The role of endobronchial ultrasound in lung cancer diagnosis and staging: a comprehensive review

Diagnosis of Lung Cancer Using Endobronchial Ultrasonography Image Based on Multi-Scale Image and Multi-Feature Fusion Framework

Lung cancer is the leading cause of cancer-related deaths globally and ranks among the most common cancer types. Given its low overall five-year survival rate, early diagnosis and timely treatment are essential to improving patient outcomes. In recent years, advances in computer technology have enabled artificial intelligence to make groundbreaking progress in imaging-based lung cancer diagnosis. The primary aim of this study is to develop a computer-aided diagnosis (CAD) system for lung cancer using endobronchial ultrasonography (EBUS) images and deep learning algorithms to facilitate early detection and improve patient survival rates. We propose M3-Net, which is a multi-branch framework that integrates multiple features through an attention-based mechanism, enhancing diagnostic performance by providing more comprehensive information for lung cancer assessment. The framework was validated on a dataset of 95 patient cases, including 13 benign and 82 malignant cases. The dataset comprises 1140 EBUS images, with 540 images used for training, and 300 images each for the validation and test sets. The evaluation yielded the following results: accuracy of 0.76, F1-score of 0.75, AUC of 0.83, PPV of 0.80, NPV of 0.75, sensitivity of 0.72, and specificity of 0.80. These findings indicate that the proposed attention-based multi-feature fusion framework holds significant potential in assisting with lung cancer diagnosis.

Second opinion for pulmonary and pleural cytology is valuable for patient care

INTRODUCTION

Thoracic cytology can be challenging due to limited procured material or overlapping morphology between benign and malignant entities. In such cases, expert consultation might be sought. This study aimed to characterize all pulmonary and pleural cytology consult cases submitted to our practice and provide recommendations on approaching difficult cases.

MATERIALS AND METHODS

All thoracic (pulmonary and pleural) cytology cases submitted for expert consultation to the University of Michigan (MLabs) from 2013 to mid-2022 were reviewed. Cases where cytology was only part of a hematopathology or surgical pathology consult were excluded. Patient demographics, specimen location, procedure performed, referring diagnosis, and our diagnoses were recorded for each case. Diagnoses were categorized according to the Papanicolaou Society of Cytopathology recommendations for pulmonary and effusion cytology. Discordant diagnoses were stratified as major or minor. Data was analyzed using chi-square analysis and logistic models.

RESULTS

We received 784 thoracic cytology consult cases, including 530 exfoliative samples and 307 fine-needle aspirations. The most common anatomic locations sampled were the bronchial wall (n = 194, 23%), lung nodule (n = 322, 38%), and pleura (n = 296, 35%). 413 cases had a diagnostic discrepancy (48.3%), with 274 (66%) minor and 139 (34%) major discrepancies. By location, pleural effusion specimens had the highest probability of a discrepant diagnosis (P = 0.003). By specimen type, fine-needle aspiration samples were more likely to have a discrepant diagnosis (P = 0.09), approaching significance.

CONCLUSION

Nearly half of the thoracic cytology cases submitted for expert second opinion had diagnostic discrepancies. Consequently, consulting a tertiary medical care center with cytopathology expertise for challenging thoracic cytology diagnoses is beneficial.

