Computer-aided analysis of fetal cardiac ultrasound videos
<p>This thesis addresses the task of developing automatic algorithms for analysing the two-dimensional ultrasound video footage obtained from fetal heart screening scans. These scans are typically performed in the second trimester of pregnancy to check for congenital heart anomalies and requi...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | English |
| Published: |
2017
|
| Subjects: |
| _version_ | 1797094669702660096 |
|---|---|
| author | Bridge, C |
| author2 | Noble, A |
| author_facet | Noble, A Bridge, C |
| author_sort | Bridge, C |
| collection | OXFORD |
| description | <p>This thesis addresses the task of developing automatic algorithms for analysing the two-dimensional ultrasound video footage obtained from fetal heart screening scans. These scans are typically performed in the second trimester of pregnancy to check for congenital heart anomalies and require significant training and anatomical knowledge to perform.</p> <p>The aim is to develop a tool that runs at high frame rates with no user initialisation and infers the visibility, position, orientation, view classification, and cardiac phase of the heart, and additionally the locations of cardiac structures of interest (such as valves and vessels) in a manner that is robust to the various sources of variation that occur in real-world ultrasound scanning. This is the first work to attempt such a detailed automated analysis of these videos.</p> <p>The problem is posed as a Bayesian filtering problem, which provides a principled framework for aggregating uncertain measurements across a number of frames whilst exploiting the constraints imposed by anatomical feasibility. The resulting inference problem is solved approximately with a particle filter, whose state space is partitioned to reduce the problems associated with filtering in high-dimensional spaces. </p> <p>Rotation-invariant features are captured from the videos in an efficient way in order to tackle the problem of unknown orientation. These are used within random forest learning models, including a novel formulation to predict circular-valued variables.</p> <p>The algorithm is validated on an annotated clinical dataset, and the results are compared to estimates of inter- and intra-observer variation, which are significant in both cases due to the inherent ambiguity in the imagery. The results suggest that the algorithm’s output approaches these benchmarks in several respects, and fall slightly behind in others.</p> <p>The work presented here is an important first step towards developing automated clinical tools for the detection of congenital heart disease.</p> |
| first_indexed | 2024-03-07T04:17:13Z |
| format | Thesis |
| id | oxford-uuid:c9cad151-6f08-461a-acd6-9fd63477b91a |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T04:17:13Z |
| publishDate | 2017 |
| record_format | dspace |
| spelling | oxford-uuid:c9cad151-6f08-461a-acd6-9fd63477b91a2022-03-27T07:02:24ZComputer-aided analysis of fetal cardiac ultrasound videosThesishttp://purl.org/coar/resource_type/c_db06uuid:c9cad151-6f08-461a-acd6-9fd63477b91aMedical Image AnalysisMachine learningEnglishORA Deposit2017Bridge, CNoble, AGrau, VFrangi, A<p>This thesis addresses the task of developing automatic algorithms for analysing the two-dimensional ultrasound video footage obtained from fetal heart screening scans. These scans are typically performed in the second trimester of pregnancy to check for congenital heart anomalies and require significant training and anatomical knowledge to perform.</p> <p>The aim is to develop a tool that runs at high frame rates with no user initialisation and infers the visibility, position, orientation, view classification, and cardiac phase of the heart, and additionally the locations of cardiac structures of interest (such as valves and vessels) in a manner that is robust to the various sources of variation that occur in real-world ultrasound scanning. This is the first work to attempt such a detailed automated analysis of these videos.</p> <p>The problem is posed as a Bayesian filtering problem, which provides a principled framework for aggregating uncertain measurements across a number of frames whilst exploiting the constraints imposed by anatomical feasibility. The resulting inference problem is solved approximately with a particle filter, whose state space is partitioned to reduce the problems associated with filtering in high-dimensional spaces. </p> <p>Rotation-invariant features are captured from the videos in an efficient way in order to tackle the problem of unknown orientation. These are used within random forest learning models, including a novel formulation to predict circular-valued variables.</p> <p>The algorithm is validated on an annotated clinical dataset, and the results are compared to estimates of inter- and intra-observer variation, which are significant in both cases due to the inherent ambiguity in the imagery. The results suggest that the algorithm’s output approaches these benchmarks in several respects, and fall slightly behind in others.</p> <p>The work presented here is an important first step towards developing automated clinical tools for the detection of congenital heart disease.</p> |
| spellingShingle | Medical Image Analysis Machine learning Bridge, C Computer-aided analysis of fetal cardiac ultrasound videos |
| title | Computer-aided analysis of fetal cardiac ultrasound videos |
| title_full | Computer-aided analysis of fetal cardiac ultrasound videos |
| title_fullStr | Computer-aided analysis of fetal cardiac ultrasound videos |
| title_full_unstemmed | Computer-aided analysis of fetal cardiac ultrasound videos |
| title_short | Computer-aided analysis of fetal cardiac ultrasound videos |
| title_sort | computer aided analysis of fetal cardiac ultrasound videos |
| topic | Medical Image Analysis Machine learning |
| work_keys_str_mv | AT bridgec computeraidedanalysisoffetalcardiacultrasoundvideos |