Dataset Information

Applying tensor-based morphometry to parametric surfaces can improve MRI-based disease diagnosis.

ABSTRACT: Many methods have been proposed for computer-assisted diagnostic classification. Full tensor information and machine learning with 3D maps derived from brain images may help detect subtle differences or classify subjects into different groups. Here we develop a new approach to apply tensor-based morphometry to parametric surface models for diagnostic classification. We use this approach to identify cortical surface features for use in diagnostic classifiers. First, with holomorphic 1-forms, we compute an efficient and accurate conformal mapping from a multiply connected mesh to the so-called slit domain. Next, the surface parameterization approach provides a natural way to register anatomical surfaces across subjects using a constrained harmonic map. To analyze anatomical differences, we then analyze the full Riemannian surface metric tensors, which retain multivariate information on local surface geometry. As the number of voxels in a 3D image is large, sparse learning is a promising method to select a subset of imaging features and to improve classification accuracy. Focusing on vertices with greatest effect sizes, we train a diagnostic classifier using the surface features selected by an L1-norm based sparse learning method. Stability selection is applied to validate the selected feature sets. We tested the algorithm on MRI-derived cortical surfaces from 42 subjects with genetically confirmed Williams syndrome and 40 age-matched controls, multivariate statistics on the local tensors gave greater effect sizes for detecting group differences relative to other TBM-based statistics including analysis of the Jacobian determinant and the largest eigenvalue of the surface metric. Our method also gave reasonable classification results relative to the Jacobian determinant, the pair of eigenvalues of the Jacobian matrix and volume features. This analysis pipeline may boost the power of morphometry studies, and may assist with image-based classification.

SUBMITTER: Wang Y

PROVIDER: S-EPMC3641904 | biostudies-other | 2013 Jul

REPOSITORIES: biostudies-other

ACCESS DATA

Publications

Applying tensor-based morphometry to parametric surfaces can improve MRI-based disease diagnosis.

Wang Yalin Y Yuan Lei L Shi Jie J Greve Alexander A Ye Jieping J Toga Arthur W AW Reiss Allan L AL Thompson Paul M PM

NeuroImage 20130220

Many methods have been proposed for computer-assisted diagnostic classification. Full tensor information and machine learning with 3D maps derived from brain images may help detect subtle differences or classify subjects into different groups. Here we develop a new approach to apply tensor-based morphometry to parametric surface models for diagnostic classification. We use this approach to identify cortical surface features for use in diagnostic classifiers. First, with holomorphic 1-forms, we c ...[more]

PMID: 23435208

Similar Datasets

Project description:Agrammatic aphasia can be observed in neurodegenerative disorders and has been traditionally linked with damage to Broca's area, although there have been disagreements concerning whether damage to Broca's area is necessary or sufficient for the development of agrammatism. We aimed to investigate the neuroanatomical correlates of the emergence of agrammatic aphasia utilizing a unique cohort of patients with primary progressive apraxia of speech (PPAOS) that did not have agrammatism at baseline but developed agrammatic aphasia over time. Twenty PPAOS patients were recruited and underwent detailed speech/language assessments and 3T MRI at two visits, approximately two years apart. None of the patients showed evidence of agrammatism in writing or speech at baseline. Eight patients developed aphasia at follow-up (progressors) and 12 did not (non-progressors). Tensor-based morphometry utilizing symmetric normalization (SyN) was used to assess patterns of grey matter atrophy and voxel-based morphometry was used to assess patterns of grey matter loss at baseline. The progressors were younger at onset and more likely to show distorted sound substitutions or additions compared to non-progressors. Both groups showed change over time in premotor and motor cortices, posterior frontal lobe, basal ganglia, thalamus and midbrain, but the progressors showed greater rates of atrophy in left pars triangularis, thalamus and putamen compared to non-progressors. The progressors also showed greater grey matter loss in pars triangularis and putamen at baseline. This cohort provided a unique opportunity to assess the anatomical changes that accompany the development of agrammatic aphasia. The results suggest that damage to a network of regions including Broca's area, thalamus and basal ganglia are responsible for the development of agrammatic aphasia in PPAOS. Clinical and neuroimaging abnormalities were also present before the onset of agrammatism that could help improve prognosis in these subjects.

Project description:BackgroundHyperbilirubinemia is emerging as an increasingly common problem in newborns due to a decreasing hospital length of stay after birth. Jaundice is the most common disease of the newborn and although being benign in most cases it can lead to severe neurological consequences if poorly evaluated. In different areas of medicine, data mining has contributed to improve the results obtained with other methodologies.Hence, the aim of this study was to improve the diagnosis of neonatal jaundice with the application of data mining techniques.MethodsThis study followed the different phases of the Cross Industry Standard Process for Data Mining model as its methodology.This observational study was performed at the Obstetrics Department of a central hospital (Centro Hospitalar Tâmega e Sousa--EPE), from February to March of 2011. A total of 227 healthy newborn infants with 35 or more weeks of gestation were enrolled in the study. Over 70 variables were collected and analyzed. Also, transcutaneous bilirubin levels were measured from birth to hospital discharge with maximum time intervals of 8 hours between measurements, using a noninvasive bilirubinometer.Different attribute subsets were used to train and test classification models using algorithms included in Weka data mining software, such as decision trees (J48) and neural networks (multilayer perceptron). The accuracy results were compared with the traditional methods for prediction of hyperbilirubinemia.ResultsThe application of different classification algorithms to the collected data allowed predicting subsequent hyperbilirubinemia with high accuracy. In particular, at 24 hours of life of newborns, the accuracy for the prediction of hyperbilirubinemia was 89%. The best results were obtained using the following algorithms: naive Bayes, multilayer perceptron and simple logistic.ConclusionsThe findings of our study sustain that, new approaches, such as data mining, may support medical decision, contributing to improve diagnosis in neonatal jaundice.

Dataset Information

Applying tensor-based morphometry to parametric surfaces can improve MRI-based disease diagnosis.

Publications

Applying tensor-based morphometry to parametric surfaces can improve MRI-based disease diagnosis.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets