Radial-EBUS and virtual bronchoscopy planner for peripheral lung cancer diagnosis: How it became the first-line endoscopic procedure

[Clinical Application of Robotic Assisted Bronchoscopy in Peripheral Pulmonary Nodule Biopsy]

With the popularization of chest computed tomography (CT) lung cancer screening, the detection rate of peripheral pulmonary nodules is increasing day by day. Some patients could make clear diagnoses and receive early treatment by obtaining biopsy specimens. Transbronchial lung biopsy (TBLB) is one of the non-surgical biopsy methods for peripheral pulmonary nodules, which has less trauma and lower incidence of complications compared to percutaneous thoracic needle biopsy (PTNB). However, the diagnostic rate of TBLB is about 70%, which is still inferior to that of PTNB, which is about 90%. Since 2018, robot assisted bronchoscopy systems have been applied in clinical practice. This article reviews their application in further improving the diagnostic rate of peripheral pulmonary nodules by TBLB.
.

Detection of Tumor DNA in Bronchoscopic Fluids in Peripheral NSCLC: A Proof-of-Concept Study

Introduction

DNA genotyping from plasma is a useful tool for molecular characterization of NSCLC. Nevertheless, the false-negative rate justifies the development of methods with higher sensitivity, especially in difficult-to-reach peripheral lung tumors.

Methods

We aimed at comparing molecular analysis from the supernatant of guide sheath flush fluid collected during radial-EndoBronchial UltraSound (r-EBUS) bronchoscopy with plasma sampling and tumor biopsies in patients with peripheral NSCLC. The DNA was genotyped using high-throughput sequencing or the COBAS mutation test. There were 65 patients with peripheral lung tumors subjected to concomitant sampling of guide sheath flush supernatant, plasma tumor DNA, and tumor biopsy and cytology using r-EBUS. There were 33 patients (including 24 newly diagnosed with having NSCLC) with an identifiable tumor mutation in the primary lesion selected for the comparative analysis.

Results

Guide sheath flush-based genotyping yielded a mutation detection rate of 61.8% (17 of 24 mutated EGFR, one of two ERBB2, one of one KRAS, one of one MAP2K, one of four MET, and zero of one STK11), compared with 33% in plasma-based genotyping (p = 0.0151). Furthermore, in eight of 34 r-EBUS without tumor cells on microscopic examination, we were able to detect the mutation in four paired guide sheath flush supernatant, compared with only two in paired plasma.

Conclusion

The detection of tumor DNA in the supernatant of guide sheath flush fluid collected during r-EBUS bronchoscopy represents a sensitive and complementary method for genotyping NSCLC.

[Advanced bronchoscopic techniques for the diagnosis of peripheral lung nodule]

The endoscopic diagnosis of peripheral lung nodules is a challenging aspect of oncological practice. More often than not inaccessible by traditional endoscopy, these nodules necessitate multiple imagery tests, as well as diagnostic surgery for benign lesions. Even though transthoracic ultrasonography has a high diagnostic yield, a sizeable complication rate renders it suboptimal. Over recent years, a number of safe and accurate navigational bronchoscopic procedures have been developed. In this first part, we provide an overview of the bronchoscopic techniques currently applied for the excision and diagnostic analysis of peripheral lung nodules; emphasis is laid on electromagnetic navigation bronchoscopy and the association of virtual bronchoscopy planner with radial endobronchial ultrasound. We conclude by considering recent innovations, notably robotic bronchoscopy.

Real-World Impact of Robotic-Assisted Bronchoscopy on the Staging and Diagnosis of Lung Cancer: The Shape of Current and Potential Opportunities

The approach to peripheral pulmonary lesions (PPL) has been evolving continuously. Advanced bronchoscopic navigational techniques have improved the airway-based approaches to these lesions. Robotic Assisted Bronchoscopy (RAB) can be considered the current pinnacle of this evolution; allowing for a safer approach to sampling lesions previously considered outside of bronchoscopic reach. We present a comprehensive review of the changing epidemiology of lung cancer and the importance of early tissue sampling, the evolution of sampling and navigational bronchoscopic techniques, technical considerations and evidence pertaining to the use of RAB, and adjunct techniques in the diagnosis of lung cancer. Complications and future applications of RAB are also discussed.

Distinguishing bronchoscopically observed anatomical positions of airway under by convolutional neural network

Background

Artificial intelligence (AI) technology has been used for finding lesions via gastrointestinal endoscopy. However, there were few AI-associated studies that discuss bronchoscopy.

