scispace - formally typeset
Search or ask a question
Author

Giovana S. Cover

Bio: Giovana S. Cover is an academic researcher from State University of Campinas. The author has contributed to research in topics: Diffusion MRI & Segmentation. The author has an hindex of 2, co-authored 6 publications receiving 29 citations.

Papers
More filters
Journal ArticleDOI
TL;DR: A systematic literature review of computational methods focusing on CC segmentation and parcellation acquired on magnetic resonance imaging found that model-based techniques are the most recurrently used for the segmentation task, but machine learning approaches achieved better outcomes when analyzing mean values for segmentations and classification metrics results.

27 citations

Journal ArticleDOI
TL;DR: This paper proposed an automatic data-driven CC parcellation method, based on diffusion data extracted from diffusion tensor imaging that uses the Watershed transform, and was the only study that proposed a non-geometric approach for the CC par cellation, based only on the diffusion data of each subject analyzed.
Abstract: The corpus callosum (CC) is a set of neural fibers in the cerebral cortex, responsible for facilitating inter-hemispheric communication. The CC structural characteristics appear as an essential element for studying healthy subjects and patients diagnosed with neurodegenerative diseases. Due to its size, the CC is usually divided into smaller regions, also known as parcellation. Since there are no visible landmarks inside the structure indicating its division, CC parcellation is a challenging task and methods proposed in the literature are geometric or atlas-based. This paper proposed an automatic data-driven CC parcellation method, based on diffusion data extracted from diffusion tensor imaging that uses the Watershed transform. Experiments compared parcellation results of the proposed method with results of three other parcellation methods on a data set containing 150 images. Quantitative comparison using the Dice coefficient showed that the CC parcels given by the proposed method has a mean overlap higher than 0,9 for some parcels and lower than 0,6 for other parcels. Poor overlap results were confirmed by the statistically significant differences obtained for diffusion metrics values in each parcel, when using different parcellation methods. The proposed method was also validated by using the CC tractography and was the only study that proposed a non-geometric approach for the CC parcellation, based only on the diffusion data of each subject analyzed.

9 citations

Book ChapterDOI
18 Oct 2017
TL;DR: A pixel-based classifier on Diffusion-MRI (directly in Diffusions-Weighted Imaging) using a Support Vector Machine is proposed for CC segmentation, and a subsampling technique, based on K-means clustering, is used to treat the intrinsically unbalanced pixel classification problem.
Abstract: The Corpus Callosum (CC) is an important brain structure and its volume and variations in shape are correlated with diseases like Alzheimer, schizophrenia, dyslexia, epilepsy and multiple sclerosis. CC segmentation is a necessary step in both clinical and research studies. CC is commonly studied using structural Magnetic Resonance Imaging (MRI); evaluation and segmentation on Diffusion-MRI is important because there is relevant fiber and tissue information presented on these images, although it is challenging and rarely considered. In this work, a pixel-based classifier on Diffusion-MRI (directly in Diffusion-Weighted Imaging) using a Support Vector Machine is proposed for CC segmentation. A subsampling technique, based on K-means clustering, is used to treat the intrinsically unbalanced pixel classification problem. STAPLE algorithm is used to estimate both a silver-standard and a quantitative analysis through sensitivity, specificity and the Dice coefficient metrics. Our method reached a median value of \(88\%\) in Dice coefficient, had no initialization or parameters to be set and it was compared with two state-of-the-art approaches, showing higher CC detection rate.

4 citations

Book ChapterDOI
18 Oct 2017
TL;DR: An automatic CC segmentation approach on Diffusion Tensor imaging (DTI) using Growing Neural Gas (GNG) network, an unsupervised machine learning algorithm, on the fractional anisotropy map is proposed.
Abstract: The Corpus Callosum (CC) segmentation on Magnetic Resonance Images (MRI) is of utmost importance for the study of neurodegenerative diseases, since it is the largest white matter brain structure, interconnecting the two cerebral hemispheres. Operator-independent segmentation methods are desirable, even though such task is complex due to shape and intensity variation among subjects, especially on low resolution images such as Diffusion-MRI. This paper proposes an automatic CC segmentation approach on Diffusion Tensor imaging (DTI). The method uses Growing Neural Gas (GNG) network, an unsupervised machine learning algorithm, on the fractional anisotropy map. The proposed method obtained a Dice coefficient of 0.88 in experiments using DTI of fifty human subjects, while other segmentation approaches obtained Dice results below 0.73. Although the GNG network had five parameters to be set, it requires no user intervention and was the only method that successfully detected and segmented the CC on all experimented dataset.

