Advertisement

Retrieval of Medical Cases for Diagnostic Decisions: VISCERAL Retrieval Benchmark

  • Oscar Jimenez-del-Toro
  • Henning Müller
  • Antonio Foncubierta-Rodriguez
  • Georg Langs
  • Allan Hanbury
Open Access
Chapter

Abstract

Health providers currently construct their differential diagnosis for a given medical case most often based on textbook knowledge and clinical experience. Data mining of the large amount of medical records generated daily in hospitals is only very rarely done, limiting the reusability of these cases. As part of the VISCERAL project, the Retrieval benchmark was organized to evaluate available approaches for medical case-based retrieval . Participant algorithms were required to find and rank relevant medical cases from a large multimodal dataset (including semantic RadLex terms extracted from text and visual 3D data) for common query topics. The relevance assessment of the cases was done by medical experts who selected cases that are useful for a differential diagnosis for the given query case. The approaches that integrated information from both the RadLex terms and the 3D volumes (mixed techniques) obtained the best results based on five standard evaluation metrics. The benchmark set up, dataset description and result analysis are presented.

Keywords

Mean Average Precision Medical Case Medical Domain Diagnostic Decision Relevance Judgement 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Notes

Acknowledgements

The research leading to these results has received funding from the European Union Seventh Framework Programme (FP7/2007–2013) under grant agreement 318068 (VISCERAL).

