## Biomarkers for Identifying First-Episode Schizophrenia Patients Using Diffusion Weighted Imaging

### BibTeX

@MISC{Rathi_biomarkersfor,

author = {Yogesh Rathi and James Malcolm and Oleg Michailovich and Jill Goldstein and Larry Seidman and Robert W. Mccarley and Carl-fredrik Westin and Martha E. Shenton},

title = {Biomarkers for Identifying First-Episode Schizophrenia Patients Using Diffusion Weighted Imaging},

year = {}

}

### OpenURL

### Abstract

Abstract. Recent advances in diffusion weighted MR imaging (dMRI) has made it a tool of choice for investigating white matter abnormalities of the brain and central nervous system. In this work, we design a system that detects abnormal features (biomarkers) of first-episode schizophrenia patients and then classifies them using these features. We use two different models of the dMRI data, namely, spherical harmonics and the two-tensor model. The algorithm works by first computing several diffusion measures from each model. An affine-invariant representation of each subject is then computed, thus avoiding the need for registration. This representation is used within a kernel based feature selection algorithm to determine the biomarkers that are statistically different between the two populations. Confirmation of how well these biomarkers identify each population is obtained by using several classifiers such as, k-nearest neighbors, Parzen window classifier, and support vector machines to separate 21 first-episode patients from 20 age-matched normal controls. Classification results using leave-manyout cross-validation scheme are given for each representation. This algorithm is a first step towards early detection of schizophrenia. 1

### Citations

983 |
Nearest neighbor pattern classification
- Cover, Hart
- 1967
(Show Context)
Citation Context ...so as to best separate the groups in the training data set. Several classifiers have been proposed in the literature. We will use three popular ones: Parzen window classifier [26], k-nearest neighbor =-=[27]-=- and support vector machines (SVM) [28]. A typical way to ensure robustness to overfitting for any classifier is to perform a leave-many-out cross validation. In this technique, a certain percentage o... |

846 |
On Estimation of a Probability Density Function and Mode
- Parzen
- 1962
(Show Context)
Citation Context ...ing data. We achieve this by computing a probability density function (PDF) of each diffusion measure defined above. A nonparametric estimate of the PDF can be computed using the following expression =-=[25]-=-: p(z) = 1 ∑M Mh i=1 G ( ) z−I(x) h , z ∈ {Range of I}, where I(x) is a scalar value at spatial location x, M is the number of data points, G is a Gaussian kernel and h denotes the bandwidth of the ke... |

218 |
MR diffusion tensor spectroscopy and imaging
- Basser, Mattiello, et al.
- 1994
(Show Context)
Citation Context ...e), producing the corresponding signal, s = [s1,..., sn ] T ∈ Rn . One of the simplest model that explains s is the diffusion tensor model, which provides a Gaussian estimate of the fiber orientation =-=[14]-=-. However, this model is highly inadequate in regions of crossings andBiomarkers for Identifying First-Episode Schizophrenia Patients 659 branching fibers [15]. To overcome this limitation, several o... |

89 |
Q-Ball Imaging
- Tuch
- 2004
(Show Context)
Citation Context ...ssian estimate of the fiber orientation [14]. However, this model is highly inadequate in regions of crossings andBiomarkers for Identifying First-Episode Schizophrenia Patients 659 branching fibers =-=[15]-=-. To overcome this limitation, several other models have been proposed [15,16,17,18,19,20,12]. Of these, we use the nonparametric spherical harmonics (SH) model of computing the orientation distributi... |

86 |
Persistent angular structure: new insights fom diffusion magnetic resonance imaging data, in "Inverse Problems
- JANSONS, ALEXANDER
(Show Context)
Citation Context ... inadequate in regions of crossings andBiomarkers for Identifying First-Episode Schizophrenia Patients 659 branching fibers [15]. To overcome this limitation, several other models have been proposed =-=[15,16,17,18,19,20,12]-=-. Of these, we use the nonparametric spherical harmonics (SH) model of computing the orientation distribution funciton (ODF) [11] and the unscented Kalman filter (UKF) based two-tensor model proposed ... |