2 citations

Proceedings ArticleDOI
12 Mar 2018
TL;DR: This work presents a quantitative analysis of different state of art CC parcellation methods aiming to compare their results on a common dataset and shows a significant difference among the same CC parcels, but using different CC par cellation methods, and its impact on the diffusion properties.
Abstract: Corpus Callosum (CC) is the largest white matter structure and it plays a crucial role in clinical and research studies due to its shape and volume correlation to subject’s characteristics and neurodegenerative diseases. CC segmentation and parcellation are an important step for any MRI-based clinical and research study. There is only a few automatic CC parcellation methods proposed in the literature and, since it is not trivial to build a ground truth, most methods are validated qualitatively. We present a quantitative analysis of different state of art CC parcellation methods aiming to compare their results on a common dataset. Our findings show a significant difference among the same CC parcels, but using different CC parcellation methods, and its impact on the diffusion properties.

2 citations


Cited by
More filters
Journal ArticleDOI
TL;DR: A systematic review of the peer-reviewed literature on automated segmentation using computed tomography and magnetic resonance imaging for neurologic, thoracic, abdominal, musculoskeletal, and breast imaging applications should help prepare radiologists to better evaluate automated segmentsation tools and apply them not only to research, but eventually to clinical practice.

70 citations

Journal Article
TL;DR: Roger Sperry’s research on the cognitive abilities of split-brain patients following callosal section is a landmark in the study of brain–behaviour relationships.
Abstract: Eran Zaidel, Marco Iacoboni. Massachusetts: The MIT Press, 2003, pp 576, £61.95. ISBN 0-262-24044-0 Roger Sperry’s research on the cognitive abilities of split-brain patients following callosal section is a landmark in the study of brain–behaviour relationships. His studies firmly established the role of the corpus callosum in inter-hemispheric information transfer. What have we learned …

62 citations

Journal ArticleDOI
TL;DR: The proposed pipeline witnessed that the HC region is the major factor for diagnosing AD, which shows promising results due to the proper selection of global optimum solution.

60 citations

01 Jan 2009
TL;DR: In this paper, the corpus callosum shows expansions in regions connecting frontal, temporal and parietal regions in currently depressed patients only, suggestive of state-related changes in white matter in major depression that may reflect the effects of staterelated factors on white matter structure.
Abstract: Background: The corpus callosum enables the efficient linking of the two cerebral hemispheres. Reductions in the size of the anterior callosum have been described in geriatric depression, although findings in young adults have been much more equivocal. Methods: Data was acquired in 26 currently depressed (mean age 32.15 years, 5/26 male) and 28 remitted non-geriatric adults (mean age 36.36 years, 7/28 male), and 32 control subjects (mean age 34.41 years, 11/32 male). The total area, length and curvature of the callosum, and regional thickness along 39 points, from a mid-sagittal T1-weighted magnetic resonance image were compared across the groups. Results: Total area, length and curvature did not differ between the groups. The currently-depressed group showed expansions in the thickness of the posterior body and isthmus when compared to controls; this was not seen in remitted patients. Similar expansions were seen when comorbidly anxious patients were compared to depressed patients without anxiety. There was no difference between melancholic and non-melancholic patients, and medication status did not affect the results. Limitations: Currently-depressed patients showed higher rates of co-morbid anxiety and medication usage than remitted patients, although in the depression group as a whole there was no difference between medicated and unmedicated patients. Discussion: The corpus callosum shows expansions in regions connecting frontal, temporal and parietal regions in currently depressed patients only, suggestive of state-related changes in white matter in major depression that may reflect the effects of staterelated factors on white matter structure. © 2008 Elsevier B.V. All rights reserved.

39 citations

Journal ArticleDOI
TL;DR: The newly proposed callosal regions allow for a precise differentiation of M1–M1 motor connectivity and the structural integrity of these tracts.
Abstract: The corpus callosum (CC) is the largest white matter structure of the brain and offers the structural basis for an intense interaction between both cerebral hemispheres. Especially with respect to the interaction of both motor cortices it shows a differentiated somatotopic organization. Neuropathological processes are often reflected in structural alterations of the CC and a spatially precise description of structures for the healthy brain is essential for further differentiation of structural damage in patients. We performed a fine-grained parcellation of the CC on 1065 diffusion-weighted data sets of the Human Connectome Project. Interhemispheric tractograms between interhemispherically corresponding functional subdivisions of the primary motor cortex (M1; Brainnetome Atlas) were calculated, transformed into a common space, averaged and thresholded, to be assessed for localization, fractional anisotropy (FA) and mean diffusivity (MD). Spatially distinct CC regions for each functional M1 subdivision (lower and upper limbs, head/face, tongue/larynx) were identified and will be available as anatomical masks. Non-parametrical statistics for the average FA and MD values showed significant differences between all callosal regions. The newly proposed callosal regions allow for a precise differentiation of M1-M1 motor connectivity and the structural integrity of these tracts. Availability of masked regions in a common space will help to better understand inter-hemispherical callosal connectivity in patients or healthy volunteers.

20 citations