UCLA

Purpose

To develop a deep-learning-based method to quantify multiple parameters in the brain from conventional contrast-weighted images.

Methods

Eighteen subjects were imaged using an MR Multitasking sequence to generate reference T₁ and T₂ maps in the brain. Conventional contrast-weighted images consisting of T₁ MPRAGE, T₁ GRE, and T₂ FLAIR were acquired as input images. A U-Net-based neural network was trained to estimate T₁ and T₂ maps simultaneously from the contrast-weighted images. Six-fold cross-validation was performed to compare the network outputs with the MR Multitasking references.

Results

The deep-learning T₁ /T₂ maps were comparable with the references, and brain tissue structures and image contrasts were well preserved. A peak signal-to-noise ratio >32 dB and a structural similarity index >0.97 were achieved for both parameter maps. Calculated on brain parenchyma (excluding CSF), the mean absolute errors (and mean percentage errors) for T₁ and T₂ maps were 52.7 ms (5.1%) and 5.4 ms (7.1%), respectively. ROI measurements on four tissue compartments (cortical gray matter, white matter, putamen, and thalamus) showed that T₁ and T₂ values provided by the network outputs were in agreement with the MR Multitasking reference maps. The mean differences were smaller than ± 1%, and limits of agreement were within ± 5% for T₁ and within ± 10% for T₂ after taking the mean differences into account.

Conclusion

A deep-learning-based technique was developed to estimate T₁ and T₂ maps from conventional contrast-weighted images in the brain, enabling simultaneous qualitative and quantitative MRI without modifying clinical protocols.