% 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{Morawitz:265119,
      author       = {J. Morawitz and B. Sigl and C. Rubbert and N.-M. Bruckmann
                      and F. Dietzel and L. J. Häberle and S. Ting$^*$ and S.
                      Mohrmann and E. Ruckhäberle and A.-K. Bittner and O.
                      Hoffmann and P. Baltzer and P. Kapetas and T. Helbich and P.
                      Clauser and W. P. Fendler$^*$ and C. Rischpler$^*$ and K.
                      Herrmann$^*$ and B. M. Schaarschmidt and A. Stang and L.
                      Umutlu and G. Antoch and J. Caspers and J. Kirchner},
      title        = {{C}linical {D}ecision {S}upport for {A}xillary {L}ymph
                      {N}ode {S}taging in {N}ewly {D}iagnosed {B}reast {C}ancer
                      {P}atients {B}ased on 18{F}-{FDG} {PET}/{MRI} and {M}achine
                      {L}earning.},
      journal      = {Journal of nuclear medicine},
      volume       = {64},
      number       = {2},
      issn         = {0097-9058},
      address      = {New York, NY},
      publisher    = {Soc.},
      reportid     = {DKFZ-2023-00281},
      pages        = {304 - 311},
      year         = {2023},
      abstract     = {In addition to its high prognostic value, the involvement
                      of axillary lymph nodes in breast cancer patients also plays
                      an important role in therapy planning. Therefore, an imaging
                      modality that can determine nodal status with high accuracy
                      in patients with primary breast cancer is desirable. Our
                      purpose was to investigate whether, in newly diagnosed
                      breast cancer patients, machine-learning prediction models
                      based on simple assessable imaging features on MRI or
                      PET/MRI are able to determine nodal status with performance
                      comparable to that of experienced radiologists; whether such
                      models can be adjusted to achieve low rates of
                      false-negatives such that invasive procedures might
                      potentially be omitted; and whether a clinical framework for
                      decision support based on simple imaging features can be
                      derived from these models. Methods: Between August 2017 and
                      September 2020, 303 participants from 3 centers
                      prospectively underwent dedicated whole-body 18F-FDG
                      PET/MRI. Imaging datasets were evaluated for axillary lymph
                      node metastases based on morphologic and metabolic features.
                      Predictive models were developed for MRI and PET/MRI
                      separately using random forest classifiers on data from 2
                      centers and were tested on data from the third center.
                      Results: The diagnostic accuracy for MRI features was
                      $87.5\%$ both for radiologists and for the machine-learning
                      algorithm. For PET/MRI, the diagnostic accuracy was $89.3\%$
                      for the radiologists and $91.2\%$ for the machine-learning
                      algorithm, with no significant differences in diagnostic
                      performance between radiologists and the machine-learning
                      algorithm for MRI (P = 0.671) or PET/MRI (P = 0.683). The
                      most important lymph node feature was tracer uptake,
                      followed by lymph node size. With an adjusted threshold, a
                      sensitivity of $96.2\%$ was achieved by the random forest
                      classifier, whereas specificity, positive predictive value,
                      negative predictive value, and accuracy were $68.2\%,$
                      $78.1\%,$ $93.8\%,$ and $83.3\%,$ respectively. A decision
                      tree based on 3 simple imaging features could be established
                      for MRI and PET/MRI. Conclusion: Applying a high-sensitivity
                      threshold to the random forest results might potentially
                      avoid invasive procedures such as sentinel lymph node biopsy
                      in $68.2\%$ of the patients.},
      keywords     = {Humans / Female / Fluorodeoxyglucose F18 / Breast
                      Neoplasms: diagnostic imaging / Breast Neoplasms: pathology
                      / Decision Support Systems, Clinical / Sensitivity and
                      Specificity / Lymph Nodes: diagnostic imaging / Lymph Nodes:
                      pathology / Magnetic Resonance Imaging / Neoplasm Staging /
                      Radiopharmaceuticals / PET/MRI (Other) / breast cancer
                      (Other) / lymph node metastases (Other) / machine learning
                      (Other) / Fluorodeoxyglucose F18 (NLM Chemicals) /
                      Radiopharmaceuticals (NLM Chemicals)},
      cin          = {ED01},
      ddc          = {610},
      cid          = {I:(DE-He78)ED01-20160331},
      pnm          = {899 - ohne Topic (POF4-899)},
      pid          = {G:(DE-HGF)POF4-899},
      typ          = {PUB:(DE-HGF)16},
      pubmed       = {pmid:36137756},
      doi          = {10.2967/jnumed.122.264138},
      url          = {https://inrepo02.dkfz.de/record/265119},
}