Anirudh Balaraman commited on
Commit
46506c1
·
unverified ·
1 Parent(s): 3e97719

Update getting-started.md

Browse files
Files changed (1) hide show
  1. docs/getting-started.md +2 -4
docs/getting-started.md CHANGED
@@ -6,9 +6,7 @@ For installation and downloading the saved weights of the models, please check t
6
 
7
  ## Data Format
8
 
9
- Input MRI scans should be in **NRRD** format with three modalities per patient: T2W, DWI, and ADC.
10
-
11
- The data pipeline uses MONAI's decathlon-format JSON:
12
 
13
  ```json
14
  {
@@ -25,5 +23,5 @@ The data pipeline uses MONAI's decathlon-format JSON:
25
  "test": [...]
26
  }
27
  ```
28
-
29
  Paths are relative to `data_root`. PI-RADS labels are 0-indexed (`0` = PI-RADS 2, `3` = PI-RADS 5). csPCa labels are binary (0 or 1).
 
6
 
7
  ## Data Format
8
 
9
+ Input bpMRI scans should have all three sequnces, T2W, ADC and DWI as separate files in **NRRD** format. The prostate mask and heatmap are generated by the sample for each sample. To train the models or run testing with reference labels, the data pipeline uses MONAI's decathlon-format JSON:
 
 
10
 
11
  ```json
12
  {
 
23
  "test": [...]
24
  }
25
  ```
26
+ Sample JSON files are available in the github repository.
27
  Paths are relative to `data_root`. PI-RADS labels are 0-indexed (`0` = PI-RADS 2, `3` = PI-RADS 5). csPCa labels are binary (0 or 1).