Median Angular Error Research Articles

A single-layer compton camera for nuclear decommissioning: An improved back-projection algorithm

The decommissioning of nuclear facilities, a critical and hazardous process due to radiation exposure, necessitates the advancement of radiological measurement techniques concerning safety and efficiency. This study presents an optimized back-projection method, integrating a novel single-layer Compton camera and 3D camera setup with the Timepix3 readout chip to improve the precision and efficiency of gamma-ray source localization in decommissioning scenarios. Implementing ‘twin addition’ and ‘twin multiplication’ techniques addressed data ambiguities that arise from event selection in the Compton camera, enhancing the reliability of localization. Introducing a zoom function significantly improved computational efficiency, achieving 163 times faster computation times without sacrificing accuracy. Our method demonstrated enhanced precision with a median angular error of 1.41°, outperforming traditional methods and showing competitive advantages over state-of-the-art technologies, including the Caliste-HD detector. The feasibility of integrating this methodology onto mobile robotic platforms suggests a promising avenue to minimize human radiation exposure and optimize decommissioning tasks, ensuring safer and more effective nuclear facility decommissioning.

Adapting UWB AoA estimation towards unseen environments using transfer learning and data augmentation

Ultra-wideband technology has become increasingly prevalent in localization systems, particularly with the emergence of multi-antenna systems capable of estimating both distance and angle of arrival (AoA) for incoming signals. However, most scientific research analyzes the accuracy of AoA in one specific environment for which the estimator is trained. In this paper, we analyze the performance of various AoA estimation algorithms, such as deep convolutional neural networks (DCNN), multiple signal classification (MUSIC), and phase difference of arrival (PDoA), in unseen environments. Prior work already demonstrated the superior performance of ML for AoA estimation compared to PDoA or MUSIC. We show that MUSIC, PDoA and ML solutions suffer from degradation in unseen environments at the 90th percentile of error, with ML-based AoA estimation degrading by about 14 degrees in unseen environments compared to 4 degrees for PDoA. We demonstrate that while PDoA more effectively corrects AoA at the median level in unseen environments, ML-based methods excel at correcting higher-percentile AoA errors, including outliers. Finally, we propose a novel framework to further improve the correction of AoA outliers for DCNN-based AoA estimators using data augmentation and transfer learning, resulting in a median angular error of only 5 degrees in unseen environments, even considering a field of view up to 90 degrees.

Occluded apples orientation estimator based on deep learning model for robotic harvesting

Apple harvesting robot is in rapid development in the recent years due to the shortage of manual labor. Robotics vision system has been one of the main focus in the development to achieve successful grasping. Information such as the apple orientation is valuable for developing more effective fruit detachment strategies. Occlusions in the orchard environment and the lack of distinct features in an apple has made it challenging to identify the apple orientation. Our study presents a novel approach that aims to estimate the orientation of fruits by projecting 2D information onto a 3D space. This method specifically targets the field of robotic harvesting and leverages multiple well-established and reliable fundamental methods currently available that includes keypoint detection neural network and circle detection based on extracted line segments of occluded apple. Based on the extracted information, a unit vector that represents orientation of the apple can be computed and transformed according to the relative position between the apple and the camera. The proposed method is evaluated using a publicly available 3D point cloud data of 11 apple trees from an orchard farm that was additionally labeled manually with apple orientations. To verify the evaluation results, the proposed method is tested by integrating it into an apple harvesting robot to perform inspection. Results shows that the median angular error in the orchard setting is 17.6° whilst in the lab setting is 14.6°. The experimental results show that the performance of the proposed method is comparable to existing research when under heavy occlusion and thus it is suitable for harvesting robot operating in the orchard farm.

Localization of Low- and High-Frequency Sounds in Cochlear Implant Recipients Using a Contralateral Hearing Aid.

