Abstract
Background and purpose
The goal of the current study was to evaluate the commercially available atlas-based autosegmentation software for clinical use in prostate radiotherapy. The accuracy was benchmarked against interobserver variability.
Material and methods
A total of 20 planning computed tomographs (CTs) and 10 cone-beam CTs (CBCTs) were selected for prostate, rectum, and bladder delineation. The images varied regarding to individual (age, body mass index) and setup parameters (contrast agent, rectal balloon, implanted markers). Automatically created contours with ABAS® and iPlan® were compared to an expert’s delineation by calculating the Dice similarity coefficient (DSC) and conformity index.
Results
Demo-atlases of both systems showed different results for bladder (DSCABAS 0.86 ± 0.17, DSCiPlan 0.51 ± 0.30) and prostate (DSCABAS 0.71 ± 0.14, DSCiPlan 0.57 ± 0.19). Rectum delineation (DSCABAS 0.78 ± 0.11, DSCiPlan 0.84 ± 0.08) demonstrated differences between the systems but better correlation of the automatically drawn volumes. ABAS® was closest to the interobserver benchmark. Autosegmentation with iPlan®, ABAS® and manual segmentation took 0.5, 4 and 15–20 min, respectively. Automatic contouring on CBCT showed high dependence on image quality (DSC bladder 0.54, rectum 0.42, prostate 0.34).
Conclusion
For clinical routine, efforts are still necessary to either redesign algorithms implemented in autosegmentation or to optimize image quality for CBCT to guarantee required accuracy and time savings for adaptive radiotherapy.
Zusammenfassung
Hintergrund und Ziel
Zwei kommerziell erhältliche Systeme zur atlasbasierten automatischen Konturierung wurden hinsichtlich Genauigkeit mit der Interobservervariabilität bei Prostatakarzinomen verglichen.
Material und Methoden
Insgesamt wurden 20 Planungs-CTs und 10 CBCTs (cone-beam CTs) zur Konturierung von Prostata, Rektum und Blase herangezogen. Die Bilddaten variierten hinsichtlich patientenspezifischer (Alter, Body Mass Index) und planungsspezifischer Parameter (Kontrastmittel, Rektumballon, Goldmarker). Automatisch generierte Konturen von ABAS® und iPlan® wurden mit der manuellen Konturierung eines Experten mit Hilfe des „Dice-similarity“-Koeffizienten (DSC) und dem Konformitätsindex verglichen.
Ergebnisse
Die Demoatlanten beider Systeme zeigten unterschiedliche Ergebnisse für Blase (DSCABAS 0,86 ± 0,17; DSCiPlan 0,51 ± 0,30) und Prostata (DSCABAS 0,71 ± 0,14; DSCiPlan 0,57 ± 0,19). Bei den Rektumkonturen (DSCABAS 0,78 ± 0,11; DSCiPlan 0,84 ± 0,08) zeigten sich zwar auch Unterschiede, aber mit einer größeren Korrelation der automatisch erzeugten Volumen. ABAS® wies eine bessere Übereinstimmung zur Interobservervariabilität auf. Die benötigte Zeit für die automatische Konturierung mit iPlan®, ABAS® bzw. manueller Konturierung betrug jeweils 0,5 min, 4 min und 15–20 min. Automatische Konturierungen an CBCTs waren sehr stark abhängig von der Bildqualität (DSC Blase 0,54, Rektum 0,42, Prostata 0,34).
Schlussfolgerung
Für den Einsatz der Systeme in der klinischen Routine sind weitere Bestrebungen zur Verbesserung der Algorithmen als auch zur Bildqualitätsverbesserung am CBCT notwendig. Erst dadurch können die notwendige Genauigkeit und Einsparungen in der Zeit für die adaptierte Strahlentherapie erreicht werden.
