Analysis of the Structure of Surgical Activity for a Suturing and Knot-Tying Task

Vedula, Satyanarayana S; Malpani, Anand; Tao, Lingling; Gao, Yixin; Poddar, Piyush; Ahmidi, Narges; Paxton, Christopher; Vidal, René; Khudanpur, Sanjeev; Hager, Gregory D.; Chen, Grace

doi:10.1371/journal.pone.0149174

Cited by 35 publications

(28 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This shows that the described techniques perform 8× to 10× better than chance, (2) for the case of joint segmentation and classification, the granularity of the classifier is very fine at frame level which is about 0.03 second long, and (3) at this granularity, independent human annotators agree only on 75% to 80% of the frames [26], [27]. Therefore for a machine (trained to replicate manual labels) a performance of 80% is within the range of human labeling performance.…”

Section: Resultsmentioning

confidence: 99%

“…In this approach, fine-grained segmentation and labeling are thus necessary steps for surgical skill assessment. Recent studies [26]–[28] have shown that given the sequence of surgical gestures and their boundaries, one can predict the surgeon’s skill level with up to 90% accuracy for new trails of known (observed) surgeons or 75% accuracy for a new trails of unobserved surgeons.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Dataset and Benchmarks for Segmentation and Recognition of Gestures in Robotic Surgery

Ahmidi

Tao

Sefati

et al. 2017

IEEE Trans. Biomed. Eng.

Self Cite

229

182

View full text Add to dashboard Cite

Objective State-of-the-art techniques for surgical data analysis report promising results for automated skill assessment and action recognition. The contributions of many of these techniques, however, are limited to study-specific data and validation metrics, making assessment of progress across the field extremely challenging. Methods In this paper, we address two major problems for surgical data analysis: (1) lack of uniform shared datasets and benchmarks and (2) lack of consistent validation processes. We address the former by presenting the JHU-ISI Gesture and Skill Assessment Working Set (JIGSAWS), a public dataset we have created to support comparative research benchmarking. JIGSAWS contains synchronized video and kinematic data from multiple performances of robotic surgical tasks by operators of varying skill. We address the latter by presenting a well-documented evaluation methodology and reporting results for six techniques for automated segmentation and classification of time-series data on JIGSAWS. These techniques comprise four temporal approaches for joint segmentation and classification: Hidden Markov Model, Sparse HMM, Markov semi-Markov Conditional Random Field, and Skip-Chain CRF; and two feature-based ones that aim to classify fixed segments: Bag of spatiotemporal Features and Linear Dynamical Systems. Results Most methods recognize gesture activities with approximately 80% overall accuracy under both leave-one-super-trial-out and leave-one-user-out cross-validation settings. Conclusion Current methods show promising results on this shared dataset, but room for significant progress remains, particularly for consistent prediction of gesture activities across different surgeons. Significance The results reported in this paper provide the first systematic and uniform evaluation of surgical activity recognition techniques on the benchmark database.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Dataset and Benchmarks for Segmentation and Recognition of Gestures in Robotic Surgery

Ahmidi

Tao

Sefati

et al. 2017

IEEE Trans. Biomed. Eng.

Self Cite

229

182

View full text Add to dashboard Cite

show abstract

“…One of the fundamental tasks in the development of this surgical automation framework was the hierarchical decomposition of surgical motion patterns. The workflow of surgical interventions, as well as the motion of the surgeon, can be decomposed into elements on different levels of granularity [29][30][31], similar to behavior trees [32]. In the literature, there are several different definitions of some granularity levels, nevertheless, no consistent definition can be found for the whole domain.…”

Section: Methodsmentioning

confidence: 99%

A DVRK-based Framework for Surgical Subtask Automation

2019

APH

View full text Add to dashboard Cite

Robotic assistance is becoming a standard in Minimally Invasive Surgery. Despite its clinical benefits and technical potential, surgeons still have to perform manually a number of monotonous and time-consuming surgical subtasks, like knot-tying or blunt dissection. Many believe that the next bold step in the advancement of robotic surgery is the automation of such subtasks. Partial automation can reduce the cognitive load on surgeons, and support them in paying more attention to the critical elements of the surgical workflow. Our aim was to develop a software framework to ease and hasten the automation of surgical subtasks. This framework was built alongside the Da Vinci Research Kit (DVRK), while it can be ported onto other robotic platforms, since it is based on the Robot Operating System (ROS). The software includes both stereo vision-based and hierarchical motion planning, with a wide palette of often used surgical gestures-such as grasping, cutting or soft tissue manipulation-as building blocks to support the high-level implementation of autonomous surgical subtask execution routines. This open-source surgical automation framework-named irob-saf-is available at https://github.com/ABC-iRobotics/irob-saf.

show abstract

“…A suture operation can be broken down into detailed steps. There is an excellent study on the analysis of a suturing and knot-tying task [13]. This work adopted for the design and implementation of the suturing simulation.…”

Section: Running Subcuticular Suturesmentioning

confidence: 99%

Intelligent Haptic Virtual Simulation for Suture Surgery

Sung¹,

Kang²,

Kim³

et al. 2020

IJACSA

View full text Add to dashboard Cite

The aim of this study is to develop an intelligent haptic virtual simulation for suture surgery, enabled with an AI assistant. This haptic VR suture simulation mainly composed of three parts: visuo-haptic rendering for surgery, replica training for surgery, and AI assistant for surgery. In the simulation, a trainee surgeon can practice the suturing procedure using tactile touches in the stereoscopic 3D virtual environment. The simulation adopts a "precise haptic collision detection method using subdivision surface and sphere clustering" developed in the previous studies of authors. In addition, an expert surgeon's suture operations can be replicated to the medical trainee's simulation to experience it as it is. This method has the advantage of reproducing the experience of the expert's ideal movements of surgical procedures. The data recording of the skilled surgeon's motions and operations are normalized into a form suitable for AI learning. The AI assistant distinguishes five typical types of suture surgery methods and learns the proper methods for various wounds using deep learning techniques, then it suggests the most appropriate suture method. The suture simulation can reduce the cost and time required for surgical training and eventually provide safe and accurate physical surgery.

show abstract

Analysis of the Structure of Surgical Activity for a Suturing and Knot-Tying Task

Cited by 35 publications

References 23 publications

A Dataset and Benchmarks for Segmentation and Recognition of Gestures in Robotic Surgery

A Dataset and Benchmarks for Segmentation and Recognition of Gestures in Robotic Surgery

A DVRK-based Framework for Surgical Subtask Automation

Intelligent Haptic Virtual Simulation for Suture Surgery

Contact Info

Product

Resources

About