Search tips
Search criteria

Results 1-25 (356)

Clipboard (0)

Select a Filter Below

Year of Publication
1.  MRI Volume Fusion Based on 3D Shearlet Decompositions 
Nowadays many MRI scans can give 3D volume data with different contrasts, but the observers may want to view various contrasts in the same 3D volume. The conventional 2D medical fusion methods can only fuse the 3D volume data layer by layer, which may lead to the loss of interframe correlative information. In this paper, a novel 3D medical volume fusion method based on 3D band limited shearlet transform (3D BLST) is proposed. And this method is evaluated upon MRI T2* and quantitative susceptibility mapping data of 4 human brains. Both the perspective impression and the quality indices indicate that the proposed method has a better performance than conventional 2D wavelet, DT CWT, and 3D wavelet, DT CWT based fusion methods.
PMCID: PMC4003782  PMID: 24817880
2.  High-Speed GPU-Based Fully Three-Dimensional Diffuse Optical Tomographic System 
We have developed a graphics processor unit (GPU-) based high-speed fully 3D system for diffuse optical tomography (DOT). The reduction in execution time of 3D DOT algorithm, a severely ill-posed problem, is made possible through the use of (1) an algorithmic improvement that uses Broyden approach for updating the Jacobian matrix and thereby updating the parameter matrix and (2) the multinode multithreaded GPU and CUDA (Compute Unified Device Architecture) software architecture. Two different GPU implementations of DOT programs are developed in this study: (1) conventional C language program augmented by GPU CUDA and CULA routines (C GPU), (2) MATLAB program supported by MATLAB parallel computing toolkit for GPU (MATLAB GPU). The computation time of the algorithm on host CPU and the GPU system is presented for C and Matlab implementations. The forward computation uses finite element method (FEM) and the problem domain is discretized into 14610, 30823, and 66514 tetrahedral elements. The reconstruction time, so achieved for one iteration of the DOT reconstruction for 14610 elements, is 0.52 seconds for a C based GPU program for 2-plane measurements. The corresponding MATLAB based GPU program took 0.86 seconds. The maximum number of reconstructed frames so achieved is 2 frames per second.
PMCID: PMC4003791  PMID: 24891848
3.  Despeckle Filtering for Multiscale Amplitude-Modulation Frequency-Modulation (AM-FM) Texture Analysis of Ultrasound Images of the Intima-Media Complex 
The intima-media thickness (IMT) of the common carotid artery (CCA) is widely used as an early indicator of cardiovascular disease (CVD). Typically, the IMT grows with age and this is used as a sign of increased risk of CVD. Beyond thickness, there is also clinical interest in identifying how the composition and texture of the intima-media complex (IMC) changed and how these textural changes grow into atherosclerotic plaques that can cause stroke. Clearly though texture analysis of ultrasound images can be greatly affected by speckle noise, our goal here is to develop effective despeckle noise methods that can recover image texture associated with increased rates of atherosclerosis disease. In this study, we perform a comparative evaluation of several despeckle filtering methods, on 100 ultrasound images of the CCA, based on the extracted multiscale Amplitude-Modulation Frequency-Modulation (AM-FM) texture features and visual image quality assessment by two clinical experts. Texture features were extracted from the automatically segmented IMC for three different age groups. The despeckle filters hybrid median and the homogeneous mask area filter showed the best performance by improving the class separation between the three age groups and also yielded significantly improved image quality.
PMCID: PMC3966465  PMID: 24734038
4.  Active Contour Model Coupling with Higher Order Diffusion for Medical Image Segmentation 
Active contour models are very popular in image segmentation. Different features such as mean gray and variance are selected for different purpose. But for image with intensity inhomogeneities, there are no features for segmentation using the active contour model. The images with intensity inhomogeneities often occurred in real world especially in medical images. To deal with the difficulties raised in image segmentation with intensity inhomogeneities, a new active contour model with higher-order diffusion method is proposed. With the addition of gradient and Laplace information, the active contour model can converge to the edge of the image even with the intensity inhomogeneities. Because of the introduction of Laplace information, the difference scheme becomes more difficult. To enhance the efficiency of the segmentation, the fast Split Bregman algorithm is designed for the segmentation implementation. The performance of our method is demonstrated through numerical experiments of some medical image segmentations with intensity inhomogeneities.
