Target Histogram Research Articles

Inversion géostatistique par itérations de la tomographie de résistivité électrique

AbstractElectrical resistivity tomography (ERT) is a geophysical method used to create an image of the subsurface due to its sensitivity to porosity, water saturation, and pore fluid salinity. This geophysical method has been widely applied in the investigation of mineral and groundwater resources, as well as in archaeological, environmental, and engineering studies. The prediction of subsurface properties, such as electrical conductivity, from measured ERT data requires solving a challenging geophysical inversion problem. This work proposes an iterative geostatistical resistivity inversion method using stochastic sequential simulation and co-simulation as stochastic model perturbation and update techniques. Electrical resistivity models are generated conditioned to a target histogram, often retrieved from available resistivity borehole data, and assuming a spatial continuity pattern described by a variogram model. From the electrical resistivity models, a finite-volume approximation of Poisson’s equation is used to compute synthetic ERT data. The misfit between predicted and observed data drives the convergence of an iterative procedure and conditions the co-simulation of new models in the subsequent iterations. This methodology is applied to a two-dimensional synthetic case, and a set of two-dimensional profiles obtained from an ERT survey carried out in southern Portugal. In both application examples, the final models predict ERT data that match the observed ones while reproducing borehole data and imposed variogram models. The results obtained in both data sets are compared against a commercial deterministic ERT inversion methodology, showing the ability of the proposed method to model small-scale variability and assess spatial uncertainty.

Local Contrast-Based Pixel Ordering for Exact Histogram Specification.

Histogram equalization is one of the basic image processing tasks for contrast enhancement, and its generalized version is histogram specification, which accepts arbitrary shapes of target histograms including uniform distributions for histogram equalization. It is well known that strictly ordered pixels in an image can be voted to any target histogram to achieve exact histogram specification. This paper proposes a method for ordering pixels in an image on the basis of the local contrast of each pixel, where a Gaussian filter without approximation is used to avoid the duplication of pixel values that disturbs the strict pixel ordering. The main idea of the proposed method is that the problem of pixel ordering is divided into small subproblems which can be solved separately, and then the results are merged into one sequence of all ordered pixels. Moreover, the proposed method is extended from grayscale images to color ones in a consistent manner. Experimental results show that the state-of-the-art histogram specification method occasionally produces false patterns, which are alleviated by the proposed method. Those results demonstrate the effectiveness of the proposed method for exact histogram specification.

Methods to Increase the Contrast of the Image with Preserving the Visual Quality

Contrast enhancement is a technique for increasing the contrast of an image to obtain better image quality. As many existing contrast enhancement algorithms typically add too much contrast to an image, maintaining visual quality should be considered as a part of enhancing image contrast. This paper focuses on a contrast enhancement method that is based on histogram transformations to improve contrast and uses image quality assessment to automatically select the optimal target histogram. Improvements in contrast and preservation of visual quality are taken into account in the target histogram, so this method avoids the problem of excessive increase in contrast. In the proposed method, the optimal target histogram is the weighted sum of the original histogram, homogeneous histogram and Gaussian histogram. Structural and statistical metrics of “naturalness of the image” are used to determine the weights of the corresponding histograms. Contrast images are obtained by matching the optimal target histogram. Experiments show that the proposed method gives better results compared to other existing algorithms for increasing contrast based on the transformation of histograms.

A novel unsupervised approach based on the hidden features of Deep Denoising Autoencoders for COVID-19 disease detection

Chest imaging can represent a powerful tool for detecting the Coronavirus disease 2019 (COVID-19). Among the available technologies, the chest Computed Tomography (CT) scan is an effective approach for reliable and early detection of the disease. However, it could be difficult to rapidly identify by human inspection anomalous area in CT images belonging to the COVID-19 disease. Hence, it becomes necessary the exploitation of suitable automatic algorithms able to quick and precisely identify the disease, possibly by using few labeled input data, because large amounts of CT scans are not usually available for the COVID-19 disease. The method proposed in this paper is based on the exploitation of the compact and meaningful hidden representation provided by a Deep Denoising Convolutional Autoencoder (DDCAE). Specifically, the proposed DDCAE, trained on some target CT scans in an unsupervised way, is used to build up a robust statistical representation generating a target histogram. A suitable statistical distance measures how this target histogram is far from a companion histogram evaluated on an unknown test scan: if this distance is greater of a threshold, the test image is labeled as anomaly, i.e. the scan belongs to a patient affected by COVID-19 disease. Some experimental results and comparisons with other state-of-the-art methods show the effectiveness of the proposed approach reaching a top accuracy of 100% and similar high values for other metrics. In conclusion, by using a statistical representation of the hidden features provided by DDCAEs, the developed architecture is able to differentiate COVID-19 from normal and pneumonia scans with high reliability and at low computational cost.