Pitfalls in Respiratory Tract Cytopathology

BACKGROUND

Cytopathology is integral to the investigation and diagnosis of respiratory disease, and, in the last decade or so, transbronchial needle aspiration by endobronchial ultrasound has made possible diagnosis and staging of malignant thoracic tumours at a single procedure. In addition, interventional teams increasingly include cytopathologists and cytotechnologists who, by providing rapid onsite evaluation, ensure efficient sampling of intrathoracic targets with the ultimate goal of accurate diagnosis as well as sufficient material for comprehensive predictive testing. Nonetheless, "traditional" cytological investigations such as bronchial washings, brushings, and lavages are still carried out for investigation of both suspected neoplastic and non-neoplastic conditions, and all these procedures still produce specimens in which florid benign cells mimic malignancy, while truly neoplastic cells lurk quietly in the background. Furthermore, even when neoplasia is not suspected, issues in preparation and interpretation may render a final assessment inaccurate and, therefore, clinically unhelpful or misleading. In this overview, we have tried to adopt a format partly modelled on the passage of a specimen from clinical acquisition to laboratory endpoint, thus taking in potential pitfalls in communication, clinical interaction, transport, and clinic-based preparation, as well as in morphology, immunocytochemistry, and suitability for predictive testing. It is not exhaustive but highlights areas that may frequently be encountered or are part of our personal experience.

SUMMARY

The account highlights potential pitfalls in respiratory cytopathology at key stages of the process from acquisition to reporting and presents these in both flow diagram and tabular form. We hope this is useful for the increasingly collaborative roles of cytotechnologist and cytopathologist and their wider involvement in the clinical investigative teams.

KEY MESSAGES

Correct clinical and radiological information is crucially important and promotes the correct acquisition and processing of cytopathological specimens. Cross-discipline collaborative working ensures the most efficient use of the specimen such that diagnoses and predictive tests are performed on optimal material, reducing the potential for misinterpretation. Nonetheless, even with optimal material, morphological mimics and atypical antigen expression may mislead and render accurate diagnosis challenging.

Performance insights of endobronchial ultrasonography (EBUS) and mediastinoscopy for mediastinal lymph node staging in lung cancer

INTRODUCTION

Endobronchial Ultrasonography (EBUS) and mediastinoscopy are used for mediastinal lymph node staging in patients with suspected non-small cell lung carcinoma (NSCLC). In our hospital, confirmatory mediastinoscopy has been largely abandoned, which may reduce the number of surgical interventions and health care costs. This study provides insight into EBUS and mediastinoscopy performance in patients with proven NSCLC from January 2007 until January 2019.

METHODS

This is a single-centre, retrospective study, evaluating unforeseen N2 rates, negative predictive value and survival, providing insight into the diagnostic yield of EBUS and mediastinoscopy. Surgical lung resection with lymph node dissection was used as reference.

RESULTS

A total of 418 patients with proven NSCLC after lung resection (mean age: 66 years; 61 % male) and 118 patients who underwent mediastinoscopy, have been included in the study. The overall prevalence of N2 metastases after lung resection was 10.5 %. The percentage of unforeseen N2 cases after negative EBUS was 14.5 %, and 14.3 % after negative mediastinoscopy. Over the past nine years, none of the confirmatory mediastinoscopies were tumor positive after negative EBUS results. The median survival in patients with surgically confirmed N2 metastases was 33 months, compared to 23 months in patients with EBUS/mediastinoscopy-proven N2 metastases.

CONCLUSION

Despite optimisation of mediastinal staging procedures, it remains difficult to identify all patients with N2 metastases in the workup of NSCLC. In our institute, confirmatory mediastinoscopy has no added value after tumor-negative EBUS procedures, and has been abandoned as standard procedure.

A pragmatic application of endobronchial ultrasound-guided transbronchial needle aspiration: a single institution experience

Background

Endobronchial ultrasound-guided trans-bronchial needle aspiration (EBUS-TBNA) is minimally invasive technique used for diagnosis and/or staging of benign and malignant pulmonary and non-pulmonary disease. Previous studies have established the utility of EBUS-TBNA in narrowly defined indications and populations. In this pragmatic ‘real world’ study we have analysed the use of EBUS-TBNA for a variety of clinical presentations and its clinical application in conjunction with other invasive investigations.

Methods

All EBUS-TBNA procedures performed at Sir Charles Gardiner Hospital in 2012–2014 were reviewed retrospectively, using relevant hospital databases.