PMCID: PMC3958712  PMID: 24723941
5.  A Framework for the Objective Assessment of Registration Accuracy 
Validation and accuracy assessment are the main bottlenecks preventing the adoption of image processing algorithms in the clinical practice. In the classical approach, a posteriori analysis is performed through objective metrics. In this work, a different approach based on Petri nets is proposed. The basic idea consists in predicting the accuracy of a given pipeline based on the identification and characterization of the sources of inaccuracy. The concept is demonstrated on a case study: intrasubject rigid and affine registration of magnetic resonance images. Both synthetic and real data are considered. While synthetic data allow the benchmarking of the performance with respect to the ground truth, real data enable to assess the robustness of the methodology in real contexts as well as to determine the suitability of the use of synthetic data in the training phase. Results revealed a higher correlation and a lower dispersion among the metrics for simulated data, while the opposite trend was observed for pathologic ones. Results show that the proposed model not only provides a good prediction performance but also leads to the optimization of the end-to-end chain in terms of accuracy and robustness, setting the ground for its generalization to different and more complex scenarios.
PMCID: PMC3934625  PMID: 24659997
6.  Registration of the Cone Beam CT and Blue-Ray Scanned Dental Model Based on the Improved ICP Algorithm 
Multimodality image registration and fusion has complementary significance for guiding dental implant surgery. As the needs of the different resolution image registration, we develop an improved Iterative Closest Point (ICP) algorithm that focuses on the registration of Cone Beam Computed Tomography (CT) image and high-resolution Blue-light scanner image. The proposed algorithm includes two major phases, coarse and precise registration. Firstly, for reducing the matching interference of human subjective factors, we extract feature points based on curvature characteristics and use the improved three point's translational transformation method to realize coarse registration. Then, the feature point set and reference point set, obtained by the initial registered transformation, are processed in the precise registration step. Even with the unsatisfactory initial values, this two steps registration method can guarantee the global convergence and the convergence precision. Experimental results demonstrate that the method has successfully realized the registration of the Cone Beam CT dental model and the blue-ray scanner model with higher accuracy. So the method could provide researching foundation for the relevant software development in terms of the registration of multi-modality medical data.
PMCID: PMC3912889  PMID: 24511309
7.  Blind Deconvolution for Ultrasound Sequences Using a Noninverse Greedy Algorithm 
The blind deconvolution of ultrasound sequences in medical ultrasound technique is still a major problem despite the efforts made. This paper presents a blind noninverse deconvolution algorithm to eliminate the blurring effect, using the envelope of the acquired radio-frequency sequences and a priori Laplacian distribution for deconvolved signal. The algorithm is executed in two steps. Firstly, the point spread function is automatically estimated from the measured data. Secondly, the data are reconstructed in a nonblind way using proposed algorithm. The algorithm is a nonlinear blind deconvolution which works as a greedy algorithm. The results on simulated signals and real images are compared with different state of the art methods deconvolution. Our method shows good results for scatters detection, speckle noise suppression, and execution time.
PMCID: PMC3893842  PMID: 24489533
8.  An Investigation of Calibration Phantoms for CT Scanners with Tube Voltage Modulation 
The effects of calibration phantoms on the correction results of the empirical artifacts correction method (ECCU) for the case of tube modulation were investigated. To improve the validity of the ECCU method, the effect of the geometry parameter of a typical single-material calibration phantom (water calibration phantom) on the ECCU algorithm was investigated. Dual-material calibration phantoms (such as water-bone calibration phantom), geometry arrangement, and the area-ratio of dual-material calibration phantoms were also studied. Preliminary results implied that, to assure the effectiveness of the ECCU algorithm, the polychromatic projections of calibration phantoms must cover the polychromatic projection data of the scanning object. However, the projection range of a water calibration phantom is limited by the scan field of view (SFOV), thus leading to methodological limitations. A dual-material phantom of a proper size and material can overcome the limitations of a single-material phantom and achieve good correction effects.
PMCID: PMC3886221  PMID: 24454334
9.  Computer Aided Diagnostic Support System for Skin Cancer: A Review of Techniques and Algorithms 
Image-based computer aided diagnosis systems have significant potential for screening and early detection of malignant melanoma. We review the state of the art in these systems and examine current practices, problems, and prospects of image acquisition, pre-processing, segmentation, feature extraction and selection, and classification of dermoscopic images. This paper reports statistics and results from the most important implementations reported to date. We compared the performance of several classifiers specifically developed for skin lesion diagnosis and discussed the corresponding findings. Whenever available, indication of various conditions that affect the technique's performance is reported. We suggest a framework for comparative assessment of skin cancer diagnostic models and review the results based on these models. The deficiencies in some of the existing studies are highlighted and suggestions for future research are provided.
