Showing papers in "IEEE Transactions on Medical Imaging in 2015"

The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS)

Abstract: In this paper we report the set-up and results of the Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) organized in conjunction with the MICCAI 2012 and 2013 conferences Twenty state-of-the-art tumor segmentation algorithms were applied to a set of 65 multi-contrast MR scans of low- and high-grade glioma patients—manually annotated by up to four raters—and to 65 comparable scans generated using tumor image simulation software Quantitative evaluations revealed considerable disagreement between the human raters in segmenting various tumor sub-regions (Dice scores in the range 74%–85%), illustrating the difficulty of this task We found that different algorithms worked best for different sub-regions (reaching performance comparable to human inter-rater variability), but that no single algorithm ranked in the top for all sub-regions simultaneously Fusing several good algorithms using a hierarchical majority vote yielded segmentations that consistently ranked above all individual algorithms, indicating remaining opportunities for further methodological improvements The BRATS image data and manual annotations continue to be publicly available through an online evaluation system as an ongoing benchmarking resource

Spatiotemporal Clutter Filtering of Ultrafast Ultrasound Data Highly Increases Doppler and fUltrasound Sensitivity

Abstract: Ultrafast ultrasonic imaging is a rapidly developing field based on the unfocused transmission of plane or diverging ultrasound waves. This recent approach to ultrasound imaging leads to a large increase in raw ultrasound data available per acquisition. Bigger synchronous ultrasound imaging datasets can be exploited in order to strongly improve the discrimination between tissue and blood motion in the field of Doppler imaging. Here we propose a spatiotemporal singular value decomposition clutter rejection of ultrasonic data acquired at ultrafast frame rate. The singular value decomposition (SVD) takes benefits of the different features of tissue and blood motion in terms of spatiotemporal coherence and strongly outperforms conventional clutter rejection filters based on high pass temporal filtering. Whereas classical clutter filters operate on the temporal dimension only, SVD clutter filtering provides up to a four-dimensional approach (3D in space and 1D in time). We demonstrate the performance of SVD clutter filtering with a flow phantom study that showed an increased performance compared to other classical filters (better contrast to noise ratio with tissue motion between 1 and 10mm/s and axial blood flow as low as 2.6 mm/s). SVD clutter filtering revealed previously undetected blood flows such as microvascular networks or blood flows corrupted by significant tissue or probe motion artifacts. We report in vivo applications including small animal fUltrasound brain imaging (blood flow detection limit of 0.5 mm/s) and several clinical imaging cases, such as neonate brain imaging, liver or kidney Doppler imaging.

The Delay Multiply and Sum Beamforming Algorithm in Ultrasound B-Mode Medical Imaging

Abstract: Most of ultrasound medical imaging systems currently on the market implement standard Delay and Sum (DAS) beamforming to form B-mode images. However, image resolution and contrast achievable with DAS are limited by the aperture size and by the operating frequency. For this reason, different beamformers have been presented in the literature that are mainly based on adaptive algorithms, which allow achieving higher performance at the cost of an increased computational complexity. In this paper, we propose the use of an alternative nonlinear beamforming algorithm for medical ultrasound imaging, which is called Delay Multiply and Sum (DMAS) and that was originally conceived for a RADAR microwave system for breast cancer detection. We modify the DMAS beamformer and test its performance on both simulated and experimentally collected linear-scan data, by comparing the Point Spread Functions, beampatterns, synthetic phantom and in vivo carotid artery images obtained with standard DAS and with the proposed algorithm. Results show that the DMAS beamformer outperforms DAS in both simulated and experimental trials and that the main improvement brought about by this new method is a significantly higher contrast resolution (i.e., narrower main lobe and lower side lobes), which turns out into an increased dynamic range and better quality of B-mode images.

3-D In Vitro Acoustic Super-Resolution and Super-Resolved Velocity Mapping Using Microbubbles

Abstract: Standard clinical ultrasound (US) imaging frequencies are unable to resolve microvascular structures due to the fundamental diffraction limit of US waves. Recent demonstrations of 2-D super-resolution both in vitro and in vivo have demonstrated that fine vascular structures can be visualized using acoustic single bubble localization. Visualization of more complex and disordered 3-D vasculature, such as that of a tumor, requires an acquisition strategy which can additionally localize bubbles in the elevational plane with high precision in order to generate super-resolution in all three dimensions. Furthermore, a particular challenge lies in the need to provide this level of visualization with minimal acquisition time. In this paper, we develop a fast, coherent US imaging tool for microbubble localization in 3-D using a pair of US transducers positioned at 90°. This allowed detection of point scatterer signals in 3-D with average precisions equal to $1.9~\mu \text{m}$ in axial and elevational planes, and $11~\mu \text{m}$ in the lateral plane, compared to the diffraction limited point spread function full-widths at half-maximum of 488, 1188, and $953~\mu \text{m}$ of the original imaging system with a single transducer. Visualization and velocity mapping of 3-D in vitro structures was demonstrated far beyond the diffraction limit. The capability to measure the complete flow pattern of blood vessels associated with disease at depth would ultimately enable analysis of in vivo microvascular morphology, blood flow dynamics, and occlusions resulting from disease states.

