Application of deep learning methods for the optimization of organs at risk (OARs) delineation in breast cancer radiotherapy treatment planning
During breast radiotherapy treatment planning, contouring the healthy organs surrounding breast has a significant role. Unfortunately, this process, of contouring the organs at risks (OARs), can be time consuming and in many cases difficult to shape them correctly. So, this thesis is inspired to...
Κύριος συγγραφέας: | |
---|---|
Άλλοι συγγραφείς: | |
Γλώσσα: | Greek |
Έκδοση: |
2022
|
Θέματα: | |
Διαθέσιμο Online: | https://hdl.handle.net/10889/23945 |
id |
nemertes-10889-23945 |
---|---|
record_format |
dspace |
spelling |
nemertes-10889-239452022-11-16T04:35:36Z Application of deep learning methods for the optimization of organs at risk (OARs) delineation in breast cancer radiotherapy treatment planning Εφαρμογές μεθόδων βαθιάς μάθησης για τη βελτιστοποίηση του σχεδιασμού οργάνων σε κίνδυνο κατά το σχεδιασμό πλάνου ακτινοθεραπείας για τον καρκίνο του μαστού Μακρή-Λεβίδου, Ελένη Makri-Levidou, Eleni Neural networks Radiotherapy Treatment planning Νευρωνικά δίκτυα Ακτινοθεραπεία Σχεδιασμός πλάνου During breast radiotherapy treatment planning, contouring the healthy organs surrounding breast has a significant role. Unfortunately, this process, of contouring the organs at risks (OARs), can be time consuming and in many cases difficult to shape them correctly. So, this thesis is inspired to solve this problem using a CNN to eliminate contouring time. Κατά τον σχεδιασμό ενός πλάνου ακτινοθεραπείας, ο σχεδιασμός των υγιών οργάνων που περιβάλλουν τον όγκο-στόχο μπορεί να γίνει αρκετά χρονοβόρο και σε πολλές περιπτώσεις δύσκολο σε ακρίβεια. Προκειμένου να ελαχιστοποιηθεί αυτός ο χρόνος, προτάθηκε να σχεδιαστεί ένα νευρωνικό δίκτυο που θα λύνει αυτό το πρόβλημα. 2022-11-15T06:49:23Z 2022-11-15T06:49:23Z 2021-12-15 https://hdl.handle.net/10889/23945 gr application/pdf |
institution |
UPatras |
collection |
Nemertes |
language |
Greek |
topic |
Neural networks Radiotherapy Treatment planning Νευρωνικά δίκτυα Ακτινοθεραπεία Σχεδιασμός πλάνου |
spellingShingle |
Neural networks Radiotherapy Treatment planning Νευρωνικά δίκτυα Ακτινοθεραπεία Σχεδιασμός πλάνου Μακρή-Λεβίδου, Ελένη Application of deep learning methods for the optimization of organs at risk (OARs) delineation in breast cancer radiotherapy treatment planning |
description |
During breast radiotherapy treatment planning, contouring the healthy organs surrounding breast has a significant role. Unfortunately, this process, of contouring the organs at risks (OARs), can be time consuming and in many cases difficult to shape them correctly. So, this thesis is inspired to solve this problem using a CNN to eliminate contouring time. |
author2 |
Makri-Levidou, Eleni |
author_facet |
Makri-Levidou, Eleni Μακρή-Λεβίδου, Ελένη |
author |
Μακρή-Λεβίδου, Ελένη |
author_sort |
Μακρή-Λεβίδου, Ελένη |
title |
Application of deep learning methods for the optimization of organs at risk (OARs) delineation in breast cancer radiotherapy treatment planning |
title_short |
Application of deep learning methods for the optimization of organs at risk (OARs) delineation in breast cancer radiotherapy treatment planning |
title_full |
Application of deep learning methods for the optimization of organs at risk (OARs) delineation in breast cancer radiotherapy treatment planning |
title_fullStr |
Application of deep learning methods for the optimization of organs at risk (OARs) delineation in breast cancer radiotherapy treatment planning |
title_full_unstemmed |
Application of deep learning methods for the optimization of organs at risk (OARs) delineation in breast cancer radiotherapy treatment planning |
title_sort |
application of deep learning methods for the optimization of organs at risk (oars) delineation in breast cancer radiotherapy treatment planning |
publishDate |
2022 |
url |
https://hdl.handle.net/10889/23945 |
work_keys_str_mv |
AT makrēlebidouelenē applicationofdeeplearningmethodsfortheoptimizationoforgansatriskoarsdelineationinbreastcancerradiotherapytreatmentplanning AT makrēlebidouelenē epharmogesmethodōnbathiasmathēsēsgiatēbeltistopoiēsētouschediasmouorganōnsekindynokatatoschediasmoplanouaktinotherapeiasgiatonkarkinotoumastou |
_version_ |
1771297203903528960 |