PMCID: PMC3885227  PMID: 24575126
10.  Robust Vessel Segmentation in Fundus Images 
One of the most common modalities to examine the human eye is the eye-fundus photograph. The evaluation of fundus photographs is carried out by medical experts during time-consuming visual inspection. Our aim is to accelerate this process using computer aided diagnosis. As a first step, it is necessary to segment structures in the images for tissue differentiation. As the eye is the only organ, where the vasculature can be imaged in an in vivo and noninterventional way without using expensive scanners, the vessel tree is one of the most interesting and important structures to analyze. The quality and resolution of fundus images are rapidly increasing. Thus, segmentation methods need to be adapted to the new challenges of high resolutions. In this paper, we present a method to reduce calculation time, achieve high accuracy, and increase sensitivity compared to the original Frangi method. This method contains approaches to avoid potential problems like specular reflexes of thick vessels. The proposed method is evaluated using the STARE and DRIVE databases and we propose a new high resolution fundus database to compare it to the state-of-the-art algorithms. The results show an average accuracy above 94% and low computational needs. This outperforms state-of-the-art methods.
PMCID: PMC3876700  PMID: 24416040
11.  Improving Image Quality in Medical Images Using a Combined Method of Undecimated Wavelet Transform and Wavelet Coefficient Mapping 
We propose a method for improving image quality in medical images by using a wavelet-based approach. The proposed method integrates two components: image denoising and image enhancement. In the first component, a modified undecimated discrete wavelet transform is used to eliminate the noise. In the second component, a wavelet coefficient mapping function is applied to enhance the contrast of denoised images obtained from the first component. This methodology can be used not only as a means for improving visual quality of medical images but also as a preprocessing module for computer-aided detection/diagnosis systems to improve the performance of screening and detecting regions of interest in images. To confirm its superiority over existing state-of-the-art methods, the proposed method is experimentally evaluated via 30 mammograms and 20 chest radiographs. It is demonstrated that the proposed method can further improve the image quality of mammograms and chest radiographs, as compared to two other methods in the literature. These results reveal the effectiveness and superiority of the proposed method.
PMCID: PMC3870612  PMID: 24382951
12.  A Comparative Study of Theoretical Graph Models for Characterizing Structural Networks of Human Brain 
Previous studies have investigated both structural and functional brain networks via graph-theoretical methods. However, there is an important issue that has not been adequately discussed before: what is the optimal theoretical graph model for describing the structural networks of human brain? In this paper, we perform a comparative study to address this problem. Firstly, large-scale cortical regions of interest (ROIs) are localized by recently developed and validated brain reference system named Dense Individualized Common Connectivity-based Cortical Landmarks (DICCCOL) to address the limitations in the identification of the brain network ROIs in previous studies. Then, we construct structural brain networks based on diffusion tensor imaging (DTI) data. Afterwards, the global and local graph properties of the constructed structural brain networks are measured using the state-of-the-art graph analysis algorithms and tools and are further compared with seven popular theoretical graph models. In addition, we compare the topological properties between two graph models, namely, stickiness-index-based model (STICKY) and scale-free gene duplication model (SF-GD), that have higher similarity with the real structural brain networks in terms of global and local graph properties. Our experimental results suggest that among the seven theoretical graph models compared in this study, STICKY and SF-GD models have better performances in characterizing the structural human brain network.
PMCID: PMC3863486  PMID: 24369454
13.  Comparison of User-Directed and Automatic Mapping of the Planned Isocenter to Treatment Space for Prostate IGRT 
Image-guided radiotherapy (IGRT), adaptive radiotherapy (ART), and online reoptimization rely on accurate mapping of the radiation beam isocenter(s) from planning to treatment space. This mapping involves rigid and/or nonrigid registration of planning (pCT) and intratreatment (tCT) CT images. The purpose of this study was to retrospectively compare a fully automatic approach, including a non-rigid step, against a user-directed rigid method implemented in a clinical IGRT protocol for prostate cancer. Isocenters resulting from automatic and clinical mappings were compared to reference isocenters carefully determined in each tCT. Comparison was based on displacements from the reference isocenters and prostate dose-volume histograms (DVHs). Ten patients with a total of 243 tCTs were investigated. Fully automatic registration was found to be as accurate as the clinical protocol but more precise for all patients. The average of the unsigned x, y, and z offsets and the standard deviations (σ) of the signed offsets computed over all images were (avg. ±  σ (mm)): 1.1 ± 1.4, 1.8 ± 2.3, 2.5 ± 3.5 for the clinical protocol and 0.6 ± 0.8, 1.1 ± 1.5 and 1.1 ± 1.4 for the automatic method. No failures or outliers from automatic mapping were observed, while 8 outliers occurred for the clinical protocol.
