pl-mricnn_predict

Table of Contents

• Abstract
• Synopsis
• Description
• Arguments
• Run
  • Using PyPI
  • Using docker run
• Examples

Abstract

An app to predict segmented brain MRI images from a given unsegmented brain MRI

Synopsis

python mricnn_predict.py                                           \
    [-v <level>] [--verbosity <level>]                          \
    [--version]                                                 \
    [--man]                                                     \
    [--meta]                                                    \
    [--testDir]                                                 \
    [--model]                                                   \
    <inputDir>
    <outputDir>

Description

mricnn_predict.py is a ChRIS-based application that...

Arguments

[-v <level>] [--verbosity <level>]
Verbosity level for app. Not used currently.

[--version]
If specified, print version number.

[--man]
If specified, print (this) man page.

[--meta]
If specified, print plugin meta data.

[--model]
The name of the training model

[--testDir]
The name of the training dir

Run

This plugin can be run in two modes: natively as a python package or as a containerized docker image.

Using PyPI

To run from PyPI, simply do a

pip install mricnn_predict

and run with

mricnn_predict.py --man /tmp /tmp

to get inline help. The app should also understand being called with only two positional arguments

mricnn_predict.py /some/input/directory /destination/directory

Using docker run

To run using docker, be sure to assign an "input" directory to /incoming and an output directory to /outgoing. Make sure that the $(pwd)/out directory is world writable!

Now, prefix all calls with

docker run --rm -v $(pwd)/out:/outgoing                             \
        fnndsc/pl-mricnn_predict mricnn_predict.py                        \

Thus, getting inline help is:

mkdir in out && chmod 777 out
docker run --rm -v $(pwd)/in:/incoming -v $(pwd)/out:/outgoing      \
        fnndsc/pl-mricnn_predict mricnn_predict.py                        \
        --man                                                       \
        /incoming /outgoing

Examples

mkdir in out && chmod 777 out
docker run --rm -v $(pwd)/in:/incoming -v $(pwd)/out:/outgoing      \
        fnndsc/pl-mricnn_predict mricnn_predict.py                  \
        --testDir test                                              \
        --model model                                               \
        /incoming /outgoing