diff --git a/examples/healthcare/application/TED_CT_Detection/README.md b/examples/healthcare/application/TED_CT_Detection/README.md
index ee0e3b425..f23e2404a 100644
--- a/examples/healthcare/application/TED_CT_Detection/README.md
+++ b/examples/healthcare/application/TED_CT_Detection/README.md
@@ -2,10 +2,15 @@
 
 We have successfully applied the idea of prototype loss in various medical image classification task to improve performance, for example detection thyroid eye disease from CT images. Here we provide the implementation of the convolution prototype model in Singa. Due to data privacy, we are not able to release the CT image dataset used. The training scripts `./train.py` demonstrate how to apply this model on cifar-10 dataset.
 
+
 ## run
 
-At Singa project root directory `python examples/healthcare/application/TED_CT_Detection/train.py`
+1. Download `healthcare` directory then change to the `healthcare/application/TED_CT_Detection` directory.
+2. Command.
+```bash
+python train.py -dir pathToDataset
+```
 
 ## reference
 
-[Robust Classification with Convolutional Prototype Learning](https://arxiv.org/abs/1805.03438)
+[Robust Classification with Convolutional Prototype Learning](https://arxiv.org/abs/1805.03438)
\ No newline at end of file