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

Learning-Based Multimodal Information Fusion and Behavior Recognition of Vascular Interventionists' Operating Skills

The operating skills of vascular interventionists have an important impact on the effect of surgery. However, current research on behavior recognition and skills learning of interventionists' operating skills is limited. In this study, an innovative deep learning-based multimodal information fusion architecture is proposed for recognizing and analyzing eight common operating behaviors of interventionists. An experimental platform integrating four modal sensors is used to collect multimodal data from interventionists. The ANOVA and Manner-Whitney tests is used for relevance analysis of the data. The analysis results demonstrate that there is almost no significant difference ( p <0.001) between the actions related to the unimodal data, which cannot be used for accurate behavior recognition. Therefore, a study of the fusion architecture based on the existing machine learning classifier and the proposed deep learning fusion architecture is carried out. The research findings indicate that the proposed deep learning-based fusion architecture achieves an impressive overall accuracy of 98.5%, surpassing both the machine learning classifier (93.51%) and the unimodal data (90.05%). The deep learning-based multimodal information fusion architecture proves the feasibility of behavior recognition and skills learning of interventionist's operating skills. Furthermore, the application of deep learning-based multimodal fusion technology of surgeon's operating skills will help to improve the autonomy and intelligence of surgical robotic systems.

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

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.

A Unified Framework for Multi-Guidewire Endpoint Localization in Fluoroscopy Images

OBJECTIVE

In this paper, Keypoint Localization Region-based CNN (KL R-CNN) is proposed, which can simultaneously accomplish the guidewire detection and endpoint localization in a unified model.

METHODS

KL R-CNN modifies Mask R-CNN by replacing the mask branch with a novel keypoint localization branch. Besides, some settings of Mask R-CNN are also modified to generate the keypoint localization results at a higher detail level. At the same time, based on the existing metrics of Average Precision (AP) and Percentage of Correct Keypoints (PCK), a new metric named AP PCK is proposed to evaluate the overall performance on the multi-guidewire endpoint localization task. Compared with existing metrics, AP PCK is easy to use and its results are more intuitive.

RESULTS

Compared with existing methods, KL R-CNN has better performance when the threshold is loose, reaching a mean AP PCK of 90.65% when the threshold is 9 pixels.

CONCLUSION

KL R-CNN achieves the state-of-the-art performance on the multi-guidewire endpoint localization task and has application potentials.

SIGNIFICANCE

KL R-CNN can achieve the localization of guidewire endpoints in fluoroscopy images, which is a prerequisite for computer-assisted percutaneous coronary intervention. KL R-CNN can also be extended to other multi-instrument localization tasks.