Results

A total of 327 patients underwent 337 EBUS-TBNA procedures. EBUS-TBNA procedures were used to diagnose a wide spectrum of benign and malignant conditions. The main application was in the diagnosis and staging of malignant conditions (70.6%), and in the diagnosis of benign conditions such as sarcoidosis 40 (12.2%), and silicoanthracosis 17 (5.2%). EBUS-TBNA was sufficient to diagnose and stage the disease as a single stand-alone invasive procedure in 191 (59.2%) patients. EBUS-TBNA was the final invasive procedure undertaken in 283 (87.6%) patients. Only 13.3% of non small cell lung cancer (NSCLC) patients who had EBUS-TBNA as a first investigation required multiple procedures compared to 51.1% of all NSCLC patients undergoing EBUS-TBNA. Overall sensitivity, specificity, NPV and diagnostic accuracy for EBUS-TBNA were 89.7, 100, 85.1 and 89.9%, respectively and three minor complications (0.9%) occurred as a result of the procedure.

Conclusions

EBUS-TBNA was undertaken for a wide variety of clinical conditions. Good diagnostic accuracy and safety profiles were demonstrated for the procedure, supporting its application as a first line investigation in the diagnosis and/or staging of a range of malignant and benign conditions. Our study was unique in its documentation of the use of EBUS-TBNA in a real-world setting in conjunction with other invasive modalities. EBUS-TBNA was utilised as a stand alone invasive procedure in more than half of the patients. Importantly, in NSCLC, when EBUS-TBNA was performed as primary diagnostic and staging investigation, less patients underwent subsequent invasive procedures.

Lung Cancer

Lung cancer is the world's leading cause of cancer death. Screening for lung cancer by low-dose computed tomography improves mortality. Various modalities exist for diagnosis and staging. Treatment is determined by subtype and stage of cancer; there are several personalized therapies that did not exist just a few years ago. Caring for the patient with lung cancer is a complex task. This review provides a broad outline of this disease, helping clinicians identify such patients and familiarizing them with lung cancer care options, so they are better equipped to guide their patients along this challenging journey.

Endobronchial Ultrasound-guided Transbronchial Needle Aspiration With a 19-G Needle Device

BACKGROUND

Endobronchial ultrasound (EBUS)-guided transbronchial needle aspiration is a well-established first-line minimally invasive modality for mediastinal lymph node sampling. Although results are excellent overall, the technique underperforms in certain situations. We aimed to describe our results using a new 19-G EBUS-guided transbronchial needle aspiration device to determine safety and feasibility of this approach.

METHODS

We completed a retrospective chart review of all cases performed to the time of data analysis at each of 3 study sites.

RESULTS

A total of 165 procedures were performed with a total of 297 individual lymph nodes or lesions sampled with the 19-G device by 10 bronchoscopists. Relatively large targets were selected for sampling with the device (mean lymph node size: 20.4 mm; lung lesions: 33.5 mm). A specific diagnosis was obtained in 77.3% of cases with an additional 13.6% of cases with benign lymphocytes, for a procedural adequacy rate of 90.9%. Procedure sample adequacy was 88.6% in suspected malignant cases, 91.0% in suspected sarcoidosis/lymphadenopathy cases, and 85.7% of cases with suspected lymphoma. On a per-node basis, a specific diagnosis was noted in 191/280 (68.2%) of samples, with an additional 61 showing benign lymphocytes for a per-node sample adequacy rate of 90%. One case (0.6%) of intraprocedure bleeding was noted.

CONCLUSIONS

A new flexible 19-G EBUS needle was successfully and safely applied in a large patient cohort for sampling of lung and enlarged mediastinal lesions with high diagnostic rates across clinical indications.

Bronchoscopy: Diagnostic and Therapeutic for Non-Small Cell Lung Cancer

The bronchoscope has gone through much advancement from its origin as a thin metal tube. It has become a highly sophisticated tool for clinicians. Both rigid and the flexible bronchoscopes are invaluable in the diagnosis and treatment of non-small cell lung cancer. Treatment of this disease process hinges on accurate diagnosis and lymph node staging. Technologies, such as endobronchial ultrasound, navigational bronchoscopy, and autofluorescence, have improved efficacy of endobronchial diagnosis and sample collection. If a patient is not a candidate for surgery and has a complication from a centrally located mass, the bronchoscope has been used to deliver palliative therapies.

