scikit-surgery-evaluation

Author: Stephen Thompson

scikit-surgery-evaluation provides an application to evaluate surgical skills. You can provide a set of unstructured grids representing a set of locations that the user is then expected to target using a tracked pointer, utilising a SciKit-Surgery tracking library (scikit-surgeryarucotracker, or scikit-surgerynditracker). You can specify paths for the user to follow, or let the system select target meshes automatically.

scikit-surgery-evaluation is part of the SciKit-Surgery software project, developed at the Wellcome EPSRC Centre for Interventional and Surgical Sciences, part of University College London (UCL).

scikit-surgery-evaluation supports Python 3.X.

python sksurgeryeval.py -c configuration.json

Developing

Cloning

You can clone the repository using the following command:

git clone https://github.com/SciKit-Surgery/scikit-surgery-evaluation

Running tests

Pytest is used for running unit tests:

pip install pytest
python -m pytest

Linting

This code conforms to the PEP8 standard. Pylint can be used to analyse the code:

pip install pylint
pylint --rcfile=tests/pylintrc sksurgeryeval

Installing

You can pip install directly from the repository as follows:

pip install git+https://github.com/SciKit-Surgery/scikit-surgery-evaluation

Contributing

Please see the contributing guidelines.

Useful links

• Source code repository
• Documentation

Licensing and copyright

Copyright 2019 University College London. scikit-surgery-evaluation is released under the BSD-3 license. Please see the license file for details.

Acknowledgements

Supported by Wellcome and EPSRC.

Requirements for scikit-surgery-evaluation

This is the software requirements file for scikit-surgery-evaluation, part of the SNAPPY project. The requirements listed below should define what scikit-surgery-evaluation does. Each requirement can be matched to a unit test that checks whether the requirement is met.

Requirements

ID	Description	Test
0000	Module has a help page	pylint, see tests/pylint.rc and tox.ini
0001	Functions are documented	pylint, see tests/pylint.rc and tox.ini
0002	Package has a version number	No test yet, handled by git.

latest

sksurgeryeval package

Subpackages

sksurgeryeval.algorithms package

Submodules

sksurgeryeval.algorithms.algorithms module

Algorithms for the surgery evaluation application

sksurgeryeval.algorithms.algorithms.add_map(config)

Loads vtk models from a directory and returns a list of vtk actors, with mesh visualisation

Param:configuration, may contain a “map” key Param:model_to_world: 4x4 matrix, of dtype float32 Returns:actors, None if no “map” key

sksurgeryeval.algorithms.algorithms.configure_tracker(config)

Configures the tracking system. :param: A dictionary containing configuration data :return: The tracker object :raises: KeyError if no tracker entry in config

sksurgeryeval.algorithms.algorithms.np2vtk(mat)

Converts a Numpy array to a vtk matrix :param: the number array, should be 4x4 :return: a vtk 4x4 matrix :raises: ValueError when matrix is not 4x4

sksurgeryeval.algorithms.algorithms.point_in_locator(point, point_locators, radius=1.0)

Tests whether a point is within a set distance of any of a list of point locators.

Parameters:

• point – the point to test, in 3D (x,y,z)
• point_locators – a list of vtkPointLocators
• radius – optional search radius in mm (default=1.0)

Return locator:

the index of the nearest point locator,

-1 if no locators within radius) :return distance: distance to nearest point_locator

Raises:delegates to vtk

sksurgeryeval.algorithms.algorithms.populate_models(config)

Loads vtk models from a directory and returns a list of vtk actors and associated vtkPointLocators

Param:configuration, should contain a target value Param:model_to_world: 4x4 matrix, of dtype float32 Returns:locators Returns:actors Raises:KeyError if target not in config

sksurgeryeval.algorithms.algorithms.random_targets(count)

Create a list of targets

sksurgeryeval.algorithms.background_image module

A class to provide the background image

class sksurgeryeval.algorithms.background_image.OverlayBackground(config)

Bases: object

Provides the background image for the overlay window.

next_image()

Returns a background image. The behaviour is determined by the configuration dictionary used at init.

sksurgeryeval.algorithms.locators module

Main loop for surgery evaluation

class sksurgeryeval.algorithms.locators.Locators(config)

Bases: object

stores a list of vtk models and corresponding locators, and handles associated logic

is_hit(tracking, logger)

Checks whether a target has been hit :param: the tracking data (3D point) :param: a logger to write notification to

Module contents

sksurgeryeval.logging package

Submodules

sksurgeryeval.logging.surgery_logger module

Class to handle logging

class sksurgeryeval.logging.surgery_logger.Logger(config)

Bases: object

Implements logging functionality for sksurgery-evaluation. Configuration is done by passing a dictionary on construction. Subsequent calls to log(“message”) will write to log file.

log(message)

If logging, passes message to logger

Module contents

sksurgeryeval.shapes package

Submodules

sksurgeryeval.shapes.cone module

VTK pipeline to represent a surface model via a vtkPolyData.

class sksurgeryeval.shapes.cone.VTKConeModel(height, radius, colour, name, visibility=True, opacity=1.0)

Bases: sksurgeryvtk.models.vtk_surface_model.VTKSurfaceModel

Class to create a VTK surface model of a cone.

Module contents

sksurgeryeval.ui package

Submodules

sksurgeryeval.ui.sksurgeryeval_command_line module

Command line processing

sksurgeryeval.ui.sksurgeryeval_command_line.main(args=None)

Entry point for scikit-surgery-evaluation application

sksurgeryeval.ui.sksurgeryeval_demo module

Hello world demo module

sksurgeryeval.ui.sksurgeryeval_demo.run_demo(configfile, verbose)

Run the application

Module contents

scikit-surgery-evaluation

sksurgeryeval.widgets package

Submodules

sksurgeryeval.widgets.overlay module

Main loop for surgery evaluation

class sksurgeryeval.widgets.overlay.OverlayApp(config)

Bases: sksurgeryutils.common_overlay_apps.OverlayBaseApp

Inherits from OverlayBaseApp, adding code to test the proximity of a tracked object to a set of vtk objects

update()

Update the background renderer with a new frame, move the model(s) and render

Module contents

Module contents

scikit-surgery-evaluation

First notebook

You can write up experiments in notebooks, and they can be generated into Sphinx docs using tox -e docs, and for example set up to run on readthedocs.

See this and this examples.

NOTE:

Getting jupyter to run your code in this package relies on 3 things:

• You must ensure you start jupyter within the tox environment.

# If not already done.
source .tox/py36/bin/activate

# Then launch jupyter
jupyter notebook

• Then when you navigate to and run this notebook, select the right kernel (named after your project) from the kernel menu item, in the web browser.
• Add project folder to system path, as below.

# Jupyter notebook sets the cwd to the folder containing the notebook.
# So, you want to add the root of the project to the sys path, so modules load correctly.
import sys
sys.path.append("../../")

• Module Index
• Index
• Search Page