A Histogram-Based Low-Complexity Approach for the Effective Detection of COVID-19 Disease from CT and X-ray Images

The global COVID-19 pandemic certainly has posed one of the more difficult challenges for researchers in the current century. The development of an automatic diagnostic tool, able to detect the disease in its early stage, could undoubtedly offer a great advantage to the battle against the pandemic. In this regard, most of the research efforts have been focused on the application of Deep Learning (DL) techniques to chest images, including traditional chest X-rays (CXRs) and Computed Tomography (CT) scans. Although these approaches have demonstrated their effectiveness in detecting the COVID-19 disease, they are of huge computational complexity and require large datasets for training. In addition, there may not exist a large amount of COVID-19 CXRs and CT scans available to researchers. To this end, in this paper, we propose an approach based on the evaluation of the histogram from a common class of images that is considered as the target. A suitable inter-histogram distance measures how this target histogram is far from the histogram evaluated on a test image: if this distance is greater than a threshold, the test image is labeled as anomaly, i.e., the scan belongs to a patient affected by COVID-19 disease. Extensive experimental results and comparisons with some benchmark state-of-the-art methods support the effectiveness of the developed approach, as well as demonstrate that, at least when the images of the considered datasets are homogeneous enough (i.e., a few outliers are present), it is not really needed to resort to complex-to-implement DL techniques, in order to attain an effective detection of the COVID-19 disease. Despite the simplicity of the proposed approach, all the considered metrics (i.e., accuracy, precision, recall, and F-measure) attain a value of 1.0 under the selected datasets, a result comparable to the corresponding state-of-the-art DNN approaches, but with a remarkable computational simplicity.

Optimized histogram computation model using cuckoo search for color image contrast distortion

This paper proposes a novel optimized histogram modification framework using a cuckoo search (CS) algorithm for brightness preserved contrast enhancement. The histogram modification has been modeled as an optimization problem and the CS algorithm is used to find an optimum solution. The proposed method's chief objective is to find a fair tradeoff between contrast improvement and mean-brightness preservation. A new target histogram has been generated using the CS algorithm using a target function composed of tuning parameters. The extent of the image contrast range can be adjusted by selecting appropriately designed tuning parameters. The proposed technique can control the enhancement with the values chosen to fix the enhancement level and retain the enhanced image features. Finally, the optimized histogram generated from the CS algorithm is employed in the histogram equalization (HE) process to generate the final enhanced image. Its performance is validated with qualitative and quantitative assessment against well-known state-of-the-art techniques.

FPGA Implementation of Real-Time Pedestrian Detection Using Normalization-Based Validation of Adaptive Features Clustering

Presently, many researchers and engineers have investigated autonomous driving, which has significantly influenced the revolution of artificial intelligence (AI). One of the critical challenges for autonomous driving is the inadequate precision of autonomous vehicles in detecting pedestrians, which is a major safety hazard to human beings. In this paper,a Field Programmable Gate Array (FPGA) demonstration system with a normalization-based validity index (NbVI) has been proposed for real-time pedestrian detection. The proposed algorithm can accurately detect pedestrians by calculating the Manhattan distance between the target histogram of oriented gradient (HOG) features and real-time pedestrian HOG features. In lieu of sophisticated circuit layout and substantial training burden with neuron computation circuit, the proposed detection system with adaptive features clustering is hardware-friendly and is capable of real-time pedestrian detection using fewer training images with high detection rate (up to 99.2%). Moreover, the function execution time of pedestrian detection is shortened by 25% using FPGA acceleration.