83 |
Probabilistic diffusion tractography with multiple fibre orientations. What can we gain?, in "NeuroImage
- BEHRENS, JOHANSEN-BERG, et al.
- 2007
(Show Context)
Citation Context ...work on distinguishing chronic schizophrenia used the single tensor model, which is known to be inadequate in regions of crossing and branching - a common configuration occurring throughout the brain =-=[10]-=-. In this work, we use a nonparametric spherical harmonics model [11], as well as a parametric two-tensor model [12] to detect biomarkers and perform classification of FE patients. These models can be... |

78 | A.J.: Advances in kernel methods: Support Vector Learning
- Bernhard, Burges, et al.
- 1999
(Show Context)
Citation Context ...e training data set. Several classifiers have been proposed in the literature. We will use three popular ones: Parzen window classifier [26], k-nearest neighbor [27] and support vector machines (SVM) =-=[28]-=-. A typical way to ensure robustness to overfitting for any classifier is to perform a leave-many-out cross validation. In this technique, a certain percentage of the available data are randomly selec... |

76 |
Direct estimation of the fiber orientation density function from diffusion-weighted MRI data using spherical deconvolution
- Tournier, Calamante, et al.
- 2004
(Show Context)
Citation Context ... inadequate in regions of crossings andBiomarkers for Identifying First-Episode Schizophrenia Patients 659 branching fibers [15]. To overcome this limitation, several other models have been proposed =-=[15,16,17,18,19,20,12]-=-. Of these, we use the nonparametric spherical harmonics (SH) model of computing the orientation distribution funciton (ODF) [11] and the unscented Kalman filter (UKF) based two-tensor model proposed ... |

73 |
A kernel method for the two-sample-problem
- Gretton, Borgwardt, et al.
- 2007
(Show Context)
Citation Context ... an affine invariant probabilistic representation of each subject, which avoids the computational cost of registration along with errors due to mis-registration. Finally, we use a kernel based method =-=[13]-=- to locate statistically different diffusion measures (biomarkers) followed by classification of FE patients using several classifiers, i.e., Parzen window classifier, k-nearest neighbor and support v... |

50 |
Measurement of fiber orientation distributions using high angular resolution diffusion imaging
- Anderson
- 2005
(Show Context)
Citation Context ... inadequate in regions of crossings andBiomarkers for Identifying First-Episode Schizophrenia Patients 659 branching fibers [15]. To overcome this limitation, several other models have been proposed =-=[15,16,17,18,19,20,12]-=-. Of these, we use the nonparametric spherical harmonics (SH) model of computing the orientation distribution funciton (ODF) [11] and the unscented Kalman filter (UKF) based two-tensor model proposed ... |

34 |
robust analytical q-ball imaging
- Descoteaux, Angelino, et al.
(Show Context)
Citation Context ...odel, which is known to be inadequate in regions of crossing and branching - a common configuration occurring throughout the brain [10]. In this work, we use a nonparametric spherical harmonics model =-=[11]-=-, as well as a parametric two-tensor model [12] to detect biomarkers and perform classification of FE patients. These models can better capture multi-fiber configurations and hence the abnormality in ... |

34 |
A unified computational framework for deconvolution to reconstruct multiple fibers from diffusion weighted MRI
- Jian, Vemuri, et al.
- 2007
(Show Context)
Citation Context |

32 |
Cross-validation of regression models
- Picard, Cook
- 1984
(Show Context)
Citation Context ... were randomly generated from the original data and testing was done on the remaining samples. This method of crossvalidation is a very good estimator of the generalization property of any classifier =-=[29]-=-. For the k-nearest neighbor (knn) classifier, we used 6 nearest neighbors, with cosine of the angle between the PDF’s as a measure of similarity (the PDF’s can be thought of as nb dimensional vectors... |

31 |
Regularized PositiveDefinite Fourth-Order Tensor Field Estimation from DW-MRI, in "NeuroImage
- BARMPOUTIS, HWANG, et al.
- 2009
(Show Context)
Citation Context |