The Use of Endobronchial Ultrasound in the Diagnosis of Subacute Pulmonary Histoplasmosis

Objective. Endobronchial ultrasound (EBUS) utility in diagnosis in malignant and granulomatous mediastinal disease has been well demonstrated. We propose to examine the role of EBUS transbronchial needle aspiration (EBUS-TBNA) in the diagnosis of subacute pulmonary histoplasmosis (SPH) with mediastinal lymphadenopathy in an area where histoplasmosis is endemic. Methods. A retrospective review was performed in a single academic institution between 2009 and 2012 of patients referred for EBUS-TBNA who had radiographic imaging and clinical symptomatology suspicious for SPH. Seven patients were reviewed. TBNA results showing granulomatous disease with areas of necrosis in the appropriate clinical setting were considered to be adequate for the diagnosis of SPH when alternative diagnosis was excluded. Patients underwent further clinical follow-up of 12 months to determine the final diagnosis. Results. All seven patients were felt to have SPH diagnosis reached by a combination of clinical presentation, EBUS-TBNA results, fungal serologies, and antigen testing. None of the patients needed further invasive procedures. Conclusions. EBUS-TBNA is a minimally invasive tool that can be used to support a diagnosis of SPH in patients with a high degree of clinical suspicion. EBUS-TBNA should be considered as an adjunctive diagnostic procedure for patients with SPH in an appropriate clinical setting.

The Natural Course of Endobronchial Inflammatory Polyps as a Complication after Endobronchial Ultrasound-Guided Transbronchial Needle Aspiration

We presented a case of unusual endobronchial inflammatory polyps as a complication following endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA) in a patient with tuberculous lymphadenitis. EBUS-TBNA of the right hilar lymph node was performed in a 29-year-old, previously healthy man. The patient was confirmed with tuberculous lymphadenitis and received antituberculosis medication over the course of 6 months. Chest computed tomography, after 6 months of antituberculosis therapy following the EBUS-TBNA showed nodular bronchial wall thickening of the right main bronchus. Histological and microbiological examinations revealed inflammatory polyps. After 7 months, the inflammatory polyps regressed almost completely without need for removal.

Endobronchial ultrasound-guided transbronchial needle aspiration in lung cancer diagnosis and staging

Lung cancer is one of the most prevalent types of cancer in the world. A complete diagnosis of lung cancer involves tissue acquisition for pathological subtype, molecular diagnosis and accurate staging of the disease to guide appropriate therapy. Real-time endobronchial ultrasound transbronchial needle aspiration (EBUS-TBNA) is minimally invasive and relatively safe procedure, which can be done on an outpatient basis under moderate sedation. EBUS-TBNA has been shown to be a safe modality to obtain tissue for diagnosis, staging and molecular profiling in lung cancer. EBUS-TBNA stands out in comparison with other modalities for tissue acquisition in lung cancer. EBUS-TBNA performed with the patient under moderate sedation yields sufficient tissue for sequential molecular analysis in most patients. In this review, we describe the role of EBUS-TBNA in various aspects of diagnosis and staging of lung cancer in the present era along with its future aspects.

New-onset malignant pleural effusion after abscess formation of a subcarinal lymph node associated with endobronchial ultrasound-guided transbronchial needle aspiration

We present a case of an unusual infectious complication of a ruptured mediastinal abscess after endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA), which led to malignant pleural effusion in a patient with stage IIIA non-small-cell lung cancer. EBUS-TBNA was performed in a 48-year-old previously healthy male, and a mediastinal abscess developed at 4 days post-procedure. Video-assisted thoracoscopic surgery was performed for debridement and drainage, and the intraoperative findings revealed a large volume pleural effusion that was not detected on the initial radiographic evaluation. Malignant cells were unexpectedly detected in the aspirated pleural fluid, which was possibly due to increased pleural permeability and transport of malignant cells originating in a ruptured subcarinal lymph node from the mediastinum to the pleural space. Hence, the patient was confirmed to have squamous cell lung carcinoma with malignant pleural effusion and his TNM staging was changed from stage IIIA to IV.

