sct_deepseg_lesion

MS lesion Segmentation using convolutional networks. Reference: Gros C et al. Automatic segmentation of the spinal cord and intramedullary multiple sclerosis lesions with convolutional neural networks. Neuroimage. 2018 Oct 6;184:901-915.

usage: sct_deepseg_lesion -i <file> -c {t2,t2_ax,t2s}
                          [-centerline {svm,cnn,viewer,file}]
                          [-file_centerline <str>] [-brain {0,1}]
                          [-ofolder <str>] [-h] [-v <int>]
                          [-profile-time [<file>]] [-trace-memory [<folder>]]
                          [-r {0,1}]

MANDATORY ARGUMENTS

-i

Input image. Example: t2.nii.gz

-c

Possible choices: t2, t2_ax, t2s

Type of image contrast.

  • t2: T2w scan with isotropic or anisotropic resolution.

  • t2_ax: T2w scan with axial orientation and thick slices.

  • t2s: T2*w scan with axial orientation and thick slices.

OPTIONAL ARGUMENTS

-centerline

Possible choices: svm, cnn, viewer, file

Method used for extracting the centerline:

  • svm: Automatic detection using Support Vector Machine algorithm.

  • cnn: Automatic detection using Convolutional Neural Network.

  • viewer: Semi-automatic detection using manual selection of a few points with an interactive viewer followed by regularization.

  • file: Use an existing centerline (use with flag -file_centerline)

Default: “svm”

-file_centerline

Input centerline file (to use with flag -centerline file). Example: t2_centerline_manual.nii.gz

-brain

Possible choices: 0, 1

Indicate if the input image contains brain sections (to speed up segmentation). This flag is only effective with -centerline cnn.

Default: 1

-ofolder

Output folder.

Default: “/home/docs/checkouts/readthedocs.org/user_builds/spinalcordtoolbox/checkouts/stable/documentation/source”

MISC ARGUMENTS

-v

Possible choices: 0, 1, 2

Verbosity. 0: Display only errors/warnings, 1: Errors/warnings + info messages, 2: Debug mode.

Default: 1

-profile-time

Enables time-based profiling of the program, dumping the results to the specified file.

If no file is specified, human-readable results are placed into a ‘time_profiling_results.txt’ document in the current directory (’/home/docs/checkouts/readthedocs.org/user_builds/spinalcordtoolbox/checkouts/stable/documentation/source’). If the specified file is a .prof file, the file will instead be in binary format, ready for use with common post-profiler utilities (such as snakeviz).

-trace-memory

Enables memory tracing of the program.

When active, a measure of the peak memory (in KiB) will be output to the file peak_memory.txt. Optionally, developers can also modify the SCT code to add additional snapshot_memory() calls. These calls will ‘snapshot’ the memory usage at that moment, saving the memory trace at that point into a second file (memory_snapshots.txt).

By default, both outputs will be placed in the current directory (’/home/docs/checkouts/readthedocs.org/user_builds/spinalcordtoolbox/checkouts/stable/documentation/source’). Optionally, you may provide an alternative directory (-trace-memory <dir_name>), in which case all files will be placed in that directory instead. Note that this WILL incur an overhead to runtime, so it is generally advised that you do not run this in conjunction with the time profiler or in time-sensitive contexts.

-r

Possible choices: 0, 1

Remove temporary files.

Default: 1