Convolutional neural network-based dosimetry evaluation of esophageal radiation treatment planning.

A dosimetry evaluation model for treatment planning of esophageal radiation therapy is developed using a deep learning model. The model predicts dose volume histogram (DVH) from distance to target histogram (DTH) based on stacked de-noise auto-encoder (SDAE) and one-dimensional convolutional network (1D-CN). First, SDAE is used to extract the features from the curves of DTH and DVH. Then 1D-CN model is employed to learn the relationship between the features of DTH and DVH, and later used to predict the features of DVH from the features of DTH. Finally, the curve of DVH is restored from the features of DVH based on SDAE. Two hundred and seventy treatment plans are used for training 1D-CN and another sixty-three treatment plans are used for evaluating this model. This method is also compared with another two popular prediction methods based on support vector machine (SVM) and U-net. Based on the experimental result, the proposed model achieves the lowest dose endpoint error comparing to the other models. The average prediction error on planned target volume, left lung, right lung, heart, and spinal cord is 2.94% for the proposed model, while the average prediction errors are 6.79% and 3.41% for SVM and U-net, respectively. A dosimetry evaluation method based on SDAE and 1D-CN is developed in characterizing the correlation relationship between DTH and DVH of treatment plans. The results show that the model could be trained more efficiently in this framework and the DVH could be predicted with higher accuracy comparing to those existing methods. It provides a useful tool in supporting automated treatment planning of esophageal intensity-modulated radiotherapy.

Informed Histogram-Based Watermarking

The existing works on histogram-based watermark embedding share the common notions of non-informed random host sample selection and uniform embedding, resulting in limited and yet similar performances. This letter develops two methods to improve imperceptibility and robustness of histogram-based embedding. We first propose a content-aware method which performs uniform embedding in ranked energy-significant regions of the host signal. We show that the embedded ternary watermark signal is more likely to be masked by the strong host signal component, thus improving imperceptibility without compromising robustness. Further, a non-uniform embedding method is proposed, which modifies host samples according to their relationships with the center of the target histogram bin. It ensures minimum host sample modifications without reducing the payload size. Meanwhile, watermark robustness could also be improved since it becomes the most difficult to move samples at bin centers into other bins via attacks. The proposed methods are supported by extensive experimental results.

Location histogram privacy by Sensitive Location Hiding and Target Histogram Avoidance/Resemblance

A location histogram is comprised of the number of times a user has visited locations as they move in an area of interest, and it is often obtained from the user in the context of applications such as recommendation and advertising. However, a location histogram that leaves a user’s computer or device may threaten privacy when it contains visits to locations that the user does not want to disclose (sensitive locations), or when it can be used to profile the user in a way that leads to price discrimination and unsolicited advertising (e.g., as “wealthy” or “minority member”). Our work introduces two privacy notions to protect a location histogram from these threats: Sensitive Location Hiding, which aims at concealing all visits to sensitive locations, and Target Avoidance/Resemblance, which aims at concealing the similarity/dissimilarity of the user’s histogram to a target histogram that corresponds to an undesired/desired profile. We formulate an optimization problem around each notion: Sensitive Location Hiding ({ SLH}), which seeks to construct a histogram that is as similar as possible to the user’s histogram but associates all visits with nonsensitive locations, and Target Avoidance/Resemblance ({ TA}/{ TR}), which seeks to construct a histogram that is as dissimilar/similar as possible to a given target histogram but remains useful for getting a good response from the application that analyzes the histogram. We develop an optimal algorithm for each notion, which operates on a notion-specific search space graph and finds a shortest or longest path in the graph that corresponds to a solution histogram. In addition, we develop a greedy heuristic for the { TA}/{ TR} problem, which operates directly on a user’s histogram. Our experiments demonstrate that all algorithms are effective at preserving the distribution of locations in a histogram and the quality of location recommendation. They also demonstrate that the heuristic produces near-optimal solutions while being orders of magnitude faster than the optimal algorithm for { TA}/{ TR}.

Deep Learning Based Dosimetry Evaluation at Organs-at-Risk in Esophageal Radiation Treatment Planning.

