Comparing deep learning-based auto-segmentation of organs at risk and clinical target volumes to expert inter-observer variability in radiotherapy planning.

Jordan Wong¹, Allan Fong², Nevin McVicar³, Sally Smith⁴, Joshua Giambattista⁵, Derek Wells⁶, Carter Kolbeck⁷, Jonathan Giambattista⁸, Lovedeep Gondara⁹, Abraham Alexander¹⁰

¹BC Cancer - Vancouver Center, Canada. Electronic address: Jordan.wong@bccancer.bc.ca.

²BC Cancer - Vancouver Center, Canada. Electronic address: allan.fong1@bccancer.bc.ca.

³BC Cancer - Vancouver Center, Canada. Electronic address: mcvicarn@rvh.on.ca.

⁴BC Cancer - Victoria Center, Canada. Electronic address: ssmith11@bccancer.bc.ca.

⁵Saskatchewan Cancer Agency, Regina, Canada; Limbus AI Inc., Regina, Canada. Electronic address: joshua.giambattista@saskcancer.ca.

⁶BC Cancer - Victoria Center, Canada. Electronic address: DWells@bccancer.bc.ca.

⁷Limbus AI Inc., Regina, Canada. Electronic address: carter@limbus.ai.

⁸Limbus AI Inc., Regina, Canada. Electronic address: jon@limbus.ai.

⁹BC Cancer - Vancouver Center, Canada. Electronic address: Lovedeep.Gondara@bccancer.bc.ca.

¹⁰BC Cancer - Victoria Center, Canada. Electronic address: AAlexander3@bccancer.bc.ca.

PubMed DOI

Abstract

BACKGROUND: Deep learning-based auto-segmented contours (DC) aim to alleviate labour intensive contouring of organs at risk (OAR) and clinical target volumes (CTV). Most previous DC validation studies have a limited number of expert observers for comparison and/or use a validation dataset related to the training dataset. We determine if DC models are comparable to Radiation Oncologist (RO) inter-o…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free Account Sign In

Want unlimited research access? See Pro plans

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.