Dataset Information

Visual-Assisted Probe Movement Guidance for Obstetric Ultrasound Scanning using Landmark Retrieval

ABSTRACT: Automated ultrasound (US)-probe movement guidance is desirable to assist inexperienced human operators during obstetric US scanning. In this paper, we present a new visual-assisted probe movement technique using automated landmark retrieval for assistive obstetric US scanning. In a first step, a set of landmarks is constructed uniformly around a virtual 3D fetal model. Then, during obstetric scanning, a deep neural network (DNN) model locates the nearest landmark through descriptor search between the current observation and landmarks. The global position cues are visualised in real-time on a monitor to assist the human operator in probe movement. A Transformer-VLAD network is proposed to learn a global descriptor to represent each US image. This method abandons the need for deep parameter regression to enhance the generalization ability of the network. To avoid prohibitively expensive human annotation, anchor-positive-negative US image-pairs are automatically constructed through a KD-tree search of 3D probe positions. This leads to an end-to-end network trained in a self-supervised way through contrastive learning.

SUBMITTER: Zhao C

PROVIDER: S-EPMC7612564 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundUltrasound guidance for central venous catheterization is a commonly used alternative to the conventional landmark method. Because from the German perspective, the cost-effectiveness of ultrasound guidance is unclear, this study examined the cost-effectiveness of ultrasound guidance versus the landmark method for adults undergoing a central venous catheterization.MethodsA decision-tree based model was built to estimate the costs of averted catheter-related complications. Clinical data (e.g. arterial puncture, failed attempts) were obtained from a Cochrane review and a randomized controlled trial, whilst information about cost parameters were taken from a German hospital of maximum care. The analysis was conducted from the perspective of the German Statutory Health Insurance. Results were presented as incremental cost-effectiveness ratios. To assess the parameter uncertainty, several sensitivity analyses were performed (deterministic, probabilistic and with regard to the model structure).ResultsOur analysis revealed that ultrasound guidance resulted in fewer complications per person (0.04 versus 0.17 for the landmark method) and was less expensive (€51 versus €230 for the landmark method). Results were robust to changes in the model parameters and in the model structure. Whilst our model population reflected approximately 49% of adults undergoing a central venous catheterization cannulation per year, structural sensitivity analyses (e.g. extending the study cohort to patients at higher baseline risk of complications, pediatric patients, or using real-time/indirect catheterization) indicated the cost-effectiveness of ultrasound guidance for a broader spectrum of patients. The results should be interpreted by considering the assumptions (e.g. target population) and approximations (e.g. cost parameters) underpinning the model.ConclusionsUltrasound guidance for central venous catheterization averts more catheter-related complications and may save the resources of the German Statutory Health Insurance compared with landmark method.

Dataset Information

Visual-Assisted Probe Movement Guidance for Obstetric Ultrasound Scanning using Landmark Retrieval

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets