Shape-based discriminative analysis of combined bilateral hippocampi using multiple object alignment

Li Shen, Fillia Makedon, Andrew Saykin

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

Shape analysis of hippocampi in schizophrenia has been preformed previously using the spherical harmonic SPHARM description. In these studies, the left and right hippocampi are aligned independently and the spatial relation between them is not explored. This paper presents a new SPHARM-based technique which examines not only the individual shape information of the two hippocampi but also the spatial relation between them. The left and right hippocampi are treated as a single shape configuration. A ploy-shape alignment algorithm is developed for aligning configurations of multiple SPHARM surfaces as follows: (1) the total volume is normalized; (2) the parameter space is aligned for creating the surface correspondence; (3) landmarks are created by a uniform sampling of multiple surfaces for each configuration; (4) a quaternion-based algorithm is employed to align each landmark representation to the mean configuration through the least square rotation and translation iteratively until the mean converges. After applying the poly-shape alignment algorithm, a point distribution model is applied to aligned landmarks for feature extraction. Classification is performed using Fisher's linear discriminant with an effective feature selection scheme. Applying the above procedure to our hippocampal data (14 controls versus 25 schizophrenics, all right-handed males), we achieve the best cross-validation accuracy of 92%, supporting the idea that the whole shape configuration of the two hippocampi provides valuable information in detecting schizophrenia. The results of an ROC analysis and a visualization of discriminative patterns are also included.

Original languageEnglish (US)
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
EditorsJ.M. Fitzpatrick, M. Sonka
Pages283-293
Number of pages11
Volume5370 I
DOIs
StatePublished - 2004
Externally publishedYes
EventProgress in Biomedical Optics and Imaging - Medical Imaging 2004: Imaging Processing - San Diego, CA, United States
Duration: Feb 16 2004Feb 19 2004

Other

OtherProgress in Biomedical Optics and Imaging - Medical Imaging 2004: Imaging Processing
CountryUnited States
CitySan Diego, CA
Period2/16/042/19/04

Fingerprint

hippocampus
alignment
landmarks
Feature extraction
schizophrenia
configurations
Visualization
Sampling
quaternions
spherical harmonics
pattern recognition
sampling

Keywords

  • Classification
  • Hippocampus
  • MRI
  • Shape alignment
  • Shape analysis
  • Surface modeling

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Shen, L., Makedon, F., & Saykin, A. (2004). Shape-based discriminative analysis of combined bilateral hippocampi using multiple object alignment. In J. M. Fitzpatrick, & M. Sonka (Eds.), Proceedings of SPIE - The International Society for Optical Engineering (Vol. 5370 I, pp. 283-293) https://doi.org/10.1117/12.536223

Shape-based discriminative analysis of combined bilateral hippocampi using multiple object alignment. / Shen, Li; Makedon, Fillia; Saykin, Andrew.

Proceedings of SPIE - The International Society for Optical Engineering. ed. / J.M. Fitzpatrick; M. Sonka. Vol. 5370 I 2004. p. 283-293.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Shen, L, Makedon, F & Saykin, A 2004, Shape-based discriminative analysis of combined bilateral hippocampi using multiple object alignment. in JM Fitzpatrick & M Sonka (eds), Proceedings of SPIE - The International Society for Optical Engineering. vol. 5370 I, pp. 283-293, Progress in Biomedical Optics and Imaging - Medical Imaging 2004: Imaging Processing, San Diego, CA, United States, 2/16/04. https://doi.org/10.1117/12.536223
Shen L, Makedon F, Saykin A. Shape-based discriminative analysis of combined bilateral hippocampi using multiple object alignment. In Fitzpatrick JM, Sonka M, editors, Proceedings of SPIE - The International Society for Optical Engineering. Vol. 5370 I. 2004. p. 283-293 https://doi.org/10.1117/12.536223
Shen, Li ; Makedon, Fillia ; Saykin, Andrew. / Shape-based discriminative analysis of combined bilateral hippocampi using multiple object alignment. Proceedings of SPIE - The International Society for Optical Engineering. editor / J.M. Fitzpatrick ; M. Sonka. Vol. 5370 I 2004. pp. 283-293
@inproceedings{8c63dd428e6f45f2ab48169738823bf2,
title = "Shape-based discriminative analysis of combined bilateral hippocampi using multiple object alignment",
abstract = "Shape analysis of hippocampi in schizophrenia has been preformed previously using the spherical harmonic SPHARM description. In these studies, the left and right hippocampi are aligned independently and the spatial relation between them is not explored. This paper presents a new SPHARM-based technique which examines not only the individual shape information of the two hippocampi but also the spatial relation between them. The left and right hippocampi are treated as a single shape configuration. A ploy-shape alignment algorithm is developed for aligning configurations of multiple SPHARM surfaces as follows: (1) the total volume is normalized; (2) the parameter space is aligned for creating the surface correspondence; (3) landmarks are created by a uniform sampling of multiple surfaces for each configuration; (4) a quaternion-based algorithm is employed to align each landmark representation to the mean configuration through the least square rotation and translation iteratively until the mean converges. After applying the poly-shape alignment algorithm, a point distribution model is applied to aligned landmarks for feature extraction. Classification is performed using Fisher's linear discriminant with an effective feature selection scheme. Applying the above procedure to our hippocampal data (14 controls versus 25 schizophrenics, all right-handed males), we achieve the best cross-validation accuracy of 92{\%}, supporting the idea that the whole shape configuration of the two hippocampi provides valuable information in detecting schizophrenia. The results of an ROC analysis and a visualization of discriminative patterns are also included.",
keywords = "Classification, Hippocampus, MRI, Shape alignment, Shape analysis, Surface modeling",
author = "Li Shen and Fillia Makedon and Andrew Saykin",
year = "2004",
doi = "10.1117/12.536223",
language = "English (US)",
volume = "5370 I",
pages = "283--293",
editor = "J.M. Fitzpatrick and M. Sonka",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

