% 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{Zhang:179659,
      author       = {K. S. Zhang$^*$ and P. Schelb$^*$ and N. Netzer$^*$ and A.
                      A. Tavakoli$^*$ and M. Keymling$^*$ and E. Wehrse$^*$ and R.
                      Hog$^*$ and L. T. Rotkopf$^*$ and M. Wennmann$^*$ and P. A.
                      Glemser$^*$ and H. Thierjung$^*$ and N. von Knebel
                      Doeberitz$^*$ and J. Kleesiek$^*$ and M. Görtz$^*$ and V.
                      Schütz and T. Hielscher$^*$ and A. Stenzinger and M.
                      Hohenfellner and H.-P. Schlemmer$^*$ and K. Maier-Hein$^*$
                      and D. Bonekamp$^*$},
      title        = {{P}seudoprospective {P}araclinical {I}nteraction of
                      {R}adiology {R}esidents {W}ith a {D}eep {L}earning {S}ystem
                      for {P}rostate {C}ancer {D}etection: {E}xperience,
                      {P}erformance, and {I}dentification of the {N}eed for
                      {I}ntermittent {R}ecalibration.},
      journal      = {Investigative radiology},
      volume       = {57},
      number       = {9},
      issn         = {0020-9996},
      address      = {[s.l.]},
      publisher    = {Ovid},
      reportid     = {DKFZ-2022-00831},
      pages        = {601-612},
      year         = {2022},
      note         = {#EA:E010#LA:E010# / 2022 Sep 1;57(9):601-612},
      abstract     = {The aim of this study was to estimate the prospective
                      utility of a previously retrospectively validated
                      convolutional neural network (CNN) for prostate cancer (PC)
                      detection on prostate magnetic resonance imaging (MRI).The
                      biparametric (T2-weighted and diffusion-weighted) portion of
                      clinical multiparametric prostate MRI from consecutive men
                      included between November 2019 and September 2020 was fully
                      automatically and individually analyzed by a CNN briefly
                      after image acquisition (pseudoprospective design).
                      Radiology residents performed 2 research Prostate Imaging
                      Reporting and Data System (PI-RADS) assessments of the
                      multiparametric dataset independent from clinical reporting
                      (paraclinical design) before and after review of the CNN
                      results and completed a survey. Presence of clinically
                      significant PC was determined by the presence of an
                      International Society of Urological Pathology grade 2 or
                      higher PC on combined targeted and extended systematic
                      transperineal MRI/transrectal ultrasound fusion biopsy.
                      Sensitivities and specificities on a patient and prostate
                      sextant basis were compared using the McNemar test and
                      compared with the receiver operating characteristic (ROC)
                      curve of CNN. Survey results were summarized as absolute
                      counts and percentages.A total of 201 men were included. The
                      CNN achieved an ROC area under the curve of 0.77 on a
                      patient basis. Using PI-RADS ≥3-emulating probability
                      threshold (c3), CNN had a patient-based sensitivity of
                      $81.8\%$ and specificity of $54.8\%,$ not statistically
                      different from the current clinical routine PI-RADS ≥4
                      assessment at $90.9\%$ and $54.8\%,$ respectively (P =
                      0.30/P = 1.0). In general, residents achieved similar
                      sensitivity and specificity before and after CNN review. On
                      a prostate sextant basis, clinical assessment possessed the
                      highest ROC area under the curve of 0.82, higher than CNN
                      (AUC = 0.76, P = 0.21) and significantly higher than
                      resident performance before and after CNN review (AUC = 0.76
                      / 0.76, P ≤ 0.03). The resident survey indicated CNN to be
                      helpful and clinically useful.Pseudoprospective paraclinical
                      integration of fully automated CNN-based detection of
                      suspicious lesions on prostate multiparametric MRI was
                      demonstrated and showed good acceptance among residents,
                      whereas no significant improvement in resident performance
                      was found. General CNN performance was preserved despite an
                      observed shift in CNN calibration, identifying the
                      requirement for continuous quality control and
                      recalibration.},
      cin          = {E010 / E250 / E230 / HD01 / C060},
      ddc          = {610},
      cid          = {I:(DE-He78)E010-20160331 / I:(DE-He78)E250-20160331 /
                      I:(DE-He78)E230-20160331 / I:(DE-He78)HD01-20160331 /
                      I:(DE-He78)C060-20160331},
      pnm          = {315 - Bildgebung und Radioonkologie (POF4-315)},
      pid          = {G:(DE-HGF)POF4-315},
      typ          = {PUB:(DE-HGF)16},
      pubmed       = {pmid:35467572},
      doi          = {10.1097/RLI.0000000000000878},
      url          = {https://inrepo02.dkfz.de/record/179659},
}