Fluence-map generation for prostate intensity-modulated radiotherapy planning using a deep-neural-network

Cited 26 time in webofscience Cited 24 time in scopus
  • Hit : 493
  • Download : 296
A deep-neural-network (DNN) was successfully used to predict clinically-acceptable dose distributions from organ contours for intensity-modulated radiotherapy (IMRT). To provide the next step in the DNN-based plan automation, we propose a DNN that directly generates beam fluence maps from the organ contours and volumetric dose distributions, without inverse planning. We collected 240 prostate IMRT plans and used to train a DNN using organ contours and dose distributions. After training was done, we made 45 synthetic plans (SPs) using the generated fluence-maps and compared them with clinical plans (CP) using various plan quality metrics including homogeneity and conformity indices for the target and dose constraints for organs at risk, including rectum, bladder, and bowel. The network was able to generate fluence maps with small errors. The qualities of the SPs were comparable to the corresponding CPs. The homogeneity index of the target was slightly worse in the SPs, but there was no difference in conformity index of the target, V-60Gy of rectum, the V-60Gy of bladder and the V-4(5G)y of bowel. The time taken for generating fluence maps and qualities of SPs demonstrated the proposed method will improve efficiency of the treatment planning and help maintain the quality of plans.
Publisher
NATURE PUBLISHING GROUP
Issue Date
2019-10
Language
English
Article Type
Article
Citation

SCIENTIFIC REPORTS, v.9

ISSN
2045-2322
DOI
10.1038/s41598-019-52262-x
URI
http://hdl.handle.net/10203/268451
Appears in Collection
NE-Journal Papers(저널논문)
Files in This Item
s41598-019-52262-x.pdf(3.3 MB)Download
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 26 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0