Automated Vessel Segmentation Using Infinite Perimeter Active Contour Model with Hybrid Region Information with Application to Retinal Images

Abstract: Automated detection of blood vessel structures is becoming of crucial interest for better management of vascular disease. In this paper, we propose a new infinite active contour model that uses hybrid region information of the image to approach this problem. More specifically, an infinite perimeter regularizer, provided by using ${\cal L}^{2}$ Lebesgue measure of the $\gamma$ -neighborhood of boundaries, allows for better detection of small oscillatory (branching) structures than the traditional models based on the length of a feature's boundaries (i.e., ${\cal H}^{1}$ Hausdorff measure). Moreover, for better general segmentation performance, the proposed model takes the advantage of using different types of region information, such as the combination of intensity information and local phase based enhancement map. The local phase based enhancement map is used for its superiority in preserving vessel edges while the given image intensity information will guarantee a correct feature's segmentation. We evaluate the performance of the proposed model by applying it to three public retinal image datasets (two datasets of color fundus photography and one fluorescein angiography dataset). The proposed model outperforms its competitors when compared with other widely used unsupervised and supervised methods. For example, the sensitivity (0.742), specificity (0.982) and accuracy (0.954) achieved on the DRIVE dataset are very close to those of the second observer's annotations.

Geodesic Information Flows: Spatially-Variant Graphs and Their Application to Segmentation and Fusion

Abstract: Clinical annotations, such as voxel-wise binary or probabilistic tissue segmentations, structural parcellations, pathological regions-of-interest and anatomical landmarks are key to many clinical studies. However, due to the time consuming nature of manually generating these annotations, they tend to be scarce and limited to small subsets of data. This work explores a novel framework to propagate voxel-wise annotations between morphologically dissimilar images by diffusing and mapping the available examples through intermediate steps. A spatially-variant graph structure connecting morphologically similar subjects is introduced over a database of images, enabling the gradual diffusion of information to all the subjects, even in the presence of large-scale morphological variability. We illustrate the utility of the proposed framework on two example applications: brain parcellation using categorical labels and tissue segmentation using probabilistic features. The application of the proposed method to categorical label fusion showed highly statistically significant improvements when compared to state-of-the-art methodologies. Significant improvements were also observed when applying the proposed framework to probabilistic tissue segmentation of both synthetic and real data, mainly in the presence of large morphological variability.

Transfer Learning Improves Supervised Image Segmentation Across Imaging Protocols

Abstract: The variation between images obtained with different scanners or different imaging protocols presents a major challenge in automatic segmentation of biomedical images. This variation especially hampers the application of otherwise successful supervised-learning techniques which, in order to perform well, often require a large amount of labeled training data that is exactly representative of the target data. We therefore propose to use transfer learning for image segmentation. Transfer-learning techniques can cope with differences in distributions between training and target data, and therefore may improve performance over supervised learning for segmentation across scanners and scan protocols. We present four transfer classifiers that can train a classification scheme with only a small amount of representative training data, in addition to a larger amount of other training data with slightly different characteristics. The performance of the four transfer classifiers was compared to that of standard supervised classification on two magnetic resonance imaging brain-segmentation tasks with multi-site data: white matter, gray matter, and cerebrospinal fluid segmentation; and white-matter-/MS-lesion segmentation. The experiments showed that when there is only a small amount of representative training data available, transfer learning can greatly outperform common supervised-learning approaches, minimizing classification errors by up to 60%.

LRTV: MR Image Super-Resolution With Low-Rank and Total Variation Regularizations

Abstract: Image super-resolution (SR) aims to recover high-resolution images from their low-resolution counterparts for improving image analysis and visualization. Interpolation methods, widely used for this purpose, often result in images with blurred edges and blocking effects. More advanced methods such as total variation (TV) retain edge sharpness during image recovery. However, these methods only utilize information from local neighborhoods, neglecting useful information from remote voxels. In this paper, we propose a novel image SR method that integrates both local and global information for effective image recovery. This is achieved by, in addition to TV, low-rank regularization that enables utilization of information throughout the image. The optimization problem can be solved effectively via alternating direction method of multipliers (ADMM). Experiments on MR images of both adult and pediatric subjects demonstrate that the proposed method enhances the details in the recovered high-resolution images, and outperforms methods such as the nearest-neighbor interpolation, cubic interpolation, iterative back projection (IBP), non-local means (NLM), and TV-based up-sampling.

