Enhancing nasal endoscopy: Classification, detection, and segmentation of anatomic landmarks using a convolutional neural network

Vinayak Ganeshan; Jonathan Bidwell; Dipesh Gyawali; Thinh S Nguyen; Jonathan Morse; Madeline P Smith; Blair M Barton; Edward D McCoul

doi:10.1002/alr.23384

Enhancing nasal endoscopy: Classification, detection, and segmentation of anatomic landmarks using a convolutional neural network

Int Forum Allergy Rhinol. 2024 Sep;14(9):1521-1524. doi: 10.1002/alr.23384. Epub 2024 Jun 10.

Authors

Vinayak Ganeshan¹, Jonathan Bidwell¹, Dipesh Gyawali¹, Thinh S Nguyen¹, Jonathan Morse¹, Madeline P Smith^{2

3}, Blair M Barton^{1

2

3}, Edward D McCoul^{1

2

3}

Affiliations

¹ Department of Otorhinolaryngology, Ochsner Health, New Orleans, Louisiana, USA.
² Ochsner Clinical School, University of Queensland, New Orleans, Louisiana, USA.
³ Department of Otolaryngology, Tulane University School of Medicine, New Orleans, Louisiana, USA.

PMID: 38853655
DOI: 10.1002/alr.23384

Abstract

A convolutional neural network (CNN)-based model can accurately localize and segment turbinates in images obtained during nasal endoscopy (NE). This model represents a starting point for algorithms that comprehensively interpret NE findings.

Keywords: artificial intelligence; deep learning; machine learning; nasal endoscopy; neural network; turbinate.

MeSH terms

Algorithms
Anatomic Landmarks
Endoscopy* / methods
Humans
Neural Networks, Computer*
Nose / anatomy & histology
Nose / diagnostic imaging
Turbinates / anatomy & histology
Turbinates / diagnostic imaging
Turbinates / pathology

Grants and funding

EE220702/EE220802/Eye, Ear, Nose, and Throat Foundation