Implementation of endoscopic ultrasound for lung cancer staging

A deep learning-based system for mediastinum station localization in linear EUS (with video)

Background and Objectives

EUS is a crucial diagnostic and therapeutic method for many anatomical regions, especially in the evaluation of mediastinal diseases and related pathologies. Rapidly finding the standard stations is the key to achieving efficient and complete mediastinal EUS imaging. However, it requires substantial technical skills and extensive knowledge of mediastinal anatomy. We constructed a system, named EUS-MPS (EUS-mediastinal position system), for real-time mediastinal EUS station recognition.

Methods

The standard scanning of mediastinum EUS was divided into 7 stations. There were 33 010 images in mediastinum EUS examination collected to construct a station classification model. Then, we used 151 videos clips for video validation and used 1212 EUS images from 2 other hospitals for external validation. An independent data set containing 230 EUS images was applied for the man-machine contest. We conducted a crossover study to evaluate the effectiveness of this system in reducing the difficulty of mediastinal ultrasound image interpretation.

Results

For station classification, the model achieved an accuracy of 90.49% in image validation and 83.80% in video validation. At external validation, the models achieved 89.85% accuracy. In the man-machine contest, the model achieved an accuracy of 84.78%, which was comparable to that of expert (83.91%). The accuracy of the trainees' station recognition was significantly improved in the crossover study, with an increase of 13.26% (95% confidence interval, 11.04%-15.48%; P < 0.05).

Conclusions

This deep learning-based system shows great performance in mediastinum station localization, having the potential to play an important role in shortening the learning curve and establishing standard mediastinal scanning in the future.

Developing a simulation-based training curriculum in transesophageal ultrasound with the use of the endobronchial ultrasound-endoscope

There is an increasing need to focus on how best to train respiratory physicians to perform EUS with bronchoscope-guided fine-needle aspiration biopsy (EUS-B-FNA). At current, training is mostly performed in the clinical environment under expert supervision; however, the advent of simulation-based education now provides a low-risk setting for novice trainees to learn and practice basic endosonography skills from identifying and understanding normal anatomy as well as pathology, maneuvering of endoscope, interpretation of images, and mastering of sampling techniques. In this descriptive educational paper, we used a six-step approach as a framework to describe the development of a structured training program combining EUS-B-FNA with the already well-established certification training program in endobronchial ultrasound transbronchial needle aspiration. This comprehensive training curriculum includes a theoretical course to achieve foundational knowledge, followed by simulation-based training until mastery standards are met, and supervised clinical apprenticeship. All steps should end with an objective assessment to achieve certification. This systematic development will hopefully encourage endosonography leaders and educators to collaborate and implement an evidence-based comprehensive endosonography curriculum that aims to provide the trainee with the essential EUS-B competencies to ensure that lung cancer patients are diagnosed and staged correctly.

Mediastinal lymph node staging for lung cancer

Mediastinal lymph node staging is crucial in deciding the treatment strategy for lung carcinoma. The diagnosis rate of computed tomography is not high; however, it is a standard examination. Although the contrast computed tomography is necessary for an accurate diagnosis, images from the positron emission tomography are excellent, and these two technologies are independent and complementary. Positron emission tomography has a disadvantage of false positives and false negatives, but it should also be used in cases where lymph node diameters are 1 cm or more. However, image-based diagnostic methods are not an alternative to histological examination. The results of a transbronchial needle biopsy are extremely dependent on the inspection method, the diagnostic ability of the physician, and the staging of the case. The transesophageal ultrasound endoscope is useful for reaching parts inaccessible by a mediastinoscope. Although its employment requires technical training, it is becoming popular as a minimally invasive method of obtaining cell and the tissue samples. A thoracoscopic biopsy is considered as a last resort for mediastinal lymph node diagnosis. Carefully-chosen invasive procedures are necessary to diagnose swollen lymph nodes. Although mediastinoscopy is still considered as the gold standard, most procedures will be replaced by a comparatively minimally invasive method in the future.

When trainees reach competency in performing endoscopic ultrasound: a systematic review

Background/Study aim The American Society for Gastrointestinal Endoscopy (ASGE) recommends that trainees complete 150 endoscopic ultrasound (EUS) procedures before assessing competency. However, this recommendation is largely based on limited evidence and expert opinion. With new evidence suggesting that this historical threshold is underestimating training requirements, we evaluated the learning curve for achieving competency in EUS. Patients/Materials and methods Two investigators independently searched MEDLINE for full-text citations assessing the learning curve for achieving competency in EUS in the period 1946 to 25 March 2016. A learning curve was defined as either a tabulated or graphic representation of competency as a function of increasing EUS experience. Results Eight studies assessing 28 trainees and 7051 EUS procedures were included. When stratifying studies based on procedural indication: three studies assessed competency in evaluating mucosal lesions, three studies assessed competency in EUS fine-needle aspiration (EUS-FNA), and two studies assessed comprehensive competency. Among studies assessing mucosal lesion T-staging accuracy, competency was achieved by 65 to 231 procedures. Among studies assessing EUS-FNA, competency was achieved by 30 to 40 procedures. Among the two studies assessing comprehensive competency in EUS, competency was not achieved in either study across all trainees. Only four of 17 trainees reached competency by 225 to 295 EUS procedures. Conclusion As EUS competency assessment has evolved to more closely reflect independent clinical practice, the number of procedures required to achieve competency has risen well above ASGE recommendations. Advanced endoscopy training programs and specialty societies need to re-assess the structure of EUS training.

Accuracy and consequences of same-day, invasive lung cancer workup - a retrospective study in patients treated with surgical resection

BACKGROUND

Though widely used, little is known about accuracy and efficacy of same-day, invasive workup of suspected lung cancer.

OBJECTIVE

To evaluate the accuracy and efficacy of same-day, invasive lung cancer workup (diagnosis and mediastinal staging), and to identify differences between patients without (Group A) or with (Group B) need for resampling.

METHODS

A retrospective study was performed on all consecutive patients referred for surgical treatment for localised lung cancer after invasive diagnostic and staging workup at our unit. Data were extracted from electronic medical files. Surgical specimens served as gold standard for correct diagnosis and stage.

RESULTS

A total of 129 patients (peripheral lesion: 84%; mediastinal staging: 97%) were included. After same-day, invasive workup, 71% had no need for further invasive workup (Group A), while 29% had (Group B). Group A differed significantly from Group B in fewer invasive tests, fewer days from referral to surgery, and lower pneumothorax incidence, while no differences were observed in diagnostic accuracy, cancer subtype, tumour size, tumour stage, peripheral lesion, nodal involvement, gender, or presence of chronic obstructive pulmonary disease. Tumour located in right upper lobe was associated with need for resampling.

DISCUSSION

Our retrospective study suggests that same-day, invasive workup for lung cancer is safe, accurate, and efficacious in reducing time to therapy, even in patients with small lesions and low tumour burden.

Endosonography for mediastinal disease: esophageal ultrasound vs. endobronchial ultrasound

BACKGROUND AND STUDY AIMS

One can approach mediastinal pathology via esophageal ultrasound (EUS) and/or endobronchial ultrasound (EBUS). It has been suggested that EUS is better tolerated by patients. If so, EUS might be the procedure of choice when suspect lesions are accessible via EUS. We studied procedural characteristics of EUS with fine needle aspiration (EUS-FNA) and EBUS with transbronchial needle aspiration (EBUS-TBNA) to see how they differed.

PATIENTS AND METHODS

Retrospective review of consecutive EBUS and EUS procedures performed on patients over nine months. One hundred fifty-five procedures were analyzed (61 EUS, 73 EBUS, 21 EUS + EBUS). For EUS, EBUS, and EUS + EBUS, 1.4, 2.0 and 2.5 sites (mean) were sampled, respectively. EUS required approximately one-half of the time of EBUS or the combined procedures; 13.1 vs. 24.1 and 26.9 min, respectively (P < 0.0001 for EUS vs. both EBUS and EUS + EBUS). Sedation dosing was statistically lower for EUS and not significantly different between EBUS and the combined approach. EUS also involved lower oxygen requirements and shorter time to discharge. Because fewer mean sites were sampled with EUS than with EBUS or the combined procedure, we performed analysis restricted to procedures that involved sampling of ≤ 2 sites to determine whether approach-related differences in procedure characteristics were preserved. There were 56 such EUS procedures and 52 such EBUS procedures. EUS remained significantly faster and required less patient sedation.

CONCLUSIONS

EUS involved statistically significant economies of time and sedation. This has implications with respect to safety and productivity. When applicable, EUS is the procedure of choice.

