# How can I keep the association between input image coordinate (z-axis) and segmentation mask?
**URL:** https://discourse.itk.org/t/how-can-i-keep-the-association-between-input-image-coordinate-z-axis-and-segmentation-mask/5467
**Category:** Uncategorized
**Tags:** dicom, simpleitk, python
**Created:** [November 3, 2022, 3:55pm UTC](https://discourse.itk.org/t/how-can-i-keep-the-association-between-input-image-coordinate-z-axis-and-segmentation-mask/5467 "2022-11-03T15:55:43Z")
**Posts on this page:** 8
**Page:** 1
### Author:  [@DushiFdo](https://discourse.itk.org/u/DushiFdo)
#### Post date: [November 3, 2022, 3:55pm UTC](https://discourse.itk.org/t/how-can-i-keep-the-association-between-input-image-coordinate-z-axis-and-segmentation-mask/5467/1 "2022-11-03T15:55:43Z")
Hello,
I am working with 3D CT images which are consists of a series of 2D slices. I resized them into (128 x 128 x 128)
My segmentation masks are provided as xml files and have segmentations only for like 3 or 4 slices (where the tumor is visible). I am trying to construct a segmentation volume as same size as the input image (128 x 128 x 128). My question is how I can keep the same z position in my segmentation volume as the input image?
I create the numpy image array form xml file as follows:
```python
Bs_data = BeautifulSoup(data, "lxml")
# Finding all instances of tag
# `unique`
b_unique_X = Bs_data.find_all('x')
b_unique_Y = Bs_data.find_all('y')
#print(b_unique)
#Extract the X, Y co-ordinates of contours from the xml file
X_coord = []
Y_coord = []
for i,j in zip(range(0,len(b_unique_X)),range(0,len(b_unique_Y))):
X_coord.append(b_unique_X[i].get('value'))
Y_coord.append(b_unique_Y[i].get('value'))
final = np.column_stack((X_coord, Y_coord))
np.set_printoptions(threshold=sys.maxsize)
pixelCoords = final.astype(float).astype(int)
arr = np.zeros((512,512))
poly = pixelCoords[:,:2].copy()
cv2.fillPoly(arr, pts=[poly], color = 255)
mask1 = arr.astype(int)
```
I can get the slice number from the xml file as follows.
```python
description_tag = Bs_data.description
# Get the attribute
attribute = description_tag['value']
```
My input images dicom and are named based on the slice number as well (e.g., here the slice number is 215):
(1.2.826.0.1.3680043.2.133.1.3.49.1.124.27456-3-215-1fx0wj3.dcm)
---
### Author:  [@dzenanz](https://discourse.itk.org/u/dzenanz)
#### Post date: [November 3, 2022, 4:10pm UTC](https://discourse.itk.org/t/how-can-i-keep-the-association-between-input-image-coordinate-z-axis-and-segmentation-mask/5467/2 "2022-11-03T16:10:07Z")
You have all the necessary information. Use `TransformPhysicalPointToIndex()` and `TransformIndexToPhysicalPoint` to go between index space (pixel indices) and physical point coordinates. Read more about it in [ITKSoftwareGuide](https://itk.org/ITKSoftwareGuide/html/Book1/ITKSoftwareGuide-Book1ch4.html), section 4.1.4 Defining Origin and Spacing.
---
### Author:  [@DushiFdo](https://discourse.itk.org/u/DushiFdo)
#### Post date: [November 3, 2022, 6:29pm UTC](https://discourse.itk.org/t/how-can-i-keep-the-association-between-input-image-coordinate-z-axis-and-segmentation-mask/5467/3 "2022-11-03T18:29:35Z")
I am not sure I understand. Could you please explain it little bit more?
---
### Author:  [@dzenanz](https://discourse.itk.org/u/dzenanz)
#### Post date: [November 3, 2022, 7:18pm UTC](https://discourse.itk.org/t/how-can-i-keep-the-association-between-input-image-coordinate-z-axis-and-segmentation-mask/5467/4 "2022-11-03T19:18:25Z")
You seem to be discarding Z (slice index) when reading points from XML file. Without that, it is impossible to put those contours into 3D space.
In a better case, the point coordinates are in physical 3D space already, and you only need to call `index = image128.TransformPhysicalPointToIndex(point3)`, where `point3` is X\_coord[i], Y\_coord[i], Z\_coord[i]. Then use `index` in a call to `cv2.fillPoly`.
In a worse case, the coordinates are in index space of the corresponding image, and we need to convert them to physical first. I assume those contours refer to slices in the original image grid, not your new 128^3 grid. If so, you need to keep the original grid information, and use it to go from original index space to physical space, via `point3 = original.TransformIndexToPhysicalPoint([X_coord[i], Y_coord[i], Z_coord[i]])` or something similar.
---
### Author:  [@DushiFdo](https://discourse.itk.org/u/DushiFdo)
#### Post date: [November 3, 2022, 9:26pm UTC](https://discourse.itk.org/t/how-can-i-keep-the-association-between-input-image-coordinate-z-axis-and-segmentation-mask/5467/5 "2022-11-03T21:26:35Z")
I don’t have a slice index in my xml file. I have a separate xml file for each slice.
---
### Author:  [@dzenanz](https://discourse.itk.org/u/dzenanz)
#### Post date: [November 3, 2022, 9:38pm UTC](https://discourse.itk.org/t/how-can-i-keep-the-association-between-input-image-coordinate-z-axis-and-segmentation-mask/5467/6 "2022-11-03T21:38:00Z")
Then get slice index from the file name.
---
### Author:  [@DushiFdo](https://discourse.itk.org/u/DushiFdo)
#### Post date: [November 11, 2022, 1:46am UTC](https://discourse.itk.org/t/how-can-i-keep-the-association-between-input-image-coordinate-z-axis-and-segmentation-mask/5467/7 "2022-11-11T01:46:57Z")
@dzenanz Thank You so much! This worked.
---
### Author:  [@dzenanz](https://discourse.itk.org/u/dzenanz)
#### Post date: [November 11, 2022, 1:46pm UTC](https://discourse.itk.org/t/how-can-i-keep-the-association-between-input-image-coordinate-z-axis-and-segmentation-mask/5467/8 "2022-11-11T13:46:35Z")
If you share your code, or the main part of your code, it might be useful to someone in the future.