Unsupervised domain adaptation for bladder segmentation by U-net in Cone Beam CT

Details

Supervisors

Macq, Benoît

Faculty

Ecole polytechnique de Louvain

Degree label

Master [120] : ingénieur civil électricien

Abstract

Radiotherapy is a medical treatment used to control or kill cancerous cells in cancer patients. At the beginning of the treatment planning process, the patient takes a CT scan in order to plan his radiation dose and, sometimes, he can take a Cone Beam CT scan some days after, right before receiving his radiation, to adjust his couch position for the delivery. The main difference between CT and CBCT scans is that the first one has a higher quality and contrast, and the second one is taken directly at the isocenter. As the treatment planning takes several days, when the patient receives his radiation his organs might not be in the same position as they were at the beginning, so the healthy tissues around the tumor area can receive more radiation than what it was planned and get damaged. Our aim is to implement an automatic segmentation of the bladder in CBCT 3D images using deep learning, in order to get a clearer idea of the position of those organs. Materials and Methods: In order to implement the segmentation we performed unsu- pervised domain adaptation between CT (the source) and CBCT 3D images (the target), as we didn’t have a large labeled CBCT dataset but we did for CT, as their segmenta- tion is already part of the treatment planning process. We have used a subset dataset of 120 patients: 60 CT and 60 CBCT of the male pelvic region. We have implemented a deep learning network using Unet as a segmenter and a regular CNN as a domain discriminator (an adversarial network), which also includes a gradient reversal layer. We have used the Dice score coefficient and the Hausdorff distance in order to evaluate the performance of our network and compare it with some previous works developed in the same field. Results: We have performed three main experiments, for which we have obtained the following DSC and Hausdorff distance (in voxels): (i) lower boundary: 0.383 ± 0.260 and 36.47, (ii) upper boundary: 0.717 ± 0.177 and 27.44, (iii) unsupervised domain adapta- tion: 0.623 ± 0.149 and 39.18. With this implementation we have closed the gap between training the network only on CT and only on CBCT by a 72%. Conclusions: Cone Beam CT image segmentation using unsupervised domain adap- tation proves to be an improving methodology in radiotherapy and presents different applications in other fields.