PMCID: PMC3857747  PMID: 24348526
14.  Contrast Improvement in Sub- and Ultraharmonic Ultrasound Contrast Imaging by Combining Several Hammerstein Models 
Sub- and ultraharmonic (SUH) ultrasound contrast imaging is an alternative modality to the second harmonic imaging, since, in specific conditions it could produce high quality echographic images. This modality enables the contrast enhancement of echographic images by using SUH present in the contrast agent response but absent from the nonperfused tissue. For a better access to the components generated by the ultrasound contrast agents, nonlinear techniques based on Hammerstein model are preferred. As the major limitation of Hammerstein model is its capacity of modeling harmonic components only, in this work we propose two methods allowing to model SUH. These new methods use several Hammerstein models to identify contrast agent signals having SUH components and to separate these components from harmonic components. The application of the proposed methods for modeling simulated contrast agent signals shows their efficiency in modeling these signals and in separating SUH components. The achieved gain with respect to the standard Hammerstein model was 26.8 dB and 22.8 dB for the two proposed methods, respectively.
PMCID: PMC3838838  PMID: 24307890
15.  Endoscopy-MR Image Fusion for Image Guided Procedures 
Minimally invasive endoscope based abdominal procedures provide potential advantages over conventional open surgery such as reduced trauma, shorter hospital stay, and quick recovery. One major limitation of using this technique is the narrow view of the endoscope and the lack of proper 3D context of the surgical site. In this paper, we propose a rapid and accurate method to align intraoperative stereo endoscopic images of the surgical site with preoperative Magnetic Resonance (MR) images. Gridline light pattern is projected on the surgical site to facilitate the registration. The purpose of this surface-based registration is to provide 3D context of the surgical site to the endoscopic view. We have validated the proposed method on a liver phantom and achieved the surface registration error of 0.76 ± 0.11 mm.
PMCID: PMC3835800  PMID: 24298281
16.  Measurement of Intervertebral Cervical Motion by Means of Dynamic X-Ray Image Processing and Data Interpolation 
Accurate measurement of intervertebral kinematics of the cervical spine can support the diagnosis of widespread diseases related to neck pain, such as chronic whiplash dysfunction, arthritis, and segmental degeneration. The natural inaccessibility of the spine, its complex anatomy, and the small range of motion only permit concise measurement in vivo. Low dose X-ray fluoroscopy allows time-continuous screening of cervical spine during patient's spontaneous motion. To obtain accurate motion measurements, each vertebra was tracked by means of image processing along a sequence of radiographic images. To obtain a time-continuous representation of motion and to reduce noise in the experimental data, smoothing spline interpolation was used. Estimation of intervertebral motion for cervical segments was obtained by processing patient's fluoroscopic sequence; intervertebral angle and displacement and the instantaneous centre of rotation were computed. The RMS value of fitting errors resulted in about 0.2 degree for rotation and 0.2 mm for displacements.
PMCID: PMC3833295  PMID: 24288523
17.  Optical Coherence Tomography Noise Reduction Using Anisotropic Local Bivariate Gaussian Mixture Prior in 3D Complex Wavelet Domain 
In this paper, MMSE estimator is employed for noise-free 3D OCT data recovery in 3D complex wavelet domain. Since the proposed distribution for noise-free data plays a key role in the performance of MMSE estimator, a priori distribution for the pdf of noise-free 3D complex wavelet coefficients is proposed which is able to model the main statistical properties of wavelets. We model the coefficients with a mixture of two bivariate Gaussian pdfs with local parameters which are able to capture the heavy-tailed property and inter- and intrascale dependencies of coefficients. In addition, based on the special structure of OCT images, we use an anisotropic windowing procedure for local parameters estimation that results in visual quality improvement. On this base, several OCT despeckling algorithms are obtained based on using Gaussian/two-sided Rayleigh noise distribution and homomorphic/nonhomomorphic model. In order to evaluate the performance of the proposed algorithm, we use 156 selected ROIs from 650 × 512 × 128 OCT dataset in the presence of wet AMD pathology. Our simulations show that the best MMSE estimator using local bivariate mixture prior is for the nonhomomorphic model in the presence of Gaussian noise which results in an improvement of 7.8 ± 1.7 in CNR.
