SonoRank: Towards Calibration-Free Real-Time Finger Flexion Detection from Forearm Ultrasound Sequences

2026-07-08

AI Summary

This work addresses the challenge of achieving calibration-free, real-time finger flexion detection in ultrasound-based prosthetic control, which traditionally relies on user-specific calibration. The authors propose a novel approach that first pretrains a model using pairwise ranking of relative motion magnitudes from ultrasound video sequences, then fine-tunes it with each individual’s initial resting state as a reference to classify active finger flexion. By integrating ranking-based learning with transfer learning, the method substantially enhances cross-user generalization and reduces dependence on per-user calibration. Evaluated via leave-one-subject-out cross-validation on 12 participants, the approach achieves a 28% improvement in F1 score over a direct classification baseline, demonstrating its effectiveness and superiority in calibration-free scenarios.

Abstract

Powered prosthetic hands are frequently abandoned, largely due to the limited functionality of current devices that rely on surface electromyography (sEMG). Sonomyography (ultrasound) has emerged as a promising alternative, owing to its ability to observe muscle activity in real time and control a greater number of degrees of freedom. Yet, existing ultrasound-based methods require per-user fine-tuning, limiting their commercialization. We propose SonoRank, an important step towards calibration-free finger flexion detection from forearm ultrasound video. SonoRank first learns to rank pairs of ultrasound sequences by their relative motion magnitude for each of the five fingers. The learned representations are then fine-tuned to classify whether each finger is actively flexing, using a rest reference that is captured at the beginning of the operation. Under 12-fold leave-one-subject-out cross-validation on a dataset of twelve subjects with synchronized kinematics, SonoRank achieves a 28% improvement in F1 score over direct classification baselines that skip the ranking stage. These results establish pairwise ranking as an effective pretraining signal for subject-independent control, bringing ultrasound-based prosthetics closer to practical, calibration-free deployment.

Problem

• calibration-free
• finger flexion detection
• ultrasound
• prosthetic control
• subject-independent

Innovation

• SonoRank
• calibration-free
• ultrasound-based control
• pairwise ranking
• finger flexion detection