26 | Generalized Scalar Measures for Diffusion MRI Using Trace, Variance and Entropy
- ÖZARSLAN, VEMURI, et al.
(Show Context)
Citation Context ...e measures are potential candidates for being used as biomarkers. In the case of the SH model, generalized fractional anisotropy (GFA) and generalized norm (GN) are the diffusion measures of interest =-=[23]-=-. These measures can be readily computed in the SH basis as follows 1 : √ n GFA = ∑n i=1 (Si − ¯ S) 2 (n − 1) ∑n i=1 S2 , GN =‖ c ‖2, with S =[S1S2...Sn], i where S is the estimated signal using the S... |

25 |
A review of diffusion tensor imaging studies in schizophrenia
- Kubicki, McCarley, et al.
- 2007
(Show Context)
Citation Context ...features are then used within a classification system to determine their potential use as biomarkers. While several studies have reported statistical differences in diffusion measures for FE patients =-=[8,9]-=-, to the best of our knowledge, this is the first study that uses them to perform classification. Existing work on distinguishing chronic schizophrenia used the single tensor model, which is known to ... |

15 |
Anisotropic diffusion in human white matter: demonstration with MR techniques in vivo, Radiology 177
- Chenevert, Brunberg, et al.
- 1990
(Show Context)
Citation Context ...ods Validation studies have indicated the correlation between de-myelination, cellular packing, and axonal damage to diffusion measures such as fractional anisotropy (FA), trace (TR), norm (N), etc., =-=[21,22]-=-. Thus, these measures are potential candidates for being used as biomarkers. In the case of the SH model, generalized fractional anisotropy (GFA) and generalized norm (GN) are the diffusion measures ... |

12 |
Whole-brain morphometric study of schizophrenia revealing a spatially complex set of focal abnormalities
- Davatzikos, Shen, et al.
- 2005
(Show Context)
Citation Context ...izophrenia or other subtle psychiatric disorders such as mild to moderate traumatic brain injury. There has been some work done on classifying patients with chronic schizophrenia using structural MRI =-=[2,3]-=-. The authors in [4,5] use dimensionality reduction followed by linear discriminant analysis for classification of patients with schizophrenia (chronic). They, however, only use the fractional anisotr... |

12 | C.F.: Diffusion tensor analysis with invariant gradients and rotation tangents
- Kindlmann, Ennis, et al.
- 2007
(Show Context)
Citation Context ...d by s, while the estimated signal is denoted by S.660 Y. Rathi et al. The F2T model allows for computation of a different set of orthogonal diffusion measures such as the FA, Mode (MD) and norm (N) =-=[24]-=-. These measures capture different (orthogonal) aspects of the shape of the tensor. Thus, FA measures the anisotropy while norm captures the amount of diffusion. Mode distinguishes between planar, ell... |

11 |
F.: Shaving diffusion tensor images in discriminant analysis: A study into schizophrenia. Medical Image Analysis 10
- Caan, Vermeer, et al.
- 2006
(Show Context)
Citation Context ...btle psychiatric disorders such as mild to moderate traumatic brain injury. There has been some work done on classifying patients with chronic schizophrenia using structural MRI [2,3]. The authors in =-=[4,5]-=- use dimensionality reduction followed by linear discriminant analysis for classification of patients with schizophrenia (chronic). They, however, only use the fractional anisotropy (FA) images derive... |

10 | Neural tractography using an unscented Kalman filter
- Malcolm, Shenton, et al.
- 2009
(Show Context)
Citation Context ...s of crossing and branching - a common configuration occurring throughout the brain [10]. In this work, we use a nonparametric spherical harmonics model [11], as well as a parametric two-tensor model =-=[12]-=- to detect biomarkers and perform classification of FE patients. These models can better capture multi-fiber configurations and hence the abnormality in the underlying anatomy. Another novel aspect in... |

