A Volunteer Study to Collect Imaging Data for the Development and Validation of Intelligent Ultrasound ScanNav Anatomy PNB
Overview
- Phase
- Not Applicable
- Intervention
- Not specified
- Conditions
- Ultrasound Imaging of Anatomical Structures
- Sponsor
- IntelligentUltrasound Limited
- Enrollment
- 100
- Locations
- 1
- Primary Endpoint
- Change in per-class Mean Intersection over Union (IoU) scores of deep-learning segmentation models compared to baseline models
- Status
- Completed
- Last Updated
- 3 years ago
Overview
Brief Summary
This is a single-centre, prospective, non-randomised volunteer study to be undertaken in Intelligent Ultrasound's offices at Hodge House, 114-116 St Mary Street, Cardiff, CF10 1DY, UK.
Detailed Description
This is a single-centre, non-randomised, prospective study involving up to 100 participants. The data collected in this study will augment the data collected in ML2018_AG_01, ML2018_AG_02, IU2019_AG_03, and IU2020_AG_04. Phase I Collect data from participants for each indicated block area. This set will be used to develop and verify models for the identification and highlighting of target anatomical structures on ultrasound images. Phase II Validation will proceed by feeding the videos into the ScanNav AnatomyGuide system and recording the output anatomy highlighting, overlaid on the original ultrasound image. The overlaid video will be examined by experts to identify safety and performance issues.
Investigators
Eligibility Criteria
Inclusion Criteria
- •Potential participants who meet the following criteria will be considered eligible for the study:
- •Male or female, at least 18 years of age;
- •Able to comprehend and sign the Informed Consent prior to enrolment in the study.
Exclusion Criteria
- •Potential participants who meet the following criteria will NOT be eligible for the study:
- •Aged \<18 years of age;
- •Unwilling or unable to provide informed consent;
- •Previous surgery or trauma to the affected area.
Outcomes
Primary Outcomes
Change in per-class Mean Intersection over Union (IoU) scores of deep-learning segmentation models compared to baseline models
Time Frame: 6 months
The mean Intersection over Union will be computed for each class for each model trained with the enlarged dataset, using the existing unseen test data set. These scores will be compared with the scores from the existing baseline models to determine the effect of the enlarged training data