The ability to localize sounds is partly recovered in patients using a cochlear implant (CI) in one ear and a hearing aid (HA) on the contralateral side. Binaural processing seems effective at least to some extent, despite the difference between electric and acoustic stimulation in each ear. To obtain further insights into the mechanisms of binaural hearing in these listeners, localization of low- and high-frequency sounds was tested. The study used a within-subject design, where participants were tasked with localizing sound sources in the horizontal plane. The experiment was conducted in an anechoic chamber, where an array of seven loudspeakers was mounted along the 24 azimuthal angle span from -90° to +90°. Stimuli were applied with different frequencies: broadband noise and high- and low-frequency noise. Ten CI recipients participated in the study. All had an asymmetric hearing loss with a CI in the poorer ear and an HA on the contralateral side. Accuracy of sound localization in terms of angular error and percentage of correct localization scores. The median angular error was 40° in bimodal conditions for both broadband noise and high-frequency noise stimuli. The angular error increased to 47° for low-frequency noise stimuli. In the unilaterally aided condition with an HA, only a median angular error of 78° was observed. Irrespective of the frequency composition of the stimuli, this group of bimodal listeners showed some ability to localize sounds. Angular errors were larger than those reported in the literature for bilateral CI users or single-sided deaf listeners with a CI. In the unilateral listening condition with HA, only localization of sounds was not possible for most subjects.

Toward mechatronic MRI-guided focal laser ablation of the prostate: Robust registration for improved needle delivery.

Multiparametric MRI (mpMRI) is an effective tool for detecting and staging prostate cancer (PCa), guiding interventional therapy, and monitoring PCa treatment outcomes. MRI-guided focal laser ablation (FLA) therapy is an alternative, minimally invasive treatment method to conventional therapies, which has been demonstrated to control low-grade, localized PCa while preserving patient quality of life. The therapeutic success of FLA depends on the accurate placement of needles for adequate delivery of ablative energy to the target lesion. We previously developed an MR-compatible mechatronic system for prostate FLA needle guidance and validated its performance in open-air and clinical 3T in-bore experiments using virtualtargets. To develop a robust MRI-to-mechatronic system registration method and evaluate its in-bore MR-guided needle delivery accuracy in tissue-mimicking prostatephantoms. The improved registration multifiducial assembly houses thirty-six aqueous gadolinium-filled spheres distributed over a 7.3 × 7.3 × 5.2 cm volume. MRI-guided needle guidance accuracy was quantified in agar-based tissue-mimicking prostate phantoms on trajectories (N = 44) to virtual targets covering the mechatronic system's range of motion. 3T gradient-echo recalled (GRE) MRI images were acquired after needle insertions to each target, and the air-filled needle tracks were segmented. Needle guidance error was measured as the shortest Euclidean distance between the target point and the segmented needle trajectory, and angular error was measured as the angle between the targeted trajectory and the segmented needle trajectory. These measurements were made using both the previously designed four-sphere registration fiducial assembly on trajectories (N = 7) and compared with the improved multifiducial assembly using a Mann-Whitney Utest. The median needle guidance error of the system using the improved registration fiducial assembly at a depth of 10 cm was 1.02 mm with an interquartile range (IQR) of 0.42-2.94 mm. The upper limit of the one-sided 95% prediction interval of needle guidance error was 4.13 mm. The median (IQR) angular error was 0.0097 rad (0.0057-0.015rad) with a one-sided 95% prediction interval upper limit of 0.022 rad. The median (IQR) positioning error using the previous four-sphere registration fiducial assembly was 1.87 mm (1.77-2.14mm). This was found to be significantly different (p = 0.0012) from the median (IQR) positioning error of 0.28 mm (0.14-0.95 mm) using the new registration fiducial assembly on the same trajectories. No significant difference was detected between the medians of the angular errors (p = 0.26). This is the first study presenting an improved registration method and validation in tissue-mimicking phantoms of our remotely actuated MR-compatible mechatronic system for delivery of prostate FLA needles. Accounting for the effects of needle deflection, the system was demonstrated to be capable of needle delivery with an error of 4.13 mm or less in 95% of cases under ideal conditions, which is a statistically significant improvement over the previous method. The system will next be validated in a clinicalsetting.

Preclinical evaluation of a prototype freehand drill video guidance system for orthopedic surgery.

Purpose: Internal fixation of pelvic fractures is a challenging task requiring the placement of instrumentation within complex three-dimensional bone corridors, typically guided by fluoroscopy. We report a system for two- and three-dimensional guidance using a drill-mounted video camera and fiducial markers with evaluation in first preclinical studies. Approach: The system uses a camera affixed to a surgical drill and multimodality (optical and radio-opaque) markers for real-time trajectory visualization in fluoroscopy and/or CT. Improvements to a previously reported prototype include hardware components (mount, camera, and fiducials) and software (including a system for detecting marker perturbation) to address practical requirements necessary for translation to clinical studies. Phantom and cadaver experiments were performed to quantify the accuracy of video-fluoroscopy and video-CT registration, the ability to detect marker perturbation, and the conformance in placing guidewires along realistic pelvic trajectories. The performance was evaluated in terms of geometric accuracy and conformance within bone corridors. Results: The studies demonstrated successful guidewire delivery in a cadaver, with a median entry point error of 1.00mm (1.56mm IQR) and median angular error of 1.94deg (1.23deg IQR). Such accuracy was sufficient to guide K-wire placement through five of the six trajectories investigated with a strong level of conformance within bone corridors. The sixth case demonstrated a cortical breach due to extrema in the registration error. The system was able to detect marker perturbations and alert the user to potential registration issues. Feasible workflows were identified for orthopedic-trauma scenarios involving emergent cases (with no preoperative imaging) or cases with preoperative CT. Conclusions: A prototype system for guidewire placement was developed providing guidance that is potentially compatible with orthopedic-trauma workflow. First preclinical (cadaver) studies demonstrated accurate guidance of K-wire placement in pelvic bone corridors and the ability to automatically detect perturbations that degrade registration accuracy. The preclinical prototype demonstrated performance and utility supporting translation to clinical studies.

Sound localisation of low- and high-frequency sounds in cochlear implant users with single-sided deafness

Objective Localisation of low- and high-frequency sounds in single-sided deaf cochlear implant users was investigated using noise stimuli designed to mitigate monaural localisation cues. Design Within subject design. Sound source localisation was tested in the horizontal plane using an array of seven loudspeakers along the azimuthal angle span from −90° to +90°. Stimuli were broadband noise and high- and low-frequency noise. Study sample Twelve adult subjects with single-sided deafness participated in the study. All had normal hearing in the healthy ear and were supplied with a cochlear implant (CI) in their deaf ear. Results With broadband noise, the mean angular localisation error was 39° in aided condition as compared to a median angular error of 83.6° when the speech processor was not worn. For high-frequency noise, the median angular error was 30° and for low-frequency noise, it was 46° in the CI-aided condition. Conclusions Single-sided deaf CI users show the best sound localisation for high-frequency sounds. This supports the view that interaural level differences are dominant for sound localisation in these listeners. Nonetheless, a limited ability to localise low-frequency sounds was observed, which may be based on the supportive perception of interaural time differences.

Computer-assisted contralateral side comparison of the ankle joint using flat panel technology

PurposeReduction and osteosynthesis of ankle fractures is a challenging surgical procedure when it comes to the verification of the reduction result. Evaluation is conducted using intra-operative imaging of the injured ankle and depends on the expertise of the surgeon. Studies suggest that intra-individual variance of the ankle bone shape and pose is considerably lower than the inter-individual variance. It stands to reason that the information gain from the healthy contralateral side can help to improve the evaluation.MethodIn this paper, an assistance system is proposed that provides a side-to-side view of the two ankle joints for visual comparison and instant evaluation using only one 3D C-arm image. Two convolutional neural networks (CNN) are employed to extract the relevant image regions and pose information of each ankle so that they can be aligned with each other. A first U-Net uses a sliding window to predict the location of each ankle. The standard plane estimation is formulated as segmentation problem so that a second U-Net predicts the three viewing planes for alignment.ResultsExperiments were conducted to assess the accuracy of the individual steps on 218 unilateral ankle datasets as well as the overall performance on 7 bilateral ankle datasets. The experiments on unilateral ankles yield a median position-to-plane error of 0.73pm 1.36 mm and a median angular error between 2.98^circ and 3.71^circ for the plane normals.ConclusionStandard plane estimation via segmentation outperforms direct pose regression. Furthermore, the complete pipeline was evaluated including ankle detection and subsequent plane estimation on bilateral datasets. The proposed pipeline enables a direct contralateral side comparison without additional radiation. This has the potential to ease and improve the intra-operative evaluation for the surgeons in the future and reduce the need for revision surgery.

Iterative Convolutional Neural Network-Based Illumination Estimation

In the image processing pipelines of digital cameras, one of the first steps is to achieve invariance in terms of scene illumination, namely computational color constancy. Usually, this is done in two successive steps which are illumination estimation and chromatic adaptation. The illumination estimation aims at estimating a three-dimensional vector from image pixels. This vector represents the scene illumination, and it is used in the chromatic adaptation step, which aims at eliminating the bias in image colors caused by the color of the illumination. An accurate illumination estimation is crucial for successful computational color constancy. However, this is an ill-posed problem, and many methods try to comprehend it with different assumptions. In this paper, an iterative method for estimating the scene illumination color is proposed. The method calculates the illumination vector by a series of intermediate illumination estimations and chromatic adaptations of an input image using a convolutional neural network. The network has been trained to iteratively compute intermediate incremental illumination estimates from the original image. Incremental illumination estimates are combined by per element multiplication to obtain the final illumination estimation. The approach is aimed to reduce large estimation errors usually occurring with highly saturated light sources. Experimental results show that the proposed method outperforms the vast majority of illumination estimation methods in terms of median angular error. Moreover, in terms of worst-performing samples, i.e., the samples for which a method errs the most, the proposed method outperforms all other methods by a margin of more than 18% with respect to the mean of estimation errors in the third quartile.

Deep learning segmentation of general interventional tools in two-dimensional ultrasound images.

Many interventional procedures require the precise placement of needles or therapy applicators (tools) to correctly achieve planned targets for optimal diagnosis or treatment of cancer, typically leveraging the temporal resolution of ultrasound (US) to provide real-time feedback. Identifying tools in two-dimensional (2D) images can often be time-consuming with the precise position difficult to distinguish. We have developed and implemented a deep learning method to segment tools in 2D US images in near real-time for multiple anatomical sites, despite the widely varying appearances across interventional applications. A U-Net architecture with a Dice similarity coefficient (DSC) loss function was used to perform segmentation on input images resized to 256×256pixels. The U-Net was modified by adding 50% dropouts and the use of transpose convolutions in the decoder section of the network. The proposed approach was trained with 917 images and manual segmentations from prostate/gynecologic brachytherapy, liver ablation, and kidney biopsy/ablation procedures, as well as phantom experiments. Real-time data augmentation was applied to improve generalizability and doubled the dataset for each epoch. Postprocessing to identify the tool tip and trajectory was performed using two different approaches, comparing the largest island with a linear fit to random sample consensus (RANSAC) fitting. Comparing predictions from 315 unseen test images to manual segmentations, the overall median [first quartile, third quartile] tip error, angular error, and DSC were 3.5 [1.3, 13.5] mm, 0.8 [0.3, 1.7]°, and 73.3 [56.2, 82.3]%, respectively, following RANSAC postprocessing. The predictions with the lowest median tip and angular errors were observed in the gynecologic images (median tip error: 0.3mm; median angular error: 0.4°) with the highest errors in the kidney images (median tip error: 10.1mm; median angular error: 2.9°). The performance on the kidney images was likely due to a reduction in acoustic signal associated with oblique insertions relative to the US probe and the increased number of anatomical interfaces with similar echogenicity. Unprocessed segmentations were performed with a mean time of approximately 50ms per image. We have demonstrated that our proposed approach can accurately segment tools in 2D US images from multiple anatomical locations and a variety of clinical interventional procedures in near real-time, providing the potential to improve image guidance during a broad range of diagnostic and therapeutic cancer interventions.

DeepSymmetry: using 3D convolutional networks for identification of tandem repeats and internal symmetries in protein structures.

Thanks to the recent advances in structural biology, nowadays 3D structures of various proteins are solved on a routine basis. A large portion of these structures contain structural repetitions or internal symmetries. To understand the evolution mechanisms of these proteins and how structural repetitions affect the protein function, we need to be able to detect such proteins very robustly. As deep learning is particularly suited to deal with spatially organized data, we applied it to the detection of proteins with structural repetitions. We present DeepSymmetry, a versatile method based on 3D convolutional networks that detects structural repetitions in proteins and their density maps. Our method is designed to identify tandem repeat proteins, proteins with internal symmetries, symmetries in the raw density maps, their symmetry order and also the corresponding symmetry axes. Detection of symmetry axes is based on learning 6D Veronese mappings of 3D vectors, and the median angular error of axis determination is less than one degree. We demonstrate the capabilities of our method on benchmarks with tandem-repeated proteins and also with symmetrical assemblies. For example, we have discovered about 7800 putative tandem repeat proteins in the PDB. The method is available at https://team.inria.fr/nano-d/software/deepsymmetry. It consists of a C++ executable that transforms molecular structures into volumetric density maps, and a Python code based on the TensorFlow framework for applying the DeepSymmetry model to these maps. Supplementary data are available at Bioinformatics online.

Reconstructing Human Joint Motion with Computational Fabrics

Accurate and continuous monitoring of joint rotational motion is crucial for a wide range of applications such as physical rehabilitation [6, 85] and motion training [22, 54, 68]. Existing motion capture systems, however, either need instrumentation of the environment, or fail to track arbitrary joint motion, or impose wearing discomfort by requiring rigid electrical sensors right around the joint area. This work studies the use of everyday fabrics as a flexible and soft sensing medium to monitor joint angular motion accurately and reliably. Specifically we focus on the primary use of conductive stretchable fabrics to sense the skin deformation during joint motion and infer the joint rotational angle. We tackle challenges of fabric sensing originated by the inherent properties of elastic materials by leveraging two types of sensing fabric and characterizing their properties based on models in material science. We apply models from bio-mechanics to infer joint angles and propose the use of dual strain sensing to enhance sensing robustness against user diversity and fabric position offsets. We fabricate prototypes using off-the-shelf fabrics and micro-controller. Experiments with ten participants show 9.69° median angular error in tracking joint angle and its sensing robustness across various users and activities.

A novel approach for detecting the horizon using a convolutional neural network and multi-scale edge detection

This paper proposes a novel method for horizon detection that combines a multi-scale approach and a convolutional neural network (CNN). The ability to detect the horizon is the first step toward situational awareness of autonomous ships, which have recently attracted interest, and greatly affects the performance of subsequent steps and that of the overall system. Since typical approaches for horizon detection mainly use edge information, two challenging issues need to be overcome: non-stability of edge detection and complex maritime scenes. The proposed method first detects line features by combining edge information from the various scales to reduce the computational time while mitigating the non-stability of edge detection. Subsequently, CNN is used to verify the edge pixels belonging to the horizon to process complex maritime scenes that contain line features similar to the horizon and changes in the sea status. Finally, linear curve fitting along with median filtering are iteratively used to estimate the horizon line accurately. We compared the performance of the proposed method with state-of-the-art methods using the largest database publicly available. The experimental results showed that the accuracy with which the proposed method can identify the horizon is superior to that of state-of-the-art methods. Our method has a median positional error of less than 1.7 pixels from the center of the horizon and a median angular error of approximately 0.1 $$^{\circ }$$ . Further, our results showed that our method is the only one capable of detecting the horizon at high speed with high accuracy, which is attractive for practical applications.

MuSCoWERT: multi-scale consistence of weighted edge Radon transform for horizon detection in maritime images.

