Procesamiento de imágenes cerebrales en GPU

Abstract: As time has passed, the general purpose programming paradigm has evolved, producing different hardware architectures whose characteristics differ widely. In this work, we are going to demonstrate, through different applications belonging to the field of Image Processing, the existing difference between three Nvidia hardware platforms: two of them belong to the GeForce graphics cards series, the GTX 480 and the GTX 980 and one of the low consumption platforms which purpose is to allow the execution of embedded applications as well as providing an extreme efficiency: the Jetson TK1. With respect to the test applications we will use five examples from Nvidia CUDA Samples. These applications are directly related to Image Processing, as the algorithms they use are similar to those from the field of medical image registration. After the tests, it will be proven that GTX 980 is both the device with the highest computational power and the one that has greater consumption, it will be seen that Jetson TK1 is the most efficient platform, it will be shown that GTX 480 produces more heat than the others and we will learn other effects produced by the existing difference between the architecture of the devices.

Multimodal Registration Procedure for the Initial Spatial Alignment of a Retinal Video Sequence to a Retinal Composite Image

Accurate placement of lesions is crucial for the effectiveness and safety of a retinal laser photocoagulation treatment. Computer assistance provides the capability for improvements to treatment accuracy and execution time. The idea is to use video frames acquired from a scanning digital ophthalmoscope (SDO) to compensate for retinal motion during laser treatment. This paper presents a method for the multimodal registration of the initial frame from an SDO retinal video sequence to a retinal composite image, which may contain a treatment plan. The retinal registration procedure comprises the following steps: 1) detection of vessel centerline points and identification of the optic disc; 2) prealignment of the video frame and the composite image based on optic disc parameters; and 3) iterative matching of the detected vessel centerline points in expanding matching regions. This registration algorithm was designed for the initialization of a real-time registration procedure that registers the subsequent video frames to the composite image. The algorithm demonstrated its capability to register various pairs of SDO video frames and composite images acquired from patients.

Multimodal target correction by local bone registration: a PET/CT evaluation

PET/CT guidance for percutaneous interventions allows biopsy of suspicious metabolically active bone lesions even when no morphological correlation is delineable in the CT images. Clinical use of PET/CT guidance with conventional step-by-step technique is time consuming and complicated especially in cases in which the target lesion is not shown in the CT image. Our recently developed multimodal instrument guidance system (IGS) for PET/CT improved this situation. Nevertheless, bone biopsies even with IGS have a trade-off between precision and intervention duration which is proportional to patient and personnel exposure to radiation. As image acquisition and reconstruction of PET may take up to 10 minutes, preferably only one time consuming combined PET/CT acquisition should be needed during an intervention. In case of required additional control images in order to check for possible patient movements/deformations, or to verify the final needle position in the target, only fast CT acquisitions should be performed. However, for precise instrument guidance accounting for patient movement and/or deformation without having a control PET image, it is essential to be able to transfer the position of the target as identified in the original PET/CT to a changed situation as shown in the control CT.

Surface registration from range image fusion

The registration of full 3-D models is an important task in computer vision. Range finders only reconstruct a partial view of the object. Many authors have proposed several techniques to register 3D surfaces from multiple views in which there are basically two aspects to consider. First, poor registration in which some sort of correspondences are established. Second, accurate registration in order to obtain a better solution. A survey of the most common techniques is presented and includes experimental results of some of them

Multimodal evaluation for medical image segmentation

This paper is a joint effort between five institutionsthat introduces several novel similarity measures andcombines them to carry out a multimodal segmentationevaluation. The new similarity measures proposed arebased on the location and the intensity values of themisclassified voxels as well as on the connectivity andthe boundaries of the segmented data. We showexperimentally that the combination of these measuresimprove the quality of the evaluation. The study that weshow here has been carried out using four differentsegmentation methods from four different labs applied toa MRI simulated dataset of the brain. We claim that ournew measures improve the robustness of the evaluation andprovides better understanding about the differencebetween segmentation methods.

Model-based Segmentation and Image Fusion of 3D Computed Tomography and 3D Ultrasound of the Eye for Radiotherapy Planning

For radiotherapy treatment planning of retinoblastoma inchildhood, Computed Tomography (CT) represents thestandard method for tumor volume delineation, despitesome inherent limitations. CT scan is very useful inproviding information on physical density for dosecalculation and morphological volumetric information butpresents a low sensitivity in assessing the tumorviability. On the other hand, 3D ultrasound (US) allows ahigh accurate definition of the tumor volume thanks toits high spatial resolution but it is not currentlyintegrated in the treatment planning but used only fordiagnosis and follow-up. Our ultimate goal is anautomatic segmentation of gross tumor volume (GTV) in the3D US, the segmentation of the organs at risk (OAR) inthe CT and the registration of both. In this paper, wepresent some preliminary results in this direction. Wepresent 3D active contour-based segmentation of the eyeball and the lens in CT images; the presented approachincorporates the prior knowledge of the anatomy by usinga 3D geometrical eye model. The automated segmentationresults are validated by comparing with manualsegmentations. Then, for the fusion of 3D CT and USimages, we present two approaches: (i) landmark-basedtransformation, and (ii) object-based transformation thatmakes use of eye ball contour information on CT and USimages.

