Ward van Rooij1, Max Dahele2, Hugo Ribeiro Brandao2, Alexander R Delaney2, Berend J Slotman2, Wilko F Verbakel2. 1. Amsterdam UMC, Vrije Universiteit Amsterdam, Department of Radiation Oncology, Cancer Center Amsterdam, Amsterdam, the Netherlands. Electronic address: w.vanrooij@vumc.nl. 2. Amsterdam UMC, Vrije Universiteit Amsterdam, Department of Radiation Oncology, Cancer Center Amsterdam, Amsterdam, the Netherlands.
Abstract
PURPOSE: Organ-at-risk (OAR) delineation is a key step in treatment planning but can be time consuming, resource intensive, subject to variability, and dependent on anatomical knowledge. We studied deep learning (DL) for automated delineation of multiple OARs; in addition to geometric evaluation, the dosimetric impact of using DL contours for treatment planning was investigated. METHODS AND MATERIALS: The following OARs were delineated with DL developed in-house: both submandibular and parotid glands, larynx, cricopharynx, pharyngeal constrictor muscle (PCM), upper esophageal sphincter, brain stem, oral cavity, and esophagus. DL contours were benchmarked against the manual delineation (MD) clinical contours using the Sørensen-Dice similarity coefficient. Automated knowledge-based treatment plans were used. The mean dose to the manually delineated OAR structures was reported for the MD and DL plans. RESULTS: DL delineation of all OARs took <10 seconds per patient. For 7 of 11 OARs, the average Sørensen-Dice similarity coefficient was good (0.78-0.83). However, performance was lower for the esophagus (0.60), brainstem (0.64), PCM (0.68), and cricopharynx (0.73), often because of variations in MD. Although the average dose was statistically significantly higher in the DL plans for the inferior PCM (1.4 Gy) and esophagus (2.2 Gy), these average differences were not clinically significant. Dose to 28 of 209 (13.4%) and 7 of 209 (3.3%) OARs was >2 Gy higher and >2 Gy lower, respectively, in the DL plans. CONCLUSIONS: DL-based segmentation for head and neck OARs is fast; for most organs and most patients, it performs sufficiently well for treatment-planning purposes. It has the potential to increase efficiency and facilitate online adaptive radiation therapy.
PURPOSE: Organ-at-risk (OAR) delineation is a key step in treatment planning but can be time consuming, resource intensive, subject to variability, and dependent on anatomical knowledge. We studied deep learning (DL) for automated delineation of multiple OARs; in addition to geometric evaluation, the dosimetric impact of using DL contours for treatment planning was investigated. METHODS AND MATERIALS: The following OARs were delineated with DL developed in-house: both submandibular and parotid glands, larynx, cricopharynx, pharyngeal constrictor muscle (PCM), upper esophageal sphincter, brain stem, oral cavity, and esophagus. DL contours were benchmarked against the manual delineation (MD) clinical contours using the Sørensen-Dice similarity coefficient. Automated knowledge-based treatment plans were used. The mean dose to the manually delineated OAR structures was reported for the MD and DL plans. RESULTS: DL delineation of all OARs took <10 seconds per patient. For 7 of 11 OARs, the average Sørensen-Dice similarity coefficient was good (0.78-0.83). However, performance was lower for the esophagus (0.60), brainstem (0.64), PCM (0.68), and cricopharynx (0.73), often because of variations in MD. Although the average dose was statistically significantly higher in the DL plans for the inferior PCM (1.4 Gy) and esophagus (2.2 Gy), these average differences were not clinically significant. Dose to 28 of 209 (13.4%) and 7 of 209 (3.3%) OARs was >2 Gy higher and >2 Gy lower, respectively, in the DL plans. CONCLUSIONS: DL-based segmentation for head and neck OARs is fast; for most organs and most patients, it performs sufficiently well for treatment-planning purposes. It has the potential to increase efficiency and facilitate online adaptive radiation therapy.
Authors: Rosie J Goodburn; Marielle E P Philippens; Thierry L Lefebvre; Aly Khalifa; Tom Bruijnen; Joshua N Freedman; David E J Waddington; Eyesha Younus; Eric Aliotta; Gabriele Meliadò; Teo Stanescu; Wajiha Bano; Ali Fatemi-Ardekani; Andreas Wetscherek; Uwe Oelfke; Nico van den Berg; Ralph P Mason; Petra J van Houdt; James M Balter; Oliver J Gurney-Champion Journal: Magn Reson Med Date: 2022-09-21 Impact factor: 3.737
Authors: Ellen J L Brunenberg; Isabell K Steinseifer; Sven van den Bosch; Johannes H A M Kaanders; Charlotte L Brouwer; Mark J Gooding; Wouter van Elmpt; René Monshouwer Journal: Phys Imaging Radiat Oncol Date: 2020-07-10
Authors: Xianjin Dai; Yang Lei; Jacob Wynne; James Janopaul-Naylor; Tonghe Wang; Justin Roper; Walter J Curran; Tian Liu; Pretesh Patel; Xiaofeng Yang Journal: Med Phys Date: 2021-10-13 Impact factor: 4.071
Authors: Aditi Iyer; Maria Thor; Ifeanyirochukwu Onochie; Jennifer Hesse; Kaveh Zakeri; Eve LoCastro; Jue Jiang; Harini Veeraraghavan; Sharif Elguindi; Nancy Y Lee; Joseph O Deasy; Aditya P Apte Journal: Phys Med Biol Date: 2022-01-17 Impact factor: 3.609
Authors: Ekin Ermiş; Alain Jungo; Robert Poel; Marcela Blatti-Moreno; Raphael Meier; Urspeter Knecht; Daniel M Aebersold; Michael K Fix; Peter Manser; Mauricio Reyes; Evelyn Herrmann Journal: Radiat Oncol Date: 2020-05-06 Impact factor: 3.481