email:
bendix <at> staff.uni-marburg.de
Deutschhausstraße 12
Room No. 02 A 48
35032 Marburg
Faculty of Geography
Germany
Individual:
Wiebke Laffers
Contact:
email:
webmaster <at> lcrs.de
Abstract:
Hyperspectral imaging (HSI) is increasingly gaining acceptance in the medical field.<br/>
Up until now, HSI has been used in conjunction with rigid endoscopy to detect cancer in vivo.<br/>
The logical next step is to pair HSI with flexible endoscopy, since it improves access to hard-to-reach<br/>
areas. While the flexible endoscope’s fiber optic cables provide the advantage of flexibility, they<br/>
also introduce an interfering honeycomb-like pattern onto images. Due to the substantial impact<br/>
this pattern has on locating cancerous tissue, it must be removed before the HS data can be further<br/>
processed. Thereby, the loss of information is to minimize avoiding the suppression of small-area<br/>
variations of pixel values. We have developed a system that uses flexible endoscopy to record HS<br/>
cubes of the larynx and designed a special filtering technique to remove the honeycomb-like pattern<br/>
with minimal loss of information. We have confirmed its feasibility by comparing it to conventional<br/>
filtering techniques using an objective metric and by applying unsupervised and supervised<br/>
classifications to raw and pre-processed HS cubes. Compared to conventional techniques, our<br/>
method successfully removes the honeycomb-like pattern and considerably improves classification<br/>
performance, while preserving image details.
Keywords:
| hyperspectral | oropharyngeal cancer |
Literature type specific fields:
ARTICLE
Journal:
Sensors
Volume:
16
Page Range:
1-14
Metadata Provider:
Individual:
Jörg Bendix
Contact:
email:
bendix <at> staff.uni-marburg.de
Deutschhausstraße 12
Room No. 02 A 48
35032 Marburg
Faculty of Geography
Germany