Image Segmentation Using Information Bottleneck Method

In image processing, segmentation algorithms constitute one of the main focuses of research. In this paper, new image segmentation algorithms based on a hard version of the information bottleneck method are presented. The objective of this method is to extract a compact representation of a variable, considered the input, with minimal loss of mutual information with respect to another variable, considered the output. First, we introduce a split-and-merge algorithm based on the definition of an information channel between a set of regions (input) of the image and the intensity histogram bins (output). From this channel, the maximization of the mutual information gain is used to optimize the image partitioning. Then, the merging process of the regions obtained in the previous phase is carried out by minimizing the loss of mutual information. From the inversion of the above channel, we also present a new histogram clustering algorithm based on the minimization of the mutual information loss, where now the input variable represents the histogram bins and the output is given by the set of regions obtained from the above split-and-merge algorithm. Finally, we introduce two new clustering algorithms which show how the information bottleneck method can be applied to the registration channel obtained when two multimodal images are correctly aligned. Different experiments on 2-D and 3-D images show the behavior of the proposed algorithms

Articulated Model Registration of MRI/X-Ray Spine Data

This paper presents a method based on articulated models for the registration of spine data extracted from multimodal medical images of patients with scoliosis. With the ultimate aim being the development of a complete geometrical model of the torso of a scoliotic patient, this work presents a method for the registration of vertebral column data using 3D magnetic resonance images (MRI) acquired in prone position and X-ray data acquired in standing position for five patients with scoliosis. The 3D shape of the vertebrae is estimated from both image modalities for each patient, and an articulated model is used in order to calculate intervertebral transformations required in order to align the vertebrae between both postures. Euclidean distances between anatomical landmarks are calculated in order to assess multimodal registration error. Results show a decrease in the Euclidean distance using the proposed method compared to rigid registration and more physically realistic vertebrae deformations compared to thin-plate-spline (TPS) registration thus improving alignment.

Surface registration from range image fusion

The registration of full 3-D models is an important task in computer vision. Range finders only reconstruct a partial view of the object. Many authors have proposed several techniques to register 3D surfaces from multiple views in which there are basically two aspects to consider. First, poor registration in which some sort of correspondences are established. Second, accurate registration in order to obtain a better solution. A survey of the most common techniques is presented and includes experimental results of some of them

Image Segmentation Using Information Bottleneck Method

In image processing, segmentation algorithms constitute one of the main focuses of research. In this paper, new image segmentation algorithms based on a hard version of the information bottleneck method are presented. The objective of this method is to extract a compact representation of a variable, considered the input, with minimal loss of mutual information with respect to another variable, considered the output. First, we introduce a split-and-merge algorithm based on the definition of an information channel between a set of regions (input) of the image and the intensity histogram bins (output). From this channel, the maximization of the mutual information gain is used to optimize the image partitioning. Then, the merging process of the regions obtained in the previous phase is carried out by minimizing the loss of mutual information. From the inversion of the above channel, we also present a new histogram clustering algorithm based on the minimization of the mutual information loss, where now the input variable represents the histogram bins and the output is given by the set of regions obtained from the above split-and-merge algorithm. Finally, we introduce two new clustering algorithms which show how the information bottleneck method can be applied to the registration channel obtained when two multimodal images are correctly aligned. Different experiments on 2-D and 3-D images show the behavior of the proposed algorithms

Multimodal augmented reality system for surgical microscopy

Image-guided, computer-assisted neurosurgery has emerged to improve localization and targeting, to provide a better anatomic definition of the surgical field, and to decrease invasiveness. Usually, in image-guided surgery, a computer displays the surgical field in a CT/MR environment, using axial, coronal or sagittal views, or even a 3D representation of the patient. Such a system forces the surgeon to look away from the surgical scene to the computer screen. Moreover, this kind of information, being pre-operative imaging, can not be modified during the operation, so it remains valid for guidance in the first stage of the surgical procedure, and mainly for rigid structures like bones. In order to solve the two constraints mentioned before, we are developing an ultrasoundguided surgical microscope. Such a system takes the advantage that surgical microscopy and ultrasound systems are already used in neurosurgery, so it does not add more complexity to the surgical procedure. We have integrated an optical tracking device in the microscope and an augmented reality overlay system with which we avoid the need to look away from the scene, providing correctly aligned surgical images with sub-millimeter accuracy. In addition to the standard CT and 3D views, we are able to track an ultrasound probe, and using a previous calibration and registration of the imaging, the image obtained is correctly projected to the overlay system, so the surgeon can always localize the target and verify the effects of the intervention. Several tests of the system have been already performed to evaluate the accuracy, and clinical experiments are currently in progress in order to validate the clinical usefulness of the system.

Stochastic rank correlation: a robust merit function for 2D/3D registration of image data obtained at different energies

In this article, the authors evaluate a merit function for 2D/3D registration called stochastic rank correlation (SRC). SRC is characterized by the fact that differences in image intensity do not influence the registration result; it therefore combines the numerical advantages of cross correlation (CC)-type merit functions with the flexibility of mutual-information-type merit functions. The basic idea is that registration is achieved on a random subset of the image, which allows for an efficient computation of Spearman's rank correlation coefficient. This measure is, by nature, invariant to monotonic intensity transforms in the images under comparison, which renders it an ideal solution for intramodal images acquired at different energy levels as encountered in intrafractional kV imaging in image-guided radiotherapy. Initial evaluation was undertaken using a 2D/3D registration reference image dataset of a cadaver spine. Even with no radiometric calibration, SRC shows a significant improvement in robustness and stability compared to CC. Pattern intensity, another merit function that was evaluated for comparison, gave rather poor results due to its limited convergence range. The time required for SRC with 5% image content compares well to the other merit functions; increasing the image content does not significantly influence the algorithm accuracy. The authors conclude that SRC is a promising measure for 2D/3D registration in IGRT and image-guided therapy in general.