advertisement

Reading group - 22/05/2013

50 %
50 %
advertisement
Information about Reading group - 22/05/2013
Technology

Published on March 4, 2014

Author: kevinkeraudren

Source: slideshare.net

Description

Slides from the reading group presentation where I introduced a new Python interface for IRTK.

See http://kevin-keraudren.blogspot.co.uk/2013/12/irtk-python.html for more details and the iPython notebook demo.
advertisement

Organ Detection in Fetal MRI Kevin Keraudren Imperial College London May 22nd , 2013

1 Overview 2 Python interface for IRTK 3 Future work 2/27

1 Overview 2 Python interface for IRTK 3 Future work 3/27

Overview 1 Brain detection & reconstruction 2 3D visualisation 3 Organ localisation 4/27

People Brain reconstruction: Maria Murgasova 3D visualisation: Christina Malamateniou Organ detection: Bernhard Kainz 5/27

Localisation of the Brain in Fetal MRI Using Bundled SIFT Features For every slice Detect MSER regions Filter by size RANSAC Classify using SIFT features 6/27

Detections results averaged over the cross validation (all orientations combined) Centiles 25th 50th 75th 2D SIFT 10.9 15.5 20.5 Error (mm) 3D SIFT 14.8 20.8 30.4 Bundled SIFT 4.0 5.7 8.4 Detection Complete brain 98% 38% 85% 23% 100% 85% 7/27

1 Overview 2 Python interface for IRTK 3 Future work 8/27

Why Python? ls *.nii | python -c ’import sys, irtk; [sys.stdout.write( str(irtk.imread(line.rstrip(), dtype="float32").max())+"n") for line in sys.stdin]’ numpy, matplotlib, OpenCV, VTK, scipy.ndimage... & C++ via cython 9/27

Why another library? import itk pixelType = itk.UC imageType = itk.Image[pixelType, 3] readerType = itk.ImageFileReader[imageType] writerType = itk.ImageFileWriter[imageType] reader = readerType.New() reader.SetFileName( "input.nii" ) reader.Update() itk2np = itk.PyBuffer[imageType] data = itk2np.GetArrayFromImage( reader.GetOutput() ) ... 10/27

Why another library? import SimpleITK as sitk img = sitk.ReadImage( "input.nii" ) data = sitk.GetArrayFromImage( img ) ... output = sitk.GetImageFromArray( data ) output.SetSpacing( img.GetSpacing() ) output.SetOrigin( img.GetOrigin() ) output.SetDirection( img.GetDirection() ) sitk.WriteImage( output, "output.nii" ) 11/27

Why another library? import irtk img = irtk.imread( "input.nii" ) ... irtk.imwrite( "output.nii", img ) 12/27

Key features simple and pythonic overload getitem instead of GetRegion parallelisation using joblib visualisation functions 13/27

Implementation template <class dtype> void irtk2py( irtkGenericImage<dtype>& irtk_image, dtype* img, double* pixelSize, double* xAxis, double* yAxis, double* zAxis, double* origin, int* dim ); 14/27

Implementation void py2rigid( irtkRigidTransformation &transform, double tx, double ty, double tz, double rx, double ry, double rz, bool invert=false ); 15/27

Demo ipython notebook 16/27

Parallelisation example                     import irtk from joblib import Parallel, delayed from glob import glob def register( f, img1): img2 = irtk.imread( f, dtype=’float32’) img2 = img2.rescale().resample(2) t = img2.register(img1) return t filenames = glob( raw_folder + "/" + patient_id + "_*.nii") img1 = irtk.imread(filenames[0], dtype=’float32’) img1 = img1.rescale().resample(2) transformations = [irtk.RigidTransformation()] transformations.extend( Parallel(n_jobs=-1)(delayed(register)(f, img1) for f in filenames[1:] ) ) 17/27

1 Overview 2 Python interface for IRTK 3 Future work 18/27

Coarse segmentation as side product of detection 19/27

Convex hull of all detections 20/27

Iterative detection/reconstruction 21/27

Iterative detection/reconstruction 22/27

Iterative detection/reconstruction 23/27

Room for improvement Refine motion model (statistics on slice transformations) Patch based segmentation instead of graphcut Detect head orientation to solve more difficult registrations Could the detection process produce more than a mask? 24/27

Could we reconstruct more than the brain? 25/27

For the future (hanging projects) Spine detection using SLIC supervoxels Dense volumetric features: SURF 3D Alignment of mothers’ bodies to model of a pregnant woman 26/27

Suggestions or questions? 27/27

Add a comment

Related presentations

Presentación que realice en el Evento Nacional de Gobierno Abierto, realizado los ...

In this presentation we will describe our experience developing with a highly dyna...

Presentation to the LITA Forum 7th November 2014 Albuquerque, NM

Un recorrido por los cambios que nos generará el wearabletech en el futuro

Um paralelo entre as novidades & mercado em Wearable Computing e Tecnologias Assis...

Microsoft finally joins the smartwatch and fitness tracker game by introducing the...

Related pages

22 | May | 2013 | Debden Park High School

The Carnegie Book Awards is a National reading scheme that DPHS have chosen to take part in. The group consists of Gifted and Talented students and keen ...
Read more

Glen Taylor School - 22/05/2013 | Education Review Office

... 22/05/2013. On this ... The school is justifiably proud of the progress of students in reading, ... Teacher and Friends of Glen Taylor School group ...
Read more

Reading Group Notes: Clade | Penguin Books Australia

Love Reading? You need Read More, ... Reading Group Notes. ... Published: 22/05/2013. Format: Paperback. ISBN: ...
Read more

May | 2013 | rdn32

I intermittently attend a “science and literature” reading group. The last thing I read for the group was “The Languages ... photo on 22/05/2013 ...
Read more

Teaching Resources | Reading comprehension: Snappy the ...

Reading comprehension: ... 22 05 2013; Reading comprehension: ... They are asked to use resources like the in... Report Form ...
Read more

News Flash - Date for the Diary | Lisa Cooley | Blog

... Date for the Diary posted by Lisa Cooley on 22/05/2013 [Back to Home Page] ... Esoteric Reading Discussion Group; Esoteric Reading Discussion Group;
Read more

Reading group - Wireless and Dynamic Networks - LINCS

22/05/2013, Wed, 10:30 ... //www.lincs.fr/activities/reading-groups/reading-group-wireless-and-dynamic-networks/
Read more

May | 2013 | Open Moves

Monthly Archives: May 2013. ... Weekly newsletter 22.05.2013. ... Open Moves is a division of Incommunities Group Limited.
Read more