GraphCutSegmentation: Multithreaded Graph-Cut execution

PRLEC Framework for OCT Processing and Visualization

OCT_GUI.Algorithms.AutomaticSegmentation.GraphCutSegmentation.execute_graphcut(oct_volume, gradient_volume, scaling, mode, dictParameters)[source]

Execute Graph-Cut algorithm.

Parameters:
oct_volume: numpy array 2D/3D

list of original volume slices for inpainting the results

gradient_volume: numpy array 2D/3D

preprocessed gradient_volume

scaling: scalar, optional

scale factor for image down or upscaling

mode = string

mode =’RPE’ segments RPE, ‘ILM’ the inner limiting membrane

dictParameters: dictionary

Parameters from parameters.txt

class OCT_GUI.Algorithms.AutomaticSegmentation.GraphCutSegmentation.thread_pipeline(threadID, volume_slice, gradient_slice, prior_shortest_path, scaling, UPORDOWN, mode, dictParameters)[source]

Threaded Graph-Cut pipeline

shortestPath: dict
storing the latest shortest path as input for next iteration
y_offset_dict: dict
storing the latest y_offset as input for next iteration -> runtime minimization
Attributes:
daemon

A boolean value indicating whether this thread is a daemon thread.

ident

Thread identifier of this thread or None if it has not been started.

name

A string used for identification purposes only.

Methods

isAlive() Return whether the thread is alive.
is_alive() Return whether the thread is alive.
join() Returns resulting segmentation slice and thread id
run() Execute Algorithm
runPipeline() Pipeline implementation
start() Start the thread’s activity.
getName  
isDaemon  
setDaemon  
setName  
join()[source]

Returns resulting segmentation slice and thread id

run()[source]

Execute Algorithm

runPipeline()[source]

Pipeline implementation