ATTENTION/WARNING - NE PAS DÉPOSER ICI/DO NOT SUBMIT HERE

Ceci est la version de TEST de DIAL.mem. Veuillez ne pas soumettre votre mémoire sur ce site mais bien à l'URL suivante: 'https://thesis.dial.uclouvain.be'.
This is the TEST version of DIAL.mem. Please use the following URL to submit your master thesis: 'https://thesis.dial.uclouvain.be'.
 

Atlas-based segmentation of the bladder and rectum in prostate cancer patients : application to radiotherapy

(2018)

Files

Adant_70781200_2018.pdf
  • Open access
  • Adobe PDF
  • 17.5 MB

Details

Supervisors
Faculty
Degree label
Abstract
Nowadays, more than half of the patients suffering from cancer will need radiotherapy during their treatment. Radiotherapy is a treatment modality that uses radiation to irradiate cancerous cells to destroy them by blocking their ability to proliferate. Unfortunately, these radiations will also reach healthy cells. In order to spare the healthy tissues while maximizing the dose in the tumor a plan has to be established before the treatment. This plan requires a precise segmentation of the tumor and of the organs around it. Currently this delineation step is manually executed by physicians at the hospital and is very time consuming. Moreover a radiotherapy treatment consists of approximately 30 sessions spread over 5-6 weeks. During this period, patients may undergo anatomical changes due to weight loss or due to the treatment. The plan should potentially be adapted to take these changes into account, requiring a new delineation step to spot these changes and determine the new plan. In this context, we evaluate in this master thesis several methods that use atlases and pairwise registration in order to automatically segment the bladder and rectum in prostate cancer patient on CT and CBCT images. The goal being at first to give indications to the physicians about the need for re-planning or not and then to be used as an actual contour during the planning.