Towards Large-Scale Histopathological Image Analysis: Hashing-Based Image Retrieval

Abstract: Automatic analysis of histopathological images has been widely utilized leveraging computational image-processing methods and modern machine learning techniques. Both computer-aided diagnosis (CAD) and content-based image-retrieval (CBIR) systems have been successfully developed for diagnosis, disease detection, and decision support in this area. Recently, with the ever-increasing amount of annotated medical data, large-scale and data-driven methods have emerged to offer a promise of bridging the semantic gap between images and diagnostic information. In this paper, we focus on developing scalable image-retrieval techniques to cope intelligently with massive histopathological images. Specifically, we present a supervised kernel hashing technique which leverages a small amount of supervised information in learning to compress a 10 $\thinspace$ 000-dimensional image feature vector into only tens of binary bits with the informative signatures preserved. These binary codes are then indexed into a hash table that enables real-time retrieval of images in a large database. Critically, the supervised information is employed to bridge the semantic gap between low-level image features and high-level diagnostic information. We build a scalable image-retrieval framework based on the supervised hashing technique and validate its performance on several thousand histopathological images acquired from breast microscopic tissues. Extensive evaluations are carried out in terms of image classification (i.e., benign versus actionable categorization) and retrieval tests. Our framework achieves about 88.1% classification accuracy as well as promising time efficiency. For example, the framework can execute around 800 queries in only 0.01 s, comparing favorably with other commonly used dimensionality reduction and feature selection methods.

A Stochastic Polygons Model for Glandular Structures in Colon Histology Images

Abstract: In this paper, we present a stochastic model for glandular structures in histology images of tissue slides stained with Hematoxylin and Eosin, choosing colon tissue as an example. The proposed Random Polygons Model (RPM) treats each glandular structure in an image as a polygon made of a random number of vertices, where the vertices represent approximate locations of epithelial nuclei. We formulate the RPM as a Bayesian inference problem by defining a prior for spatial connectivity and arrangement of neighboring epithelial nuclei and a likelihood for the presence of a glandular structure. The inference is made via a Reversible-Jump Markov chain Monte Carlo simulation. To the best of our knowledge, all existing published algorithms for gland segmentation are designed to mainly work on healthy samples, adenomas, and low grade adenocarcinomas. One of them has been demonstrated to work on intermediate grade adenocarcinomas at its best. Our experimental results show that the RPM yields favorable results, both quantitatively and qualitatively, for extraction of glandular structures in histology images of normal human colon tissues as well as benign and cancerous tissues, excluding undifferentiated carcinomas.

COMMIT: Convex Optimization Modeling for Microstructure Informed Tractography

Abstract: Tractography is a class of algorithms aiming at in vivo mapping the major neuronal pathways in the white matter from diffusion magnetic resonance imaging (MRI) data. These techniques offer a powerful tool to noninvasively investigate at the macroscopic scale the architecture of the neuronal connections of the brain. However, unfortunately, the reconstructions recovered with existing tractography algorithms are not really quantitative even though diffusion MRI is a quantitative modality by nature. As a matter of fact, several techniques have been proposed in recent years to estimate, at the voxel level, intrinsic microstructural features of the tissue, such as axonal density and diameter, by using multicompartment models. In this paper, we present a novel framework to reestablish the link between tractography and tissue microstructure. Starting from an input set of candidate fiber-tracts, which are estimated from the data using standard fiber-tracking techniques, we model the diffusion MRI signal in each voxel of the image as a linear combination of the restricted and hindered contributions generated in every location of the brain by these candidate tracts. Then, we seek for the global weight of each of them, i.e., the effective contribution or volume, such that they globally fit the measured signal at best. We demonstrate that these weights can be easily recovered by solving a global convex optimization problem and using efficient algorithms. The effectiveness of our approach has been evaluated both on a realistic phantom with known ground-truth and in vivo brain data. Results clearly demonstrate the benefits of the proposed formulation, opening new perspectives for a more quantitative and biologically plausible assessment of the structural connectivity of the brain.

