Impact of the implementation of a Contouring Atlas on Therapeutic Radiographer inter-observer contour variation in prostate radiotherapy

Abstract

Purpose: The clinical implementation of MR-guided adaptive radiotherapy requires fast, accurate delineation of target volumes and organs at risk (OAR's). It is important with the introduction of new online imaging strategies to mitigate the potential for contouring inaccuracies, as they could potentially result in treatment errors. To support the introduction of radiographer-led real-time MR-guided adaptive radiotherapy on the MR-Linac (MRL), an MR contouring atlas for prostate radiotherapy delineation guidance was developed. This tool was based on the ‘Male Pelvis Normal Tissue RTOG Consensus Contouring’ recommendations and local guidelines, and its impact on inter-observer variation was subsequently determined. Methods: Multi-disciplinary consensus on the contouring of the prostate, seminal vesicles and associated OAR's was obtained by developing a contouring guide (3 MRL radiographers, 2 clinical oncologists and 1 diagnostic radiographer). Contours were defined on T2-weighted three-dimensional turbo spin echo sequences, reconstructed axially (T2w 3D Tra) acquired on the MRL. To assess the guide's utility, 9 radiographers with varying MRL experience contoured 5 MRI scans in the Monaco treatment planning system, from 5 different patients (n= 25). Each radiographer contoured the prostate, seminal vesicles, bladder, and rectum on each data set before and after the introduction of the atlas. The ‘after’ contours were generated >21 days following the ‘before’ contours to minimise the effects of repetition. In addition to DICE coefficients and descriptive statistics, inter-observer contour variations, time to contour and observer contouring confidence was determined prior to and following the introduction of the atlas utilising a 5-point Likert scale (observers score confidence 1 not confident to 5 extremely confident). Results: The contouring atlas has been agreed by the multidisciplinary team incorporating locally defined gold-standard contours and RTOG guidance. Five sets of images from 5 different patients have been acquired on the MRL (T2w 3D Tra) and to date the ‘before’ contours have been completed. Mean contouring time without the atlas for all contours was 54 minutes with the rectum and prostate contouring taking the greatest amount of time, a mean time of 15 minutes each. Contour confidence levels varied between participants greatly. Minimum contour variability between the observers was for the bladder contour, with the maximum range being 22.0cm3. This corresponded with the participants scoring the bladder contour with the higher confidence level rates (majority scoring ≥ 3). Prostate and rectum structures had the greatest contour variability between observers with the maximum range being 32.6cm3 and 36.1 cm3 respectively. Confidence levels also corresponded with this large variation with majority of observers scoring ≤ 2. The same radiographers will repeat the process with the aid of the contouring atlas. Conclusion: It is anticipated that the new atlas for contouring prostate and surrounding OAR anatomy during both online and offline radiotherapy planning scenarios will reduce inter-observer variability, uncertainty and the time needed to contour. This will be of particular benefit in future adapt to shape pathways.