update MRI recon demo (Project-MONAI#1024)

Signed-off-by: mersad95zd <[email protected]>

Fixes # .

### Description
Update the readme file for the MRI recon demo. The update is adding more
details to the dataset section.

### Checks
<!--- Put an `x` in all the boxes that apply, and remove the not
applicable items -->
- [ ] Notebook runs automatically `./runner [-p <regex_pattern>]`

Signed-off-by: mersad95zd <[email protected]>

Author: mersad95zd

reconstruction/MRI_reconstruction/unet_demo/README.md

@@ -31,12 +31,14 @@ This folder contains code to train and validate a U-Net for accelerated MRI reco
 
 # Dataset
 
-The experiments are performed on the [fastMRI](https://fastmri.org/dataset) dataset. Users should request access to the dataset
+The experiments are performed on the [fastMRI](https://fastmri.org/dataset) brain multi-coil dataset (AXT2 modality). Users should request access to the dataset
 from the [owner's website](https://fastmri.org/dataset). Remember to use the `$PATH` where you downloaded the data in `train.py`
 or `inference.ipynb` accordingly.
 
 For our experiments we created a subset of the fastMRI dataset which contains a `500/179/133` split for `train/val/test`. Please download [fastmri_data_split.json](https://github.com/Project-MONAI/MONAI-extra-test-data/releases/download/0.8.1/fastmri_data_split.json) and put it here under `./data`.
 
+**Note.** The dataset files that need to be downloaded from [fastMRI](https://fastmri.org/dataset) are `brain_multicoil_train.tar.gz` (~1228.8 GB) and `brain_multicoil_val.tar.gz` (~350.9 GB).
+
 # Model checkpoint
 
 We have already provided a model checkpoint [unet_mri_reconstruction.pt](https://github.com/Project-MONAI/MONAI-extra-test-data/releases/download/0.8.1/unet_mri_reconstruction.pt) for a U-Net with `7,782,849` parameters. To obtain this checkpoint, we trained