Magnetic Particle Imaging With Tailored Iron Oxide Nanoparticle Tracers

Abstract: Magnetic particle imaging (MPI) shows promise for medical imaging, particularly in angiography of patients with chronic kidney disease. As the first biomedical imaging technique that truly depends on nanoscale materials properties, MPI requires highly optimized magnetic nanoparticle tracers to generate quality images. Until now, researchers have relied on tracers optimized for MRI ${\rm T}2^ {\ast} $ -weighted imaging that are sub-optimal for MPI. Here, we describe new tracers tailored to MPI's unique physics, synthesized using an organic-phase process and functionalized to ensure biocompatibility and adequate in vivo circulation time. Tailored tracers showed up to 3 $\,\times$ greater signal-to-noise ratio and better spatial resolution than existing commercial tracers in MPI images of phantoms.

Global Linking of Cell Tracks Using the Viterbi Algorithm

Abstract: Automated tracking of living cells in microscopy image sequences is an important and challenging problem. With this application in mind, we propose a global track linking algorithm, which links cell outlines generated by a segmentation algorithm into tracks. The algorithm adds tracks to the image sequence one at a time, in a way which uses information from the complete image sequence in every linking decision. This is achieved by finding the tracks which give the largest possible increases to a probabilistically motivated scoring function, using the Viterbi algorithm. We also present a novel way to alter previously created tracks when new tracks are created, thus mitigating the effects of error propagation. The algorithm can handle mitosis, apoptosis, and migration in and out of the imaged area, and can also deal with false positives, missed detections, and clusters of jointly segmented cells. The algorithm performance is demonstrated on two challenging datasets acquired using bright-field microscopy, but in principle, the algorithm can be used with any cell type and any imaging technique, presuming there is a suitable segmentation algorithm.

Fast Volume Reconstruction From Motion Corrupted Stacks of 2D Slices

Abstract: Capturing an enclosing volume of moving subjects and organs using fast individual image slice acquisition has shown promise in dealing with motion artefacts. Motion between slice acquisitions results in spatial inconsistencies that can be resolved by slice-to-volume reconstruction (SVR) methods to provide high quality 3D image data. Existing algorithms are, however, typically very slow, specialised to specific applications and rely on approximations, which impedes their potential clinical use. In this paper, we present a fast multi-GPU accelerated framework for slice-to-volume reconstruction. It is based on optimised 2D/3D registration, super-resolution with automatic outlier rejection and an additional (optional) intensity bias correction. We introduce a novel and fully automatic procedure for selecting the image stack with least motion to serve as an initial registration target. We evaluate the proposed method using artificial motion corrupted phantom data as well as clinical data, including tracked freehand ultrasound of the liver and fetal Magnetic Resonance Imaging. We achieve speed-up factors greater than 30 compared to a single CPU system and greater than 10 compared to currently available state-of-the-art multi-core CPU methods. We ensure high reconstruction accuracy by exact computation of the point-spread function for every input data point, which has not previously been possible due to computational limitations. Our framework and its implementation is scalable for available computational infrastructures and tests show a speed-up factor of 1.70 for each additional GPU. This paves the way for the online application of image based reconstruction methods during clinical examinations. The source code for the proposed approach is publicly available.

PET Image Reconstruction Using Kernel Method

Abstract: Image reconstruction from low-count positron emission tomography (PET) projection data is challenging because the inverse problem is ill-posed. Prior information can be used to improve image quality. Inspired by the kernel methods in machine learning, this paper proposes a kernel based method that models PET image intensity in each pixel as a function of a set of features obtained from prior information. The kernel-based image model is incorporated into the forward model of PET projection data and the coefficients can be readily estimated by the maximum likelihood (ML) or penalized likelihood image reconstruction. A kernelized expectation-maximization algorithm is presented to obtain the ML estimate. Computer simulations show that the proposed approach can achieve better bias versus variance trade-off and higher contrast recovery for dynamic PET image reconstruction than the conventional maximum likelihood method with and without post-reconstruction denoising. Compared with other regularization-based methods, the kernel method is easier to implement and provides better image quality for low-count data. Application of the proposed kernel method to a 4-D dynamic PET patient dataset showed promising results.

Benchmark for Algorithms Segmenting the Left Atrium From 3D CT and MRI Datasets

Abstract: Knowledge of left atrial (LA) anatomy is important for atrial fibrillation ablation guidance, fibrosis quantification and biophysical modelling. Segmentation of the LA from Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) images is a complex problem. This manuscript presents a benchmark to evaluate algorithms that address LA segmentation. The datasets, ground truth and evaluation code have been made publicly available through the http://www.cardiacatlas.org website. This manuscript also reports the results of the Left Atrial Segmentation Challenge (LASC) carried out at the STACOM’13 workshop, in conjunction with MICCAI’13. Thirty CT and 30 MRI datasets were provided to participants for segmentation. Each participant segmented the LA including a short part of the LA appendage trunk and proximal sections of the pulmonary veins (PVs). We present results for nine algorithms for CT and eight algorithms for MRI. Results showed that methodologies combining statistical models with region growing approaches were the most appropriate to handle the proposed task. The ground truth and automatic segmentations were standardised to reduce the influence of inconsistently defined regions (e.g., mitral plane, PVs end points, LA appendage). This standardisation framework, which is a contribution of this work, can be used to label and further analyse anatomical regions of the LA. By performing the standardisation directly on the left atrial surface, we can process multiple input data, including meshes exported from different electroanatomical mapping systems.

