Search

In this paper, we describe a statistical video representation and modeling scheme. Video representation schemes are needed to segment a video stream into meaningful video-objects, useful for later indexing and retrieval applications. In the proposed methodology, unsupervised clustering via Gaussian mixture modeling extracts coherent space-time regions in feature space, and corresponding coherent segments (video-regions) in the video content. A key feature of the system is the analysis of video input as a single entity as opposed to a sequence of separate frames. Space and time are treated uniformly. The probabilistic space-time video representation scheme is extended to a piecewise GMM framework in which a succession of GMMs are extracted for the video sequence, instead of a single global model for the entire sequence. The piecewise GMM framework allows for the analysis of extended video sequences and the description of nonlinear, nonconvex motion patterns. The extracted space-time regions allow for the detection and recognition of video events. Results of segmenting video content into static versus dynamic video regions and video content editing are presented. Index Terms--Video representation, video segmentation, detection of events in video, Gaussian mixture model.

White matter tractography mapping is an important tool for neuro-surgical planning and navigation. It relies on the accurate manual delineation of anatomical seeding ROIs (sROIs) by neuroanatomy experts. Stringent pre-operative time-constraints and limited availability of experts suggest that automation tools are strongly needed for the task. In this article, we propose and compare several multi-modal fully convolutional network architectures for segmentation of sROIs. Inspired by their manual segmentation practice, anatomical information from T1w maps is fused by the network with directionally encoded color (DEC) maps to compute the segmentation. Qualitative and quantitative validation was performed on image data from 75 real tumor resection candidates for the sROIs of the motor tract, the arcuate fasciculus, and optic radiation. Favorable comparison was also obtained with state-of-the-art methods for the tumor dataset as well as the ISMRM 2017 traCED challenge dataset. The proposed networks showed promising results, indicating they may significantly improve the efficiency of pre-surgical tractography mapping, without compromising its quality. [ABSTRACT FROM AUTHOR]

Abstract: In the last two decades functional magnetic resonance imaging (fMRI) has dominated research in neuroscience. However, only recently has it taken the first steps in translation to the clinical field. In this paper we describe the advantages of fMRI and DTI and the possible benefits of implementing these methods in clinical practice. We review the current clinical usages of fMRI and DTI and discuss the challenges and difficulties of translating these methods to clinical use. The most common application today is in neurosurgery. fMRI and DTI are done preoperatively for brain tumor patients who are having tumors removed and for epilepsy patients who are candidates for temporal resection. Imaging results supply the neurosurgeon with essential information regarding possible functional damage and thereby aid both in planning and performing surgery. Scientific research suggests more promising potential implementations of fMRI and DTI in improving diagnosis and rehabilitation. These advanced imaging methods can be used for pre-symptomatic diagnosis, as a differentiating biomarker in the absence of anatomical measurements, and for identification of mental response in the absence of motor-sensory abilities. These methods can aid and direct rehabilitation by predicting the success of possible interventions and rehabilitation options and by supplying a measure for biofeedback. This review opens a window to the state of the art neuroimaging methods being implemented these days into the clinical practice and provides a glance to the future clinical possibilities of fMRI and DTI. [Copyright &y& Elsevier]

A supervised framework is presented for the automatic registration and segmentation of white matter (WM) tractographies extracted from brain DT-MRI. The framework relies on the direct registration between the fibers, without requiring any intensity-based registration as preprocessing. An affine transform is recovered together with a set of segmented fibers. A recently introduced probabilistic boosting tree classifier is used in a segmentation refinement step to improve the precision of the target tract segmentation. The proposed method compares favorably with a state-of-the-art intensity-based algorithm for affine registration of DTI tractographies. Segmentation results for 12 major WM tracts are demonstrated. Quantitative results are also provided for the segmentation of a particularly difficult case, the optic radiation tract. An average precision of 80% and recall of 55% were obtained for the optimal configuration of the presented method. [ABSTRACT FROM AUTHOR]

