RESUMEN

Ultrasound (US) imaging deals with forming a brightness image from the amplified backscatter echo when an ultrasound wave is triggered at the region of interest. Imaging artifacts and speckles occur in the image as a consequence of backscattering and subsequent amplification. We demonstrate the usefulness of speckle-related pixels and imaging artifacts as sources of information to perform multiorgan segmentation in US images of the thyroid gland. The speckle-related pixels are clustered based on a similarity constraint to quantize the image. The quantization results are used to locate useful anatomical landmarks that aid the detection of multiple organs in the image, which are the thyroid gland, the carotid artery, the muscles, and the trachea. The spatial locations of the carotid artery and the trachea are used to estimate the boundaries of the thyroid gland in transverse US scans. Experiments performed on a multivendor dataset yield good quality segmentation results with probabilistic Rand index > 0.83 and boundary error 1 mm, and an average accuracy greater than 94%. Analysis of the results using the Dice coefficient as the metric shows that the proposed method performs better than the state-of-the-art methods. Further, experiments conducted on 971 images of a publicly available dataset prove the effectiveness of the algorithm to track the carotid artery for guided interventions. In addition to US-guided interventions, the algorithm can be used as a general framework in applications pertaining to volumetric analysis and computer-aided diagnosis.

Asunto(s)

RESUMEN

Recent development in sampling theory now allows the sampling and reconstruction of certain non-bandlimited functions on the sphere, namely a sum of weighted Diracs. Because the signal acquired in diffusion Magnetic Resonance Imaging (dMRI) can be modeled as the convolution between a sampling kernel and two dimensional Diracs defined on the sphere, these advances have great potential in dMRI. In this work, we introduce a local reconstruction method for dMRI based on a new sampling theorem for non-bandlimited signals on the sphere. This new algorithm, named Spherical Finite Rate of Innovation (SFRI), is able to recover fibers crossing at very narrow angles with little dependence on the b-value. Because of its parametric formulation, SFRI can distinguish crossing fibers even when using a DTI-like acquisition (≈32 directions). This opens new perspective for low b-value and low number of gradient directions diffusion acquisitions and tractography studies. We evaluate the angular resolution of SFRI using state of the art synthetic data and compare its performance using in-vivo data. Our results show that, at low b-values, SFRI recovers crossing fibers not identified by constrained spherical deconvolution. We also show that low b-value results obtained using SFRI are similar to those obtained with constrained spherical deconvolution at a higher b-value.

Asunto(s)

RESUMEN

PURPOSE: To describe the relationship between peripapillary choroidal thickness and retinal nerve fiber layer (RNFL) thickness in a population-based sample of nonglaucomatous eyes. DESIGN: Population-based, cross-sectional study. METHODS: A total of 478 nonglaucomatous subjects aged over 40 years were recruited from the Singapore Malay Eye Study (SiMES-2). All participants underwent a detailed ophthalmic examination, including Cirrus and Spectralis optical coherence tomography (OCT) for the measurements of RNFL thickness and peripapillary choroidal thickness, respectively. Associations between peripapillary choroidal thickness and RNFL thickness were assessed using linear regression models with generalized estimating equations. RESULTS: Of the 424 included subjects (843 nonglaucomatous eyes), 60.9% were women, and the mean (SD) age was 66.74 (10.44) years. The mean peripapillary choroidal thickness was 135.59 ± 56.74 µm and the mean RNFL thickness was 92.92 ± 11.41 µm. In terms of distribution profile, peripapillary choroid was thickest (150.04 ± 59.72 µm) at the superior and thinnest (110.71 ± 51.61 µm) at the inferior quadrant, whereas RNFL was thickest (118.60 ± 19.83 µm) at the inferior and thinnest (67.36 ± 11.36 µm) at the temporal quadrant. We found that thinner peripapillary choroidal thickness (PPCT) was independently associated with thinner RNFL thickness globally (regression coefficient [ß] = -1.334 µm for per-SD decrease in PPCT, P = .003), and in the inferior (ß = -2.565, P = .001) and superior (ß = -2.340, P = .001) quadrants even after adjusting for potential confounders. CONCLUSIONS: Thinner peripapillary choroid was independently associated with thinner RNFL globally and in the inferior and superior regions. This structure-structure relationship may need further exploration in glaucomatous eyes prior to its application in clinical settings.