PMCID: PMC3810483  PMID: 24222760
18.  Using Dynamic Contrast-Enhanced Magnetic Resonance Imaging Data to Constrain a Positron Emission Tomography Kinetic Model: Theory and Simulations 
We show how dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) data can constrain a compartmental model for analyzing dynamic positron emission tomography (PET) data. We first develop the theory that enables the use of DCE-MRI data to separate whole tissue time activity curves (TACs) available from dynamic PET data into individual TACs associated with the blood space, the extravascular-extracellular space (EES), and the extravascular-intracellular space (EIS). Then we simulate whole tissue TACs over a range of physiologically relevant kinetic parameter values and show that using appropriate DCE-MRI data can separate the PET TAC into the three components with accuracy that is noise dependent. The simulations show that accurate blood, EES, and EIS TACs can be obtained as evidenced by concordance correlation coefficients >0.9 between the true and estimated TACs. Additionally, provided that the estimated DCE-MRI parameters are within 10% of their true values, the errors in the PET kinetic parameters are within approximately 20% of their true values. The parameters returned by this approach may provide new information on the transport of a tracer in a variety of dynamic PET studies.
PMCID: PMC3814089  PMID: 24222761
19.  Comparison of Super Resolution Reconstruction Acquisition Geometries for Use in Mouse Phenotyping 
3D isotropic imaging at high spatial resolution (30–100 microns) is important for comparing mouse phenotypes. 3D imaging at high spatial resolutions is limited by long acquisition times and is not possible in many in vivo settings. Super resolution reconstruction (SRR) is a postprocessing technique that has been proposed to improve spatial resolution in the slice-select direction using multiple 2D multislice acquisitions. Any 2D multislice acquisition can be used for SRR. In this study, the effects of using three different low-resolution acquisition geometries (orthogonal, rotational, and shifted) on SRR images were evaluated and compared to a known standard. Iterative back projection was used for the reconstruction of all three acquisition geometries. The results of the study indicate that super resolution reconstructed images based on orthogonally acquired low-resolution images resulted in reconstructed images with higher SNR and CNR in less acquisition time than those based on rotational and shifted acquisition geometries. However, interpolation artifacts were observed in SRR images based on orthogonal acquisition geometry, particularly when the slice thickness was greater than six times the inplane voxel size. Reconstructions based on rotational geometry appeared smoother than those based on orthogonal geometry, but they required two times longer to acquire than the orthogonal LR images.
PMCID: PMC3794539  PMID: 24174930
20.  Skin Parameter Map Retrieval from a Dedicated Multispectral Imaging System Applied to Dermatology/Cosmetology 
In vivo quantitative assessment of skin lesions is an important step in the evaluation of skin condition. An objective measurement device can help as a valuable tool for skin analysis. We propose an explorative new multispectral camera specifically developed for dermatology/cosmetology applications. The multispectral imaging system provides images of skin reflectance at different wavebands covering visible and near-infrared domain. It is coupled with a neural network-based algorithm for the reconstruction of reflectance cube of cutaneous data. This cube contains only skin optical reflectance spectrum in each pixel of the bidimensional spatial information. The reflectance cube is analyzed by an algorithm based on a Kubelka-Munk model combined with evolutionary algorithm. The technique allows quantitative measure of cutaneous tissue and retrieves five skin parameter maps: melanin concentration, epidermis/dermis thickness, haemoglobin concentration, and the oxygenated hemoglobin. The results retrieved on healthy participants by the algorithm are in good accordance with the data from the literature. The usefulness of the developed technique was proved during two experiments: a clinical study based on vitiligo and melasma skin lesions and a skin oxygenation experiment (induced ischemia) with healthy participant where normal tissues are recorded at normal state and when temporary ischemia is induced.
PMCID: PMC3789448  PMID: 24159326
21.  Computational Representation of White Matter Fiber Orientations 
We present a new methodology based on directional data clustering to represent white matter fiber orientations in magnetic resonance analyses for high angular resolution diffusion imaging. A probabilistic methodology is proposed for estimating intravoxel principal fiber directions, based on clustering directional data arising from orientation distribution function (ODF) profiles. ODF reconstructions are used to estimate intravoxel fiber directions using mixtures of von Mises-Fisher distributions. The method focuses on clustering data on the unit sphere, where complexity arises from representing ODF profiles as directional data. The proposed method is validated on synthetic simulations, as well as on a real data experiment. Based on experiments, we show that by clustering profile data using mixtures of von Mises-Fisher distributions it is possible to estimate multiple fiber configurations in a more robust manner than currently used approaches, without recourse to regularization or sharpening procedures. The method holds promise to support robust tractographic methodologies and to build realistic models of white matter tracts in the human brain.