Combining Ordered Subsets and Momentum for Accelerated X-Ray CT Image Reconstruction

Abstract: Statistical X-ray computed tomography (CT) reconstruction can improve image quality from reduced dose scans, but requires very long computation time. Ordered subsets (OS) methods have been widely used for research in X-ray CT statistical image reconstruction (and are used in clinical PET and SPECT reconstruction). In particular, OS methods based on separable quadratic surrogates (OS-SQS) are massively parallelizable and are well suited to modern computing architectures, but the number of iterations required for convergence should be reduced for better practical use. This paper introduces OS-SQS-momentum algorithms that combine Nesterov's momentum techniques with OS-SQS methods, greatly improving convergence speed in early iterations. If the number of subsets is too large, the OS-SQS-momentum methods can be unstable, so we propose diminishing step sizes that stabilize the method while preserving the very fast convergence behavior. Experiments with simulated and real 3D CT scan data illustrate the performance of the proposed algorithms.

Sparse-View Spectral CT Reconstruction Using Spectral Patch-Based Low-Rank Penalty

Abstract: Spectral computed tomography (CT) is a promising technique with the potential for improving lesion detection, tissue characterization, and material decomposition. In this paper, we are interested in kVp switching-based spectral CT that alternates distinct kVp X-ray transmissions during gantry rotation. This system can acquire multiple X-ray energy transmissions without additional radiation dose. However, only sparse views are generated for each spectral measurement; and the spectra themselves are limited in number. To address these limitations, we propose a penalized maximum likelihood method using spectral patch-based low-rank penalty, which exploits the self-similarity of patches that are collected at the same position in spectral images. The main advantage is that the relatively small number of materials within each patch allows us to employ the low-rank penalty that is less sensitive to intensity changes while preserving edge directions. In our optimization formulation, the cost function consists of the Poisson log-likelihood for X-ray transmission and the nonconvex patch-based low-rank penalty. Since the original cost function is difficult to minimize directly, we propose an optimization method using separable quadratic surrogate and concave convex procedure algorithms for the log-likelihood and penalty terms, which results in an alternating minimization that provides a computational advantage because each subproblem can be solved independently. We performed computer simulations and a real experiment using a kVp switching-based spectral CT with sparse-view measurements, and compared the proposed method with conventional algorithms. We confirmed that the proposed method improves spectral images both qualitatively and quantitatively. Furthermore, our GPU implementation significantly reduces the computational cost.

Retinal Artery-Vein Classification via Topology Estimation

Abstract: We propose a novel, graph-theoretic framework for distinguishing arteries from veins in a fundus image. We make use of the underlying vessel topology to better classify small and midsized vessels. We extend our previously proposed tree topology estimation framework by incorporating expert, domain-specific features to construct a simple, yet powerful global likelihood model. We efficiently maximize this model by iteratively exploring the space of possible solutions consistent with the projected vessels. We tested our method on four retinal datasets and achieved classification accuracies of 91.0%, 93.5%, 91.7%, and 90.9%, outperforming existing methods. Our results show the effectiveness of our approach, which is capable of analyzing the entire vasculature, including peripheral vessels, in wide field-of-view fundus photographs. This topology-based method is a potentially important tool for diagnosing diseases with retinal vascular manifestation.

Bayesian Model Selection for Pathological Neuroimaging Data Applied to White Matter Lesion Segmentation

Abstract: In neuroimaging studies, pathologies can present themselves as abnormal intensity patterns. Thus, solutions for detecting abnormal intensities are currently under investigation. As each patient is unique, an unbiased and biologically plausible model of pathological data would have to be able to adapt to the subject's individual presentation. Such a model would provide the means for a better understanding of the underlying biological processes and improve one's ability to define pathologically meaningful imaging biomarkers. With this aim in mind, this work proposes a hierarchical fully unsupervised model selection framework for neuroimaging data which enables the distinction between different types of abnormal image patterns without pathological a priori knowledge. Its application on simulated and clinical data demonstrated the ability to detect abnormal intensity clusters, resulting in a competitive to improved behavior in white matter lesion segmentation when compared to three other freely-available automated methods.