In this paper, we present a robust approach to the registration of white matter tractographies extracted from diffusion tensor-magnetic resonance imaging scans. The fibers are projected into a high dimensional feature space based on the sequence of their 3-D coordinates. Adaptive mean-shift clustering is applied to extract a compact set of representative fiber-modes (FM). Each FM is assigned to a multivanate Gaussian distribution according to its population thereby leading to a Gaussian mixture model (GMM) representation for the entire set of fibers. The registration between two fiber sets is treated as the alignment of two GMMs and is performed by maximizing their correlation ratio. A nine-parameters affine transform is recovered and eventually refined to a twelve-parameters affine transform using an innovative mean-shift based registration refinement scheme presented in this paper. The validation of the algorithm on synthetic intrasubject data demonstrates its robustness to interrupted and deviating fiber artifacts as well as outliers. Using real intrasubject data, a comparison is conducted to other intensity based and fiber-based registration algorithms, demonstrating competitive results. An option for tracking-in-time, on specific white matter fiber tracts, is also demonstrated on the real data. [ABSTRACT FROM AUTHOR]

Purpose: Measurement of the fetal brain can be achieved by different modalities, we aimed to assess the agreement between these methods and the head circumference at birth.Methods: A retrospective study conducted between 2011-2018 at a tertiary referral medical center. Sonographic head circumference (HC), 2D MRI bi-parietal diameter (BPD) and occipito-frontal diameter (OFD), 3D MRI supra-tentorial volume (STV), and head circumference (HC) at birth were measured and converted into centiles according to gestational age. Spearman's rank correlation coefficient was used to assess the correlation between the modalities.Results: A total of 88 fetuses were included. Mean gestational age at the time of fetal US and brain MRI acquisition were 34.4 ± 2.8 and 34.6 ± 2.6 weeks, respectively. A correlation was found between prenatal sonographic HC and the 3D MRI STV centiles (Rs = 0.859, p < 0.001), the BPD in 2D MRI (Rs = 0.813, p < 0.001), and the OFD in 2D MRI (Rs = 0.840, p < 0.001). Sonographic HC, OFD on 2D MRI, and STV on 3D MRI were all found to be correlated with the HC at birth (Rs = 0.865, p < 0.001; Rs 0.816, p < 0.001; Rs = 0.825, p < 0.001, respectively).Conclusions: There is a statistically significant agreement among the different prenatal clinically used modalities for measuring fetal brain and the head circumference at birth, however, this correlation is not perfect. Further study is needed to investigate the long-term prognosis of these fetuses. [ABSTRACT FROM AUTHOR]

Histopathological analysis is crucial for the diagnosis of a large number of cancer types. A lot of progress has been made in the development of molecular based assays, but many of the cases still require the careful analysis of the stained tissue under a bright-field microscope and its analysis. This procedure is costly and time-consuming. We present a novel method for classification of cancer cells in lymph node images. It is based on the measurement of the spectral image of hematoxylin and eosin stained sample under the microscope and the analysis of the acquired data using state of the art machine learning techniques. The method is based on the analysis of the spectral information of the cells as well as their morphological properties. A large number of descriptors is extracted for each cell location, which are used to train a supervised classifier which discriminates between normal and cancer cells. We show that a reliable analysis can be made with detection rate (recall) of 81%-100% for the cancer class.

Extravasation during intravenous (IV) infusion is a common secondary effect with potentially serious clinical consequences. The correct positioning of the needle in the vein may be difficult to confirm when no blood return is observed. In this paper, a novel method is proposed for the detection of extravasation during infusion therapy. A small volume of a sodium bicarbonate solution is administrated IV and, following its consecutive dissociation, an excess of carbon dioxide (CO2) is rapidly exhaled by the lungs. The analysis of the exhaled CO2 signal by a pattern recognition algorithm enables the robust detection of the CO2 excess release, thereby confirming the absence of extravasation. Initial results are presented for the application of the method on a group of 89 oncology patients.