References
Aljabar P, Heckemann RA, Hammers A et al (2009) Multi-atlas based segmentation of brain images: atlas selection and its effect on accuracy. Neuroimage 46:726–738
Boda-Heggemann J, Lohr F, Wenz F et al (2011) kV cone-beam CT-based IGRT: a clinical review. Strahlenther Onkol 187(5):284–291
Commowick O, Vincent G, Gregoire M (2008) Atlas-based delineation of lymph node levels in head and neck computed tomography images. Radiother Oncol 87:281–289
Ehrhardt J, Handels H, Malina T et al (2001) Atlas-based segmentation of bone structures to support the virtual planning of hip operations. Int J Med Inform 64:439–447
Fiorino C, Renib M, Bolognesi M et al (1998) Intra- and inter-observer variability in contouring prostate and seminal vesicles: implications for conformal treatment planning. Radiother Oncol 47:285–292
Genovesi D, Cèfaro GA, Vinciguerra A et al (2011) Interobserver variability of clinical target volume delineation in supra-diaphragmatic Hodgkin’s disease: a multi-institutional experience. Strahlenther Onkol 187(6):357–366
Gerstner N, Wachter S, Dorner D et al (1999) Significance of a rectal balloon as internal immobilization device in conformal radiotherapy of prostatic carcinoma. Strahlenther Onkol 175(5):232–238
Ghadjar P, Gwerder N, Manser P et al (2010) High-dose (80 Gy) intensity-modulated radiation therapy with daily image-guidance as primary treatment for localized prostate cancer. Strahlenther Onkol 186(12):687–692
Ghilezan M, Yan D, Martinez A (2010) Adaptive radiation therapy for prostate cancer. Semin Radiat Oncol 20:130–137
Guckenberger M, Ok S, Polat B et al (2010) Toxicity after intensity-modulated, image-guided radiotherapy for prostate cancer. Strahlenther Onkol 186(10):535–543
Haas B, Coradi T, Scholz M et al (2008) Automatic segmentation of thoracic and pelvic CT images for radiotherapy planning using implicit anatomic knowledge and organ specific segmentation strategies. Phys Med Biol 53:1751–1771
Han X, Hoogeman MS, Levendag PC et al (2008) Atlas-based auto-segmentation of head and neck ct-images. Med Image Comput Comput Assist Interv 5242:434–441
Heinze P, Meister D, Kober R et al (2002) Atlas-based segmentation of pathological knee joints. Stud Health Technol Inform 85:198–203
Huyskens DP, Maingon P, Vanuytsel L et al (2008) A qualitative and quantitative analysis of an auto-segmentation module for prostate cancer. Radiother Oncol 90:337–345
Isambert A, Dhermain F, Bidault F et al (2008) Evaluation of an atlas-based automatic segmentation software for the delineation of brain organs at risk in a radiation therapy clinical context. Radiother Oncol 87:93–99
Jarry G, Graham SA, Moseley DJ et al (2006) Characterization of scattered radiation in kV CBCT images using Monte Carlo simulations. Med Phys 33(11):4320–4329
Klein S, Heide U van der, Lips I et al (2008) Automatic segmentation of the prostate in 3D MR images by atlas matching using localized mutual information. Med Phys 35:1407–1417
Kouwenhouven E, Giezen M, Struikmans H (2009) Measuring the similarity of target volume delineations independent of the number of observers. Phys Med Biol 54:2863–2873
Linguraru MG, Sandberg JK, Li Z et al (2009) Atlas-based automated segmentation of spleen and liver using adaptive enhancement estimation. Med Image Comput Comput Assist Interv 5762:1001–1008
Luetgendorf-Caucig C, Fotina I, Stock M et al (2011) Feasibility of CBCT-based target and normal structure delineation in prostate cancer radiotherapy: multi-observer and image multi-modality study. Radiother Oncol 98:154–161
McLaughlin P, Evans C, Feng M, Narayana V (2010) Radiographic and anatomic basis for prostate contouring errors and methods to improve prostate contouring accuracy. Int J Radiat Oncol Biol Phys 76:369–378
Michopoulou SK, Costaridou L, Panagiotopoulos E et al (209) Atlas-based segmentation of degenerated lumbar intervertebral discs from MR images of the spine. IEEE Trans Biomed Eng 56:2225–2231
Nakamura N, Shikama N, Takahashi O et al (2010) Variability in bladder volumes of full bladders in definitive radiotherapy for cases of localized prostate cancer. Strahlenther Onkol 186(11):637–642
Pallotta S, Bucciolini M, Russo S et al (2006) Accuracy evaluation of image registration and segmentation tools used in conformal treatment planning of prostate cancer. Comput Med Imaging Graph 30:1–7
Pasquier D, Lacornerie T, Vermandel M et al (2007) Automatic segmentation of pelvic structures from magnetic resonance images for prostate cancer radiotherapy. Int J Radiat Oncol Biol Phys 68:592–600
Pekar V, Mc Nutt T, Kaus M (2004) Automated model-based organ delineation for radiotherapy planning in prostate region. Int J Radiat Oncol Biol Phys 60:973–980
Pinkawa M, Piroth MD, Holy R et al (2011) Combination of dose escalation with technological advances (intensity-modulated and image-guided radiotherapy) is not associated with increased morbidity for patients with prostate cancer. Strahlenther Onkol 187(80):479–484
Sims R, Isambert A, Grégoire V et al (2009) A pre-clinical assessment of an atlas-based automatic segmentation tool for the head and neck. Radiother Oncol 93:474–478
Stock M, Pasler M, Birkfellner W et al (2009) Image quality and stability of image-guided radiotherapy (IGRT) devices: a comparative study. Radiother Oncol 93(1):1–7
Teguh DN, Levendag PC, Voet PW et al (2011) Clinical validation of atlas-based auto-segmentation of multiple target volumes and normal tissue (swallowing/mastication) structures in the head and neck. Int J Radiat Oncol Biol Phys 81(4):950–957
Zhang T, Chi Y, Meldolesi E, Yan D (2007) Automatic delineation of on-line head and neck computed tomography images: toward on-line adaptive radiotherapy. Int J Radiat Oncol Biol Phys 68:522–530
Acknowledgment
This work was supported by the Austrian Science Foundation FWF under project L503.
Conflict of interest
On behalf of all authors, the corresponding author states that there are no conflicts of interest.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Simmat, I., Georg, P., Georg, D. et al. Assessment of accuracy and efficiency of atlas-based autosegmentation for prostate radiotherapy in a variety of clinical conditions. Strahlenther Onkol 188, 807–815 (2012). https://doi.org/10.1007/s00066-012-0117-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00066-012-0117-0
Keywords
- Radiotherapy
- Prostate neoplasms
- Radiotherapy setup errors
- Cone-beam computed tomography
- Computed tomography