Search results for "Artificial Intelligence"
showing 10 items of 6122 documents
Model order effects on ICA of resting-state complex-valued fMRI data : application to schizophrenia
2018
Abstract Background Component splitting at higher model orders is a widely accepted finding for independent component analysis (ICA) of functional magnetic resonance imaging (fMRI) data. However, our recent study found that intact components occurred with subcomponents at higher model orders. New method This study investigated model order effects on ICA of resting-state complex-valued fMRI data from 82 subjects, which included 40 healthy controls (HCs) and 42 schizophrenia patients. In addition, we explored underlying causes for distinct component splitting between complex-valued data and magnitude-only data by examining model order effects on ICA of phase fMRI data. A best run selection me…
Asymmetric modulation of human visual cortex activity during 10 degrees lateral gaze (fMRI study).
2005
We used BOLD fMRI to study the differential effects of the direction of gaze on the visual and the ocular motor systems. Fixation of a target straight ahead was compared to fixation of a target 10 degrees to the right and 10 degrees to the left from gaze straight ahead, and to eyes open in complete darkness in thirteen healthy volunteers. While retinotopic coordinates remained the same in all fixation conditions, the fixation target shifted with respect to a head-centered frame of reference. During lateral fixation, deactivations in higher-order visual areas (one ventral cluster in the lingual and fusiform gyri and one dorsal cluster in the postero-superior cuneus) and, as a trend, activati…
MRI radiomics-based machine-learning classification of bone chondrosarcoma.
2019
Abstract Purpose To evaluate the diagnostic performance of machine learning for discrimination between low-grade and high-grade cartilaginous bone tumors based on radiomic parameters extracted from unenhanced magnetic resonance imaging (MRI). Methods We retrospectively enrolled 58 patients with histologically-proven low-grade/atypical cartilaginous tumor of the appendicular skeleton (n = 26) or higher-grade chondrosarcoma (n = 32, including 16 appendicular and 16 axial lesions). They were randomly divided into training (n = 42) and test (n = 16) groups for model tuning and testing, respectively. All tumors were manually segmented on T1-weighted and T2-weighted images by drawing bidimensiona…
Automatic Evaluation of Histological Prognostic Factors Using Two Consecutive Convolutional Neural Networks on Kidney Samples
2022
BACKGROUND AND OBJECTIVES: The prognosis of patients undergoing kidney tumor resection or kidney donation is linked to many histologic criteria. These criteria notably include glomerular density, glomerular volume, vascular luminal stenosis, and severity of interstitial fibrosis/tubular atrophy. Automated measurements through a deep-learning approach could save time and provide more precise data. This work aimed to develop a free tool to automatically obtain kidney histologic prognostic features. DESIGN, SETTING, PARTICIPANTS, & MEASUREMENTS: In total, 241 samples of healthy kidney tissue were split into three independent cohorts. The “Training” cohort (n=65) was used to train two convoluti…
Identification of unknown dead bodies by X-ray image comparison of the skull using the X-ray simulation program FoXSIS.
2001
The aim of the study was to improve the objectivity of X-ray image comparison for the identification of unknown dead individuals. CT-data were collected for 30 macerated skulls. An already presented computer program which uses CT data to establish virtual X-ray images was used to obtain X-rays with different beam angulations simulating rotation, dorsal flexion, and ventral flexion. Specific parameters were measured on the simulated images. The frontal sinus reveals the highest variability not only between the individual skulls but also within an individual skull in different positions. The most consistent parameters with respect to different positions were the skull breadth, the biorbital b…
Effect of Kernels Used for the Reconstruction of MDCT Datasets on the Semi-Automated Segmentation and Volumetry of Liver Lesions
2014
Purpose: To evaluate the effect of different reconstruction kernels on the semi-automated segmentation of liver lesions in MDCT. Materials and Methods: A total 62 liver lesions were measured by three independent radiologists with the semi-automated segmentation software Oncology-Prototype (Fraunhofer MEVIS, Siemens Healthcare, Germany) using MDCT datasets (3-mm slice thickness, 2-mm increment) reconstructed with standard, soft and detailed kernels (Philips B, A and D). To ensure objective measurements, only lesions with satisfactory initial segmentation were included, and manual correction was not used. The effective diameter and volume were recorded for each lesion. Segmentation in the sof…
Frontoparietal cortex and cerebellum contribution to the update of actual and mental motor performance during the day
2016
AbstractActual and imagined movement speed increases from early morning until mid-afternoon. Here, we investigated the neural correlates of these daily changes. Fifteen subjects performed actual and imagined right finger opposition movement sequences at 8 am and 2 pm. Both actual and imagined movements were significantly faster at 2 pm than 8 am. In the morning, actual movements significantly activated the left primary somatosensory and motor areas, and bilaterally the cerebellum; in the afternoon activations were similar but reduced. Contrast analysis revealed greater activity in the cerebellum, the left primary sensorimotor cortex and parietal lobe in the morning than in the afternoon. Im…
Blurring the boundaries between frame-based and frameless stereotaxy: feasibility study for brain biopsies performed with the use of a head-mounted r…
2015
OBJECT Frame-based stereotactic interventions are considered the gold standard for brain biopsies, but they have limitations with regard to flexibility and patient comfort because of the bulky head ring attached to the patient. Frameless image guidance systems that use scalp fiducial markers offer more flexibility and patient comfort but provide less stability and accuracy during drilling and biopsy needle positioning. Head-mounted robot-guided biopsies could provide the advantages of these 2 techniques without the downsides. The goal of this study was to evaluate the feasibility and safety of a robotic guidance device, affixed to the patient’s skull through a small mounting platform, for …
Synergy of spatial frequency and orientation bandwidth in texture segregation
2021
Defining target textures by increased bandwidths in spatial frequency and orientation, we observed strong cue combination effects in a combined texture figure detection and discrimination task. Performance for double-cue targets was better than predicted by independent processing of either cue and even better than predicted from linear cue integration. Application of a texture-processing model revealed that the oversummative cue combination effect is captured by calculating a low-level summary statistic (\(\Delta CE_m\)), which describes the differential contrast energy to target and reference textures, from multiple scales and orientations, and integrating this statistic across channels wi…
On orienting the hand to reach and grasp an object.
1996
Subjects were required to reach and grasp a parallelepiped, the position, orientation and size of which were varied. The kinematics of reaching and grasping movements was studied in full vision and in no vision conditions. Both direction and movement amplitude of reaching were affected by object orientation. Conversely, both the time course of finger axis orientation and the angular displacement of the hand at wrist were influenced by object position. These results were not modified by the absence of visual control. Finger aperture during grasping was affected by both object size and orientation. This latter result was not due to a distorted size perception, as shown by a control matching e…