}

TY - GEN

T1 - Shape-based discriminative analysis of combined bilateral hippocampi using multiple object alignment

AU - Shen, Li

AU - Makedon, Fillia

AU - Saykin, Andrew

PY - 2004

Y1 - 2004

N2 - Shape analysis of hippocampi in schizophrenia has been preformed previously using the spherical harmonic SPHARM description. In these studies, the left and right hippocampi are aligned independently and the spatial relation between them is not explored. This paper presents a new SPHARM-based technique which examines not only the individual shape information of the two hippocampi but also the spatial relation between them. The left and right hippocampi are treated as a single shape configuration. A ploy-shape alignment algorithm is developed for aligning configurations of multiple SPHARM surfaces as follows: (1) the total volume is normalized; (2) the parameter space is aligned for creating the surface correspondence; (3) landmarks are created by a uniform sampling of multiple surfaces for each configuration; (4) a quaternion-based algorithm is employed to align each landmark representation to the mean configuration through the least square rotation and translation iteratively until the mean converges. After applying the poly-shape alignment algorithm, a point distribution model is applied to aligned landmarks for feature extraction. Classification is performed using Fisher's linear discriminant with an effective feature selection scheme. Applying the above procedure to our hippocampal data (14 controls versus 25 schizophrenics, all right-handed males), we achieve the best cross-validation accuracy of 92%, supporting the idea that the whole shape configuration of the two hippocampi provides valuable information in detecting schizophrenia. The results of an ROC analysis and a visualization of discriminative patterns are also included.

AB - Shape analysis of hippocampi in schizophrenia has been preformed previously using the spherical harmonic SPHARM description. In these studies, the left and right hippocampi are aligned independently and the spatial relation between them is not explored. This paper presents a new SPHARM-based technique which examines not only the individual shape information of the two hippocampi but also the spatial relation between them. The left and right hippocampi are treated as a single shape configuration. A ploy-shape alignment algorithm is developed for aligning configurations of multiple SPHARM surfaces as follows: (1) the total volume is normalized; (2) the parameter space is aligned for creating the surface correspondence; (3) landmarks are created by a uniform sampling of multiple surfaces for each configuration; (4) a quaternion-based algorithm is employed to align each landmark representation to the mean configuration through the least square rotation and translation iteratively until the mean converges. After applying the poly-shape alignment algorithm, a point distribution model is applied to aligned landmarks for feature extraction. Classification is performed using Fisher's linear discriminant with an effective feature selection scheme. Applying the above procedure to our hippocampal data (14 controls versus 25 schizophrenics, all right-handed males), we achieve the best cross-validation accuracy of 92%, supporting the idea that the whole shape configuration of the two hippocampi provides valuable information in detecting schizophrenia. The results of an ROC analysis and a visualization of discriminative patterns are also included.

KW - Classification

KW - Hippocampus

KW - MRI

KW - Shape alignment

KW - Shape analysis

KW - Surface modeling

UR - http://www.scopus.com/inward/record.url?scp=5644268130&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=5644268130&partnerID=8YFLogxK

U2 - 10.1117/12.536223

DO - 10.1117/12.536223

M3 - Conference contribution

AN - SCOPUS:5644268130

VL - 5370 I

SP - 283

EP - 293

BT - Proceedings of SPIE - The International Society for Optical Engineering

A2 - Fitzpatrick, J.M.

A2 - Sonka, M.

ER -