MIDAS Journal - Automated MS-Lesion Segmentation by K-Nearest Neighbor Classification

Automated MS-Lesion Segmentation by K-Nearest Neighbor Classification

Anbeek P., Vincken K.L., Viergever M.A.

Image Sciences Institute, UMC Utrecht

Please use this identifier to cite or link to this publication: http://hdl.handle.net/10380/1448

Published in The MIDAS Journal - MS Lesion Segmentation (MICCAI 2008 Workshop).

Submitted by Petronella Anbeek on 08-11-2008.

This paper proposes a new method for fully automated multiple sclerosis (MS) lesion segmentation in cranial magnetic resonance (MR) imaging. The algorithm uses the T1-weighted and the fluid attenuation inversion recovery scans. It is based the K-Nearest Neighbor (KNN) classification technique. The data has been acquired at the Children�s Hospital Boston (CHB) and the University of North Carolina (UNC). Manual segmentations, composed by a human expert of the CHB, were used for training of the KNN-classification. The method uses voxel location and signal intensity information for determination of the probability being a lesion per voxel, thus generating probabilistic segmentation images. By applying a threshold on the probabilistic images binary segmentations are derived. Automatic segmentations were performed on a set of testing images, and compared with manual segmentations from a CHB and a UNC expert rater. Furthermore, a combined segmentation was composed from segmentations from different algorithms, and used for evaluation. The proposed method shows good resemblance with the segmentations of the CHB rater. High specificity and lower specificity has been observed in comparison with the combined segmentations. Over- and undersegmentation can be easily corrected in this procedure by varying the threshold on the probabilistic segmentation image. The proposed method offers an automated and fully reproducible approach that accurate and applicable on standard clinical MR images.

Reviews

KNN tissue classification for MS lesion detection by Martin Styner on 07-29-2008 for revision #1

expertise: 5 sensitivity: 5

The paper presents a voxelwise KNN tissue classification for MS lesion detection.

Can you elaborate why only T1 and FLAIR was employed, when more MR scans were available?

Overall the results are quite good as they are similar to the CHB rater's performance (the rater used in the training), while they are still appropriate as compared to the UNC rater.

Also, the STAPLE segmentation incorporate all segmentation results used in this competition and the majority of the segmentations seem to oversegment the MS lesions. This explains why your results indicate an over segmentation as compared to the human raters and under segmentation as compared to the STAPLE computation.

Another revision, maybe by an english native speaker, would improve the quality of the submission.

Minor:

Abstract: "It is based the K-..." should be "It is based on the K-...", "that accurate" should be "that is accurate"

Image Processing section: "..performed before they were provided" should be "....performed as provided by the workshop organizers."

Comment by Petronella Anbeek: Comment to Martin Styner

Review Martin Styner:
The paper presents a voxelwise KNN tissue classification for MS lesion detection.
Can you elaborate why only T1 and FLAIR was employed, when more MR scans were available?
âI have added a more elaborate motivation of why only the T1 and the FLAIR where used in the Methods and in the Discussion section.â
Overall the results are quite good as they are similar to the CHB rater's performance (the rater used in the training), while they are still appropriate as compared to the UNC rater.
Also, the STAPLE segmentation incorporate all segmentation results used in this competition and the majority of the segmentations seem to oversegment the MS lesions. This explains why your results indicate an over segmentation as compared to the human raters and under segmentation as compared to the STAPLE computation.
Another revision, maybe by an english native speaker, would improve the quality of the submission.
âAccording to the suggestion of the reviewer, the paper has been revised by two excellent English speakers.â
Minor:
Abstract: "It is based the K-..." should be "It is based on the K-...", "that accurate" should be "that is accurate"
Image Processing section: "..performed before they were provided" should be "....performed as provided by the workshop organizers."
âAll textual errors have been corrected.â

Review by Simon Warfield on 07-25-2008 for revision #1

expertise: 5 sensitivity: 5

Add a new review

Quick Comments

Resources


Download Package
Download Paper, View Paper

Statistics more


Global rating:
Review rating:	[review]
Views:	3732
Downloads:	276
Paper Quality:

Information more


Paper Id:	610
Categories:	Bayesian Decision Theory, Classification, Data, Data Representation, Density Estimation, Feature extraction, Filtering, Image, Images, Mathematics, Neural networks, Parameter Techniques, Probability, Programming, Registration, Segmentation, Thresholding
Keywords:	MS, Multiple Sclerosis, brain, segmentation, lesion, white matter,
Revision:
Export citation:
Status:	Open for public review

Share

Associated Publications more


A robust Expectation-Maximization algorithm for Multiple Sclerosis lesion segmentation
3D Segmentation In The Clinic: A Grand Challenge II at MICCAI 2008 - MS Lesion Segmentation
Automatic MS Lesion Segmentation by Outlier Detection and Information Theoretic Region Partitioning

View license

Loading license...

Send a message to the author