June 2022
Volume 63, Issue 7
Open Access
ARVO Annual Meeting Abstract  |   June 2022
Qualitative comparison of AutoML explainability tools with bespoke saliency methods
Author Affiliations & Notes
  • Sara Beqiri
    Moorfields Eye Hospital NHS Foundation Trust, London, London, United Kingdom
    University College London Medical School, London, London, United Kingdom
  • Eneda Rustemi
    Ophthalmology, University Hospital Centre Mother Teresa, Tirana, Albania
  • Madeline Kelly
    Moorfields Eye Hospital NHS Foundation Trust, London, London, United Kingdom
    University College London Medical School, London, London, United Kingdom
  • Robbert Struyven
    University College London Medical School, London, London, United Kingdom
    Moorfields Eye Hospital NHS Foundation Trust, London, London, United Kingdom
  • Edward Korot
    Byers Eye Institute, Stanford University, Stanford, CA, United States., California, United States
    Moorfields Eye Hospital NHS Foundation Trust, London, London, United Kingdom
  • Pearse Andrew Keane
    Moorfields Eye Hospital NHS Foundation Trust, London, London, United Kingdom
  • Footnotes
    Commercial Relationships   Sara Beqiri None; Eneda Rustemi None; Madeline Kelly None; Robbert Struyven None; Edward Korot Genentech, Code E (Employment), Reti Health, Code I (Personal Financial Interest); Pearse Keane DeepMind, Roche, Novartis, Apellis, Code C (Consultant/Contractor), Big Picture Medical, Code I (Personal Financial Interest), Heidelberg Engineering, Bayer, Topcon, Allergan, Code R (Recipient)
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science June 2022, Vol.63, 200 – F0047. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Sara Beqiri, Eneda Rustemi, Madeline Kelly, Robbert Struyven, Edward Korot, Pearse Andrew Keane; Qualitative comparison of AutoML explainability tools with bespoke saliency methods. Invest. Ophthalmol. Vis. Sci. 2022;63(7):200 – F0047.

      Download citation file:


      © ARVO (1962-2015); The Authors (2016-present)

      ×
  • Supplements
Abstract

Purpose : Google Cloud Platform (GCP) empowers clinicians to explore Artificial Intelligence (AI) via its code-free user interface. This, however, is associated with a low level of transparency and control over algorithm design. As a solution, the GCP Explainable AI features can produce saliency heatmaps with minimal coding, highlighting regions of model interest to guide clinician’s understanding.
We present a qualitative evaluation of these explanations through a user survey, comparing them to the same saliency technique produced from a bespoke model.

Methods : We trained two algorithms for the binary classification of referrable vs non-referrable Diabetic Retinopathy (DR), using the same 60,133 fundus images from publicly available datasets. The AutoML and bespoke models reached accuracies of 93.7%, and 96.5% respectively, sufficient for our purposes of saliency map assessment.
12 test images were selected to represent varying degrees of AutoML prediction confidence. For each image, an XRAI saliency map was produced for both the AutoML and bespoke algorithms. The prior involved minimal coding, whereas the latter required a fully coded Jupyter notebook.
These maps were provided to a consultant ophthalmologist with 20 years of experience, who answered a survey of three specified questions per image, via a 5-point Likert scale. These focused on the map’s localisation ability, clarity of information, and overall quality.

Results : Paired t-tests showed no statistically significant difference between the AutoML and bespoke map scores (3.25±0.75 vs 3.58±0.51) when comparing quality, however localisation ability and clarity of information were significantly higher for the bespoke model (2.75±1.14 vs 3.92±0.51, and 2.67±1.07 vs 3.83±0.58). A combined score for the three questions also showed a significant difference with a mean of 11.3±2.9 for bespoke and 8.67±1.44 for AutoML.

Conclusions : Our results showed that utilising the same saliency method and dataset in two different models can lead to significantly differing maps. Our qualitative evaluation depicted superiority of bespoke saliency maps in localisation and clarity when compared to the AutoML explainability tools.

This abstract was presented at the 2022 ARVO Annual Meeting, held in Denver, CO, May 1-4, 2022, and virtually.

×
×

This PDF is available to Subscribers Only

Sign in or purchase a subscription to access this content. ×

You must be signed into an individual account to use this feature.

×