This paper addresses the problem of horizon detection, a fundamental process in numerous object detection algorithms, in a maritime environment. The maritime environment is characterized by the absence of fixed features, the presence of numerous linear features in dynamically changing objects and background and constantly varying illumination, rendering the typically simple problem of detecting the horizon a challenging one. We present a novel method called multi-scale consistence of weighted edge Radon transform, abbreviated as MuSCoWERT. It detects the long linear features consistent over multiple scales using multi-scale median filtering of the image followed by Radon transform on a weighted edge map and computing the histogram of the detected linear features. We show that MuSCoWERT has excellent performance, better than seven other contemporary methods, for 84 challenging maritime videos, containing over 33,000 frames, and captured using visible range and near-infrared range sensors mounted onboard, onshore, or on floating buoys. It has a median error of about 2 pixels (less than 0.2%) from the center of the actual horizon and a median angular error of less than 0.4 deg. We are also sharing a new challenging horizon detection dataset of 65 videos of visible, infrared cameras for onshore and onboard ship camera placement.

Color constancy by combining low-mid-high level image cues

In general, computational methods to estimate the color of the light source are based on single, low-level image cues such as pixel values and edges. Only a few methods are proposed exploiting multiple cues for color constancy by incorporating pixel values, edge information and higher-order image statistics. However, expanding color constancy beyond these low-level image statistics (pixels, edges and n-jets) to include high-level cues and integrate all these cues together into a unified framework has not been explored.In this paper, the color of the light source is estimated using (low-level) image statistics, (intermediate-level) regions, and (high-level) scene characteristics. A Bayesian framework is proposed combining the different cues in a principled way.Our experiments show that the proposed algorithm outperforms the original Bayesian method. The mean error is reduced by 33.3% with respect to the original Bayesian method and the median error is reduced by 37.1% on the re-processed version of the Gehler color constancy dataset. Our method outperforms most of the state-of-the-art color constancy algorithms in mean angular error and obtains the highest accuracy in terms of median angular error.

Color constancy using 3D scene geometry derived from a single image.

The aim of color constancy is to remove the effect of the color of the light source. As color constancy is inherently an ill-posed problem, most of the existing color constancy algorithms are based on specific imaging assumptions (e.g., gray-world and white patch assumption). In this paper, 3D geometry models are used to determine which color constancy method to use for the different geometrical regions (depth/layer) found in images. The aim is to classify images into stages (rough 3D geometry models). According to stage models, images are divided into stage regions using hard and soft segmentation. After that, the best color constancy methods are selected for each geometry depth. To this end, we propose a method to combine color constancy algorithms by investigating the relation between depth, local image statistics, and color constancy. Image statistics are then exploited per depth to select the proper color constancy method. Our approach opens the possibility to estimate multiple illuminations by distinguishing nearby light source from distant illuminations. Experiments on state-of-the-art data sets show that the proposed algorithm outperforms state-of-the-art single color constancy algorithms with an improvement of almost 50% of median angular error. When using a perfect classifier (i.e, all of the test images are correctly classified into stages); the performance of the proposed method achieves an improvement of 52% of the median angular error compared with the best-performing single color constancy algorithm.

Improving Edge based Color Constancy using Grid based Sampling

Color constancy refers to stable psychological tendency in perception even the lighting circumstances changed and it plays an important role in many computer vision applications. Color constancy is the ability to measure the impact of light onto a digital image independent of the color of the light source. Many color constancy algorithms for estimating the color of the light source, are developed so far but all the existing algorithm are based on single light source i.e. they consider that an image is affected by only one light source or single uniform illumination, which is not the case every time, because an image may be affected with more than one illuminations. The illusion of single light source is now violated by multiple sources of light. In this paper, we will discuss a new method which considers that an image is affected by multiple sources of light, without any clue about the color of the light sources. Grid based sampling technique along with Grey Edge algorithm is used to estimate the color of multiple light sources. The use of Bilateral Filter after applying color correction is giving most promising results and it has provided the consistency of this algorithm over different types of images taken from different datasets. Experimental and visual results show that the proposed method achieves much better results than existing methods for color constancy. The qualitative results are tested over some well known parameters i.e. Median Angular Error (MAE), Peak Signal to Noise Ratio (PSNR) etc.