Rapid esophageal radiation treatment planning is often obstructed by manually adjusting optimization parameters. The adjustment process is commonly guided by the dose-volume histogram (DVH), which evaluates dosimetry at planning target volume (PTV) and organs at risk (OARs). DVH is highly correlated with the geometrical relationship between PTV and OARs, which motivates us to explore deep learning techniques to model such correlation and predict DVHs of different OARs. Distance to target histogram (DTH) is chosen to measure the geometrical relationship between PTV and OARs. DTH and DVH features are then undergone dimension reduction by autoencoder. The reduced feature vectors are finally imported into deep belief network to model the correlation between DTH and DVH. This correlation can be used to predict DVH of the corresponding OAR for new patients. Validation results revealed that the relative dose difference of the predicted and clinical DVHs on four different OARs were less than 3%. These promising results suggested that the predicted DVH could provide near-optimal parameters to significantly reduce the planning time.

Modeling and Prediction of SIB Prostate IMRT Plans

To use retrospective data from simultaneously integrated boost (SIB) prostate intensity modulated radiation therapy (IMRT) plans to model and optimize dose plan outcomes. Modeled outcomes could provide plan guidance for new cases and could also be used as a plan comparison tool. A nonlinear regression based model was developed to map distance to target histograms (DTH) for organs at risk (OARs) to their dose volume histograms (DVH). Contours of patients' planning target volumes (PTVs) and OARs were overlaid on CT image data to compute organ volumes and DTHs. For the training cohort, DVHs were extracted from the SIB PTV (58.8 - 70 Gy) and the OARs. Principle component analysis (PCA) was used to elicit the key feature correlations between the DTH and DVH curves. The initial model cohort consisted of 23 retrospective prostate SIB plans. A leave-one-out training scheme was followed to generate a predicted DVH for each plan. For 85% of the cases, the expert planned OAR DVHs either fell within the 68% confidence interval of the predicted DVH, or the model predicted that a lower dose could be delivered to the OARs. A regression based model was used to map patient anatomical features to OAR DVHs. Cases where the trained model differed significantly from the planned DVH can be further examined to evaluate plan integrity. The results are promising considering the small training set, and model robustness should improve with a larger training cohort. Future work will focus on comparing models trained locally to national planning data. Lung cases, along with head and neck cases will also be considered.

Fast Adaptive Bilateral Filtering.

In the classical bilateral filter, a fixed Gaussian range kernel is used along with a spatial kernel for edge-preserving smoothing. We consider a generalization of this filter, the so-called adaptive bilateral filter, where the center and width of the Gaussian range kernel are allowed to change from pixel to pixel. Though this variant was originally proposed for sharpening and noise removal, it can also be used for other applications, such as artifact removal and texture filtering. Similar to the bilateral filter, the brute-force implementation of its adaptive counterpart requires intense computations. While several fast algorithms have been proposed in the literature for bilateral filtering, most of them work only with a fixed range kernel. In this paper, we propose a fast algorithm for adaptive bilateral filtering, whose complexity does not scale with the spatial filter width. This is based on the observation that the concerned filtering can be performed purely in range space using an appropriately defined local histogram. We show that by replacing the histogram with a polynomial and the finite range-space sum with an integral, we can approximate the filter using analytic functions. In particular, an efficient algorithm is derived using the following innovations: the polynomial is fitted by matching its moments to those of the target histogram (this is done using fast convolutions), and the analytic functions are recursively computed using integration-by-parts. Our algorithm can accelerate the brute-force implementation by at least , without perceptible distortions in the visual quality. We demonstrate the effectiveness of our algorithm for sharpening, JPEG deblocking, and texture filtering.