Asunto(s)

RESUMEN

AIMS: To objectively quantify the thickness of peripapillary choroid using spectral-domain optical coherence tomography (SD-OCT) with enhanced depth imaging (EDI) followed by a novel automated choroidal segmentation software in Asian eyes and to evaluate its systemic and ocular determinants. METHODS: We recruited 520 subjects (1040 eyes) from the Singapore Malay Eye Study, a cross-sectional population-based study. Subjects underwent standardised detailed ophthalmic examination including SD-OCT (Spectralis) with EDI for measurement of peripapillary choroidal thickness (PPCT). RESULTS: The mean age of the subjects was 66.7±10.4 years (range 47-88 years) and the mean spherical equivalent was -0.01±2.28 D (range -18.50 to +7.00 D). The intra-session repeatability of PPCT measurements at four quadrants using automated choroidal segmentation software was excellent (intraclass correlation coefficient 0.9998-0.9999). The overall mean PPCT was 136.2±56.8 µm. Peripapillary choroid showed geographical differences among the four quadrants, being thickest in the superior quadrant (150.5±59.6 µm), followed by the nasal (143.5±58.4 µm) and temporal quadrants (139.4±68.9 µm), and thinnest in the inferior quadrant (111.3±51.7 µm). Among the range of ocular and systemic factors studied, shorter axial length (p=0.002), younger age (p=0.018), lower triglyceride level (p=0.015) and the presence of diabetes (p=0.036) were the only significant predictors of thicker peripapillary choroid. CONCLUSIONS: Using novel automated choroidal segmentation software, we provide reliable objective measurements of PPCT in a population-based setting. Shorter axial length, younger age, lower triglyceride levels and the presence of diabetes are the factors independently associated with thicker PPCT. These factors should be taken into consideration when interpreting Spectralis EDI SD-OCT-based PPCT measurements in clinics.

Asunto(s)

RESUMEN

Automatic detection and segmentation of the common carotid artery in transverse ultrasound (US) images of the thyroid gland play a vital role in the success of US guided intervention procedures. We propose in this paper a novel method to accurately detect, segment and track the carotid in 2D and 2D+t US images of the thyroid gland using concepts based on tissue echogenicity and ultrasound image formation. We first segment the hypoechoic anatomical regions of interest using local phase and energy in the input image. We then make use of a Hessian based blob like analysis to detect the carotid within the segmented hypoechoic regions. The carotid artery is segmented by making use of least squares ellipse fit for the edge points around the detected carotid candidate. Experiments performed on a multivendor dataset of 41 images show that the proposed algorithm can segment the carotid artery with high sensitivity (99.6 ±m 0.2%) and specificity (92.9 ±m 0.1%). Further experiments on a public database containing 971 images of the carotid artery showed that the proposed algorithm can achieve a detection accuracy of 95.2% with a 2% increase in performance when compared to the state-of-the-art method.

Asunto(s)

RESUMEN

PURPOSE: To objectively quantify choroidal thickness and choroidal volume using fully automated choroidal segmentation software applied to images obtained from enhanced depth imaging spectral-domain optical coherence tomography (EDI SD OCT) in a population-based study; and evaluate the ocular and systemic determinants of choroidal thickness and choroidal volume. DESIGN: Prospective cross-sectional study. METHODS: Participants ranging in age from 45 to 85 years were recruited from the Singapore Malay Eye Study-2 (SiMES-2), a follow-up population-based study. All participants (n = 540) underwent a detailed ophthalmic examination, including EDI SD OCT for measurements of thickness and volume of the choroid. RESULTS: The intrasession repeatability of choroidal thickness at 5 measured horizontal locations and macular choroidal volume using automated choroidal segmentation software was excellent (intraclass correlation coefficient, 0.97-0.99). Choroid was significantly thicker under the fovea (242.28 ± 97.58 µm), followed by 3 mm temporal (207.65 ± 80.98 µm), and was thinnest at 3 mm nasal (142.44 ± 79.19 µm) location. The mean choroidal volume at central macular region (within a circle of 1 mm diameter) was 0.185 ± 0.69 mm(3). Among the range of ocular and systemic factors studied, age, sex, and axial length were the only significant predictors of choroidal thickness and choroidal volume (all P < .05). CONCLUSIONS: Using a new automated choroidal segmentation software, we provide fast, reliable, and objective measurements of choroidal thickness and volume in a population-based sample. Male sex, younger age, and shorter axial length are the factors independently associated with thicker choroid and larger choroidal volume. These factors should be taken into consideration when interpreting EDI SD OCT-based choroidal thickness measurements in clinics.

