A Multilayer and Multimodal-Fusion Architecture for Simultaneous Recognition of Endovascular Manipulations and Assessment of Technical Skills

Zhou, Xiao-Hu; Xie, Xiao-Liang; Zhao, Feng; Hou, Zeng-Guang; Bian, Gui‐Bin; Li, Ruiqi; Ni, Zhen-Liang; Liu, Shiqi; Zhou, Yanjie

doi:10.1109/tcyb.2020.3004653

Cited by 14 publications

(2 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The recent progress in machine intelligence is attributed to the availability of exploded data, low-cost computation and storage capacities, and newly developed learning algorithms. Thus, deep learning was reported to be suboptimal when trained with small-sized data [31][32][33][34]. The in-vivo experiments produced a multimodal dataset of 54,430 samples from both animals which were pre-processed as discussed in Materials and Methods section, and used to characterize subjects' manipulation skills.…”

Section: Discussionmentioning

confidence: 99%

On Task-specific Autonomy in Robotic Interventions: A Multimodal Learning-based Approach for Multi-level Skill Assessment during Cyborg Catheterization

Omisore¹,

Duan²,

Du³

et al. 2021

Preprint

View full text Add to dashboard Cite

Lack of learning-based methods for characterizing the multimodal data generated during cyborg catheterization hinders the drive towards autonomous robotic control. Also, multiplexing salient features from multiple data-sources can enhance effective assessment and classification of domain skills for apt intelligent surgeon-robot (cyborg) catheterization during intravascular interventions. In this study, task-specific autonomous intervention is envisioned upon an isomorphic master-slave robotic catheter system that exhibit hand defter techniques used in Cath Labs. To drive cyborg catheterization, stacking-based deep neural network is developed for three-level skill assessment.<br>

show abstract

Section: Discussionmentioning

confidence: 99%

On Task-specific Autonomy in Robotic Interventions: A Multimodal Learning-based Approach for Multi-level Skill Assessment during Cyborg Catheterization

Omisore¹,

Duan²,

Du³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…In addition, a multilayer and multimodal-fusion architecture was developed to discriminate the manipulations made by surgeons with varying degrees of experience based on the aforementioned natural behaviors. An accuracy of 95% can be obtained to cluster the attempts performed by different skill-level groups [37]. Du et al [38][39][40] proposed a random forest classification framework to properly identify the surgeon's technical manipulation skills during PCI catheterization based on muscular activities and related hand motion, which were derived from physiological data detected by EM, sEMG, and flexible pressure sensors.…”

Section: Introductionmentioning

confidence: 99%

An Image Information-Based Objective Assessment Method of Technical Manipulation Skills for Intravascular Interventions

Guo

Wang

et al. 2023

Sensors

View full text Add to dashboard Cite

The clinical success of vascular interventional surgery relies heavily on a surgeon’s catheter/guidewire manipulation skills and strategies. An objective and accurate assessment method plays a critical role in evaluating the surgeon’s technical manipulation skill level. Most of the existing evaluation methods incorporate the use of information technology to find more objective assessment models based on various metrics. However, in these models, sensors are often attached to the surgeon’s hands or to interventional devices for data collection, which constrains the surgeon’s operational movements or exerts an influence on the motion trajectory of interventional devices. In this paper, an image information-based assessment method is proposed for the evaluation of the surgeon’s manipulation skills without the requirement of attaching sensors to the surgeon or catheters/guidewires. Surgeons are allowed to use their natural bedside manipulation skills during the data collection process. Their manipulation features during different catheterization tasks are derived from the motion analysis of the catheter/guidewire in video sequences. Notably, data relating to the number of speed peaks, slope variations, and the number of collisions are included in the assessment. Furthermore, the contact forces, resulting from interactions between the catheter/guidewire and the vascular model, are sensed by a 6-DoF F/T sensor. A support vector machine (SVM) classification framework is developed to discriminate the surgeon’s catheterization skill levels. The experimental results demonstrate that the proposed SVM-based assessment method can obtain an accuracy of 97.02% to distinguish between the expert and novice manipulations, which is higher than that of other existing research achievements. The proposed method has great potential to facilitate skill assessment and training of novice surgeons in vascular interventional surgery.

show abstract

Accurate Perception of Manipulation Force Makes Vascular Intervention Safer

Yao,

Zhou,

Xie

et al. 2023

Procedia Computer Science

View full text Add to dashboard Cite

A Multilayer and Multimodal-Fusion Architecture for Simultaneous Recognition of Endovascular Manipulations and Assessment of Technical Skills

Cited by 14 publications

References 43 publications

On Task-specific Autonomy in Robotic Interventions: A Multimodal Learning-based Approach for Multi-level Skill Assessment during Cyborg Catheterization

On Task-specific Autonomy in Robotic Interventions: A Multimodal Learning-based Approach for Multi-level Skill Assessment during Cyborg Catheterization

An Image Information-Based Objective Assessment Method of Technical Manipulation Skills for Intravascular Interventions

Accurate Perception of Manipulation Force Makes Vascular Intervention Safer

Contact Info

Product

Resources

About