README.md

In stnava/surgeRy: Processing, Filtering and Data Organization for Deep Learning Training

surgeRy

documentation page here

deep learning training

Common tasks for data augmentation of images, segmentations and points.

Appropriate for cascaded models.

Installing

The pre-release version of the package can be pulled from GitHub using the devtools package:

    # install.packages("devtools")
    devtools::install_github("stnava/surgeRy", build_vignettes=TRUE)

this lets you access vignettes via:

vignette(package='surgeRy')

which will list the current vignettes.

For developers

The repository includes a Makefile to facilitate some common tasks.

Running tests

$ make test. Requires the testthat package. You can also specify a specific test file or files to run by adding a "file=" argument, like $ make test file=logging. testthat::test_package() will do a regular-expression pattern match within the file names (ignoring the test- prefix and the .R file extension).

Updating documentation

$ make doc. Requires the roxygen2 package.

References to the concepts used here

• Cephalometric Landmark Regression with Convolutional Neural Networks on 3D Computed Tomography Data ( a review paper )

• Numerical Coordinate Regression with Convolutional Neural Networks

• Human pose regression by combining indirect part detection and contextual information (section 3.2)

• Automatic 3d cephalometric annotation system using shadowed 2d image-based machine learning

stnava/surgeRy documentation built on Dec. 23, 2021, 6:37 a.m.