Bronchoscopic Surgery for a Solitary Tracheal Tumor of Tracheobronchopathia Osteochondroplastica

Building and validating an artificial intelligence model to identify tracheobronchopathia osteochondroplastica by using bronchoscopic images

BACKGROUND

Given the rarity of tracheobronchopathia osteochondroplastica (TO), many young doctors in primary hospitals are unable to identify TO based on bronchoscopy findings.

OBJECTIVES

To build an artificial intelligence (AI) model for differentiating TO from other multinodular airway diseases by using bronchoscopic images.

DESIGN

We designed the study by comparing the imaging data of patients undergoing bronchoscopy from January 2010 to October 2022 by using EfficientNet. Bronchoscopic images of 21 patients with TO at Anhui Chest Hospital from October 2019 to October 2022 were collected for external validation.

METHODS

Bronchoscopic images of patients with multinodular airway lesions (including TO, amyloidosis, tumors, and inflammation) and without airway lesions in the First Affiliated Hospital of Guangzhou Medical University were collected. The images were randomized (4:1) into training and validation groups based on different diseases and utilized for deep learning by convolutional neural networks (CNNs).

RESULTS

We enrolled 201 patients with multinodular airway disease (38, 15, 75, and 73 patients with TO, amyloidosis, tumors, and inflammation, respectively) and 213 without any airway lesions. To find multinodular lesion images for deep learning, we utilized 2183 bronchoscopic images of multinodular lesions (including TO, amyloidosis, tumor, and inflammation) and compared them with images without any airway lesions (1733). The accuracy of multinodular lesion identification was 98.9%. Further, the accuracy of TO detection based on the bronchoscopic images of multinodular lesions was 89.2%. Regarding external validation (using images from 21 patients with TO), all patients could be diagnosed with TO; the accuracy was 89.8%.

CONCLUSION

We built an AI model that could differentiate TO from other multinodular airway diseases (mainly amyloidosis, tumors, and inflammation) by using bronchoscopic images. The model could help young physicians identify this rare airway disease.

Clinicopathological Features and Management Principles of Tracheobronchopathia Osteochondroplastica - A Scoping Review

Tracheobronchopathia osteochondroplastica (TO) is an orphan disease of the tracheobronchial tree without any known etiological attributes. There are several case reports published on this condition, yet the available information about the TO is discrete and of little clinical value. This scoping review is the first large-scale review on TO that collates individual patient data from the published case reports and descriptively analyses the clinicopathological features of this unique condition along with its management approaches and therapeutic outcomes. The objective was to synthesize comprehensive literature review on TO that can aid clinical practice and further research. An electronic search conducted in five large databases, including PubMed, EMBASE, CINAHL, CENTRAL, and Web of Science, for the published articles of TO yielded 1072 items. After screening, the individual patient data of 371 TO cases from 228 eligible articles were included and analysed in this scoping review.

Supplementary Information

The online version contains supplementary material available at 10.1007/s12070-023-03998-6.

Intubation Technique in a Patient with Tracheobronchopathia Osteochondroplastica

BACKGROUND Tracheobronchopathia osteochondroplastica (TO) is a rare disorder characterized by cartilaginous or ossified submucosal nodules of unknown etiology that project into the tracheobronchial lumen. TO is often accompanied by endotracheal stenosis from cartilage proliferation and is often detected by difficult endotracheal intubation incidence. CASE REPORT Here we report the case of a patient (67-year-old man) with TO scheduled to undergo robot-assisted total prostatectomy for prostate cancer. The tracheal lumen was especially narrow at an area 1 cm below the glottis, with the smallest lumen diameter being 9 mm. After rapid induction, the bronchoscope passed through the stenosed region, and a 6.5-mm spiral endotracheal tube (ETT) was inserted with bronchoscopic assistance. However, because of resistance, the spiral ETT could not pass through the stenosed area. After changing to a 6.5-mm normal ETT, intubation was successfully performed with gentle rotation. Owing to the rotation, the tip entered and gained access to the gap between nodules. With use of a bronchoscope, we confirmed that the tip of the ETT was advanced 10 cm from the glottis, where the site of maximum stenosis was not covered by the tube cuff, and where the tip did not cross the bifurcation. After surgery, no bleeding or edema was found on bronchoscopy. CONCLUSIONS In patients with TO, it is important to assess the airway condition and prepare for difficult intubation. In this case, tracheal intubation was performed with rotation using a bronchoscope and normal ETT.