RT-DEMT: A hybrid real-time acupoint detection model combining mamba and transformer

2025-02-16

AI Summary

To address the subjectivity in acupoint localization during clinical acupuncture and the low speed and accuracy of existing intelligent systems, this paper proposes a real-time Mamba-Transformer hybrid detection framework. Methodologically, we introduce the first lightweight architecture integrating the Mamba state-space model with the Transformer’s attention mechanism; furthermore, we replace conventional upsampling with residual likelihood estimation to enable end-to-end differentiable localization. Evaluated on a proprietary dorsal acupoint dataset, our approach achieves state-of-the-art performance: an average pixel error of 7.792 and a single-acupoint localization latency of only 10.05 ms. Both accuracy and speed improve by approximately 14% over the second-best method, marking the first demonstration of millisecond-level, high-precision dorsal acupoint detection.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Computer Vision: Multi-modal Vision

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization

Abstract

Traditional Chinese acupuncture methods often face controversy in clinical practice due to their high subjectivity. Additionally, current intelligent-assisted acupuncture systems have two major limitations: slow acupoint localization speed and low accuracy. To address these limitations, a new method leverages the excellent inference efficiency of the state-space model Mamba, while retaining the advantages of the attention mechanism in the traditional DETR architecture, to achieve efficient global information integration and provide high-quality feature information for acupoint localization tasks. Furthermore, by employing the concept of residual likelihood estimation, it eliminates the need for complex upsampling processes, thereby accelerating the acupoint localization task. Our method achieved state-of-the-art (SOTA) accuracy on a private dataset of acupoints on the human back, with an average Euclidean distance pixel error (EPE) of 7.792 and an average time consumption of 10.05 milliseconds per localization task. Compared to the second-best algorithm, our method improved both accuracy and speed by approximately 14%. This significant advancement not only enhances the efficacy of acupuncture treatment but also demonstrates the commercial potential of automated acupuncture robot systems. Access to our method is available at https://github.com/Sohyu1/RT-DEMT

Problem

• Improve acupoint localization speed
• Enhance acupoint detection accuracy
• Combine Mamba and Transformer for efficiency

Innovation

• Combines Mamba and transformer models
• Utilizes residual likelihood estimation
• Accelerates acupoint localization efficiently