Registration and machine learning-based automated segmentation of subcortical and cerebellar brain structures

Powell, Stephanie; Magnotta, Vincent A.; Johnson, Hans J.; Jammalamadaka, Vamsi; Pierson, Ronald; Andreasen, Nancy C.

doi:10.1016/j.neuroimage.2007.05.063

Cited by 159 publications

(163 citation statements)

References 34 publications

Supporting

Mentioning

159

Contrasting

Order By: Relevance

“…The neural networks serve as a tool in guiding tracing and additional manual editing is conducted as specified below. Utilization of the neural nets has been shown to be more reliable than manual tracings (Magnotta et al, 1999b;Powell et al, 2007).…”

Section: Mri Protocolmentioning

confidence: 99%

Thalamic atrophy and cognition in unilateral temporal lobe epilepsy

Seidenberg

Hermann

Pulsipher

et al. 2008

J Inter Neuropsych Soc

View full text Add to dashboard Cite

This study examined quantitative magnetic resonance volumes of the thalamus and hippocampus and determined their relationship with cognitive function and clinical seizure characteristics in a sample of 46 unilateral temporal lobe epilepsy (TLE) subjects (20 left and 26 right) and 29 controls. The hippocampus and thalamus exhibited different patterns of volume abnormality, different associations with clinical seizure characteristics, and different patterns of relationship with cognitive measures. Hippocampal volume reduction was primarily ipsilateral to the seizure focus, and thalamic volume reduction was bilateral. Ipsilateral hippocampal volume was significantly correlated with both early neurodevelopmental features (age of seizure onset) and disease characteristics (duration of epilepsy), whereas thalamus integrity was related only to disease variables. Hippocampal volume showed a selective association with verbal memory performance. In contrast, both left and right thalamic volumes were significantly correlated with performance on both memory and nonmemory cognitive domains. These findings underscore the importance of thalamic atrophy in chronic TLE and its potential implications for cognition. (JINS, 2008, 14, 384-393.)

show abstract

Section: Mri Protocolmentioning

confidence: 99%

Thalamic atrophy and cognition in unilateral temporal lobe epilepsy

Seidenberg

Hermann

Pulsipher

et al. 2008

J Inter Neuropsych Soc

View full text Add to dashboard Cite

show abstract

“…Powell et al propose several automated segmentation methods based on a multidimensional registration and give a direct comparison between their methods and various template, probability, artificial neural network and support vector machine based automated segmentation methods [52]. Three metrics for each segmentation method are reported in the delineation of sub-cortical and cerebellar brain regions.…”

Section: Automatic Methodsmentioning

confidence: 99%

Automatic Morphological Analysis of Medial Temporal Lobe

Chincarini¹,

Corosu²,

Gemme³

et al. 2010

TONMEDJ

View full text Add to dashboard Cite

Abstract:Research in Alzheimer's disease (AD) has seen a tremendous growth of candidate biomarkers in the last decade. The role of such established or putative biomarkers is to allow an accurate diagnosis of AD, to infer about its prognosis, to monitor disease progression and evaluate changes induced by disease-modifying drugs. An ideal biomarker should detect a specific pathophysiological feature of AD, not present in the healthy condition, in other primary dementias, or in confounding conditions. Besides being reliable, a biomarker should be detectable by means of procedures which must be relatively non-invasive, simple to perform, widely available and not too expensive. At present, no candidate meets these requirements representing the high standards aimed at by researchers. Among others, various morphological brain measures performed by means of magnetic resonance imaging (MRI), ranging from the total brain volume to some restricted regions such as the hippocampal volume, have been proposed. Nowadays the efforts are directed toward finding an automated, unsupervised method of evaluating atrophy in some specific brain region, such as the medial temporal lobe (MTL). In this work we provide an extensive review of the state of the art on the automatic and semi-automatic image processing techniques for the early assessment of patients at risk of developing AD. Our main focus is the relevance of the morphological analysis of MTL, and in particular of the hippocampal formation, in making the diagnosis of AD and in distinguishing it from other dementias.

show abstract

“…To overcome the first problem and acheive best generalization, available data is divided into training, testing, and validation datasets, where the error is controlled for the validation data. Some image segmentation algorithms have benefited from MLP-ANN (Jabarouti Magnotta et al, 1999;Powell et al, 2008). The method developed by Magnotta et al (1999) uses Image Intensity Values (IIVs) of the neighboring voxels as the image features.…”

Section: Multi-layer Perceptron Neural Networkmentioning

confidence: 99%

“…The IIVs solve the segmentation problem for the high-resolution MRI they utilized. Recently, Powell et al (2008) have further developed their previous algorithm (Magnotta et al, 1999) using 9 IIVs along with the largest gradient, a probabilistic map, and the IIVs along each of the three orthogonal axes. They use high-resolution images the same as (Magnotta et al, 1999) for the segmentation of the brain structures (putamen, caudate, thalamus, and cerebellar regions of interest).…”

Section: Multi-layer Perceptron Neural Networkmentioning

confidence: 99%