Staging of lung cancer: the role of noninvasive, minimally invasive and invasive techniques

Accurate staging and restaging of primary tumour and mediastinal nodes in patients with lung cancer is of significant importance. For primary tumours, computed tomography (CT) scans of the chest are recommended. Positron emission tomography (PET) imaging should be used in patients with curative intent treatment to evaluate metastatic disease. Diagnosis of the primary tumour should be performed using bronchoscopy or CT-guided transthoracic needle aspiration. In patients with enlarged mediastinal nodes and no distant metastasis, invasive staging of the mediastinum is required. For suspicious N2 or N3 disease, endoscopic needle techniques, such as endobronchial ultrasound and transbronchial needle aspiration, oesophageal ultrasound and fine needle aspiration, or a combination of both, are preferred to any surgical staging technique. In cases of suspicious nodes and negative results using needle aspiration techniques, invasive surgical staging using mediastinoscopy or video-assisted thoracic surgery should be performed. In central tumours or N1 nodes, preoperative invasive staging is indicated.Restaging after induction therapy remains a controversial topic. Today, neither CT, PET nor PET/CT scans are accurate enough to make final further therapeutic decisions for mediastinal nodal involvement. An invasive technique providing cytohistological information is still recommended.

Mediastinal staging for lung cancer

Staging of the mediastinal and hilar lymph nodes plays a crucial role in identifying the best treatment option for patients with confirmed or suspected lung cancer and, in many cases, can simultaneously confirm a diagnosis of cancer. Noninvasive modalities, such as computed tomography (CT), positron emission tomography (PET) and PET-CT, are an important first step in this assessment. Ultimately, invasive staging is frequently required to confirm or rule out the presence of metastatic disease within the lymph nodes. The present focused review describes and compares noninvasive and invasive modalities for mediastinal staging in lung cancer.

Complication rate of endosonography (endobronchial and endoscopic ultrasound): a systematic review

BACKGROUND

Endosonography [endoscopic ultrasound (EUS)-guided fine needle aspiration and endobronchial ultrasound (EBUS)-guided transbronchial needle aspiration] is increasingly used for lung cancer staging and the assessment of sarcoidosis. Serious adverse events (SAE) have been reported in case reports, but the true incidence of complications is yet unknown.

OBJECTIVES

To assess the rate of SAE related to endosonography and to investigate associated risk factors.

MATERIALS AND METHODS

PubMed, EMBASE and Cochrane libraries were searched for eligible references up to April 2012 and these included studies reporting on linear EUS or EBUS for the analysis of mediastinal/hilar nodal or central intrapulmonary lesions. Case series describing complications were excluded. Reported complications were classified into SAE or minor adverse events (AE).

RESULTS

190 studies met the inclusion criteria. Information on follow-up was missing in half of the studies. In 16,181 patients, 23 SAE (0.14%) and 35 AE (0.22%) were reported. No mortality was observed. SAE were more frequent in patients investigated with EUS (0.30%) than in those investigated with EBUS (0.05%). Infectious SAE were most prevalent (0.07%) and predominantly occurred in patients with cystic lesions and sarcoidosis. In lung cancer patients, complications were rare.

DISCUSSION

Endosonography for intrathoracic nodal assessment seems safe for lung cancer patients and mortality has not been reported. For cystic lesions and sarcoidosis, there may be a small, but nonnegligible risk of infectious complications. The true incidence of SAE might be higher as accurate documentation of complications is missing in most studies.

Invasive mediastinal staging: endobronchial ultrasound, endoscopic ultrasound, and mediastinoscopy

Accurate mediastinal staging is essential to determining the optimal therapeutic strategy for many patients with lung cancer. Computed tomography and positron emission tomography are first steps, but frequently tissue sampling is recommended to confirm the radiographic findings. Mediastinoscopy has been the gold standard for thirty years, but the new technologies of esophageal endoscopic ultrasound and endobronchial ultrasound provide a less invasive method for biopsy. These techniques enable needle aspiration sampling of nearly all mediastinal and hilar lymph nodes, and experience with them is now sufficiently mature to conclude that they can be equivalent if not preferable to mediastinoscopy. The keys to achieving accurate results are skillful execution combined with sound clinical judgment regarding when to use which techniques. Patients with lung cancer are best served by clinicians experienced with all three methods for invasive mediastinal staging.

