Merge different labels in a unique image

EneaP · December 21, 2022, 1:09pm

Hi, I have 7 different labels in each 7 different binary images. All of these images are 3D images provided by CT scan, they have a number of slices and 512x512 number of pixels for each slices. I want to merge these seven labels, that respectively represent the main chambers of the heart including aorta, in a single image having also different number of labels for each segmented area. Can someone can help me using sitk library?

blowekamp · December 21, 2022, 1:20pm

Hello,

You may find this notebook example useful:

github.com

InsightSoftwareConsortium/SimpleITK-Notebooks/blob/master/Python/35_Segmentation_Shape_Analysis.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Focused Ion Beam Scanning Electron Microscopy Image Segmentation\n",
    "\n",
    "\n",
    "**Summary:**\n",
    "1. SimpleITK supports a large number of filters that facilitate classical segmentation algorithms (variety of thresholding algorithms, watersheds...).\n",
    "2. Once your data is segmented SimpleITK enables you to efficiently post process the segmentation (e.g. label distinct objects, analyze object shapes).\n",
    "\n",
    "This notebook will illustrate the use of SimpleITK for segmentation of bacteria from a 3D Focused Ion Beam Scanning Electron Microscopy (FIB-SEM) image. The specific bacterium is <a href=\"https://en.wikipedia.org/wiki/Bacillus_subtilis\">bacillus subtilis</a>, a rod shaped organism naturally found in soil and plants. The bacteria have been subjected to stress to initiate the process of forming an endospore. These endospores can be seen as a generally dark ellipsoid inside the individual bacterium. \n",
    "\n",
    "Data provided courtesy of the Laboratory of Cell Biology, Center for Cancer Research, National Cancer Institute, National Institutes of Health."
   ]
  },
  {
   "cell_type": "code",

This file has been truncated. show original

One approach is to run the connected components filter, followed by the label shape statistics filter. The statistics produced can be used to create a map to relabel or remove unwanted labels/regions with an arbitrary criteria based on the computed stats. Then the ChangeLabelImageFilter can be used to apply the mapping of the components.

Alternatively classic binary morphology filters can be used too.