Improving Color Constancy by Photometric Edge Weighting

Edge-based color constancy methods make use of image derivatives to estimate the illuminant. However, different edge types exist in real-world images, such as material, shadow, and highlight edges. These different edge types may have a distinctive influence on the performance of the illuminant estimation. Therefore, in this paper, an extensive analysis is provided of different edge types on the performance of edge-based color constancy methods. First, an edge-based taxonomy is presented classifying edge types based on their photometric properties (e.g., material, shadow-geometry, and highlights). Then, a performance evaluation of edge-based color constancy is provided using these different edge types. From this performance evaluation, it is derived that specular and shadow edge types are more valuable than material edges for the estimation of the illuminant. To this end, the (iterative) weighted Gray-Edge algorithm is proposed in which these edge types are more emphasized for the estimation of the illuminant. Images that are recorded under controlled circumstances demonstrate that the proposed iterative weighted Gray-Edge algorithm based on highlights reduces the median angular error with approximately 25 percent. In an uncontrolled environment, improvements in angular error up to 11 percent are obtained with respect to regular edge-based color constancy.

Accuracy and diagnostic yield of CT-guided stereotactic liver biopsy of primary and secondary liver tumors

Objective: CT-guided biopsy still plays a decisive role in the management of liver tumors, especially if the lesions are not visible or accessible by ultrasound. As CT-guided stereotaxy appears to be a very accurate targeting technique, the aim of this study was to evaluate the targeting accuracy, diagnostic yield, and complications of CT-guided stereotactic liver biopsy of primary and secondary liver tumors.Methods and Materials: Prior to stereotactic liver biopsy, patients under general anesthesia were immobilized using a vacuum cushion. Respiratory motion was controlled by temporary disconnections of the endotracheal tube. An optical-based navigation system was used for 3D trajectory planning and placement of a 15-G coaxial needle via a stereotactic aiming device. The histological samples were obtained using a 16-G Tru-Cut™ biopsy needle system. For evaluation of targeting accuracy the control CT image with the needles in place was fused with the planning CT image. The lateral error at the tip and skin entry point and the angular error were calculated. In addition, the skin-to-liver-surface (SL) distance, the needle-to-liver-surface (NL) angle, and the presence of liver cirrhosis were evaluated. The diagnostic yield was evaluated by histological reports from the institutional pathologists.Results: The median lateral error was 2.5 mm (range: 0–6.5 mm) at the needle entry point and 3.2 mm (range: 0.01–9.4 mm) at the needle tip. The median angular error was 1.06° (range: 0–6.64°). Liver cirrhosis, NL angle and SL distance showed no significant impact on the targeting accuracy. Forty-five of the 46 liver biopsies (97.8%) were diagnostic according to the histological reports. No puncture-related complications such as bleeding or perforation of intestinal organs or lung tissue were recorded.

Color Constancy Using Natural Image Statistics and Scene Semantics

Existing color constancy methods are all based on specific assumptions such as the spatial and spectral characteristics of images. As a consequence, no algorithm can be considered as universal. However, with the large variety of available methods, the question is how to select the method that performs best for a specific image. To achieve selection and combining of color constancy algorithms, in this paper natural image statistics are used to identify the most important characteristics of color images. Then, based on these image characteristics, the proper color constancy algorithm (or best combination of algorithms) is selected for a specific image. To capture the image characteristics, the Weibull parameterization (e.g., grain size and contrast) is used. It is shown that the Weibull parameterization is related to the image attributes to which the used color constancy methods are sensitive. An MoG-classifier is used to learn the correlation and weighting between the Weibull-parameters and the image attributes (number of edges, amount of texture, and SNR). The output of the classifier is the selection of the best performing color constancy method for a certain image. Experimental results show a large improvement over state-of-the-art single algorithms. On a data set consisting of more than 11,000 images, an increase in color constancy performance up to 20 percent (median angular error) can be obtained compared to the best-performing single algorithm. Further, it is shown that for certain scene categories, one specific color constancy algorithm can be used instead of the classifier considering several algorithms.