Related Experiment Video
Updated: Jun 23, 2026
07:08
Investigating Object Representations in the Macaque Dorsal Visual Stream Using Single-unit Recordings
Published on: August 1, 2018
Computer Vision Scoring of Figure Copy and Recall
Medrxiv : the Preprint Server for Health Sciences
|June 22, 2026
Summary
This study introduces an automated scoring system for figure copy and recall tests using Vertex AI, achieving high accuracy comparable to human experts. This technology simplifies cognitive assessments, making them more accessible for clinical use.
Area of Science:
- Artificial Intelligence in Healthcare
- Cognitive Neuroscience
- Medical Imaging and Computer Vision
Background:
- Figure copy and recall tests are valuable for assessing visuoconstruction and visual episodic memory.
- Traditional manual scoring of these tests is time-consuming and labor-intensive, limiting their clinical application.
- The California Cognitive Assessment Battery (CCAB) utilizes tablet-based figure copy and recall tasks.
Purpose of the Study:
- To develop and validate an automated, element-level scoring pipeline for tablet-based figure copy and recall tasks.
- To leverage Vertex AI object detection for accurate and efficient scoring.
- To ensure the automated pipeline replicates the procedures of expert manual raters.
Main Methods:
- A normative sample of 2,011 adults (aged 18-90) completed figure copy and delayed recall trials on a tablet.
- Finger position data was digitized to analyze drawing stroke speed and timing.
- A convolutional object-detection model (Vertex AI AutoML Vision) identified 12 canonical figure elements; element presence and location scores were computed after warping drawings to a canonical template.
Main Results:
- Automated scoring showed high agreement with expert human raters (Total scores r=0.966 vs. human-human mean r=0.971; Element presence scores mean r=0.959 vs. r=0.963).
- Age significantly affected recall scores (r=-0.32) more than copy scores (r=-0.16), with a monotonic decline in Memory Cost score with age.
- Kinetic analysis revealed age-related changes in drawing speed, efficiency, stroke quality, and intersegment pauses.
Conclusions:
- The automated computer vision pipeline accurately preserves element-level scoring structure and captures memory-specific clinical signals.
- Agreement between automated and human scores significantly surpasses previously reported automated scoring methods.
- This automated scoring approach removes barriers to the broader clinical implementation of figure copy and recall tests.
Related Concept Videos
01:24Vision
Vision is the result of light being detected and transduced into neural signals by the retina of the eye. This information is then further analyzed and interpreted by the brain. First, light enters the front of the eye and is focused by the cornea and lens onto the retina—a thin sheet of neural tissue lining the back of the eye. Because of refraction through the convex lens of the eye, images are projected onto the retina upside-down and reversed.
01:26Visual System
Light enters the eye through the cornea, a transparent, dome-shaped surface covering the surface of the eyeball that helps to direct and focus incoming light. This light is then channeled toward the pupil, an adjustable opening whose size is controlled by the iris. The iris, a pigmented muscle, regulates the amount of light entering the eye by contracting or dilating the pupil, thereby ensuring optimal light levels for clear vision.
Once through the pupil, the light passes through the lens, a...
Once through the pupil, the light passes through the lens, a...