An Evaluation of Atlas Selection Methods for Atlas-Based Automatic Segmentation in Radiotherapy Treatment Planning

Autor: Mark Gooding, Johan van Soest, Bas Schipaanboord, Tim Lustberg, Devis Peressutti, Wouter van Elmpt, Andre Dekker, Djamal Boukerroui
Přispěvatelé: Radiotherapy, RS: FSE BISS, RS: FSE DACS IDS, Institute of Data Science, RS: GROW - R3 - Innovative Cancer Diagnostics & Therapy, Promovendi ODB, Radiotherapie
Rok vydání: 2019
Předmět:
Organs at Risk
atlas selection
Computer science
medicine.medical_treatment
AUTO-SEGMENTATION
Multi-atlas segmentation
Strain
030218 nuclear medicine & medical imaging
0302 clinical medicine
Image Processing
Computer-Assisted
PROSTATE
Segmentation
Computed tomography
VOLUMES
Image segmentation
Measurement
Radiological and Ultrasound Technology
Atlas (topology)
Computer Science Applications
medicine.anatomical_structure
LABEL FUSION
Head and Neck Neoplasms
REGISTRATION
Selection method
Algorithms
CT
STRATEGIES
education
Image processing
VALIDATION
Databases
03 medical and health sciences
Atlas (anatomy)
medicine
Humans
Electrical and Electronic Engineering
COMBINATION
radiotherapy
business.industry
Radiotherapy Planning
Computer-Assisted
Pattern recognition
Radiotherapy treatment planning
Radiation therapy
Planning
Automatic segmentation
Artificial intelligence
Tomography
X-Ray Computed
business
Head
Neck
Software
Zdroj: IEEE Transactions on Medical Imaging, 38(11), 2654-2664. Institute of Electrical and Electronics Engineers Inc.
Ieee Transactions on Medical Imaging, 38(11), 2654-2664. IEEE
ISSN: 1558-254X
0278-0062
DOI: 10.1109/tmi.2019.2907072
Popis: Atlas-based automatic segmentation is used in radiotherapy planning to accelerate the delineation of organs at risk (OARs). Atlas selection has been proposed as a way to improve the accuracy and execution time of segmentation, assuming that, the more similar the atlas is to the patient, the better the results will be. This paper presents an analysis of atlas selection methods in the context of radiotherapy treatment planning. For a range of commonly contoured OARs, a thorough comparison of a large class of typical atlas selection methods has been performed. For this evaluation, clinically contoured CT images of the head and neck ( ${N}={316}$ ) and thorax ( ${N}={280}$ ) were used. The state-of-the-art intensity and deformation similarity-based atlas selection methods were found to compare poorly to perfect atlas selection. Counter-intuitively, atlas selection methods based on a fixed set of representative atlases outperformed atlas selection methods based on the patient image. This study suggests that atlas-based segmentation with currently available selection methods compares poorly to the potential best performance, hampering the clinical utility of atlas-based segmentation. Effective atlas selection remains an open challenge in atlas-based segmentation for radiotherapy planning.
Databáze: OpenAIRE
Externí odkaz: