Advertisement

Breast Cancer Research

, 14:P28 | Cite as

Structured evaluation of the effectiveness of an interactive tool for developing interpretation skills in mammography

  • R Pietrosanu
  • H Gay
  • A Patel
  • L Blot
  • M Hartswood
  • R Proctor
  • P Taylor
  • L Wilkinson
Poster presentation

Keywords

Cancer Research Learning Curve Baseline Assessment Detailed Comparison Valuable Addition 
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.

Introduction

Lesion Zoo, a computer-based training tool, was developed to give trainee radiologists access to a wide range of possible mammographic appearances. Users describe lesions using terms from the BI-RADS lexicon and are given feedback on how their descriptions compare with those of by a panel of experts.

Methods

A zoo is a collection of lesions presented to a trainee, who is invited to ascribe features to the lesions and provide a confidence estimate. Trainees receive feedback on their progress, through a detailed comparison of their assessment with that of a panel of experts, and from a learning curve showing how their confidence changes. During this evaluation, two sets of test cases (masses and calcifications) were offered initially as a baseline assessment, followed by training on masses or calcifications, followed by a second assessment after which training was swapped (the group that had initially trained on masses was trained on calcifications and vice versa), and then a third assessment was carried out, allowing a test of the impact of the training on performance.

Results

Analysis of variance shows significant two-way interaction: participants receiving training on calcifications improve more on calcifications than on masses and participants receiving training on masses improve more on masses.

Conclusion

Computer-based training tools provide a valuable addition to conventional training and allow trainees to get rapid access to experience with large numbers of cases. Well-designed tools that provide meaningful feedback on interpretation tasks are likely to be effective in improving performance.

Copyright information

© Pietrosanu et al.; licensee BioMed Central Ltd. 2012

This article is published under license to BioMed Central Ltd. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/2.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Authors and Affiliations

  • R Pietrosanu
    • 1
  • H Gay
    • 1
  • A Patel
    • 2
  • L Blot
    • 3
  • M Hartswood
    • 4
  • R Proctor
    • 5
  • P Taylor
    • 6
  • L Wilkinson
    • 1
  1. 1.St Georges Hospital NHS TrustLondonUK
  2. 2.The Royal Surrey County Hospital NHS Foundation TrustGuildfordUK
  3. 3.University of YorkUK
  4. 4.University of EdinburghUK
  5. 5.University of MiddlesexUK
  6. 6.University College LondonUK

Personalised recommendations