Search results for "image processing"
showing 10 items of 3285 documents
Evaluation of Deep Neural Networks for Semantic Segmentation of Prostate in T2W MRI
2020
In this paper, we present an evaluation of four encoder&ndash
Deep Learning Network for Segmentation of the Prostate Gland With Median Lobe Enlargement in T2-weighted MR Images: Comparison With Manual Segmentati…
2021
Purpose: Aim of this study was to evaluate a fully automated deep learning network named Efficient Neural Network (ENet) for segmentation of prostate gland with median lobe enlargement compared to manual segmentation. Materials and Methods: One-hundred-three patients with median lobe enlargement on prostate MRI were retrospectively included. Ellipsoid formula, manual segmentation and automatic segmentation were used for prostate volume estimation using T2 weighted MRI images. ENet was used for automatic segmentation; it is a deep learning network developed for fast inference and high accuracy in augmented reality and automotive scenarios. Student t-test was performed to compare prostate vol…
Bilingualism at the core of the brain. Structural differences between bilinguals and monolinguals revealed by subcortical shape analysis.
2015
Naturally acquiring a language shapes the human brain through a long-lasting learning and practice process. This is supported by previous studies showing that managing more than one language from early childhood has an impact on brain structure and function. However, to what extent bilingual individuals present neuroanatomical peculiarities at the subcortical level with respect to monolinguals is yet not well understood, despite the key role of subcortical gray matter for a number of language functions, including monitoring of speech production and language control — two processes especially solicited by bilinguals. Here we addressed this issue by performing a subcortical surface-based anal…
Automatic classification of tissues on pelvic MRI based on relaxation times and support vector machine
2019
International audience; Tissue segmentation and classification in MRI is a challenging task due to a lack of signal intensity standardization. MRI signal is dependent on the acquisition protocol, the coil profile, the scanner type, etc. While we can compute quantitative physical tissue properties independent of the hardware and the sequence parameters, it is still difficult to leverage these physical properties to segment and classify pelvic tissues. The proposed method integrates quantitative MRI values (T1 and T2 relaxation times and pure synthetic weighted images) and machine learning (Support Vector Machine (SVM)) to segment and classify tissues in the pelvic region, i.e.: fat, muscle, …
Reading for meaning in dyslexic and young children : distinct neural pathways but common endpoints
2009
Developmental dyslexia is a highly prevalent and specific disorder of reading acquisition characterised by impaired reading fluency and comprehension. We have previously identified fMRI- and ERP-based neural markers of impaired sentence reading in dyslexia that indicated both deviant basic word processing and deviant semantic incongruency processing. However, it remained unclear how specific these impairments are for dyslexia, as they occurred when children with dyslexia (DYS) were compared to chronological age-matched controls (CA) who also differ in the amount of reading experience. Adding a younger control group at a similar reading level (RL) as the dyslexic group, we examined here whic…
Computer assisted morphometric analysis of ram sperm heads: Evaluation of different fixative techniques
1998
The recent development of automated systems for morphometric sperm head analysis has provided a series of objective parameters which have facilitated the standardization of morphological semen evaluation. This current work attempts to establish the optimum fixing conditions for the morphometric characterization of ram spermatozoa. Ejaculates were obtained from 5 Merino rams used for periodic collection of semen and were diluted at 1:50 with TEST medium. Air-dried smears were fixed either in ethanol-ether (1:1), 50% methanol, 2% glutaraldehyde or SUZA fixative, in which case the smear was pretreated with chloramine. The samples were then stained with commercial kit Hemacolor. Once the prepar…
Engineered microenvironments for synergistic VEGF - Integrin signalling during vascularization
2017
We have engineered polymer-based microenvironments that promote vasculogenesis both in vitro and in vivo through synergistic integrin-growth factor receptor signalling. Poly(ethyl acrylate) (PEA) triggers spontaneous organization of fibronectin (FN) into nanonetworks which provide availability of critical binding domains. Importantly, the growth factor binding (FNIII12-14) and integrin binding (FNIII9-10) regions are simultaneously available on FN fibrils assembled on PEA. This material platform promotes synergistic integrin/VEGF signalling which is highly effective for vascularization events in vitro with low concentrations of VEGF. VEGF specifically binds to FN fibrils on PEA compared to …
Fungal polysaccharopeptide inhibits tumor angiogenesis and tumor growth in mice
2003
Angiogenesis is crucial to tumor growth and metastasis, and interruption of this process is a prime avenue for therapeutic intervention of tumor proliferation. The present study has made use of the S180 tumor-bearing mouse model to investigate the polysaccharopeptide, PSP, isolated from the edible mushroom Coriolus versicolor, a herbal medicine known for its anti-angiogenesis properties. Quantitative analysis of microcorrosion casting of the tumor tissue showed more angiogenic features such as dense sinusoids and hot spots, in control (untreated) than in PSP-treated animals. Immunostaining of tumor tissues with antibody against the endothelial cell marker (Factor VIII) demonstrated a positi…
Common variation in PHACTR1 is associated with susceptibility to cervical artery dissection
2014
Item does not contain fulltext Cervical artery dissection (CeAD), a mural hematoma in a carotid or vertebral artery, is a major cause of ischemic stroke in young adults although relatively uncommon in the general population (incidence of 2.6/100,000 per year). Minor cervical traumas, infection, migraine and hypertension are putative risk factors, and inverse associations with obesity and hypercholesterolemia are described. No confirmed genetic susceptibility factors have been identified using candidate gene approaches. We performed genome-wide association studies (GWAS) in 1,393 CeAD cases and 14,416 controls. The rs9349379[G] allele (PHACTR1) was associated with lower CeAD risk (odds ratio…
Echocardiographic reference ranges for normal left atrial function parameters results from the EACVI NORRE study
2018
International audience; Aims - To obtain the normal ranges for echocardiographic measurements of left atrial (LA) function from a large group of healthy volunteers accounting for age and gender. Methods and results - A total of 371 (median age 45 years) healthy subjects were enrolled at 22 collaborating institutions collaborating in the Normal Reference Ranges for Echocardiography (NORRE) study of the European Association of Cardiovascular Imaging (EACVI). Left atrial data sets were analysed with a vendor-independent software (VIS) package allowing homogeneous measurements irrespective of the echocardiographic equipment used to acquire data sets. The lowest expected values of LA function we…