KIT | KIT-Bibliothek | Impressum | Datenschutz

Essential parameters needed for a U-Net-based segmentation of individual bones on planning CT images in the head and neck region using limited datasets for radiotherapy application

Yawson, Ama Katseena; Walter, Alexandra ORCID iD icon 1,2; Wolf, Nora; Klüter, Sebastian; Hoegen, Philip; Adeberg, Sebastian; Debus, Jürgen; Frank, Martin ORCID iD icon 1,2,3; Jäkel, Oliver; Giske, Kristina
1 Fakultät für Mathematik (MATH), Karlsruher Institut für Technologie (KIT)
2 Institut für Angewandte und Numerische Mathematik (IANM), Karlsruher Institut für Technologie (KIT)
3 Scientific Computing Center (SCC), Karlsruher Institut für Technologie (KIT)

Abstract:

Objective. The field of radiotherapy is highly marked by the lack of datasets even with the availability of public datasets. Our study uses a very limited dataset to provide insights on essential parameters needed to automatically and accurately segment individual bones on planning CT images of head and neck cancer patients. Approach. The study was conducted using 30 planning CT images of real patients acquired from 5 different cohorts. 15 cases from 4 cohorts were randomly selected as training and validation datasets while the remaining were used as test datasets. Four experimental sets were formulated to explore parameters such as background patch reduction, class-dependent augmentation and incorporation of a weight map on the loss function. Main results. Our best experimental scenario resulted in a mean Dice score of 0.93 ± 0.06 for other bones (skull, mandible, scapulae, clavicles, humeri and hyoid), 0.93 ± 0.02 for ribs and 0.88 ± 0.03 for vertebrae on 7 test cases from the same cohorts as the training datasets. We compared our proposed solution approach to a retrained nnU-Net and obtained comparable results for vertebral bones while outperforming in the correct identification of the left and right instances of ribs, scapulae, humeri and clavicles. ... mehr


Verlagsausgabe §
DOI: 10.5445/IR/1000168151
Veröffentlicht am 06.02.2024
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Angewandte und Numerische Mathematik (IANM)
Scientific Computing Center (SCC)
Publikationstyp Zeitschriftenaufsatz
Publikationsdatum 07.02.2024
Sprache Englisch
Identifikator ISSN: 0031-9155, 1361-6560
KITopen-ID: 1000168151
Erschienen in Physics in Medicine & Biology
Verlag Institute of Physics Publishing Ltd (IOP Publishing Ltd)
Band 69
Heft 3
Seiten Art.-Nr.: 035008
Vorab online veröffentlicht am 24.01.2024
Schlagwörter head and neck cancer, radiotherapy, planning CT, bone segmentation, U-Net, nnU-Net
Nachgewiesen in Scopus
Dimensions
Web of Science
Globale Ziele für nachhaltige Entwicklung Ziel 3 – Gesundheit und Wohlergehen
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page