed to analyze the application of endobronchial ultrasound multimodal imaging on lung lesions.

Methods

Patients undergoing endobronchial ultrasound-guided transbronchial needle aspiration in Shanghai Chest Hospital from July 2018 to December 2019 were retrospectively enrolled. Nine grayscale features (long and short axes, margin, shape, lobulation sign, echogenicity, necrosis, liquefaction, calcification, and air-bronchogram), blood flow volume and elastography five-score method were analyzed to explore the best diagnostic method. The gold standard for diagnosing lesions depends on the histological and cytopathological findings of endobronchial ultrasound-guided transbronchial needle aspiration, transthoracic biopsy, resected sample of lesions, microbiological examination or clinical follow-up of at least 6 months.

Results

Endobronchial ultrasound multimodal imaging of 97 malignant lung lesions and 19 benign lung lesions from 116 patients were analyzed. There were statistically significant differences in distinct margin, presence of lobulation sign, presence of necrosis, and elastography grading score 4–5 between malignant and benign lung lesions, among which presence of lobulation sign and elastography grading score 4–5 were independent predictors. A diagnostic scoring model was then constructed based on the above four features, and when two or more features were present, the sensitivity, specificity, positive predictive value, negative predictive value and accuracy for malignant lung lesions prediction were 92.78%, 57.89%, 91.84%, 61.11% and 87.07%, respectively.

Conclusions

The combination of endobronchial ultrasound grayscale and elastography has potential value for malignant and benign lung lesions differentiation. The diagnostic scoring model established in this study needs further validation to guide the malignant and benign diagnosis of lung lesions.