% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@ARTICLE{Neishabouri:166498,
      author       = {A. Neishabouri$^*$ and N. Wahl$^*$ and A. Mairani and U.
                      Köthe and M. Bangert$^*$},
      title        = {{L}ong short-term memory networks for proton dose
                      calculation in highly heterogeneous tissues.},
      journal      = {Medical physics},
      volume       = {48},
      number       = {4},
      issn         = {2473-4209},
      address      = {College Park, Md.},
      publisher    = {AAPM},
      reportid     = {DKFZ-2020-02941},
      pages        = {1893-1908},
      year         = {2021},
      note         = {#EA:E040#LA:E040# / 2021 Apr;48(4):1893-1908},
      abstract     = {To investigate the feasibility and accuracy of proton dose
                      calculations with artificial neural networks (ANN) in
                      challenging 3D anatomies.A novel proton dose calculation
                      approach was designed based on the application of a long
                      short-term memory (LSTM) network. It processes the 3D
                      geometry as a sequence of two-dimensional (2D) computed
                      tomography slices and outputs a corresponding sequence of
                      (2D) slices that forms the 3D dose distribution. The general
                      accuracy of the approach is investigated in comparison to
                      Monte Carlo reference simulations and pencil beam dose
                      calculations. We consider both artificial phantom geometries
                      and clinically realistic lung cases for three different
                      pencil beam energies.For artificial phantom cases, the
                      trained LSTM model achieved a $98:57\%$ γ -index pass rate
                      $([1\%,$ 3mm]) in comparison to MC simulations for a pencil
                      beam with initial energy 104:25MeV. For a lung patient case,
                      we observe pass rates of $98:56\%,$ $97:74\%,$ and $94:51\%$
                      for an initial energy of 67:85MeV, 104:25MeV, and 134:68MeV,
                      respectively. Applying the LSTM dose calculation on patient
                      cases that were fully excluded from the training process
                      yields an average - γ index pass rate of $97:85\%.LSTM$
                      networks are well suited for proton dose calculation tasks.
                      Further research, especially regarding model generalization
                      and computational performance in comparison to established
                      dose calculation methods, is warranted.},
      cin          = {E040},
      ddc          = {610},
      cid          = {I:(DE-He78)E040-20160331},
      pnm          = {315 - Bildgebung und Radioonkologie (POF4-315)},
      pid          = {G:(DE-HGF)POF4-315},
      typ          = {PUB:(DE-HGF)16},
      pubmed       = {pmid:33332644},
      doi          = {10.1002/mp.14658},
      url          = {https://inrepo02.dkfz.de/record/166498},
}