Objectives

To use convolutional neural network (CNN) to recognize the observed anatomical positions of the airway under bronchoscopy.

Design

We designed the study by comparing the imaging data of patients undergoing bronchoscopy from March 2022 to October 2022 by using EfficientNet (one of the CNNs) and U-Net.

Methods

Based on the inclusion and exclusion criteria, 1527 clear images of normal anatomical positions of the airways from 200 patients were used for training, and 475 clear images from 72 patients were utilized for validation. Further, 20 bronchoscopic videos of examination procedures in another 20 patients with normal airway structures were used to extract the bronchoscopic images of normal anatomical positions to evaluate the accuracy for the model. Finally, 21 respiratory doctors were enrolled for the test of recognizing corrected anatomical positions using the validating datasets.

Results

In all, 1527 bronchoscopic images of 200 patients with nine anatomical positions of the airway, including carina, right main bronchus, right upper lobe bronchus, right intermediate bronchus, right middle lobe bronchus, right lower lobe bronchus, left main bronchus, left upper lobe bronchus, and left lower lobe bronchus, were used for supervised machine learning and training, and 475 clear bronchoscopic images of 72 patients were used for validation. The mean accuracy of recognizing these 9 positions was 91% (carina: 98%, right main bronchus: 98%, right intermediate bronchus: 90%, right upper lobe bronchus: 91%, right middle lobe bronchus 92%, right lower lobe bronchus: 83%, left main bronchus: 89%, left upper bronchus: 91%, left lower bronchus: 76%). The area under the curves for these nine positions were >0.98. In addition, the accuracy of extracting the images via the video by the trained model was 94.7%. We also conducted a deep learning study to segment 10 segment bronchi in right lung, and 8 segment bronchi in Left lung. Because of the problem of radial depth, only segment bronchi distributions below right upper bronchus and right middle bronchus could be correctly recognized. The accuracy of recognizing was 84.33 ± 7.52% by doctors receiving interventional pulmonology education in our hospital over 6 months.

Conclusion

Our study proved that AI technology can be used to distinguish the normal anatomical positions of the airway, and the model we trained could extract the corrected images via the video to help standardize data collection and control quality.

Beyond the Frontline: A Triple-Line Approach of Thoracic Surgeons in Lung Cancer Management-State of the Art

Non-small cell lung cancer (NSCLC) is now described as an extremely heterogeneous disease in its clinical presentation, histology, molecular characteristics, and patient conditions. Over the past 20 years, the management of lung cancer has evolved with positive results. Immune checkpoint inhibitors have revolutionized the treatment landscape for NSCLC in both metastatic and locally advanced stages. The identification of molecular alterations in NSCLC has also allowed the development of targeted therapies, which provide better outcomes than chemotherapy in selected patients. However, patients usually develop acquired resistance to these treatments. On the other hand, thoracic surgery has progressed thanks to minimally invasive procedures, pre-habilitation and enhanced recovery after surgery. Moreover, within thoracic surgery, precision surgery considers the patient and his/her disease in their entirety to offer the best oncologic strategy. Surgeons support patients from pre-operative rehabilitation to surgery and beyond. They are involved in post-treatment follow-up and lung cancer recurrence. When conventional therapies are no longer effective, salvage surgery can be performed on selected patients.

Proposal of a novel pipeline involving precise bronchoscopy of distal peripheral pulmonary lesions for genetic testing

Next-generation sequencing (NGS) has become increasingly more important for lung cancer management. We now expect biopsies to be sensitive, safe, and yielding sufficient samples for NGS. In this study, we propose ultraselective biopsy (USB) with sample volume adjustment (SVA) as a novel method that integrates an ultrathin bronchoscope, radial probe endobronchial ultrasound, and the direct oblique method for ultraselective navigation, and adjustment of sample volume for NGS. Our purpose was to estimate the diagnostic potential and the applicability of USB-SVA for amplicon-based NGS analysis. The diagnostic yield of bronchoscopy in forty-nine patients with malignant peripheral pulmonary lesions (PPLs) was retrospectively analyzed, and amplicon-based NGS analysis was performed on samples from some patients using USB. The diagnostic yields of distal PPLs in the USB group were significantly higher than those in the non-USB group (90.5% vs. 50%, respectively, p = 0.015). The extracted amounts of nucleic acids were at least five times the minimum requirement and the sequence quality met the criteria for the Oncomine™ Target Test. Only the tumor cell content of some samples was insufficient. The feasibility of the pipeline for USB, SVA, and amplicon-based NGS in distal PPLs was demonstrated.