Multi-atlas-based segmentation of prostatic urethra from planning CT imaging to quantify dose distribution in prostate cancer radiotherapy

Oscar Acosta (1) , Eugenia Mylona (1) , Mathieu Le Dain (1) , Camille Voisin (1) , Thibaut Lizee (1) , Bastien Rigaud (1) , Carolina Lafond (1, 2) , Khemara Gnep (1, 2) , Renaud de Crevoisier (1, 2)

1 LTSI - Laboratoire Traitement du Signal et de l'Image
2 CRLCC - CRLCC Eugène Marquis

Background and purpose Segmentation of intra-prostatic urethra for dose assessment from planning CT may help explaining urinary toxicity in prostate cancer radiotherapy. This work sought to: i) propose an automatic method for urethra segmentation in CT, ii) compare it with previously proposed surrogate models and iii) quantify the dose received by the urethra in patients treated with IMRT. Materials and methods A weighted multi-atlas-based urethra segmentation method was devised from a training data set of 55 CT scans of patients receiving brachytherapy with visible urinary catheters. Leave-one-out cross validation was performed to quantify the error between the urethra segmentation and the catheter ground truth with two scores: the centerlines distance (CLD) and the percentage of centerline within a certain distance from the catheter (PWR). The segmentation method was then applied to a second test data set of 95 prostate cancer patients having received 78 Gy IMRT to quantify dose to the urethra. Results Mean CLD was 3.25 ± 1.2 mm for the whole urethra and 3.7 ± 1.7 mm, 2.52 ± 1.5 mm, and 3.01 ± 1.7 mm for the top, middle, and bottom thirds, respectively. In average, 53% of the segmented centerlines were within a radius < 3.5 mm from the centerline ground truth and 83% in a radius < 5 mm. The proposed method outperformed existing surrogate models. In IMRT, urethra DVH was significantly higher than prostate DVH from V74 Gy to V79 Gy. Conclusion A multi-atlas-based segmentation method was proposed enabling assessment of the dose within the prostatic urethra. .

Mots clés: Urinary toxicity; Urethra segmentation; Atlas-based segmentation; Dose computation; prostate cancer radiotherapy; urinary toxicity; atlas-based segmentation; urethra; segmentation; dose computation

Domaines: Traitement du signal et de l'image [eess.SP]; Ingénierie biomédicale; Imagerie

Oscar Acosta, Eugenia Mylona, Mathieu Le Dain, Camille Voisin, Thibaut Lizee, et al.. Multi-atlas-based segmentation of prostatic urethra from planning CT imaging to quantify dose distribution in prostate cancer radiotherapy. Radiotherapy & Oncology, 2017, 125 (3), pp.492 - 499. ⟨10.1016/j.radonc.2017.09.015⟩. ⟨hal-01671693⟩