Merge branch 'master' of https://github.com/radxtools/collageradiomics

README.md

@@ -5,24 +5,13 @@
 # Table of Contents
 - [Science](#science)
   - [Overview](#overview)
-  - [Features](#features)
   - [References](#references)
 - [Code](#code)
-  - [Idempotence](#idempotence)
-  - [Documentation](#documentation)
-  - [Dependencies](#dependencies)
-- [Installation & Usage](#installation--usage)
-  - [Executive Summary for Experts](#executive-summary-for-experts)
-  - [Docker](#docker)
-    - [Docker Setup](#docker-setup)
-    - [collageradiomics-examples Docker Image](#collageradiomics-examples-docker-image)
-    - [collageradiomics-pip Docker Image](#collageradiomics-pip-docker-image)
-  - [Pip](#pip)
-  - [Python Usage](#python-usage)
-    - [Basic Example](#basic-example)
-    - [Real Data](#real-data)
-- [Other Platforms](#other-platforms)
-- [Contact](#contact)
+- [Installation & Setup](#installation--setup)
+  - [Pip Usage](#pip-usage)
+  - [Docker Notebooks](#docker-notebooks)
+  - [Docker Sandbox](#docker-sandbox)
+- [Python Usage](#python-usage)
 
 # Science
 ## Overview
@@ -63,21 +52,21 @@ If you make use of this implementation, please cite the following paper:
 # Code
 _[Back to **Table of Contents**](#table-of-contents)_
 
-## Idempotence
 We made the collage object idempotent Our **CoLlAGe** module includes parameter tuning information in the output. It contains the image(s) and mask(s), and the settings applied upon them. This allows multiple fully reproducible runs without having to remember or find the original parameters.
 
-## Documentation
+Documentation can be found at
 http://collageradiomics.rtfd.io/
 
-## Dependencies:
+We depend on the following libraries:
 - `matplotlib`
 - `numpy`
 - `scikit-learn`
 - `scikit-build`
+- `sklearn`
 - `mahotas`
 - `scipy`
 
-# Installation & Usage
+# Installation & Setup
 _[Back to **Table of Contents**](#table-of-contents)_
 
 ## Pip Usage
@@ -100,7 +89,8 @@ sudo apt -y install build-essential gcc gfortran python-dev libopenblas-dev libl
 pip3 install -r requirements.txt
 
 # run test script
-python3 collageradiomics/modules/test_script.py
+cd modules
+python3 test_script.py
 ```
 
 ## Docker Notebooks
@@ -158,3 +148,79 @@ Type "help", "copyright", "credits" or "license" for more information.
 >>> collageradiomics.__name__
 'collageradiomics'
 ```
+
+# Python Usage
+_[Back to **Table of Contents**](#table-of-contents)_
+```python
+
+##################################################
+# imports
+import collageradiomics
+import pydicom
+import logging
+from pydicom.pixel_data_handlers.util import apply_modality_lut, apply_voi_lut
+from skimage.exposure import equalize_hist
+import numpy as np
+from sklearn.preprocessing import minmax_scale
+from random import randint
+##################################################
+
+
+##################################################
+# logging
+level = logging.INFO
+logging.basicConfig(level=level)
+logger = logging.getLogger()
+logger.setLevel(level)
+logger.info('Hello, world.')
+##################################################
+
+
+##################################################
+# loading data
+local_dcm_file = 'test.dcm'
+instance = pydicom.dcmread(local_dcm_file)
+slice_instance_uid = instance.SOPInstanceUID
+logger.debug(f'slice_instance_uid  = {slice_instance_uid}')
+##################################################
+
+
+##################################################
+# preprocessing
+logger.info('Correcting image...')
+np_array = instance.pixel_array
+corrected = apply_modality_lut(np_array, instance)
+corrected = apply_voi_lut(corrected, instance)
+scaled_array = equalize_hist(corrected)
+logger.debug(f'np.histogram(scaled_array) = {np.histogram(scaled_array)}')
+logger.info('done.')
+##################################################
+
+
+##################################################
+# rectangular selection
+width = 50
+height = 50
+min_row = randint(30,300)
+max_row = min_row + height
+min_col = randint(30,300)
+max_col = min_col + width
+
+original_shape = np_array.shape
+logger.debug(f'original_shape = {original_shape}')
+logger.info('Calculating collage features...')
+mask_array = np.zeros(original_shape, dtype='int')
+mask_array[min_row:max_row, min_col:max_col] = 1
+##################################################
+
+
+##################################################
+# run collage
+textures = collageradiomics.Collage(scaled_array, mask_array).execute()
+
+logger.debug(f'textures.shape = {textures.shape}')
+logger.debug(f'textures.dtype = {textures.dtype}')
+logger.debug(f'np.histogram(textures.flatten()) = {np.histogram(textures.flatten(), range=(np.nanmin(textures), np.nanmax(textures)))}')
+##################################################
+
+```