Perceptually Controlled Reshaping of Sound Histograms

Many audio processing algorithms have optimal performance for specific signal statistical distributions that may not be fulfilled for all signals. When the original signal is available, we propose to add an inaudible noise so that the distribution of the signal-plus-noise mixture is as close as possible to a given target distribution. The proposed generic algorithm (independent from the application) adds iteratively a low-power white noise to a flat-spectrum version of the signal, until the target distribution or the noise audibility is reached. The latter is assessed through a frequency masking model. Two implementations of this sound reshaping are described, according to the level of the targeted transformation and to the foreseen application: histogram global reshaping (HGR) to change the global shape of the histogram and histogram local reshaping (HLR) to locally “chisel” the histogram, but keeping the global shape unchanged. These two variants are illustrated by two applications, where the inaudibility of the noise generated by the algorithm is required: “sparsification” for source separation and low-pass filtering of the histogram for application of the quantization theorem, respectively. In both cases, the target histogram is reached or almost reached, and the transformation is inaudible. The experiments show that the source separation performs better with HGR and that the HLR allows a better application of the quantization theorem.

Histogram-based standardization of intravascular optical coherence tomography images acquired from different imaging systems.

Intravascular optical coherence tomography (OCT) is widely used for analysis of the coronary artery disease. Its high spatial resolution allows for visualization of arterial tissue components in detail. There are different OCT systems on the market, each of which produces data characterized by its own intensity range and distribution. These differences should be taken into account for the development of image processing algorithms. In order to overcome this difference in the intensity range and distribution, we developed a framework for matching intensities based on the exact histogram matching technique. In our method, the key step for using the exact histogram matching is to determine the target histogram. For this, we proposed two schemes: a global scheme that uses a single histogram as the target histogram for all the pullbacks, and a local scheme that selects for each single image a target histogram from a predefined database. These two schemes are compared on a unique dataset containing pairs of pullbacks that were acquired shortly after each other with systems from two vendors, St. Jude and Terumo. Pullbacks were aligned according to anatomical landmarks, and a database of matched histogram pairs was created. A leave-one-out cross validation was used to compare performance of the two schemes. The matching accuracy was evaluated by comparing: (a) histograms using Euclidean (dx2 ) and Kolmogorov-Smirnov (dKS ) distances, and (b) median intensity level within anatomical regions of interest. Leave-one-out validation indicated that both matching schemes yield comparably high accuracies across the entire validation dataset. The local scheme outperforms the global scheme with marginally lower dissimilarities at both histogram level and intensity level. High visual similarity was observed when comparing the matched images to their aligned counterparts. Both local and global schemes are robust and produce accurate intensity matching. While local scheme performs marginally better than the global scheme, it requires a predefined histogram dataset and is more time consuming. Thus, for offline standardization of the images, the local scheme should be preferred for being more accurate. For online standardization or when another system is involved, the global scheme can be used as a simple and nearly-as-accurate alternative.

Tensor Decompositions for Integral Histogram Compression and Look-Up.

Histograms are a fundamental tool for multidimensional data analysis and processing, and many applications in graphics and visualization rely on computing histograms over large regions of interest (ROI). Integral histograms (IH) greatly accelerate the calculation in the case of rectangular regions, but come at a large extra storage cost. Based on the tensor train decomposition model, we propose a new compression and approximate retrieval algorithm to reduce the overall IH memory usage by several orders of magnitude at a user-defined accuracy. To this end we propose an incremental tensor decomposition algorithm that allows us to compress integral histograms of hundreds of gigabytes. We then encode the borders of any desired rectangular ROI in the IH tensor-compressed domain and reconstruct the target histogram at a high speed which is independent of the region size. We furthermore generalize the algorithm to support regions of arbitrary shape rather than only rectangles, as well as histogram field computation, i.e., recovering many histograms at once. We test our method with several multidimensional data sets and demonstrate that it radically speeds up costly histogram queries while avoiding storing massive, uncompressed IHs.

RGB Color Cube-Based Histogram Specification for Hue-Preserving Color Image Enhancement

A large number of color image enhancement methods are based on the methods for grayscale image enhancement in which the main interest is contrast enhancement. However, since colors usually have three attributes, including hue, saturation and intensity of more than only one attribute of grayscale values, the naive application of the methods for grayscale images to color images often results in unsatisfactory consequences. Conventional hue-preserving color image enhancement methods utilize histogram equalization (HE) for enhancing the contrast. However, they cannot always enhance the saturation simultaneously. In this paper, we propose a histogram specification (HS) method for enhancing the saturation in hue-preserving color image enhancement. The proposed method computes the target histogram for HS on the basis of the geometry of RGB (rad, green and blue) color space, whose shape is a cube with a unit side length. Therefore, the proposed method includes no parameters to be set by users. Experimental results show that the proposed method achieves higher color saturation than recent parameter-free methods for hue-preserving color image enhancement. As a result, the proposed method can be used for an alternative method of HE in hue-preserving color image enhancement.

