Difference between revisions of "Publications/carlinet.19.csi"

From LRDE

Line 5: Line 5:
 
| title = Intervertebral Disc Segmentation Using Mathematical Morphology—A CNN-Free Approach
 
| title = Intervertebral Disc Segmentation Using Mathematical Morphology—A CNN-Free Approach
 
| booktitle = Proceedings of the 5th MICCAI Workshop & Challenge on Computational Methods and Clinical Applications for Spine Imaging (CSI)
 
| booktitle = Proceedings of the 5th MICCAI Workshop & Challenge on Computational Methods and Clinical Applications for Spine Imaging (CSI)
| publisher = Springer-Verlag
+
| publisher = Springer
 
| series = Lecture Notes in Computer Science
 
| series = Lecture Notes in Computer Science
 
| volume = 11384
 
| volume = 11384
| pages = 1 to 14
+
| pages = 105 to 118
 
| abstract = In the context of the challenge of “automatic InterVertebral Disc (IVD) localization and segmentation from 3D multi-modality MR images” that took place at MICCAI 2018, we have proposed a segmentation method based on simple image processing operators. Most of these operators come from the mathematical morphology framework. Driven by some prior knowledge on IVDs (basic information about their shape and the distance between them), and on their contrast in the different modalities, we were able to segment correctly almost every IVD. The most interesting feature of our method is to rely on the morphological structure called the Three of Shapes, which is another way to represent the image contents. This structure arranges all the connected components of an image obtained by thresholding into a tree, where each node represents a particular region. Such structure is actually powerful and versatile for pattern recognition tasks in medical imaging.
 
| abstract = In the context of the challenge of “automatic InterVertebral Disc (IVD) localization and segmentation from 3D multi-modality MR images” that took place at MICCAI 2018, we have proposed a segmentation method based on simple image processing operators. Most of these operators come from the mathematical morphology framework. Driven by some prior knowledge on IVDs (basic information about their shape and the distance between them), and on their contrast in the different modalities, we were able to segment correctly almost every IVD. The most interesting feature of our method is to rely on the morphological structure called the Three of Shapes, which is another way to represent the image contents. This structure arranges all the connected components of an image obtained by thresholding into a tree, where each node represents a particular region. Such structure is actually powerful and versatile for pattern recognition tasks in medical imaging.
 
| lrdepaper = http://www.lrde.epita.fr/dload/papers/carlinet.19.csi.pdf
 
| lrdepaper = http://www.lrde.epita.fr/dload/papers/carlinet.19.csi.pdf
Line 26: Line 26:
 
Imaging (CSI)<nowiki>}</nowiki>,
 
Imaging (CSI)<nowiki>}</nowiki>,
 
year = <nowiki>{</nowiki>2019<nowiki>}</nowiki>,
 
year = <nowiki>{</nowiki>2019<nowiki>}</nowiki>,
publisher = <nowiki>{</nowiki>Springer-Verlag<nowiki>}</nowiki>,
+
publisher = <nowiki>{</nowiki>Springer<nowiki>}</nowiki>,
 
series = <nowiki>{</nowiki>Lecture Notes in Computer Science<nowiki>}</nowiki>,
 
series = <nowiki>{</nowiki>Lecture Notes in Computer Science<nowiki>}</nowiki>,
 
volume = <nowiki>{</nowiki>11384<nowiki>}</nowiki>,
 
volume = <nowiki>{</nowiki>11384<nowiki>}</nowiki>,
pages = <nowiki>{</nowiki>1--14<nowiki>}</nowiki>,
+
pages = <nowiki>{</nowiki>105--118<nowiki>}</nowiki>,
 
abstract = <nowiki>{</nowiki>In the context of the challenge of ``automatic
 
abstract = <nowiki>{</nowiki>In the context of the challenge of ``automatic
 
InterVertebral Disc (IVD) localization and segmentation
 
InterVertebral Disc (IVD) localization and segmentation

Revision as of 08:51, 19 March 2019

Abstract

In the context of the challenge of “automatic InterVertebral Disc (IVD) localization and segmentation from 3D multi-modality MR images” that took place at MICCAI 2018, we have proposed a segmentation method based on simple image processing operators. Most of these operators come from the mathematical morphology framework. Driven by some prior knowledge on IVDs (basic information about their shape and the distance between them), and on their contrast in the different modalities, we were able to segment correctly almost every IVD. The most interesting feature of our method is to rely on the morphological structure called the Three of Shapes, which is another way to represent the image contents. This structure arranges all the connected components of an image obtained by thresholding into a tree, where each node represents a particular region. Such structure is actually powerful and versatile for pattern recognition tasks in medical imaging.

Documents

Source code

Source code available in this archive.

To build and run the method

tar xf ivdm3seg-lrde.tar.gz
mkdir build && cd build
cmake ../ivdm3seg-lrde -DCMAKE_BUILD_TYPE=Release
cmake --build . --target ivdm3seg



Usage

Usage: ./ivdm3seg [OPTIONS] FAT.nii INN.nii OPP.nii WAT.nii output.nii


The program uses Pylene, our image processing library.

Bibtex (lrde.bib)

@InProceedings{	  carlinet.19.csi,
  author	= {Edwin Carlinet and Thierry G\'eraud},
  title		= {Intervertebral Disc Segmentation Using Mathematical
		  Morphology---{A} {CNN}-Free Approach},
  booktitle	= {Proceedings of the 5th MICCAI Workshop \& Challenge on
		  Computational Methods and Clinical Applications for Spine
		  Imaging (CSI)},
  year		= {2019},
  publisher	= {Springer},
  series	= {Lecture Notes in Computer Science},
  volume	= {11384},
  pages		= {105--118},
  abstract	= {In the context of the challenge of ``automatic
		  InterVertebral Disc (IVD) localization and segmentation
		  from 3D multi-modality MR images'' that took place at
		  MICCAI 2018, we have proposed a segmentation method based
		  on simple image processing operators. Most of these
		  operators come from the mathematical morphology framework.
		  Driven by some prior knowledge on IVDs (basic information
		  about their shape and the distance between them), and on
		  their contrast in the different modalities, we were able to
		  segment correctly almost every IVD. The most interesting
		  feature of our method is to rely on the morphological
		  structure called the Three of Shapes, which is another way
		  to represent the image contents. This structure arranges
		  all the connected components of an image obtained by
		  thresholding into a tree, where each node represents a
		  particular region. Such structure is actually powerful and
		  versatile for pattern recognition tasks in medical
		  imaging.}
}