Asunto(s)

RESUMEN

Optical coherence tomography is a high resolution, rapid, and noninvasive diagnostic tool for angle closure glaucoma. In this paper, we present a new strategy for the classification of the angle closure glaucoma using morphological shape analysis of the iridocorneal angle. The angle structure configuration is quantified by the following six features: (1) mean of the continuous measurement of the angle opening distance; (2) area of the trapezoidal profile of the iridocorneal angle centered at Schwalbe's line; (3) mean of the iris curvature from the extracted iris image; (4) complex shape descriptor, fractal dimension, to quantify the complexity, or changes of iridocorneal angle; (5) ellipticity moment shape descriptor; and (6) triangularity moment shape descriptor. Then, the fuzzy k nearest neighbor (fkNN) classifier is utilized for classification of angle closure glaucoma. Two hundred and sixty-four swept source optical coherence tomography (SS-OCT) images from 148 patients were analyzed in this study. From the experimental results, the fkNN reveals the best classification accuracy (99.11 ± 0.76%) and AUC (0.98 ± 0.012) with the combination of fractal dimension and biometric parameters. It showed that the proposed approach has promising potential to become a computer aided diagnostic tool for angle closure glaucoma (ACG) disease.

RESUMEN

This paper proposes a new method for detecting P and T waves in multilead ECG based on the Finite Rate of Innovation(FRI) technique [8]. A simple QRS detection scheme will be presented followed by a novel P and T wave detection algorithm. The novelty here is the modelling of the P and T wave using a Gaussian kernel. Using a 2D wavelet decomposition, the approximation coefficients are windowed based on the QRS locations. The FRI method is then used to identify the Gaussian distribution present in the window which will in turn provide the locations of the P and T wave. This method was tested on more than an hour of clean and noisy data and shows good performance in the noisy case.

Asunto(s)

RESUMEN

Manually induced artefacts, like caliper marks and anatomical labels, render an ultrasound (US) image incapable of being subjected to further processes of Computer Aided Diagnosis (CAD). In this paper, we propose a technique to remove these artefacts and restore the image as accurately as possible. The technique finds application as a pre-processing step when developing unsupervised segmentation algorithms for US images that deal with automatic estimation of the number of segments and clustering. The novelty of the algorithm lies in the image processing pipeline chosen to automatically identify the artefacts and is developed based on the histogram properties of the artefacts. The algorithm was able to successfully restore the images to a high quality when it was executed on a dataset of 18 US images of the thyroid gland on which the artefacts were induced manually by a doctor. Further experiments on an additional dataset of 10 unmarked US images of the thyroid gland on which the artefacts were simulated using Matlab showed that the restored images were again of high quality with a PSNR > 38 dB and free of any manually induced artefacts.

Asunto(s)

RESUMEN

Accurate segmentation of knee cartilage is required to obtain quantitative cartilage measurements, which is crucial for the assessment of knee pathology caused by musculoskeletal diseases or sudden injuries. This paper presents an automatic knee cartilage segmentation technique which exploits a rich set of image features from multi-contrast magnetic resonance (MR) images and the spatial dependencies between neighbouring voxels. The image features and the spatial dependencies are modelled into a support vector machine (SVM)-based association potential and a discriminative random field (DRF)-based interaction potential. Subsequently, both potentials are incorporated into an inference graphical model such that the knee cartilage segmentation is cast into an optimal labelling problem which can be efficiently solved by loopy belief propagation. The effectiveness of the proposed technique is validated on a database of multi-contrast MR images. The experimental results show that using diverse forms of image and anatomical structure information as the features are helpful in improving the segmentation, and the joint SVM-DRF model is superior to the classification models based solely on DRF or SVM in terms of accuracy when the same features are used. The developed segmentation technique achieves good performance compared with gold standard segmentations and obtained higher average DSC values than the state-of-the-art automatic cartilage segmentation studies.

Asunto(s)

RESUMEN

Enhanced Depth Imaging (EDI) optical coherence tomography (OCT) provides high-definition cross-sectional images of the choroid in vivo, and hence is used in many clinical studies. However, the quantification of the choroid depends on the manual labelings of two boundaries, Bruch's membrane and the choroidal-scleral interface. This labeling process is tedious and subjective of inter-observer differences, hence, automatic segmentation of the choroid layer is highly desirable. In this paper, we present a fast and accurate algorithm that could segment the choroid automatically. Bruch's membrane is detected by searching the pixel with the biggest gradient value above the retinal pigment epithelium (RPE) and the choroidal-scleral interface is delineated by finding the shortest path of the graph formed by valley pixels using Dijkstra's algorithm. The experiments comparing automatic segmentation results with the manual labelings are conducted on 45 EDI-OCT images and the average of Dice's Coefficient is 90.5%, which shows good consistency of the algorithm with the manual labelings. The processing time for each image is about 1.25 seconds.

RESUMEN

Enhanced Depth Imaging (EDI) optical coherence tomography (OCT) provides high-definition cross-sectional images of the choroid in vivo, and hence is used in many clinical studies. However, measurement of choroidal thickness depends on the manual labeling, which is tedious and subjective of inter-observer differences. In this paper, we propose a fast and accurate algorithm that could measure the choroidal thickness automatically. The lower boundary of the choroid is detected by searching the biggest gradient value above the retinal pigment epithelium (RPE) and the upper boundary is formed by finding the shortest path of the graph formed by valley pixels using dynamic programming. The average of Dice's Coefficient on 10 EDI-OCT images is 94.3%, which shows good consistency of the algorithm with the manual labeling. The processing time for each image is about 2 seconds.

