Deep learning-based auto-segmentation of targets and organs-at-risk for magnetic resonance imaging only planning of prostate radiotherapy. (October 2019)

• Record Type: Journal Article
• Authors: Elguindi, Sharif; Zelefsky, Michael J.; Jiang, Jue; Veeraraghavan, Harini; Deasy, Joseph O.; Hunt, Margie A.; Tyagi, Neelam
• Is Part Of: Physics and imaging in radiation oncology. Volume 12(2019)
• Page Start: 80
• Page End: 86
• Publication Date: 2019-10
• Subjects: Deep learning -- Autosegmentation -- MR-only -- U-Net -- Prostate cancer; Radiotherapy -- Periodicals; Radiation dosimetry -- Periodicals; Cancer -- Imaging -- Periodicals; Oncology -- Periodicals; 615.842
• DOI: 10.1016/j.phro.2019.11.006
• Languages: English
• ISSNs: 2405-6316

Abstract

Highlights: Auto-segmentation using Deep Learning can be difficult with a small medical dataset. Transfer learning allows deep learning networks to retrain easily on small datasets. We successfully apply this method to auto-segment targets and OARs in prostate radiation therapy. Abstract: Background and purpose: Magnetic resonance (MR) only radiation therapy for prostate treatment provides superior contrast for defining targets and organs-at-risk (OARs). This study aims to develop a deep learning model to leverage this advantage to automate the contouring process. Materials and methods: Six structures (bladder, rectum, urethra, penile bulb, rectal spacer, prostate and seminal vesicles) were contoured and reviewed by a radiation oncologist on axial T2-weighted MR image sets from 50 patients, which constituted expert delineations. The data was split into a 40/10 training and validation set to train a two-dimensional fully convolutional neural network, DeepLabV3+, using transfer learning. The T2-weighted image sets were pre-processed to 2D false color images to leverage pre-trained (from natural images) convolutional layers' weights. Independent testing was performed on an additional 50 patient's MR scans. Performance comparison was done against a U-Net deep learning method. Algorithms were evaluated using volumetric Dice similarity coefficient (VDSC) and surface Dice similarity coefficient (SDSC). Results: When comparing VDSC, DeepLabV3+ significantly outperformed U-Net for all structures except urethra ( P < 0.001). Average VDSC was 0.93 ± 0.04 (bladder), 0.83 ± 0.06 (prostate and seminal vesicles [CTV]), 0.74 ± 0.13 (penile bulb), 0.82 ± 0.05 (rectum), 0.69 ± 0.10 (urethra), and 0.81 ± 0.1 (rectal spacer). Average SDSC was 0.92 ± 0.1 (bladder), 0.85 ± 0.11 (prostate and seminal vesicles [CTV]), 0.80 ± 0.22 (penile bulb), 0.87 ± 0.07 (rectum), 0.85 ± 0.25 (urethra), and 0.83 ± 0.26 (rectal spacer). Conclusion: A deep learning-based model produced contours that show promise to streamline an MR-only planning workflow in treating prostate cancer.