Laryngeal Lesion Classification Based on Vascular Patterns in Contact Endoscopy and Narrow Band Imaging: Manual Versus Automatic Approach
Longitudinal and perpendicular changes in the vocal fold’s blood vessels are associated with the development of benign and malignant laryngeal lesions. The combination of Contact Endoscopy (CE) and Narrow Band Imaging (NBI) can provide intraoperative real-time visualization of the vascular changes i...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-07-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/20/14/4018 |
_version_ | 1797561949541629952 |
---|---|
author | Nazila Esmaeili Alfredo Illanes Axel Boese Nikolaos Davaris Christoph Arens Nassir Navab Michael Friebe |
author_facet | Nazila Esmaeili Alfredo Illanes Axel Boese Nikolaos Davaris Christoph Arens Nassir Navab Michael Friebe |
author_sort | Nazila Esmaeili |
collection | DOAJ |
description | Longitudinal and perpendicular changes in the vocal fold’s blood vessels are associated with the development of benign and malignant laryngeal lesions. The combination of Contact Endoscopy (CE) and Narrow Band Imaging (NBI) can provide intraoperative real-time visualization of the vascular changes in the laryngeal mucosa. However, the visual evaluation of vascular patterns in CE-NBI images is challenging and highly depends on the clinicians’ experience. The current study aims to evaluate and compare the performance of a manual and an automatic approach for laryngeal lesion’s classification based on vascular patterns in CE-NBI images. In the manual approach, six observers visually evaluated a series of CE+NBI images that belong to a patient and then classified the patient as benign or malignant. For the automatic classification, an algorithm based on characterizing the level of the vessel’s disorder in combination with four supervised classifiers was used to classify CE-NBI images. The results showed that the manual approach’s subjective evaluation could be reduced by using a computer-based approach. Moreover, the automatic approach showed the potential to work as an assistant system in case of disagreements among clinicians and to reduce the manual approach’s misclassification issue. |
first_indexed | 2024-03-10T18:22:46Z |
format | Article |
id | doaj.art-70113e7ccb83413faff0b46497e4413f |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-10T18:22:46Z |
publishDate | 2020-07-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-70113e7ccb83413faff0b46497e4413f2023-11-20T07:16:30ZengMDPI AGSensors1424-82202020-07-012014401810.3390/s20144018Laryngeal Lesion Classification Based on Vascular Patterns in Contact Endoscopy and Narrow Band Imaging: Manual Versus Automatic ApproachNazila Esmaeili0Alfredo Illanes1Axel Boese2Nikolaos Davaris3Christoph Arens4Nassir Navab5Michael Friebe6INKA-Application Driven Research, Otto-von-Guericke University Magdeburg, 39120 Magdeburg, GermanyINKA-Application Driven Research, Otto-von-Guericke University Magdeburg, 39120 Magdeburg, GermanyINKA-Application Driven Research, Otto-von-Guericke University Magdeburg, 39120 Magdeburg, GermanyDepartment of Otorhinolaryngology, Head and Neck Surgery, Magdeburg University Hospital, 39120 Magdeburg, GermanyDepartment of Otorhinolaryngology, Head and Neck Surgery, Magdeburg University Hospital, 39120 Magdeburg, GermanyChair for Computer Aided Medical Procedures and Augmented Reality, Technical University Munich, 85748 Munich, GermanyINKA-Application Driven Research, Otto-von-Guericke University Magdeburg, 39120 Magdeburg, GermanyLongitudinal and perpendicular changes in the vocal fold’s blood vessels are associated with the development of benign and malignant laryngeal lesions. The combination of Contact Endoscopy (CE) and Narrow Band Imaging (NBI) can provide intraoperative real-time visualization of the vascular changes in the laryngeal mucosa. However, the visual evaluation of vascular patterns in CE-NBI images is challenging and highly depends on the clinicians’ experience. The current study aims to evaluate and compare the performance of a manual and an automatic approach for laryngeal lesion’s classification based on vascular patterns in CE-NBI images. In the manual approach, six observers visually evaluated a series of CE+NBI images that belong to a patient and then classified the patient as benign or malignant. For the automatic classification, an algorithm based on characterizing the level of the vessel’s disorder in combination with four supervised classifiers was used to classify CE-NBI images. The results showed that the manual approach’s subjective evaluation could be reduced by using a computer-based approach. Moreover, the automatic approach showed the potential to work as an assistant system in case of disagreements among clinicians and to reduce the manual approach’s misclassification issue.https://www.mdpi.com/1424-8220/20/14/4018laryngeal cancercontact endoscopynarrow band imagingautomatic classificationfeature extractionmachine learning |
spellingShingle | Nazila Esmaeili Alfredo Illanes Axel Boese Nikolaos Davaris Christoph Arens Nassir Navab Michael Friebe Laryngeal Lesion Classification Based on Vascular Patterns in Contact Endoscopy and Narrow Band Imaging: Manual Versus Automatic Approach Sensors laryngeal cancer contact endoscopy narrow band imaging automatic classification feature extraction machine learning |
title | Laryngeal Lesion Classification Based on Vascular Patterns in Contact Endoscopy and Narrow Band Imaging: Manual Versus Automatic Approach |
title_full | Laryngeal Lesion Classification Based on Vascular Patterns in Contact Endoscopy and Narrow Band Imaging: Manual Versus Automatic Approach |
title_fullStr | Laryngeal Lesion Classification Based on Vascular Patterns in Contact Endoscopy and Narrow Band Imaging: Manual Versus Automatic Approach |
title_full_unstemmed | Laryngeal Lesion Classification Based on Vascular Patterns in Contact Endoscopy and Narrow Band Imaging: Manual Versus Automatic Approach |
title_short | Laryngeal Lesion Classification Based on Vascular Patterns in Contact Endoscopy and Narrow Band Imaging: Manual Versus Automatic Approach |
title_sort | laryngeal lesion classification based on vascular patterns in contact endoscopy and narrow band imaging manual versus automatic approach |
topic | laryngeal cancer contact endoscopy narrow band imaging automatic classification feature extraction machine learning |
url | https://www.mdpi.com/1424-8220/20/14/4018 |
work_keys_str_mv | AT nazilaesmaeili laryngeallesionclassificationbasedonvascularpatternsincontactendoscopyandnarrowbandimagingmanualversusautomaticapproach AT alfredoillanes laryngeallesionclassificationbasedonvascularpatternsincontactendoscopyandnarrowbandimagingmanualversusautomaticapproach AT axelboese laryngeallesionclassificationbasedonvascularpatternsincontactendoscopyandnarrowbandimagingmanualversusautomaticapproach AT nikolaosdavaris laryngeallesionclassificationbasedonvascularpatternsincontactendoscopyandnarrowbandimagingmanualversusautomaticapproach AT christopharens laryngeallesionclassificationbasedonvascularpatternsincontactendoscopyandnarrowbandimagingmanualversusautomaticapproach AT nassirnavab laryngeallesionclassificationbasedonvascularpatternsincontactendoscopyandnarrowbandimagingmanualversusautomaticapproach AT michaelfriebe laryngeallesionclassificationbasedonvascularpatternsincontactendoscopyandnarrowbandimagingmanualversusautomaticapproach |