% 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{Buchner:284394,
      author       = {J. A. Buchner and F. Kofler and M. C. Mayinger and T. B.
                      Brunner and A. Wittig and B. Menze and C. Zimmer and B.
                      Meyer and M. Guckenberger and N. Andratschke and R. E.
                      Shafie and S. Rogers and K. Schulze and O. Blanck and C.
                      Zamboglou and A. Grosu$^*$ and S. E. Combs and D.
                      Bernhardt$^*$ and B. Wiestler and J. C. Peeken},
      title        = {{W}hat {MRI} {S}equences are {N}ecessary for {A}utomated
                      {N}eural {N}etwork-{B}ased {M}etastasis {S}egmentation -
                      {A}n {A}blation {S}tudy.},
      journal      = {International journal of radiation oncology, biology,
                      physics},
      volume       = {117},
      number       = {2S},
      issn         = {0360-3016},
      address      = {Amsterdam [u.a.]},
      publisher    = {Elsevier Science},
      reportid     = {DKFZ-2023-01983},
      pages        = {e704 - e705},
      year         = {2023},
      abstract     = {Brain metastasis (BM) delineation is a time-consuming
                      process in both daily clinical practice and research.
                      Automated BM segmentation algorithms can be used to assist
                      in this task. Most approaches to brain tumor segmentation,
                      such as algorithms trained on the BraTS challenge, use four
                      magnetic resonance imaging (MRI) sequences as input, making
                      them susceptible to missing or corrupted sequences and
                      increase the number of sequences necessary for MRI RT
                      planning. The goal of this project is to compare neural
                      networks with different combinations of input sequences for
                      the segmentation of the contrast-enhancing metastasis and
                      the surrounding FLAIR hyperintense edema. All models were
                      tested in a multicenter international external test cohort.
                      This allows us to determine which MRI sequences are needed
                      for effective automated segmentations.In total, we had
                      T1-weighted sequences without (T1) and with contrast
                      enhancement (T1-CE), T2-weighted sequences (T2), and T2
                      fluid-attenuated inversion recovery (FLAIR) sequences from
                      339 patients with at least one brain metastasis from seven
                      centers available. Preprocessing yielded co-registered,
                      skull-stripped sequences with an isotropic resolution of 1
                      millimeter. The contrast-enhancing metastasis as well as the
                      surrounding FLAIR hyperintense edema were manually segmented
                      to create reference labels. A baseline 3D U-Net with all
                      four sequences as well as six additional U-Nets with
                      different clinically plausible combinations (T1-CE; T1;
                      FLAIR; T1-CE+FLAIR; T1-CE+T1+FLAIR; T1-CE+T1) of input
                      sequences were trained on a cohort of 239 patients from two
                      centers and subsequently tested on an external cohort of 100
                      patients from the remaining five centers.All models that
                      included T1-CE in their selected sequences showed similar
                      performance for metastasis segmentation with a median Dice
                      similarity coefficient (DSC) of 0.93-0.96. T1-CE alone
                      likewise achieved a performance of 0.96 (IQR 0.93-0.97). The
                      model trained with only FLAIR performed worse (DSC = 0.73,
                      IQR 0.54-0.84). For edema segmentation, models that included
                      both T1-CE and FLAIR performed best (median DSC = 0.93),
                      while the remaining four models without simultaneous
                      inclusion of these two sequences (T1-CE; T1; FLAIR;
                      T1-CE+T1) reached a median DSC of 0.81-0.89.Automatic
                      segmentation of brain metastases with less than four input
                      sequences is feasible with minimal or no loss of quality. A
                      T1-CE-only protocol suffices for metastasis segmentation. In
                      contrast, for edema segmentation, the combination of T1-CE
                      and FLAIR seems to be important. Missing either T1-CE or
                      FLAIR decreases performance. These findings may improve
                      future imaging routines by omitting unnecessary sequences,
                      thus speeding up procedures in daily clinical practice while
                      allowing for optimal neural network-based target
                      definitions.},
      cin          = {FR01 / MU01},
      ddc          = {610},
      cid          = {I:(DE-He78)FR01-20160331 / I:(DE-He78)MU01-20160331},
      pnm          = {899 - ohne Topic (POF4-899)},
      pid          = {G:(DE-HGF)POF4-899},
      typ          = {PUB:(DE-HGF)16},
      pubmed       = {pmid:37786065},
      doi          = {10.1016/j.ijrobp.2023.06.2195},
      url          = {https://inrepo02.dkfz.de/record/284394},
}