Towards Optimizing Convolutional Neural Networks for Robotic Surgery Skill Evaluation

Castro, Dayvid; Pereira, Danilo; Zanchettin, Cleber; Macêdo, David; Bezerra, Byron Leite Dantas

doi:10.1109/ijcnn.2019.8852341

Cited by 12 publications

(27 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, most CNNs take statistical features as input, eliminating the need for LSTM since the features of choice represent the temporal information. Among the studies sharing the same dataset, JIGSAWS, we found that a model proposed by Castro et al 37 achieved the highest overall score. They achieved 98.7% accuracy using a CNN with SELU activation, GMP, and quaternion convolutional layers.…”

Section: Discussionmentioning

confidence: 84%

“…Besides allowing visualization, Global Pooling also eliminates the duration difference problem that is crucial for time-series data. 36,37 Two main data processing approaches were observed. For the kinematic inputs, the data can be directly fed to the DNN, and the model outputs either the regressed score or the computed class.…”

Section: Dnn Models and Data Processingmentioning

confidence: 99%

“…33,34 CNNs were also used to assess skills and generate meaningful feedback for the trainee. [35][36][37][38] Moreover, CNNs such as Hourglass Network, Faster Region-Based CNN (Faster RCNN), Temporal Segment Networks (TSN), and others were used to extract tool locations from surgical videos. [39][40][41][42][43] This paper systematically analyzes automated and objective surgical skill assessment techniques based on deep neural networks (DNNs) using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines.…”

Section: Introductionmentioning

confidence: 99%

“…33,34 CNNs were also used to assess skills and generate meaningful feedback for the trainee. 35–38 Moreover, CNNs such as Hourglass Network, Faster Region-Based CNN (Faster RCNN), Temporal Segment Networks (TSN), and others were used to extract tool locations from surgical videos. 39–43…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Deep neural networks for the assessment of surgical skills: A systematic review

Yanik

Intes

Krüger

et al. 2021

Journal of Defense Modeling & Simulation

View full text Add to dashboard Cite

Surgical training in medical school residency programs has followed the apprenticeship model. The learning and assessment process is inherently subjective and time-consuming. Thus, there is a need for objective methods to assess surgical skills. Here, we use the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines to systematically survey the literature on the use of Deep Neural Networks for automated and objective surgical skill assessment, with a focus on kinematic data as putative markers of surgical competency. There is considerable recent interest in deep neural networks (DNNs) due to the availability of powerful algorithms, multiple datasets, some of which are publicly available, as well as efficient computational hardware to train and host them. We have reviewed 530 papers, of which we selected 25 for this systematic review. Based on this review, we concluded that DNNs are potent tools for automated, objective surgical skill assessment using both kinematic and video data. The field would benefit from large, publicly available, annotated datasets representing the surgical trainee and expert demographics and multimodal data beyond kinematics and videos.

show abstract

Section: Discussionmentioning

confidence: 84%

Section: Dnn Models and Data Processingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Deep neural networks for the assessment of surgical skills: A systematic review

Yanik

Intes

Krüger

et al. 2021

Journal of Defense Modeling & Simulation

View full text Add to dashboard Cite

show abstract

“…The first category is tool-related and makes up the majority of the literature. Methods in this category rely on tool motion data from various sources, including video object tracking or detection [24,5,44], video spatiotemporal descriptors [65,64,62,7], robotic kinematics [63,55,15,9], external sensors [13,4,23], and virtual reality interfaces [25]. The second category is proxy-related.…”

Section: Automatic Surgical Skill Assessmentmentioning

confidence: 99%

Towards Unified Surgical Skill Assessment

Liu¹,

Li²,

Jiang³

et al. 2021

Preprint

View full text Add to dashboard Cite

Surgical skills have a great influence on surgical safety and patients' well-being. Traditional assessment of surgical skills involves strenuous manual efforts, which lacks efficiency and repeatability. Therefore, we attempt to automatically predict how well the surgery is performed using the surgical video. In this paper, a unified multi-path framework for automatic surgical skill assessment is proposed, which takes care of multiple composing aspects of surgical skills, including surgical tool usage, intraoperative event pattern, and other skill proxies. The dependency relationships among these different aspects are specially modeled by a path dependency module in the framework. We conduct extensive experiments on the JIGSAWS dataset of simulated surgical tasks, and a new clinical dataset of real laparoscopic surgeries. The proposed framework achieves promising results on both datasets, with the state-of-the-art on the simulated dataset advanced from 0.71 Spearman's correlation to 0.80. It is also shown that combining multiple skill aspects yields better performance than relying on a single aspect. Codes at https://git.io/JG2OA.

show abstract

Kinematics Data Representations for Skills Assessment in Ultrasound-Guided Needle Insertion

Liu

Holden

2020

Medical Ultrasound, and Preterm, Perinatal and Paediatric Image Analysis

View full text Add to dashboard Cite

Towards Optimizing Convolutional Neural Networks for Robotic Surgery Skill Evaluation

Cited by 12 publications

References 9 publications

Deep neural networks for the assessment of surgical skills: A systematic review

Deep neural networks for the assessment of surgical skills: A systematic review

Towards Unified Surgical Skill Assessment

Kinematics Data Representations for Skills Assessment in Ultrasound-Guided Needle Insertion

Contact Info

Product

Resources

About