Methods for staging non-small cell lung cancer: Diagnosis and management of lung cancer, 3rd ed: American College of Chest Physicians evidence-based clinical practice guidelines

BACKGROUND

Correctly staging lung cancer is important because the treatment options and prognosis differ significantly by stage. Several noninvasive imaging studies and invasive tests are available. Understanding the accuracy, advantages, and disadvantages of the available methods for staging non-small cell lung cancer is critical to decision-making.

METHODS

Test accuracies for the available staging studies were updated from the second iteration of the American College of Chest Physicians Lung Cancer Guidelines. Systematic searches of the MEDLINE database were performed up to June 2012 with the inclusion of selected meta-analyses, practice guidelines, and reviews. Study designs and results are summarized in evidence tables.

RESULTS

The sensitivity and specificity of CT scanning for identifying mediastinal lymph node metastasis were approximately 55% and 81%, respectively, confirming that CT scanning has limited ability either to rule in or exclude mediastinal metastasis. For PET scanning, estimates of sensitivity and specificity for identifying mediastinal metastasis were approximately 77% and 86%, respectively. These findings demonstrate that PET scanning is more accurate than CT scanning, but tissue biopsy is still required to confirm PET scan findings. The needle techniques endobronchial ultrasound-needle aspiration, endoscopic ultrasound-needle aspiration, and combined endobronchial ultrasound/endoscopic ultrasound-needle aspiration have sensitivities of approximately 89%, 89%, and 91%, respectively. In direct comparison with surgical staging, needle techniques have emerged as the best first diagnostic tools to obtain tissue. Based on randomized controlled trials, PET or PET-CT scanning is recommended for staging and to detect unsuspected metastatic disease and avoid noncurative resections.

CONCLUSIONS

Since the last iteration of the staging guidelines, PET scanning has assumed a more prominent role both in its use prior to surgery and when evaluating for metastatic disease. Minimally invasive needle techniques to stage the mediastinum have become increasingly accepted and are the tests of first choice to confirm mediastinal disease in accessible lymph node stations. If negative, these needle techniques should be followed by surgical biopsy. All abnormal scans should be confirmed by tissue biopsy (by whatever method is available) to ensure accurate staging. Evidence suggests that more complete staging improves patient outcomes.

Involved field radiotherapy for locally advanced non-small cell lung cancer: isolated mediastinal nodal relapse

The current standard of care for locally advanced inoperable non-small cell lung cancer is high dose radiotherapy with concurrent chemotherapy. We report on a patient with stage IIIA NSCLC treated with concurrent chemoradiotherapy on the primary tumor and the 18-fluorodeoxyglucose positron emission tomography ((18)FDG-PET) positive hilar and mediastinal lymph nodes. Six months after treatment this patient developed a single isolated contralateral mediastinal nodal relapse outside but in the proximity of the irradiated target volume. This patient was successfully re-irradiated to this isolated nodal relapse after reconstruction of the dose given to the localisation of this regional recurrence. This case describes the clinical problem of a regional recurrence after involved field radiotherapy that occasionally occurs. A possible explanation for those regional recurrences is an under staging of extension of the disease because the time-interval between the staging (18)FDG-PET-CT scan and the start of the irradiation was too long. If the time-interval is 4 weeks or more, we strongly recommend a new (18)FDG-PET-CT because of the possibility of upstaging of the disease.

The evolution of endoscopic ultrasound: improved imaging, higher accuracy for fine needle aspiration and the reality of endoscopic ultrasound-guided interventions

PURPOSE OF REVIEW

Endoscopic ultrasound (EUS) is one of the fastest growing areas within gastrointestinal endoscopy. Although the growth in the United States has been steady, EUS is exploding in areas of Asia and Eastern Europe. As utilization of EUS is increasing, so is the evolution of the discipline itself. As a result, it is critically important to periodically review the current state of the art. From its inception, EUS has been primarily utilized for staging cancer, assessment of pancreatic disease and evaluation of submucosal lesions.

RECENT FINDINGS

EUS has evolved and is now dominated by the application of EUS-guided fine needle aspiration cytology (EUS-FNA), and the newest emerging application is EUS-guided interventions. The recent literature is a reflection of these trends, with some articles devoted to the standard applications for EUS, but most of the emphasis is on EUS-FNA and EUS-guided interventions.

SUMMARY

This current review has important clinical implications, as it contains new information on standard applications for endoscopic ultrasound that should be adopted into clinical practice and also provides a glimpse into the future through EUS-guided interventions.