Histogram Interpolation Methods for Image Contrast Enhancement

Histogram equalization (HE) is a well-known technique for image contrast enhancement. However, HE frequently over-enhances the contrast of a given image to produce false contours in the enhanced image. One of the reasons for the production of false contours is the sparseness of the equalized histogram, which means that there exist gaps in continuous-tone. In this paper, we propose three methods for interpolating the sparse histogram obtained by HE, and utilize the interpolated histograms as the target ones for histogram specification or histogram matching, which transforms the histogram of a given image into the specified target histogram. Filling the gaps in equalized histogram by interpolation, we can reduce the occurrence of false contours. Experimental results show that the proposed methods can alleviate the over-enhancement of the contrast, which occurs frequently when we use HE. We also evaluate the quality of contrast-enhanced images by using three image quality measures, where the proposed methods achieve better performance than HE in many cases.

Spot-Scanning Proton Arc (SPArc) Therapy: The First Robust and Delivery-Efficient Spot-Scanning Proton Arc Therapy

Topresent a novel robust and delivery-efficient spot-scanning proton arc (SPArc) therapy technique. A SPArc optimization algorithm was developed that integrates control point resampling, energy layer redistribution, energy layer filtration, and energy layer resampling. The feasibility of such a technique was evaluated using sample patients: 1 patient with locally advanced head and neck oropharyngeal cancer with bilateral lymph node coverage, and 1 with a nonmobile lung cancer. Plan quality, robustness, and total estimated delivery time were compared with the robust optimized multifield step-and-shoot arc plan without SPArc optimization (Arcmulti-field) and the standard robust optimized intensity modulated proton therapy (IMPT) plan. Dose-volume histograms of target and organs at risk were analyzed, taking into account the setup and range uncertainties. Total delivery time was calculated on the basis of a 360° gantry room with 1 revolutions per minutegantry rotation speed, 2-millisecond spot switching time, 1-nA beam current, 0.01 minimum spot monitor unit, and energy layer switching time of 0.5 to 4seconds. The SPArc plan showed potential dosimetric advantages for both clinical sample cases. Compared with IMPT, SPArc delivered 8% and 14% less integral dose for oropharyngeal and lung cancer cases, respectively. Furthermore, evaluating the lung cancer plan compared with IMPT, it was evident that the maximum skin dose, the mean lung dose, and the maximum dose to ribs were reduced by 60%, 15%, and 35%, respectively, whereas the conformity index was improved from 7.6 (IMPT) to 4.0 (SPArc). The total treatment delivery time for lung and oropharyngeal cancer patients was reduced by 55% to 60% and 56% to 67%, respectively, when compared with Arcmulti-field plans. The SPArc plan is the first robust and delivery-efficient proton spot-scanning arc therapy technique, which could potentially be implemented into routine clinical practice.

Spatially consistent imputations of forest data under a semivariogram model

This study proposes a method to perform spatially consistent imputations of forest data to serve simulation studies where spatial autocorrelation is expected to have an effect (e.g., sampling simulations and forest scenario analysis). Starting with a nearest neighbour imputation, an optimization process brings the spatially comprehensive data to a desired state, controlled by a target semivariogram and a target histogram. The target values for both parameters may be approximated using empirical data and are combined in the objective function used by the optimization algorithm. Here, we demonstrate a case study using wall-to-wall airborne laser scanner data, satellite data, and field observations for an 852 ha forest area in southern Norway. Different combinations of data types and target parameters were tested, and the target values were reached in most cases. In some cases, with a more restrictive objective function, the semivariogram did not completely converge to its target values, yet still had a convergence of at least 93%, expressed by the difference reduction between initial and target values. The results recommend the proposed method as a practical means to generate spatially explicit forest data when a particular distribution and well-defined spatial dependence are required.