References

  1. 1.
    Choi S (2015) Multimodal medical case-based retrieval on the radiology image and report: SNUMedinfo at VISCERAL retrieval benchmark. In: Müller H, Jimenez del Toro OA, Hanbury A, Langs G, Foncubierta Rodríguez A (eds) Multimodal retrieval in the medical domain. LNCS, vol 9059. Springer, Cham, pp 124–128. doi: 10.1007/978-3-319-24471-6_11
  2. 2.
    Foncubierta-Rodríguez A, Müller H (2012) Ground truth generation in medical imaging: a crowdsourcing based iterative approach. In: Workshop on crowdsourcing for multimedia. ACM Multimedia, New York, pp 9–14Google Scholar
  3. 3.
    García Seco de Herrera A (2015) Use case oriented medical visual information retrieval & system evaluation. Ph.D. thesis, University of GenevaGoogle Scholar
  4. 4.
    García Seco de Herrera A, Foncubierta-Rodríguez A, Markonis D, Schaer R, Müller, H (2014) Crowdsourcing for medical image classification. In: Annual congress SGMI 2014Google Scholar
  5. 5.
    Hofmanninger J, Krenn M, Holzer M, Schlegl T, Prosch H, Langs G (2016) Unsupervised identification of clinically relevant clusters in routine imaging data. In: Ourselin S, Joskowicz L, Sabuncu MR, Unal G, Wells W (eds) MICCAI 2016. LNCS, vol 9900. Springer, Cham, pp 192–200. doi: 10.1007/978-3-319-46720-7_23
  6. 6.
    Jiménez-del-Toro OA, Cirujeda P, Cid YD, Müller H (2015) RadLex terms and local texture features for multimodal medical case retrieval. In: Müller H, Jimenez del Toro OA, Hanbury A, Langs G, Foncubierta Rodríguez A (eds) Multimodal retrieval in the medical domain. LNCS, vol 9059. Springer, Cham, pp 144–152. doi: 10.1007/978-3-319-24471-6_14
  7. 7.
    Jiménez-del-Toro OA, Hanbury A, Langs G, Foncubierta-Rodríguez A, Müller H (2015) Overview of the VISCERAL Retrieval Benchmark 2015. In: Müller H, Jimenez del Toro OA, Hanbury A, Langs G, Foncubierta Rodríguez A (eds) Multimodal retrieval in the medical domain. LNCS, vol 9059. Springer, Cham, pp 115–123. doi: 10.1007/978-3-319-24471-6_10
  8. 8.
    Jimenez-del-Toro O, Müller H, Krenn M, Gruenberg K, Taha AA, Winterstein M, Eggel I, Foncubierta-Rodríguez A, Goksel O, Jakab A, Kontokotsios G, Langs G, Menze B, Salas Fernandez T, Schaer R, Walleyo A, Weber MA, Dicente Cid Y, Gass T, Heinrich M, Jia F, Kahl F, Kechichian R, Mai D, Spanier AB, Vincent G, Wang C, Wyeth D, Hanbury A (2016) Cloud-based evaluation of anatomical structure segmentation and landmark detection algorithms: VISCERAL anatomy benchmarks. IEEE Trans Med Imaging 35(11):2459–2475CrossRefGoogle Scholar
  9. 9.
    Kurtz C, Beaulieu CF, Napel S, Rubin DL (2014) A hierarchical knowledge-based approach for retrieving similar medical images described with semantic annotations. J Biomed Inform 49:227–244CrossRefGoogle Scholar
  10. 10.
    Langlotz CP (2006) Radlex: a new method for indexing online educational materials. Radiographics 26(6):1595–1597CrossRefGoogle Scholar
  11. 11.
    Langs G, Hanbury A, Menze B, Müller H (2013) VISCERAL: towards large data in medical imaging — challenges and directions. In: Greenspan H, Müller H, Syeda-Mahmood T (eds) MCBR-CDS 2012. LNCS, vol 7723. Springer, Heidelberg, pp 92–98. doi: 10.1007/978-3-642-36678-9_9
  12. 12.
    Peters C, Braschler M, Clough P (2012) Multilingual information retrieval: from research to practice. Springer, New York, pp 129–169Google Scholar
  13. 13.
    Quellec G, Lamard M, Bekri L, Cazuguel G, Roux C, Cochener B (2010) Medical case retrieval from a committee of decision trees. IEEE Trans Inform Technol Biomed 14(5):1227–1235CrossRefGoogle Scholar
  14. 14.
    Spanier AB, Joskowicz L (2015) Medical case-based retrieval of patient records using the RadLex hierarchical lexicon. In: Müller H, Jimenez del Toro OA, Hanbury A, Langs G, Foncubierta Rodríguez A (eds) Multimodal retrieval in the medical domain. LNCS, vol 9059. Springer, Cham, pp 129–138. doi: 10.1007/978-3-319-24471-6_12
  15. 15.
    Voorhees EM, Ellis A (eds) (2015) In: Proceedings of the twenty-fourth text REtrieval conference, TREC, Gaithersburg, Maryland, USA, 17–20 Nov 2015, vol Special Publication 500–319. National Institute of Standards and Technology (NIST)Google Scholar
  16. 16.
    Zhang F, Song Y, Cai W, Depeursinge A, Müller H (2015) USYD/HES-SO in the VISCERAL retrieval benchmark. In: Müller H, Jimenez del Toro OA, Hanbury A, Langs G, Foncubierta Rodríguez A (eds) Multimodal retrieval in the medical domain. LNCS, vol 9059. Springer, Cham, pp 139–143. doi: 10.1007/978-3-319-24471-6_13

Copyright information

© The Author(s) 2017

Open Access This chapter is distributed under the terms of the Creative Commons Attribution-NonCommercial 2.5 International License (http://creativecommons.org/licenses/by-nc/2.5/), which permits any noncommercial use, duplication, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made. The images or other third party material in this book are included in the work’s Creative Commons license, unless indicated otherwise in the credit line; if such material is not included in the work’s Creative Commons license and the respective action is not permitted by statutory regulation, users will need to obtain permission from the license holder to duplicate, adapt or reproduce the material.

Authors and Affiliations

  • Oscar Jimenez-del-Toro
    • 1
  • Henning Müller
    • 2
  • Antonio Foncubierta-Rodriguez
    • 3
  • Georg Langs
    • 4
  • Allan Hanbury
    • 5
  1. 1.University of Applied Sciences Western Switzerland (HES–SO)SierreSwitzerland
  2. 2.University and University Hospitals of GenevaGenevaSwitzerland
  3. 3.Swiss Federal Institue of Technology (ETH)ZurichSwitzerland
  4. 4.Medical University of ViennaViennaAustria
  5. 5.TU WienViennaAustria

Personalised recommendations