Learning-based quality control for cardiac MR images

Giacomo Tarroni, Ozan Oktay, Wenjia Bai, Andreas Schuh, Hideaki Suzuki, Jonathan Passerat-Palmbach, Antonio De Marvao, Declan P. O'Regan, Stuart Cook, Ben Glocker, Paul M. Matthews, Daniel Rueckert

Research output: Contribution to journalArticlepeer-review

36 Citations (Scopus)


The effectiveness of a cardiovascular magnetic resonance (CMR) scan depends on the ability of the operator to correctly tune the acquisition parameters to the subject being scanned and on the potential occurrence of imaging artifacts, such as cardiac and respiratory motion. In the clinical practice, a quality control step is performed by visual assessment of the acquired images; however, this procedure is strongly operator-dependent, cumbersome, and sometimes incompatible with the time constraints in clinical settings and large-scale studies. We propose a fast, fully automated, and learning-based quality control pipeline for CMR images, specifically for short-axis image stacks. Our pipeline performs three important quality checks: 1) heart coverage estimation; 2) inter-slice motion detection; 3) image contrast estimation in the cardiac region. The pipeline uses a hybrid decision forest method-integrating both regression and structured classification models-to extract landmarks and probabilistic segmentation maps from both long- A nd short-axis images as a basis to perform the quality checks. The technique was tested on up to 3000 cases from the UK Biobank and on 100 cases from the UK Digital Heart Project and validated against manual annotations and visual inspections performed by expert interpreters. The results show the capability of the proposed pipeline to correctly detect incomplete or corrupted scans (e.g., on UK Biobank, sensitivity and specificity, respectively, 88% and 99% for heart coverage estimation and 85% and 95% for motion detection), allowing their exclusion from the analyzed dataset or the triggering of a new acquisition.

Original languageEnglish
Article number8519790
Pages (from-to)1127-1138
Number of pages12
JournalIEEE Transactions on Medical Imaging
Issue number5
Publication statusPublished - 2019 May


  • Image quality assessment
  • heart
  • magnetic resonance imaging
  • motion compensation and analysis


Dive into the research topics of 'Learning-based quality control for cardiac MR images'. Together they form a unique fingerprint.

Cite this