Surgical management of lung cancer

Surgery serves an important role in the diagnosis, staging, and definitive management of non-small cell lung cancer (NSCLC). Resection is the primary mode of treatment for stage I and II NSCLC and an important component of the multimodality approach to stage IIIA disease. Standard resections include removal of the lobe involved with tumor and systematic evaluation of ipsilateral hilar and mediastinal lymph nodes. For early stage disease the evolving surgical treatment goals are aimed at decreasing morbidity and mortality through less invasive approaches including video-assisted thoracoscopic surgery and robotic approaches, and potentially decreasing the volume of lung removed for select patients with well-staged small peripheral tumors. For patients with locally advanced disease, ongoing research is focused on appropriately identifying patients who will most benefit from the addition of surgery to a multimodality regime and safely integrating resection with chemotherapy and radiotherapy.

Advanced bronchoscopic techniques in diagnosis and staging of lung cancer

The role of advanced brochoscopic diagnostic techniques in detection and staging of lung cancer has steeply increased in recent years. Bronchoscopic imaging techniques became widely available and easy to use. Technical improvement led to merging in technologies making autofluorescence or narrow band imaging incorporated into one bronchoscope. New tools, such as autofluorescence imagining (AFI), narrow band imaging (NBI) or fuji intelligent chromo endoscopy (FICE), found their place in respiratory endoscopy suites. Development of endobronchial ultrasound (EBUS) improved minimally invasive mediastinal staging and diagnosis of peripheral lung lesions. Linear EBUS proven to be complementary to mediastinoscopy. This technique is now available in almost all high volume centers performing bronchoscopy. Radial EBUS with mini-probes and guiding sheaths provides accurate diagnosis of peripheral pulmonary lesions. Combining EBUS guided procedures with rapid on site cytology (ROSE) increases diagnostic yield even more. Electromagnetic navigation technology (EMN) is also widely used for diagnosis of peripheral lesions. Future development will certainly lead to new improvements in technology and creation of new sophisticated tools for research in respiratory endoscopy. Broncho-microscopy, alveoloscopy, optical coherence tomography are some of the new research techniques emerging for rapid technological development.

[A comparative study on the diagnosis and staging of lung cancer between mediastinoscopy and EBUS-TBNA]

BACKGROUND

Endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA) has been gradually universal application, but its value in the preoperative staging of lung cancer and mediastinal mass biopsy remains to be explored. The aim of this study is to evaluate the value of clinical application between mediastinoscopy and EBUS-TBNA, desiring to provide an objective basis for the rational choice applications.

METHODS

Between July 2009 and December 2012, mediastinoscopy patients with 361 cases accepted biopsy, including 199 cases of lung cancer and 162 cases of mediastinal mass of unknown origin, EBUS-TBNA patients with 348 cases accepted biopsy, including 216 cases of lung cancer and 132 cases of mediastinal mass. Comparing the diagnostic results and related indicators of two methods, this article analyzed the clinical value both the preoperative staging of lung cancer and the diagnosis of mediastinal mass.

RESULTS

Taking pathology diagnosis as the gold standard, the accuracy, sensitivity and specificity of mediastinoscopy and EBUS-TBNA are 98.33%, 98.17%, 100% and 90.80%, 90.00%, 100%. Two techniques in the diagnosis and staging of lung cancer have not statistically significant (P>0.05), but in the diagnosis of mediastinal mass have statistical significance (P<0.05).

CONCLUSIONS

Mediastinoscopy and EBUS-TBNA have a similar role in the diagnosis and staging of lung cancer; but mediastinoscopy for mediastinal mass is superior to EBUS-TBNA.