Benefits of deep learning for delineation of organs at risk in head and neck cancer

•Validation of automated delineation of organs at risk in head and neck cancer.•Automated delineation is more time efficient.•Automated delineation reduces interobserver variability. Precise delineation of organs at risk (OARs) in head and neck cancer (HNC) is necessary for accurate radiotherapy. Al...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Radiotherapy and oncology Ročník 138; s. 68 - 74
Hlavní autoři:	van der Veen, J., Willems, S., Deschuymer, S., Robben, D., Crijns, W., Maes, F., Nuyts, S.
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Ireland Elsevier B.V 01.09.2019
Témata:	Aged Aged, 80 and over Deep Learning Delineation Female Head and neck neoplasms Head and Neck Neoplasms - radiotherapy Hematology, Oncology, and Palliative Medicine Humans Male Middle Aged Neural Networks, Computer Observer Variation Organs at Risk Radiotherapy mm Acc Delineation Radiotherapy Observer variation S SG U Head and neck neoplasms PG Neural networks (computer) Organs at risk PCM ASSD RO IOVm millimetres accuracy of network upper parotid gland pharyngeal constrictor muscles average symmetric surface distance supra manual interobserver variability radiation oncologist submandibular gland
ISSN:	0167-8140, 1879-0887, 1879-0887
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	•Validation of automated delineation of organs at risk in head and neck cancer.•Automated delineation is more time efficient.•Automated delineation reduces interobserver variability. Precise delineation of organs at risk (OARs) in head and neck cancer (HNC) is necessary for accurate radiotherapy. Although guidelines exist, significant interobserver variability (IOV) remains. The aim was to validate a 3D convolutional neural network (CNN) for semi-automated delineation of OARs with respect to delineation accuracy, efficiency and consistency compared to manual delineation. 16 OARs were manually delineated in 15 new HNC patients by two trained radiation oncologists (RO) independently, using international consensus guidelines. OARs were also automatically delineated by applying the CNN and corrected as needed by both ROs separately. Both delineations were performed two weeks apart and blinded to each other. IOV between both ROs was quantified using Dice similarity coefficient (DSC) and average symmetric surface distance (ASSD). To objectify network accuracy, differences between automated and corrected delineations were calculated using the same similarity measures. Average correction time of the automated delineation was 33% shorter than manual delineation (23 vs 34 minutes) (p < 10–6). IOV improved significantly with network initialisation for nearly all OARs (p < 0.05), resulting in decreased ASSD averaged over all OARs from 1.9 to 1.2 mm. The network achieved an accuracy of 90% and 84% DSC averaged over all OARs for RO1 and RO2 respectively, with an ASSD of 0.7 and 1.5 mm, which was in 93% and 73% of the cases lower than the IOV. The CNN developed for automated OAR delineation in HNC was shown to be more efficient and consistent compared to manual delineation, which justify its implementation in clinical practice.
Bibliografie:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
ISSN:	0167-8140 1879-0887 1879-0887
DOI:	10.1016/j.radonc.2019.05.010