Evaluation and Comparison of Anatomical Landmark Detection Methods for Cephalometric X-Ray Images: A Grand Challenge

Abstract: Cephalometric analysis is an essential clinical and research tool in orthodontics for the orthodontic analysis and treatment planning. This paper presents the evaluation of the methods submitted to the Automatic Cephalometric X-Ray Landmark Detection Challenge, held at the IEEE International Symposium on Biomedical Imaging 2014 with an on-site competition. The challenge was set to explore and compare automatic landmark detection methods in application to cephalometric X-ray images. Methods were evaluated on a common database including cephalograms of 300 patients aged six to 60 years, collected from the Dental Department, Tri-Service General Hospital, Taiwan, and manually marked anatomical landmarks as the ground truth data, generated by two experienced medical doctors. Quantitative evaluation was performed to compare the results of a representative selection of current methods submitted to the challenge. Experimental results show that three methods are able to achieve detection rates greater than 80% using the 4 mm precision range, but only one method achieves a detection rate greater than 70% using the 2 mm precision range, which is the acceptable precision range in clinical practice. The study provides insights into the performance of different landmark detection approaches under real-world conditions and highlights achievements and limitations of current image analysis techniques.

Automated 3-D Retinal Layer Segmentation of Macular Optical Coherence Tomography Images With Serous Pigment Epithelial Detachments

Abstract: Automated retinal layer segmentation of optical coherence tomography (OCT) images has been successful for normal eyes but becomes challenging for eyes with retinal diseases if the retinal morphology experiences critical changes. We propose a method to automatically segment the retinal layers in 3-D OCT data with serous retinal pigment epithelial detachments (PED), which is a prominent feature of many chorioretinal disease processes. The proposed framework consists of the following steps: fast denoising and B-scan alignment, multi-resolution graph search based surface detection, PED region detection and surface correction above the PED region. The proposed technique was evaluated on a dataset with OCT images from 20 subjects diagnosed with PED. The experimental results showed the following. 1) The overall mean unsigned border positioning error for layer segmentation is $7.87\pm 3.36 ~\mu{\rm m}$ , and is comparable to the mean inter-observer variability ( $7.81\pm 2.56 ~\mu {\rm m}$ ). 2) The true positive volume fraction (TPVF), false positive volume fraction (FPVF) and positive predicative value (PPV) for PED volume segmentation are 87.1%, 0.37%, and 81.2%, respectively. 3) The average running time is 220 s for OCT data of 512 $\,\times \,$ 64 $\,\times\,$ 480 voxels.

Saliency Based Ulcer Detection for Wireless Capsule Endoscopy Diagnosis

Abstract: Ulcer is one of the most common symptoms of many serious diseases in the human digestive tract. Especially for the ulcers in the small bowel where other procedures cannot adequately visualize, wireless capsule endoscopy (WCE) is increasingly being used in the diagnosis and clinical management. Because WCE generates large amount of images from the whole process of inspection, computer-aided detection of ulcer is considered an indispensable relief to clinicians. In this paper, a two-staged fully automated computer-aided detection system is proposed to detect ulcer from WCE images. In the first stage, we propose an effective saliency detection method based on multi-level superpixel representation to outline the ulcer candidates. To find the perceptually and semantically meaningful salient regions, we first segment the image into multi-level superpixel segmentations. Each level corresponds to different initial region sizes of the superpixels. Then we evaluate the corresponding saliency according to the color and texture features in superpixel region of each level. In the end, we fuse the saliency maps from all levels together to obtain the final saliency map. In the second stage, we apply the obtained saliency map to better encode the image features for the ulcer image recognition tasks. Because the ulcer mainly corresponds to the saliency region, we propose a saliency max-pooling method integrated with the Locality-constrained Linear Coding (LLC) method to characterize the images. Experiment results achieve promising 92.65% accuracy and 94.12% sensitivity, validating the effectiveness of the proposed method. Moreover, the comparison results show that our detection system outperforms the state-of-the-art methods on the ulcer classification task.

