Precision measurement of cardiac structure and function in cardiovascular magnetic resonance using machine learning.

Davies, Rhodri H; Augusto, João B; Bhuva, Anish; Xue, Hui; Treibel, Thomas A; Ye, Yang; Hughes, Rebecca K; Bai, Wenjia; Lau, Clement; Shiwani, Hunain; Fontana, Marianna; Kozor, Rebecca; Herrey, Anna; Lopes, Luis R; Maestrini, Viviana; Rosmini, Stefania; Petersen, Steffen E; Kellman, Peter; Rueckert, Daniel; Greenwood, John P; Captur, Gabriella; Manisty, Charlotte; Schelbert, Erik; Moon, James C

doi:10.1186/s12968-022-00846-4

journal article

Titel:: Precision measurement of cardiac structure and function in cardiovascular magnetic resonance using machine learning.
Dokumenttyp:: Journal Article
Autor(en):: Davies, Rhodri H; Augusto, João B; Bhuva, Anish; Xue, Hui; Treibel, Thomas A; Ye, Yang; Hughes, Rebecca K; Bai, Wenjia; Lau, Clement; Shiwani, Hunain; Fontana, Marianna; Kozor, Rebecca; Herrey, Anna; Lopes, Luis R; Maestrini, Viviana; Rosmini, Stefania; Petersen, Steffen E; Kellman, Peter; Rueckert, Daniel; Greenwood, John P; Captur, Gabriella; Manisty, Charlotte; Schelbert, Erik; Moon, James C
Abstract:: BACKGROUND: Measurement of cardiac structure and function from images (e.g. volumes, mass and derived parameters such as left ventricular (LV) ejection fraction [LVEF]) guides care for millions. This is best assessed using cardiovascular magnetic resonance (CMR), but image analysis is currently performed by individual clinicians, which introduces error. We sought to develop a machine learning algorithm for volumetric analysis of CMR images with demonstrably better precision than human analysis. METHODS: A fully automated machine learning algorithm was trained on 1923 scans (10 scanner models, 13 institutions, 9 clinical conditions, 60,000 contours) and used to segment the LV blood volume and myocardium. Performance was quantified by measuring precision on an independent multi-site validation dataset with multiple pathologies with n = 109 patients, scanned twice. This dataset was augmented with a further 1277 patients scanned as part of routine clinical care to allow qualitative assessment of generalization ability by identifying mis-segmentations. Machine learning algorithm ('machine') performance was compared to three clinicians ('human') and a commercial tool (cvi42, Circle Cardiovascular Imaging). FINDINGS: Machine analysis was quicker (20 s per patient) than human (13 min). Overall machine mis-segmentation rate was 1 in 479 images for the combined dataset, occurring mostly in rare pathologies not encountered in training. Without correcting these mis-segmentations, machine analysis had superior precision to three clinicians (e.g. scan-rescan coefficients of variation of human vs machine: LVEF 6.0% vs 4.2%, LV mass 4.8% vs. 3.6%; both P < 0.05), translating to a 46% reduction in required trial sample size using an LVEF endpoint. CONCLUSION: We present a fully automated algorithm for measuring LV structure and global systolic function that betters human performance for speed and precision.
Zeitschriftentitel:: J Cardiovasc Magn Reson
Jahr:: 2022
Band / Volume:: 24
Heft / Issue:: 1
Volltext / DOI:: doi:10.1186/s12968-022-00846-4
PubMed:: http://view.ncbi.nlm.nih.gov/pubmed/35272664
Print-ISSN:: 1097-6647
TUM Einrichtung:: Institut für KI und Informatik in der Medizin
BibTeX

Vorkommen:

mediaTUM Gesamtbestand Hochschulbibliographie 2022 Schools und Fakultäten Medizin Institut für Medizinische Statistik und Epidemiologie

mediaTUM Gesamtbestand Einrichtungen Schools TUM School of Medicine and Health Departments Clinical Medicine Institut für KI und Informatik in der Medizin (Prof. Rückert)2022