| Title: | Recovering from missing data in population imaging - Cardiac MR image imputation via conditional generative adversarial nets |
| Journal: | Medical Image Analysis |
| Published: | 2 Oct 2020 |
| Pubmed: | https://pubmed.ncbi.nlm.nih.gov/33129140/ |
| DOI: | https://doi.org/10.1016/j.media.2020.101812 |
| URL: | https://eprints.whiterose.ac.uk/176404/1/medima-I2.pdf |
Publication 9239
WARNING: the interactive features of this website use CSS3, which your browser does not support. To use the full features of this website, please update your browser.
Abstract
Accurate ventricular volume measurements are the primary indicators of normal/abnor- mal cardiac function and are dependent on the Cardiac Magnetic Resonance (CMR) volumes being complete. However, missing or unusable slices owing to the presence of image artefacts such as respiratory or motion ghosting, aliasing, ringing and signal loss in CMR sequences, significantly hinder accuracy of anatomical and functional cardiac quantification, and recovering from those is insufficiently addressed in population imaging. In this work, we propose a new robust approach, coined Image Imputation Generative Adversarial Network (I2-GAN), to learn key features of cardiac short axis (SAX) slices near missing information, and use them as conditional variables to infer missing slices in the query volumes. In I2-GAN, the slices are first mapped to latent vectors with position features through a regression net. The latent vector corresponding to the desired position is then projected onto the slice manifold, conditioned on intensity features through a generator net. The generator comprises residual blocks with normalisation layers that are modulated with auxiliary slice information, enabling propagation of fine details through the network. In addition, a multi-scale discriminator was implemented, along with a discriminator-based feature matching loss, to further enhance performance and encourage the synthesis of visually realistic slices. Experimental results show that our method achieves significant improvements over the state-of-the-art, in missing slice imputation for CMR, with an average SSIM of 0.872. Linear regression analysis yields good agreement between reference and imputed CMR images for all cardiac measurements, with correlation coefficients of 0.991 for left ventricular volume, 0.977 for left ventricular mass and 0.961 for right ventricular volume.</p>
8 Authors
- Yan Xia
- Le Zhang
- Nishant Ravikumar
- Rahman Attar
- Stefan K Piechnik
- Stefan Neubauer
- Steffen E Petersen
- Alejandro F Frangi
2 Applications
| Application ID | Title |
|---|---|
| 2964 | Description of cardiovascular phenotype in the UK Biobank population based on cardiovascular magnetic resonance and carotid ultrasound |
| 11350 | CARDIOMARKER- Computational imaging phenomics in population cardiac MRI with automatic image quality assessment: benchmarking, scalability and inference with state-of-the-art algorithms. |
Enabling scientific discoveries that improve human health