Back

Development of web-based quality-assurance tool for radiotherapy target delineation for head and neck cancer: quality evaluation of nasopharyngeal carcinoma

Kim, J. W.; Marsilla, J.; Kazmierski, M.; Tkachuk, D.; Huang, S. H.; Xu, W.; Cho, J.; Ringash, J.; Bratman, S.; Haibe-Kains, B.; Hope, A.

2021-02-26 oncology
10.1101/2021.02.24.21252123 medRxiv
Show abstract

PurposeWe developed QUANNOTATE, a new web-application for rapid review of radiotherapy (RT) target volumes, and used it to evaluate the relationship between target delineation compliance with the international guidelines and treatment outcomes in nasopharyngeal carcinoma (NPC) patients undergoing definitive RT. Methods and MaterialsThe dataset used for this study consists of anonymized CT simulation scans, RT structures, and clinical data of 332 pathologically confirmed NPC patients treated with intensity-modulated RT between July 2005 and August 2017. We imported the contours of intermediate risk clinical target volumes of the primary tumor (IR-CTVp) receiving 56 Gy into QUANNOTATE. We determined inclusion of anatomic sites within IR-CTVp in accordance with 2018 International guideline for CTV delineation for NPC and correlated the results with time to local failure (TTLF) using Cox-regression. ResultsAt a median follow-up of 5.6 years, 5-year TTLF and overall survival rates were 93.1% and 85.9% respectively. The most frequently non-guideline compliant anatomic sites were sphenoid sinus (n = 69, 20.8%), followed by cavernous sinus (n = 38, 19.3%), left and right petrous apices (n = 37 and 32, 11.1% and 9.6%), clivus (n = 14, 4.2%), and right and left foramen rotundum (n = 14 and 12, 4.2% and 3.6%). Among 23 patients with a local failure (6.9%), the number of non-compliant cases were 8 for sphenoid sinus, 7 cavernous sinus, 4 left and 3 right petrous apices, and 2 clivus. Compared to conforming cases, cases which did not contour the cavernous sinus had a higher local failure (LF) rate (89.1% vs 93.6%, p= 0.013). Multivariable analysis confirmed that lack of cavernous sinus contouring was prognostic for LF. ConclusionsQUANNOTATE allowed rapid review of target volumes in a large patient cohort. Despite an overall high compliance with the international guidelines, undercoverage of the cavernous sinus was correlated with LF.

Matching journals

The top 2 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.