CC BY-NC-ND 4.0 · Laryngorhinootologie 2020; 99(S 02): S50
DOI: 10.1055/s-0040-1710853
Abstracts
Imaging/Sonography

Standardization and quality management of lymph node diagnostics using ultrasound-based radiomics markers

Lisa Margarete Neumann
1   Hals-Nasen-Ohrenklinik, Universitätsklinikum Düsseldorf Düsseldorf
,
C Plettenberg
1   Hals-Nasen-Ohrenklinik, Universitätsklinikum Düsseldorf Düsseldorf
,
L Colter
1   Hals-Nasen-Ohrenklinik, Universitätsklinikum Düsseldorf Düsseldorf
,
Jörg Schipper
1   Hals-Nasen-Ohrenklinik, Universitätsklinikum Düsseldorf Düsseldorf
,
K Scheckenbach
1   Hals-Nasen-Ohrenklinik, Universitätsklinikum Düsseldorf Düsseldorf
› Author Affiliations
 

Introduction The ultrasound is of elementary importance in the diagnosis, therapy planning and follow-up of head and neck tumors. The previous analysis is based on subjective criteria of the examiner. The aim of our study is to implement ultrasonic-based, standardized radiomics markers in the analysis and diagnosis of cervical lymph nodes.

Methods We created a database with sonographic metadata,clinical, histological and/or serological data with 209 lymph node images of 149 patients. The image metadata were segmented and analyzed using software developed by Fraunhofer Institute and correlated with clinical data.

Results In 64 of 209 lymph nodes a malignancy was histologically confirmed. Further examinations also showed lymph node tuberculosis, toxoplasmosis, reactive lymphadenopathies or inconspicuous findings (control group). With help of the Fraunhofer software, we were able to create objective and quantitative data sets as well as a preliminary “Radiomics” signature for cervical solid lymph node metastases .

Discussion Ultrasone-based “Radiomics” of cervical lymph nodes are possible and create objective quantitative values that in principle allow the creation of illness-specific signature. We were able to establish a preliminary signature for solid, malignant lymph nodes, a further validation is planned.

Fraunhofer Institut

Poster-PDF A-1659.PDF



Publication History

Article published online:
10 June 2020

© 2020. The Author(s). This is an open access article published by Thieme under the terms of the Creative Commons Attribution-NonDerivative-NonCommercial-License, permitting copying and reproduction so long as the original work is given appropriate credit. Contents may not be used for commercial purposes, or adapted, remixed, transformed or built upon. (https://creativecommons.org/licenses/by-nc-nd/4.0/).

© Georg Thieme Verlag KG
Stuttgart · New York