Joint CS-MRI Reconstruction and Segmentation with a Unified Deep Network
This addresses the need for fast and automated MRI analysis in big data contexts, but it is incremental as it builds on existing CS-MRI and segmentation methods.
The paper tackles the problem of accelerating MRI acquisition and analysis by proposing a unified deep network, SegNetMRI, for joint compressed sensing MRI reconstruction and segmentation, showing improvements in both tasks when using compressive measurements.
The need for fast acquisition and automatic analysis of MRI data is growing in the age of big data. Although compressed sensing magnetic resonance imaging (CS-MRI) has been studied to accelerate MRI by reducing k-space measurements, in current CS-MRI techniques MRI applications such as segmentation are overlooked when doing image reconstruction. In this paper, we test the utility of CS-MRI methods in automatic segmentation models and propose a unified deep neural network architecture called SegNetMRI which we apply to the combined CS-MRI reconstruction and segmentation problem. SegNetMRI is built upon a MRI reconstruction network with multiple cascaded blocks each containing an encoder-decoder unit and a data fidelity unit, and MRI segmentation networks having the same encoder-decoder structure. The two subnetworks are pre-trained and fine-tuned with shared reconstruction encoders. The outputs are merged into the final segmentation. Our experiments show that SegNetMRI can improve both the reconstruction and segmentation performance when using compressive measurements.