Enhancing Box and Block Test with Computer Vision for Post-Stroke Upper Extremity Motor Evaluation

arXiv cs.CV / 4/1/2026

💬 OpinionSignals & Early TrendsIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper proposes a computer-vision framework to evaluate upper-extremity movement quality in the Box and Block Test using world-aligned joint-angle features rather than ordinal or purely time-based scoring.
It operates with monocular, calibration-free video (no depth sensors or calibration objects) by extracting joint angles for fingers, arm, and trunk.
The authors test the approach on 136 recordings from 48 healthy participants and 7 post-stroke patients, using unsupervised dimensionality reduction to learn movement embeddings without expert clinical labels.
The learned embeddings separate healthy movement patterns from stroke-related deviations and can distinguish patients who share similar standard BBT scores but differ in postural patterns.
The work suggests this camera-based method could augment clinical assessment routines with minimal clinician effort, relying only on phone/camera recordings.

Abstract

Standard clinical assessments of upper-extremity motor function after stroke either rely on ordinal scoring, which lacks sensitivity, or time-based task metrics, which do not capture movement quality. In this work, we present a computer vision-based framework for analysis of upper-extremity movement during the Box and Block Test (BBT) through world-aligned joint angles of fingers, arm, and trunk without depth sensors or calibration objects. We apply this framework to a dataset of 136 BBT recordings collected from 48 healthy individuals and 7 individuals post stroke. Using unsupervised dimensionality reduction of joint-angle features, we analyze movement patterns without relying on expert clinical labels. The resulting embeddings show separation between healthy movement patterns and stroke-related movement deviations. Importantly, some patients with the same BBT scores can be separated with different postural patterns. These results show that world-aligned joint angles can capture meaningful information of upper-extremity functions beyond standard time-based BBT scores, with no effort from the clinician other than monocular video recordings of the patient using a phone or camera. This work highlights the potential of a camera-based, calibration-free framework to measure movement quality in clinical assessments without changing the widely adopted clinical routine.