W Laffers1, S Westermann2, B Regeling3, R Martin2,3, B Thies3, A O H Gerstner4, F Bootz2, N A Müller2. 1. Klinik für Hals-Nasen-Ohrenheilkunde/Chirurgie, Universitätsklinikum Bonn, Sigmund-Freud-Str. 25, 53105, Bonn, Deutschland. Wiebke.Laffers@gmx.de. 2. Klinik für Hals-Nasen-Ohrenheilkunde/Chirurgie, Universitätsklinikum Bonn, Sigmund-Freud-Str. 25, 53105, Bonn, Deutschland. 3. Laboratory for Climatology and Remote Sensing, Fachbereich Geographie, Universität Marburg, Marburg, Deutschland. 4. Hals-, Nasen-, Ohrenklinik, Klinikum Braunschweig, Braunschweig, Deutschland.
Abstract
BACKGROUND: Early detection of cancerous lesions is still crucial for a patient's prognosis. Although diagnostic access to the oral cavity and oropharynx is comparably easy, the incidence of resulting disease remains high. This is due to the fact that in many cases, malignity is recognized too late on a purely visual basis. Previously, we discussed the application of hyperspectral imaging for early detection of precancerous and cancerous lesions of the larynx. This time, we evaluate the method in the oral cavity and oropharynx. MATERIALS AND METHODS: In 85 patients scheduled for endoscopy, hyperspectral imaging was performed. We used a rigid 0-degree endoscope, a light-adjustable monochromator, and a hyperspectral camera. For evaluation of the method, 3 patients were chosen exemplarily. Training sites from physiological and cancerous tissues were marked. Hyperspectral data from 1 patient were used to train a classifier, which was then used for automatic detection of precancerous and cancerous lesions in another 2 patients. RESULTS: Intraoperative hyperspectral imaging was performed without any problems. Classification showed sensitivities of 61 and 43%, and a specificity of 100%. CONCLUSION: This proof-of-concept study underscores the high potential of hyperspectral imaging for early recognition of cancer in the mouth and oropharynx. Besides a better prognosis for cancer patients, this approach could lead to higher cost efficiency in the health system.
BACKGROUND: Early detection of cancerous lesions is still crucial for a patient's prognosis. Although diagnostic access to the oral cavity and oropharynx is comparably easy, the incidence of resulting disease remains high. This is due to the fact that in many cases, malignity is recognized too late on a purely visual basis. Previously, we discussed the application of hyperspectral imaging for early detection of precancerous and cancerous lesions of the larynx. This time, we evaluate the method in the oral cavity and oropharynx. MATERIALS AND METHODS: In 85 patients scheduled for endoscopy, hyperspectral imaging was performed. We used a rigid 0-degree endoscope, a light-adjustable monochromator, and a hyperspectral camera. For evaluation of the method, 3 patients were chosen exemplarily. Training sites from physiological and cancerous tissues were marked. Hyperspectral data from 1 patient were used to train a classifier, which was then used for automatic detection of precancerous and cancerous lesions in another 2 patients. RESULTS: Intraoperative hyperspectral imaging was performed without any problems. Classification showed sensitivities of 61 and 43%, and a specificity of 100%. CONCLUSION: This proof-of-concept study underscores the high potential of hyperspectral imaging for early recognition of cancer in the mouth and oropharynx. Besides a better prognosis for cancerpatients, this approach could lead to higher cost efficiency in the health system.
Entities:
Keywords:
Early diagnosis; Endoscopy; Head and neck neoplasms; Hyperspectral imaging; Oropharyngeal cancer
Authors: A O H Gerstner; R Martin; S Westermann; A-K Mahlein; K Schmidt; B Thies; W Laffers Journal: Laryngorhinootologie Date: 2013-07-03 Impact factor: 1.057
Authors: Bianca Regeling; Wiebke Laffers; Andreas O H Gerstner; Stephan Westermann; Nina A Müller; Kai Schmidt; Jörg Bendix; Boris Thies Journal: J Biophotonics Date: 2015-06-01 Impact factor: 3.207
Authors: Jonathan Shapey; Yijing Xie; Eli Nabavi; Robert Bradford; Shakeel R Saeed; Sebastien Ourselin; Tom Vercauteren Journal: J Biophotonics Date: 2019-04-29 Impact factor: 3.207
Authors: Boris Jansen-Winkeln; Manuel Barberio; Claire Chalopin; Katrin Schierle; Michele Diana; Hannes Köhler; Ines Gockel; Marianne Maktabi Journal: Cancers (Basel) Date: 2021-02-25 Impact factor: 6.575