Tools
ToolsMayne, Violet, Rogers, Harry, Sami, Saber and de la Iglesia, Beatriz (2025) Automating the Clock Drawing Test with Deep Learning and Saliency Maps. In: Progress in Artificial Intelligence. Lecture Notes in Computer Science . Springer, pp. 86-97. ISBN 978-3-031-73499-1
![[thumbnail of 978-3-031-73500-4_8]](https://ueaeprints.uea.ac.uk/style/images/fileicons/application_pdf.png) |
PDF (978-3-031-73500-4_8)
- Accepted Version
Restricted to Repository staff only until 16 November 2025. Request a copy |
Abstract
The Clock Drawing Test (CDT) is an important tool in the diagnosis of Cognitive Decline (CD). Using Deep Learning (DL), this test can be automated with a high degree of accuracy, more so where the medium of recording allows the use of temporal information on how the clock was drawn which may not be accessible to clinicians in traditional screening. The high-risk nature of this field makes understanding the reasoning for automated results imperative. A model’s reasoning can often be described using saliency maps, however, there are a number of different methods for generating such maps. Therefore, we propose a methodology to train a DL classifier for use in the CDT which incorporates temporal information and use saliency maps to explain classification predictions. We find that our classifier achieves scores above 98% with F1 for clocks and over 96% F1 on average across a test set of 18 different classes. Our methodology also shows that Integrated Gradients using SmoothGrad produce the best saliency map results visually and statistically.
Actions (login required)
 |
View Item |