Deep learning-based fully automated detection and segmentation of lymph nodes on multiparametric-mri for rectal cancer: A multicentre study.

Item request has been placed! ×
Item request cannot be made. ×
loading   Processing Request
Read More Add to Saved list
  • Additional Information
    • Source:
      Publisher: Elsevier B.V Country of Publication: Netherlands NLM ID: 101647039 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 2352-3964 (Electronic) Linking ISSN: 23523964 NLM ISO Abbreviation: EBioMedicine Subsets: MEDLINE
    • Publication Information:
      Original Publication: [Amsterdam] : Elsevier B.V., [2014]-
    • Subject Terms:
      Adenocarcinoma/*diagnostic imaging ; Lymph Nodes/*diagnostic imaging ; Multiparametric Magnetic Resonance Imaging/*methods ; Pelvis/*diagnostic imaging ; Radiographic Image Interpretation, Computer-Assisted/*methods ; Rectal Neoplasms/*diagnostic imaging; Adenocarcinoma/pathology ; Automation ; Clinical Competence ; Deep Learning ; Diffusion Magnetic Resonance Imaging ; Female ; Humans ; Lymph Nodes/pathology ; Male ; Neoplasm Staging ; Pelvis/pathology ; Radiologists ; Rectal Neoplasms/pathology ; Sensitivity and Specificity
    • Abstract:
      Background: Accurate lymph nodes (LNs) assessment is important for rectal cancer (RC) staging in multiparametric magnetic resonance imaging (mpMRI). However, it is incredibly time-consumming to identify all the LNs in scan region. This study aims to develop and validate a deep-learning-based, fully-automated lymph node detection and segmentation (auto-LNDS) model based on mpMRI.
      Methods: In total, 5789 annotated LNs (diameter ≥ 3 mm) in mpMRI from 293 patients with RC in a single center were enrolled. Fused T2-weighted images (T2WI) and diffusion-weighted images (DWI) provided input for the deep learning framework Mask R-CNN through transfer learning to generate the auto-LNDS model. The model was then validated both on the internal and external datasets consisting of 935 LNs and 1198 LNs, respectively. The performance for LNs detection was evaluated using sensitivity, positive predictive value (PPV), and false positive rate per case (FP/vol), and segmentation performance was evaluated using the Dice similarity coefficient (DSC).
      Findings: For LNs detection, auto-LNDS achieved sensitivity, PPV, and FP/vol of 80.0%, 73.5% and 8.6 in internal testing, and 62.6%, 64.5%, and 8.2 in external testing, respectively, significantly better than the performance of junior radiologists. The time taken for model detection and segmentation was 1.3 s/case, compared with 200 s/case for the radiologists. For LNs segmentation, the DSC of the model was in the range of 0.81-0.82.
      Interpretation: This deep learning-based auto-LNDS model can achieve pelvic LNseffectively based on mpMRI for RC, and holds great potential for facilitating N-staging in clinical practice.
      (Copyright © 2020 The Authors. Published by Elsevier B.V. All rights reserved.)
    • References:
      Comput Methods Programs Biomed. 2017 May;143:67-74. (PMID: 28391820)
      IEEE Trans Med Imaging. 2012 Feb;31(2):240-50. (PMID: 21968722)
      Med Phys. 2011 Nov;38(11):6178-87. (PMID: 22047383)
      Med Image Comput Comput Assist Interv. 2007;10(Pt 2):336-43. (PMID: 18044586)
      Med Image Anal. 2013 Feb;17(2):254-70. (PMID: 23246185)
      Clin Cancer Res. 2007 Nov 15;13(22 Pt 2):6877s-84s. (PMID: 18006793)
      ANZ J Surg. 2018 Dec;88(12):1306-1310. (PMID: 29974631)
      Neuroimage. 2015 Mar;108:214-24. (PMID: 25562829)
      Eur Radiol. 2019 Jun;29(6):3200-3209. (PMID: 30413959)
      Eur Radiol. 2013 Dec;23(12):3354-60. (PMID: 23821022)
      IEEE Trans Pattern Anal Mach Intell. 2017 Jun;39(6):1137-1149. (PMID: 27295650)
      Langenbecks Arch Surg. 2006 Sep;391(5):449-54. (PMID: 16847648)
      World J Surg. 2016 Apr;40(4):995-1001. (PMID: 26541864)
      Dis Colon Rectum. 2015 Apr;58(4):406-14. (PMID: 25751797)
      Ann Surg Oncol. 2008 Mar;15(3):729-37. (PMID: 18057989)
      J Clin Oncol. 2019 Jan 1;37(1):33-43. (PMID: 30403572)
      Cancer Res. 2018 Sep 1;78(17):5135-5143. (PMID: 30026330)
      Comput Med Imaging Graph. 2004 Jan-Mar;28(1-2):33-8. (PMID: 15127747)
      Med Image Comput Comput Assist Interv. 2006;9(Pt 2):904-11. (PMID: 17354859)
      Lancet Oncol. 2009 Nov;10(11):1053-62. (PMID: 19767239)
      Australas Phys Eng Sci Med. 2018 Jun;41(2):393-401. (PMID: 29654521)
      Proc Mach Learn Res. 2019 Jun;97:1528-1537. (PMID: 31777848)
      Ann Surg Oncol. 2013 Apr;20(4):1148-55. (PMID: 23143592)
      PLoS Med. 2004 Dec;1(3):e66. (PMID: 15630471)
      Med Phys. 2016 Jul;43(7):4362. (PMID: 27370151)
      Radiology. 2019 Jan;290(1):218-228. (PMID: 30251934)
      J Gastrointest Surg. 2018 Jan;22(1):146-153. (PMID: 28900855)
    • Contributed Indexing:
      Keywords: Deep learning; Detection and segmentation; Lymph node
    • Publication Date:
      Date Created: 20200609 Date Completed: 20210412 Latest Revision: 20240729
    • Publication Date:
      20240729
    • Accession Number:
      PMC7276514
    • Accession Number:
      10.1016/j.ebiom.2020.102780
    • Accession Number:
      32512507