Item request has been placed! ×
Item request cannot be made. ×
loading  Processing Request

Towards a guideline for evaluation metrics in medical image segmentation.

Item request has been placed! ×
Item request cannot be made. ×
loading   Processing Request
Read Online Read More Add to Saved list
  • Additional Information
    • Source:
      Publisher: Biomed Central Country of Publication: England NLM ID: 101462768 Publication Model: Electronic Cited Medium: Internet ISSN: 1756-0500 (Electronic) Linking ISSN: 17560500 NLM ISO Abbreviation: BMC Res Notes Subsets: MEDLINE
    • Publication Information:
      Original Publication: London : Biomed Central, 2008.
    • Subject Terms:
      Algorithms* ; Artificial Intelligence*; Image Processing, Computer-Assisted/methods ; Benchmarking ; ROC Curve ; Reproducibility of Results ; Guidelines as Topic
    • Abstract:
      In the last decade, research on artificial intelligence has seen rapid growth with deep learning models, especially in the field of medical image segmentation. Various studies demonstrated that these models have powerful prediction capabilities and achieved similar results as clinicians. However, recent studies revealed that the evaluation in image segmentation studies lacks reliable model performance assessment and showed statistical bias by incorrect metric implementation or usage. Thus, this work provides an overview and interpretation guide on the following metrics for medical image segmentation evaluation in binary as well as multi-class problems: Dice similarity coefficient, Jaccard, Sensitivity, Specificity, Rand index, ROC curves, Cohen's Kappa, and Hausdorff distance. Furthermore, common issues like class imbalance and statistical as well as interpretation biases in evaluation are discussed. As a summary, we propose a guideline for standardized medical image segmentation evaluation to improve evaluation quality, reproducibility, and comparability in the research field.
      (© 2022. The Author(s).)
    • References:
      Sci Rep. 2020 Aug 13;10(1):13724. (PMID: 32792540)
      Nat Methods. 2019 Dec;16(12):1247-1253. (PMID: 31636459)
      Stud Health Technol Inform. 2021 May 27;281:518-519. (PMID: 34042629)
      IEEE Trans Med Imaging. 2020 Feb;39(2):499-513. (PMID: 31329113)
      BMC Med Imaging. 2015 Aug 12;15:29. (PMID: 26263899)
      Comput Med Imaging Graph. 2015 Jul;43:99-111. (PMID: 25863519)
      Nat Methods. 2021 Feb;18(2):203-211. (PMID: 33288961)
      BMC Med Imaging. 2021 Jan 18;21(1):12. (PMID: 33461500)
      Med Image Anal. 2017 Dec;42:60-88. (PMID: 28778026)
      JAMA. 2019 Dec 24;322(24):2377-2378. (PMID: 31755905)
      Comput Biol Med. 2021 Jul;134:104497. (PMID: 34022486)
      Stud Health Technol Inform. 2021 Sep 21;283:23-31. (PMID: 34545816)
      PLoS One. 2015 Oct 08;10(10):e0140381. (PMID: 26447861)
      PLoS One. 2016 Jun 06;11(6):e0157112. (PMID: 27273091)
      Curr Probl Diagn Radiol. 2021 Mar-Apr;50(2):262-267. (PMID: 32591104)
      J Pathol Inform. 2018 Nov 02;9:37. (PMID: 30533276)
      Eur Radiol Exp. 2021 Jan 21;5(1):4. (PMID: 33474675)
      J Med Imaging (Bellingham). 2021 Jan;8(Suppl 1):010902-10902. (PMID: 34646912)
      Inform Med Unlocked. 2021;25:100681. (PMID: 34337140)
      J Gastroenterol Hepatol. 2021 Jan;36(1):31-38. (PMID: 33140875)
      Brain Commun. 2020 Jul 09;2(2):fcaa096. (PMID: 33134913)
      Data Brief. 2019 Nov 21;28:104863. (PMID: 31867417)
      Radiology. 1982 Apr;143(1):29-36. (PMID: 7063747)
      PLoS One. 2019 Sep 26;14(9):e0222916. (PMID: 31557204)
      Med Image Anal. 2017 Dec;42:44-59. (PMID: 28772163)
      Stud Health Technol Inform. 2022 May 25;294:33-37. (PMID: 35612011)
    • Grant Information:
      FKZ01ZZ1804E Bundesministerium für Bildung und Forschung
    • Contributed Indexing:
      Keywords: Biomedical image segmentation; Semantic segmentation; Medical Image Analysis; Evaluation; Guideline; Performance assessment; Reproducibility
    • Publication Date:
      Date Created: 20220620 Date Completed: 20220622 Latest Revision: 20260305
    • Publication Date:
      20260305
    • Accession Number:
      PMC9208116
    • Accession Number:
      10.1186/s13104-022-06096-y
    • Accession Number:
      35725483