Asunto(s)

RESUMEN

In this paper, we investigate the reconstruction of a signal defined as the sum of K orientations from samples taken with a kernel defined on the 3D rotation group. A potential application is the recovery of fiber orientations in diffusion magnetic resonance imaging. We propose an exact reconstruction algorithm based on the finite rate of innovation theory that makes use of the spherical harmonics representation of the signal. The number of measurements needed for perfect recovery, which may be as low as 3K, depends only on the number of orientations and the bandwidth of the kernel used. Furthermore, the angular resolution of our method does not depend on the number of available measurements. We illustrate the performance of the algorithm using several simulations.

Asunto(s)

RESUMEN

Angle-closure glaucoma is a major blinding eye disease and could be detected by measuring the anterior chamber angle in the human eyes. High-definition OCT (Cirrus HD-OCT) is an emerging noninvasive, high-speed, and high-resolution imaging modality for the anterior segment of the eye. Here, we propose a novel algorithm which automatically detects a new landmark, Schwalbe's line, and measures the anterior chamber angle in the HD-OCT images. The distortion caused by refraction is corrected by dewarping the HD-OCT images, and three biometric measurements are defined to quantitatively assess the anterior chamber angle. The proposed algorithm was tested on 40 HD-OCT images of the eye and provided accurate measurements in about 1 second.

Asunto(s)

RESUMEN

Angle-closure glaucoma is a major cause of blindness in Asia and could be detected by measuring the anterior chamber angle (ACA) using gonioscopy, ultrasound biomicroscopy or anterior segment (AS) optical coherence tomography (OCT). The current software in the VisanteTM OCT system by Zeiss is based on manual labeling of the scleral spur, cornea and iris and is a tedious process for ophthalmologists. Furthermore, the scleral spur can not be identified in about 20% to 30% of OCT images and thus measurements of the ACA are not reliable. However, high definition (HD) OCT has identified a more consistent landmark: Schwalbe's line. This paper presents a novel algorithm which automatically detects Schwalbe's line in HD-OCT scans. The average deviation between the values detected using our algorithm and those labeled by the ophthalmologist is less than 0.5% and 0.35% in the horizontal and vertical image dimension, respectively. Furthermore, we propose a new measurement to quantify ACA which is defined as Schwalbe's line bounded area (SLBA).

Asunto(s)

RESUMEN

In this paper, we investigate the Stockwell Transform, a linear time-frequency spectral localisation technique, on non-stationary, multicomponent neonatal seizure EEG signals. The seizure signals of interest are namely slow wave and sharp spike seizures. The performance of Stockwell Transform is compared to that of existing quadratic time-frequency representation, namely the Choi-Williams Distribution and the B Distribution, on both simulated and real EEG seizure signals. The results show that the Stockwell Transform yields distinctive, interference free time-frequency patterns corresponding to the neonatal EEG seizure signals. By capturing both high-frequency spike components and predominantly low frequency components of neonatal seizures concurrently and accurately, the Stockwell Transform is able to distinguish these two types of neonatal seizure signals with unique signatures. These signatures can then be effectively used for seizure modelling, detection and prediction.

Asunto(s)

RESUMEN

Compression of ECG (electrocardiogram) as a signal with finite rate of innovation (FRI) is proposed in this paper. By modelling the ECG signal as the sum of bandlimited and nonuniform linear spline which contains finite rate of innovation (FRI), sampling theory is applied to achieve effective compression and reconstruction of ECG signal. The simulation results show that the performance of the algorithm is quite satisfactory in preserving the diagnostic information as compared to the classical sampling scheme which uses the sinc interpolation.

RESUMEN

Liver cancer is one of the most popular cancer diseases and causes a large amount of death every year. In order to make decisions such as liver resections, doctors will need to know the tumor volume, and further, the functional liver volume. Thus, an important task in radiology is the determination of tumor volume. Accurate segmentation of liver tumor from an abdominal image is one of the most important steps in 3D representation for liver volume measurement, liver transplant, and treatment planning[1]. Since manual segmenation is inconvenient, time consuming and depends on the individual operator to a large extent, automatic segmentation is much more preferred. In this paper, an active contour model is used to segment tumors from CT abdominal images. Initial boundary is manually placed by operators outside the tumor region. The snake deforms to the tumor boundary with the minimization of energy function. We then calculate the tumor volume using the series of segmented tumor slices. Results show that this method is quite efficient in tumor volume estimation compared with the WHO criteria, which measures the tumor by multiplying the longest perpendicular diameters.