9 |
Early detection and intervention in schizophrenia: rationale
- McGlashan, Johannessen
- 1996
(Show Context)
Citation Context .... A growing body of evidence suggests that early detection and treatment of schizophrenia (and many other brain disorders) is critical in forming and predicting the course and outcome of the disorder =-=[1]-=-. The tools proposed in this work can serve as a first step towards early detection of schizophrenia, which may result in better prognosis and functional outcome. However, very little work has been do... |

9 |
Toward accurate diagnosis of white matter pathology using diffusion tensor imaging
- Budde, Liang, et al.
- 2007
(Show Context)
Citation Context ...ods Validation studies have indicated the correlation between de-myelination, cellular packing, and axonal damage to diffusion measures such as fractional anisotropy (FA), trace (TR), norm (N), etc., =-=[21,22]-=-. Thus, these measures are potential candidates for being used as biomarkers. In the case of the SH model, generalized fractional anisotropy (GFA) and generalized norm (GN) are the diffusion measures ... |

9 |
Classifier Design with Parzen Windows
- Jain, Ramaswami
- 1988
(Show Context)
Citation Context ...izes a particular metric so as to best separate the groups in the training data set. Several classifiers have been proposed in the literature. We will use three popular ones: Parzen window classifier =-=[26]-=-, k-nearest neighbor [27] and support vector machines (SVM) [28]. A typical way to ensure robustness to overfitting for any classifier is to perform a leave-many-out cross validation. In this techniqu... |

6 |
Differential targeting of the CA1 subfield of the hippocampal formation by schizophrenia and related psychotic disorders
- Schobel, Lewandowski, et al.
- 2009
(Show Context)
Citation Context ...ors use kernel methods for discriminating schizophrenia patients. Recent work has also focussed on using other imaging modalities, such as, functional MRI for detection of schizophrenia in prodromals =-=[7]-=-. The work presented in this paper, can provide complementary anatomical input to such fMRI based techniques for early detection of schizophrenia. 2 Our Contribution In this work, we propose to design... |

5 |
Kernel-based manifold learning for statistical analysis of diffusion tensor images
- Khurd, Verma, et al.
(Show Context)
Citation Context ...ion of patients with schizophrenia (chronic). They, however, only use the fractional anisotropy (FA) images derived from single tensor estimation as a discriminant feature. Another related work is by =-=[6]-=-, where T. Jiang et al. (Eds.): MICCAI 2010, Part I, LNCS 6361, pp. 657–665, 2010. c○ Springer-Verlag Berlin Heidelberg 2010658 Y. Rathi et al. the authors use kernel methods for discriminating schiz... |

4 |
M.R.: A unified framework for mr based disease classification
- Pohl, Sabuncu
- 2009
(Show Context)
Citation Context ...izophrenia or other subtle psychiatric disorders such as mild to moderate traumatic brain injury. There has been some work done on classifying patients with chronic schizophrenia using structural MRI =-=[2,3]-=-. The authors in [4,5] use dimensionality reduction followed by linear discriminant analysis for classification of patients with schizophrenia (chronic). They, however, only use the fractional anisotr... |

3 |
Application of principal component analysis to distinguish patients with schizophrenia from healthy controls based on fractional anisotropy measurements. NeuroImage 42(2):675–682
- Caprihan, Pearlson, et al.
- 2008
(Show Context)
Citation Context ...btle psychiatric disorders such as mild to moderate traumatic brain injury. There has been some work done on classifying patients with chronic schizophrenia using structural MRI [2,3]. The authors in =-=[4,5]-=- use dimensionality reduction followed by linear discriminant analysis for classification of patients with schizophrenia (chronic). They, however, only use the fractional anisotropy (FA) images derive... |

1 |
et al.: Diffusion tensor imaging findings in first-episode and chronic schizophrenia patients
- Friedman, Tang, et al.
- 2008
(Show Context)
Citation Context ...features are then used within a classification system to determine their potential use as biomarkers. While several studies have reported statistical differences in diffusion measures for FE patients =-=[8,9]-=-, to the best of our knowledge, this is the first study that uses them to perform classification. Existing work on distinguishing chronic schizophrenia used the single tensor model, which is known to ... |