Cross-Domain Data Augmentation for Deep-Learning-Based Male Pelvic Organ Segmentation in Cone Beam CT

Institute of Information and Communication Technologies, Electronics and Applied Mathematics, Electrical Engineering Department, Université catholique de Louvain, 1348 Louvain-la-Neuve, Belgium

Institut de Recherche Expérimentale et Clinique, Imagerie Médicale, Radiothérapie et Oncologie, Université catholique de Louvain, 1200 Woluwe-Saint-Lambert, Belgium

Authors to whom correspondence should be addressed.

^†

These authors contributed equally to this work.

Appl. Sci. 2020, 10(3), 1154; https://doi.org/10.3390/app10031154

Received: 31 December 2019 / Revised: 1 February 2020 / Accepted: 5 February 2020 / Published: 8 February 2020

(This article belongs to the Special Issue Computer-aided Biomedical Imaging 2020: Advances and Prospects)

View Full-Text Download PDF

Browse Figures

Citation Export

Abstract

For prostate cancer patients, large organ deformations occurring between radiotherapy treatment sessions create uncertainty about the doses delivered to the tumor and surrounding healthy organs. Segmenting those regions on cone beam CT (CBCT) scans acquired on treatment day would reduce such uncertainties. In this work, a 3D U-net deep-learning architecture was trained to segment bladder, rectum, and prostate on CBCT scans. Due to the scarcity of contoured CBCT scans, the training set was augmented with CT scans already contoured in the current clinical workflow. Our network was then tested on 63 CBCT scans. The Dice similarity coefficient (DSC) increased significantly with the number of CBCT and CT scans in the training set, reaching

0.874

0.096

0.814

0.055

, and

0.758

0.101

for bladder, rectum, and prostate, respectively. This was about 10% better than conventional approaches based on deformable image registration between planning CT and treatment CBCT scans, except for prostate. Interestingly, adding 74 CT scans to the CBCT training set allowed maintaining high DSCs, while halving the number of CBCT scans. Hence, our work showed that although CBCT scans included artifacts, cross-domain augmentation of the training set was effective and could rely on large datasets available for planning CT scans. View Full-Text

Keywords: segmentation; deep-learning; deformable image registration; cone beam CT; pelvis; prostate cancer; radiotherapy; CNN; U-net

▼ Show Figures

Figure 1

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited

Share and Cite

MDPI and ACS Style

Léger, J.; Brion, E.; Desbordes, P.; De Vleeschouwer, C.; Lee, J.A.; Macq, B. Cross-Domain Data Augmentation for Deep-Learning-Based Male Pelvic Organ Segmentation in Cone Beam CT. Appl. Sci. 2020, 10, 1154. https://doi.org/10.3390/app10031154

AMA Style

Léger J, Brion E, Desbordes P, De Vleeschouwer C, Lee JA, Macq B. Cross-Domain Data Augmentation for Deep-Learning-Based Male Pelvic Organ Segmentation in Cone Beam CT. Applied Sciences. 2020; 10(3):1154. https://doi.org/10.3390/app10031154

Chicago/Turabian Style

Léger, Jean, Eliott Brion, Paul Desbordes, Christophe De Vleeschouwer, John A. Lee, and Benoit Macq. 2020. "Cross-Domain Data Augmentation for Deep-Learning-Based Male Pelvic Organ Segmentation in Cone Beam CT" Applied Sciences 10, no. 3: 1154. https://doi.org/10.3390/app10031154

Find Other Styles

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Metrics

Abstract views Pdf views Html views

Article Menu

Cross-Domain Data Augmentation for Deep-Learning-Based Male Pelvic Organ Segmentation in Cone Beam CT

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Article Access Map by Country/Region

Further Information

Guidelines

MDPI Initiatives

Follow MDPI