Comparing deep learning-based auto-segmentation of organs at risk and clinical target volumes to expert inter-observer variability in radiotherapy planning. (March 2020)

• Record Type: Journal Article
• Authors: Wong, Jordan; Fong, Allan; McVicar, Nevin; Smith, Sally; Giambattista, Joshua; Wells, Derek; Kolbeck, Carter; Giambattista, Jonathan; Gondara, Lovedeep; Alexander, Abraham
• Is Part Of: Radiotherapy and oncology. Volume 144(2020)
• Page Start: 152
• Page End: 158
• Publication Date: 2020-03
• Subjects: Machine learning -- Radiotherapy; Oncology -- Periodicals; Radiotherapy -- Periodicals; Tumors -- Periodicals; Medical Oncology -- Periodicals; Neoplasms -- radiotherapy -- Periodicals; Radiotherapy -- Periodicals; Radiothérapie -- Périodiques; Cancérologie -- Périodiques; Tumeurs -- Périodiques; Electronic journals; 616.9940642
• DOI: 10.1016/j.radonc.2019.10.019
• Languages: English
• ISSNs: 0167-8140

Abstract

Highlights: Deep learning-based auto-segmented contours (DC) can provide significant time savings. DCs for organs at risk accurately reproduce expert contours. DCs for target volumes are less accurate but may serve as a template for manual edits. 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-observer variability on an independent dataset. Methods: Expert contours (EC) were created by multiple ROs for central nervous system (CNS), head and neck (H&N), and prostate radiotherapy (RT) OARs and CTVs. DCs were generated using deep learning-based auto-segmentation software trained by a single RO on publicly available data. Contours were compared using Dice Similarity Coefficient (DSC) and 95% Hausdorff distance (HD). Results: Sixty planning CT scans had 2–4 ECs, for a total of 60 CNS, 53 H&N, and 50 prostate RT contour sets. The mean DC and EC contouring times were 0.4 vs 7.7 min for CNS, 0.6 vs 26.6 min for H&N, and 0.4 vs 21.3 min for prostate RT contours. There were minimal differences in DSC and 95% HD involving DCs for OAR comparisons, but more noticeable differences for CTV comparisons. Conclusions: The accuracy of DCs trained by a single RO is comparable to expert inter-observer variability for the RT planning contours in this study. Use of deep learning-based auto-segmentation in clinical practice will likely lead to significant benefits to RT planning workflow and resources.