kevin-keraudren

# http://blog.seljebu.no/2014/11/22/install-numba-in-osx-yosemite-with-brew/
# http://www.australsounds.com/2014/10/installing-numba-in-os-x-1010.html

brew tap homebrew/versions
brew install --disable-assertions --rtti llvm37

git clone https://github.com/numba/llvmlite
cd llvmlite
LLVM_CONFIG=/usr/local/Cellar/llvm37/3.7.1/bin/llvm-config-3.7 python setup.py install
cd ..

kevin-keraudren

Conferences in Medical Imaging/Computer Vision

MICCAI: Medical Image Computing and Computer Assisted Intervention

http://www.miccai.org/

BMVC: British Machine Vision Conference

kevin-keraudren

#!/bin/bash

set -x
set -e

git clone https://github.com/Kitware/VTK.git

cd VTK
mkdir build
cd build

kevin-keraudren

#!/usr/bin/python

import numpy as np
import cv2
import densecrf as dcrf
from skimage.segmentation import relabel_sequential
import sys

# Usage:
# python dense_inference.py image annotations output

kevin-keraudren

Building SimpleElastix

Swig can be installed separately:

brew install swig

Then run the SuperBuild:

git clone https://github.com/kaspermarstal/SimpleElastix

kevin-keraudren

# http://stackoverflow.com/questions/9924135/fast-cartesian-to-polar-to-cartesian-in-python

import cv2
import numpy as np
import scipy.ndimage as nd

import irtk

def polar2cart(r, theta, center):
    x = r * np.cos(theta) + center[0]

kevin-keraudren

import dicom
import numpy as np

def load_dcm(filename):
    dcm = dicom.ReadFile(filename)

    # http://www.creatis.insa-lyon.fr/pipermail/dcmlib/2005-September/002141.html
    # http://www.dabsoft.ch/dicom/3/C.7.6.2.1.1/
    # http://xmedcon.sourceforge.net/Docs/OrientationDicomStandard
    img0 = dcm[(0x5200, 0x9230)][0] # Per-frame Functional Groups Sequence 

kevin-keraudren

Note: this page was originally written in pmWiki for the wiki of the Biomedia group.

It was converted to markdown using an HTML-to-markdown converter and a markdown editor.

See the official documentation for more info about SLURM.

Example 1: looping over subjects

the --wrap option allows you to pass one-liners to sbatch (see sbatch -h):

kevin-keraudren

import numpy as np

def dr_toolbox(D,n_components=None):
    """
    Landmark isomap dimensionality reduction method
    This is the version implemented in
    http://homepage.tudelft.nl/19j49/Matlab_Toolbox_for_Dimensionality_Reduction.html
    
    Parameters
    ----------

kevin-keraudren

#!/usr/bin/env jython

#  \begin{enumerate}
#    \item Process $\rightarrow$ Gaussian Blur
#    \item Process $\rightarrow$ Enhance Contrast (normalize \& equalize histogram)
#    \item Image $\rightarrow$ Type $\rightarrow$ HSB stack
#    \item Image $\rightarrow$ Stacks $\rightarrow$ Stack to images
#    \item keep only the Hue image
#    \item Process $\rightarrow$ Find maxima... (noise tolerance 60)
# \end{enumerate}