A Framework for Automated Spine and Vertebrae Interpolation-Based Detection and Model-Based Segmentation

Abstract: Automated and semi-automated detection and segmentation of spinal and vertebral structures from computed tomography (CT) images is a challenging task due to a relatively high degree of anatomical complexity, presence of unclear boundaries and articulation of vertebrae with each other, as well as due to insufficient image spatial resolution, partial volume effects, presence of image artifacts, intensity variations and low signal-to-noise ratio. In this paper, we describe a novel framework for automated spine and vertebrae detection and segmentation from 3-D CT images. A novel optimization technique based on interpolation theory is applied to detect the location of the whole spine in the 3-D image and, using the obtained location of the whole spine, to further detect the location of individual vertebrae within the spinal column. The obtained vertebra detection results represent a robust and accurate initialization for the subsequent segmentation of individual vertebrae, which is performed by an improved shape-constrained deformable model approach. The framework was evaluated on two publicly available CT spine image databases of 50 lumbar and 170 thoracolumbar vertebrae. Quantitative comparison against corresponding reference vertebra segmentations yielded an overall mean centroid-to-centroid distance of 1.1 mm and Dice coefficient of 83.6% for vertebra detection, and an overall mean symmetric surface distance of 0.3 mm and Dice coefficient of 94.6% for vertebra segmentation. The results indicate that by applying the proposed automated detection and segmentation framework, vertebrae can be successfully detected and accurately segmented in 3-D from CT spine images.

Detecting Surgical Tools by Modelling Local Appearance and Global Shape

Abstract: Detecting tools in surgical videos is an important ingredient for context-aware computer-assisted surgical systems. To this end, we present a new surgical tool detection dataset and a method for joint tool detection and pose estimation in 2d images. Our two-stage pipeline is data-driven and relaxes strong assumptions made by previous works regarding the geometry, number, and position of tools in the image. The first stage classifies each pixel based on local appearance only, while the second stage evaluates a tool-specific shape template to enforce global shape. Both local appearance and global shape are learned from training data. Our method is validated on a new surgical tool dataset of 2 476 images from neurosurgical microscopes, which is made freely available. It improves over existing datasets in size, diversity and detail of annotation. We show that our method significantly improves over competitive baselines from the computer vision field. We achieve 15% detection miss-rate at $10^{-1}$ false positives per image (for the suction tube) over our surgical tool dataset. Results indicate that performing semantic labelling as an intermediate task is key for high quality detection.

A Digital Preclinical PET/MRI Insert and Initial Results

Abstract: Combining Positron Emission Tomography (PET) with Magnetic Resonance Imaging (MRI) results in a promising hybrid molecular imaging modality as it unifies the high sensitivity of PET for molecular and cellular processes with the functional and anatomical information from MRI. Digital Silicon Photomultipliers (dSiPMs) are the digital evolution in scintillation light detector technology and promise high PET SNR. DSiPMs from Philips Digital Photon Counting (PDPC) were used to develop a preclinical PET/RF gantry with 1-mm scintillation crystal pitch as an insert for clinical MRI scanners. With three exchangeable RF coils, the hybrid field of view has a maximum size of 160 mm $\,\times\,$ 96.6 mm (transaxial $\,\times\,$ axial). 0.1 ppm volume-root-mean-square B $_{0}$ -homogeneity is kept within a spherical diameter of 96 mm (automatic volume shimming). Depending on the coil, MRI SNR is decreased by 13% or 5% by the PET system. PET count rates, energy resolution of 12.6% FWHM, and spatial resolution of 0.73 mm $^{3}$ (isometric volume resolution at isocenter) are not affected by applied MRI sequences. PET time resolution of 565 ps (FWHM) degraded by 6 ps during an EPI sequence. Timing-optimized settings yielded 260 ps time resolution. PET and MR images of a hot-rod phantom show no visible differences when the other modality was in operation and both resolve 0.8-mm rods. Versatility of the insert is shown by successfully combining multi-nuclei MRI ( $^{1}{\rm H}/^{19}$ F) with simultaneously measured PET ( $^{18}$ F-FDG). A longitudinal study of a tumor-bearing mouse verifies the operability, stability, and in vivo capabilities of the system. Cardiac- and respiratory-gated PET/MRI motion-capturing (CINE) images of the mouse heart demonstrate the advantage of simultaneous acquisition for temporal and spatial image registration.

A Pipeline for the Generation of Realistic 3D Synthetic Echocardiographic Sequences: Methodology and Open-Access Database

Abstract: Quantification of cardiac deformation and strain with 3D ultrasound takes considerable research efforts. Nevertheless, a widespread use of these techniques in clinical practice is still held back due to the lack of a solid verification process to quantify and compare performance. In this context, the use of fully synthetic sequences has become an established tool for initial in silico evaluation. Nevertheless, the realism of existing simulation techniques is still too limited to represent reliable benchmarking data. Moreover, the fact that different centers typically make use of in-house developed simulation pipelines makes a fair comparison difficult. In this context, this paper introduces a novel pipeline for the generation of synthetic 3D cardiac ultrasound image sequences. State-of-the art solutions in the fields of electromechanical modeling and ultrasound simulation are combined within an original framework that exploits a real ultrasound recording to learn and simulate realistic speckle textures. The simulated images show typical artifacts that make motion tracking in ultrasound challenging. The ground-truth displacement field is available voxelwise and is fully controlled by the electromechanical model. By progressively modifying mechanical and ultrasound parameters, the sensitivity of 3D strain algorithms to pathology and image properties can be evaluated. The proposed pipeline is used to generate an initial library of 8 sequences including healthy and pathological cases, which is made freely accessible to the research community via our project web-page.

