Resultado de búsqueda
Our method is based on the recently developed Automap reconstruction method, which directly reconstructs high quality MR images from k-space using deep learning. We propose to use a loss function that combines mean square error with structural similarity index to robustly segment poor-quality images.
26 de sept. de 2018 · We propose two deep architectures, an end-to-end synthesis network and a latent feature interpolation network, to predict cardiac segmentation maps from extremely undersampled dynamic MRI data, bypassing the usual image reconstruction stage altogether.
18 de feb. de 2023 · An in-house pipeline was developed replicating all post-processing steps done on an MR scanner to go from raw k-space data to DICOM images viewed by clinicians for diagnostic decisions.
31 de may. de 2024 · We achieve 2D+time CMR image segmentation directly from undersampled k-space measurements without an intermediate image reconstruction step or an explicit inverse Fourier transform. We utilize a transformer architecture to extract k-space features globally and subsequently predict segmentation maps in image space.
16 de sept. de 2018 · This work proposes two deep architectures, an end-to-end synthesis network and a latent feature interpolation network, to predict cardiac segmentation maps from extremely undersampled dynamic MRI data, bypassing the usual image reconstruction stage altogether.
11 de oct. de 2019 · The method is based on our recently developed joint artefact detection and reconstruction method, which reconstructs high quality MR images from k-space using a joint loss function and essentially converts the artefact correction task to an under-sampled image reconstruction task by enforcing a data consistency term.
We perform a large-scale simulation study using UK Biobank data containing nearly 1000 test subjects and show that with the proposed approaches, an accurate estimate of clinical parameters such as ejection fraction can be obtained from fewer than 10 k-space lines per time-frame.