PMCID: PMC3762169  PMID: 24023538
22.  Microwave Imaging of Human Forearms: Pilot Study and Image Enhancement 
We present a pilot study using a microwave tomography system in which we image the forearms of 5 adult male and female volunteers between the ages of 30 and 48. Microwave scattering data were collected at 0.8 to 1.2 GHz with 24 transmitting and receiving antennas located in a matching fluid of deionized water and table salt. Inversion of the microwave data was performed with a balanced version of the multiplicative-regularized contrast source inversion algorithm formulated using the finite-element method (FEM-CSI). T1-weighted MRI images of each volunteer's forearm were also collected in the same plane as the microwave scattering experiment. Initial “blind” imaging results from the utilized inversion algorithm show that the image quality is dependent on the thickness of the arm's peripheral adipose tissue layer; thicker layers of adipose tissue lead to poorer overall image quality. Due to the exible nature of the FEM-CSI algorithm used, prior information can be readily incorporated into the microwave imaging inversion process. We show that by introducing prior information into the FEM-CSI algorithm the internal anatomical features of all the arms are resolved, significantly improving the images. The prior information was estimated manually from the blind inversions using an ad hoc procedure.
PMCID: PMC3760097  PMID: 24023539
23.  Automated Segmentation and Object Classification of CT Images: Application to In Vivo Molecular Imaging of Avian Embryos 
Background. Although chick embryogenesis has been studied extensively, there has been growing interest in the investigation of skeletogenesis. In addition to improved poultry health and minimized economic loss, a greater understanding of skeletal abnormalities can also have implications for human medicine. True in vivo studies require noninvasive imaging techniques such as high-resolution microCT. However, the manual analysis of acquired images is both time consuming and subjective. Methods. We have developed a system for automated image segmentation that entails object-based image analysis followed by the classification of the extracted image objects. For image segmentation, a rule set was developed using Definiens image analysis software. The classification engine was implemented using the WEKA machine learning tool. Results. Our system reduces analysis time and observer bias while maintaining high accuracy. Applying the system to the quantification of long bone growth has allowed us to present the first true in ovo data for bone length growth recorded in the same chick embryos. Conclusions. The procedures developed represent an innovative approach for the automated segmentation, classification, quantification, and visualization of microCT images. MicroCT offers the possibility of performing longitudinal studies and thereby provides unique insights into the morpho- and embryogenesis of live chick embryos.
PMCID: PMC3753761  PMID: 23997760
24.  Automated Diagnosis of Otitis Media: Vocabulary and Grammar 
We propose a novel automated algorithm for classifying diagnostic categories of otitis media: acute otitis media, otitis media with effusion, and no effusion. Acute otitis media represents a bacterial superinfection of the middle ear fluid, while otitis media with effusion represents a sterile effusion that tends to subside spontaneously. Diagnosing children with acute otitis media is difficult, often leading to overprescription of antibiotics as they are beneficial only for children with acute otitis media. This underscores the need for an accurate and automated diagnostic algorithm. To that end, we design a feature set understood by both otoscopists and engineers based on the actual visual cues used by otoscopists; we term this the otitis media vocabulary. We also design a process to combine the vocabulary terms based on the decision process used by otoscopists; we term this the otitis media grammar. The algorithm achieves 89.9% classification accuracy, outperforming both clinicians who did not receive special training and state-of-the-art classifiers.
PMCID: PMC3749602  PMID: 23997759
25.  Closed Contour Specular Reflection Segmentation in Laparoscopic Images 
Segmentation of specular reflections is an essential step in endoscopic image analysis; it affects all further processing steps including segmentation, classification, and registration tasks. The dichromatic reflectance model, which is often used for specular reflection modeling, is made for dielectric materials and not for human tissue. Hence, most recent segmentation approaches rely on thresholding techniques. In this work, we first demonstrate the limited accuracy that can be achieved by thresholding techniques and propose a hybrid method which is based on closed contours and thresholding. The method has been evaluated on 269 specular reflections in 49 images which were taken from 27 real laparoscopic interventions. Our method improves the average sensitivity by 16% compared to the state-of-the-art thresholding methods.
PMCID: PMC3747397  PMID: 23983675

Results 1-25 (356)