A Novel Multiple-Instance Learning-Based Approach to Computer-Aided Detection of Tuberculosis on Chest X-Rays

Abstract: To reach performance levels comparable to human experts, computer-aided detection (CAD) systems are typically optimized following a supervised learning approach that relies on large training databases comprising manually annotated lesions. However, manually outlining those lesions constitutes a difficult and time-consuming process that renders detailedly annotated data difficult to obtain. In this paper, we investigate an alternative approach, namely multiple-instance learning (MIL), that does not require detailed information for optimization. We have applied MIL to a CAD system for tuberculosis detection. Only the case condition (normal or abnormal) was required during training. Based upon the well-known miSVM technique, we propose an improved algorithm that overcomes miSVM’s drawbacks related to positive instance underestimation and costly iteration. To show the advantages of our MIL-based approach as compared with a traditional supervised one, experiments with three X-ray databases were conducted. The area under the receiver operating characteristic curve was utilized as a performance measure. With the first database, for which training lesion annotations were available, our MIL-based method was comparable to the supervised system ( $0.86$ versus $0.88$ ). When evaluating the remaining databases, given their large difference with the previous image set, the most appealing strategy was to retrain the CAD systems. However, since only the case condition was available, only the MIL-based system could be retrained. This scenario, which is common in real-world applications, demonstrates the better adaptation capabilities of the proposed approach. After retraining, our MIL-based system significantly outperformed the supervised one ( $0.86$ versus $0.79$ and $0.91$ versus $0.85$ , $p and $p=0.0002$ , respectively).

Three Dimensional Data-Driven Multi Scale Atomic Representation of Optical Coherence Tomography

Abstract: In this paper, we discuss about applications of different methods for decomposing a signal over elementary waveforms chosen in a family called a dictionary (atomic representations) in optical coherence tomography (OCT). If the representation is learned from the data, a nonparametric dictionary is defined with three fundamental properties of being data-driven, applicability on 3D, and working in multi-scale, which make it appropriate for processing of OCT images. We discuss about application of such representations including complex wavelet based K-SVD, and diffusion wavelets on OCT data. We introduce complex wavelet based K-SVD to take advantage of adaptability in dictionary learning methods to improve the performance of simple dual tree complex wavelets in speckle reduction of OCT datasets in 2D and 3D. The algorithm is evaluated on 144 randomly selected slices from twelve 3D OCTs taken by Topcon 3D OCT-1000 and Cirrus Zeiss Meditec. Improvement of contrast to noise ratio (CNR) (from 0.9 to 11.91 and from 3.09 to 88.9, respectively) is achieved. Furthermore, two approaches are proposed for image segmentation using diffusion. The first method is designing a competition between extended basis functions at each level and the second approach is defining a new distance for each level and clustering based on such distances. A combined algorithm, based on these two methods is then proposed for segmentation of retinal OCTs, which is able to localize 12 boundaries with unsigned border positioning error of $9.22 \pm 3.05 \mu {\hbox {m}}$ , on a test set of 20 slices selected from 13 3D OCTs.

Polyp Detection via Imbalanced Learning and Discriminative Feature Learning

Abstract: Recent achievement of the learning-based classification leads to the noticeable performance improvement in automatic polyp detection. Here, building large good datasets is very crucial for learning a reliable detector. However, it is practically challenging due to the diversity of polyp types, expensive inspection, and labor-intensive labeling tasks. For this reason, the polyp datasets usually tend to be imbalanced, i.e., the number of non-polyp samples is much larger than that of polyp samples, and learning with those imbalanced datasets results in a detector biased toward a non-polyp class. In this paper, we propose a data sampling-based boosting framework to learn an unbiased polyp detector from the imbalanced datasets. In our learning scheme, we learn multiple weak classifiers with the datasets rebalanced by up/down sampling, and generate a polyp detector by combining them. In addition, for enhancing discriminability between polyps and non-polyps that have similar appearances, we propose an effective feature learning method using partial least square analysis, and use it for learning compact and discriminative features. Experimental results using challenging datasets show obvious performance improvement over other detectors. We further prove effectiveness and usefulness of the proposed methods with extensive evaluation.