Automated localization and quality control of the aorta in cine CMR can significantly accelerate processing of the UK Biobank population data - Fig 7
- Luca Biasiolli (4278667)
- Evan Hann (6335927)
- Elena Lukaschuk (3662284)
- Valentina Carapella (546039)
- Jose M. Paiva (6335930)
- Nay Aung (3728887)
- Jennifer J. Rayner (6335933)
- Konrad Werys (4710669)
- Kenneth Fung (3662281)
- Henrike Puchta (6335936)
- Mihir M. Sanghvi (4487716)
- Niall O. Moon (6335939)
- Ross J. Thomson (4923208)
- Katharine E. Thomas (6335942)
- Matthew D. Robson (4278655)
- Vicente Grau (546041)
- Steffen E. Petersen (2609701)
- Stefan Neubauer (88474)
- Stefan K. Piechnik (4487719)
Publication date
February 2019
DOI Publisher
Public Library of Science (PLoS)Abstract
A) Receiver Operating Characteristic (ROC) and C) Precision-Recall (PR) analysis for AA and PDA detection-localization. Mean curves and 95% CIs were obtained from bootstrap replicas. Precision baseline was 98.5% for AA and 99.6% for PDA. B) Dice Similarity Coefficient (DSC) for AA and PDA True Positives was ≥ 0.9 in 94.8% and 99.5% of cases, respectively. Total number of scans in the test dataset = 3900.</p
Add to ORKG