Histogram Technique Research Articles

HNMH: A New Hybrid Approach Based on Near Maximum Histogram and LSB Technique for Image Steganography

HNMH: A New Hybrid Approach Based on Near Maximum Histogram and LSB Technique for Image Steganography

Local Energy Based Shape Histogram (LESH) and Adaboost Machine Learning Techniques to Detect Lung Cancer

Abstract: Numerous cancerous tissues develop in a manner that obscures the specific side effects, making it challenging to identify the effects of lung disease. This investigation's findings can be verified using high-resolution images. With this method, the LESH Algorithm's vital activity will be examined in images. In this study, the GLCM approach is used to pre-measure the previews and element extraction framework, as well as to verify a patient's infection rate at a period when it is abnormal to know it. The malignancy stage will be assessed with the help of the results. Patients with malignant growths whose endurance rates can be estimated using the informational index. The outcome is wholly determined by how accurately the tissue patterns were constructed or how incorrectly they were constructed.

Feature Generalization for Breast Cancer Detection in Histopathological Images.

Recent period has witnessed benchmarked performance of transfer learning using deep architectures in computer-aided diagnosis (CAD) of breast cancer. In this perspective, the pre-trained neural network needs to be fine-tuned with relevant data to extract useful features from the dataset. However, in addition to the computational overhead, it suffers the curse of overfitting in case of feature extraction from smaller datasets. Handcrafted feature extraction techniques as well as feature extraction using pre-trained deep networks come into rescue in aforementioned situation and have proved to be much more efficient and lightweight compared to deep architecture-based transfer learning techniques. This research has identified the competence of classifying breast cancer images using feature engineering and representation learning over the established and contemporary notion of using transfer learning techniques. Moreover, it has revealed superior feature learning capacity with feature fusion in contrast to the conventional belief of understanding unknown feature patterns better with representation learning alone. Experiments have been conducted on two different and popular breast cancer image datasets, namely, KIMIA Path960 and BreakHis datasets. A comparison of image-level accuracy is performed on these datasets using the above-mentioned feature extraction techniques. Image level accuracy of 97.81% is achieved for KIMIA Path960 dataset using individual features extracted with handcrafted (color histogram) technique. Fusion of uniform Local Binary Pattern (uLBP) and color histogram features has resulted in 99.17% of highest accuracy for the same dataset. Experimentation with BreakHis dataset has resulted in highest classification accuracy of 88.41% with color histogram features for images with 200X magnification factor. Finally, the results are contrasted to that of state-of-the-art and superior performances are observed on many occasions with the proposed fusion-based techniques. In case of BreakHis dataset, the highest accuracies 87.60% (with least standard deviation) and 85.77% are recorded for 200X and 400X magnification factors, respectively, and the results for the aforesaid magnification factors of images have exceeded the state-of-the-art.

Intelligent System Utilizing HOG and CNN for Thermal Image-Based Detection of Wild Animals in Nocturnal Periods for Vehicle Safety

ABSTRACT Animal Vehicle Collision, commonly called roadkill, is an emerging threat to drivers and wild animals, increasing fatalities every year. Currently, prevalent methods using visible light cameras are efficient for animal detection in daylight time. This paper focuses on locating wildlife close to roads during nocturnal hours by utilizing thermographic obtained images, thus enhancing vehicle safety. In particular, it proposes an intelligent system for animal detection during nighttime that combines the technique of Histogram of Oriented Gradients (HOG) with a Convolutional Neural Network (CNN). The proposed intelligent system is benchmarked against a variety of CNN’s like basic CNN and VGG16-based CNN and also with the machine learning algorithms such as Support Vector Machine (SVM), Random Forest (RF), Decision Tree Algorithm (DT), Linear Regression (LR), and Gaussian Naïve Bayes (GNB). The proposed detection system was tested on a set of real-world data acquired with a thermal camera on the move in the city of San Antonio, TX, USA that includes images of wild deer. Obtained results exhibit that the HOG-CNN combination achieved approximately 91% correct detection accuracy of wild deer on roadsides, while it outperformed the rest of the tested machine learning algorithms.

Optimising longitudinal and lateral calorimeter granularity for software compensation in hadronic showers using deep neural networks

We investigate the effect of longitudinal and transverse calorimeter segmentation on event-by-event software compensation for hadronic showers. To factorize out sampling and detector effects, events are simulated in which a single charged pion is shot at a homogenous lead glass calorimeter, split into longitudinal and transverse segments of varying size, and the total energy loss within each segment is used as the signal. As an approximation of an optimal reconstruction, a neural network-based energy regression is trained based on these signals. The architecture is based on blocks of convolutional kernels customized for shower energy regression using local energy densities; biases at the edges of the training dataset are mitigated using a histogram technique. With this approximation, we find that a longitudinal and transverse segment size less than or equal to 0.5 and 1.3 nuclear interaction lengths, respectively, is necessary to achieve an optimal energy measurement. In addition, an intrinsic energy resolution of 8%/sqrt{E} for pion showers is observed.

Segmentation of Cervical Cancer by OLHT Based DT-CWT Techniques

Every year, cervical cancer (CC) is the leading cause of death in women around the world. If detected early enough, this cancer can be treated, and patients will receive adequate care. This study introduces a novel ultrasound-based method for detecting CC. The Oriented Local Histogram Technique (OLHT) is used to improve the image corners in the cervical image (CI), and the Dual-Tree Complex Wavelet Transform (DT-CWT) is used to build a multi-resolution image (CI). Wavelet, and Local Binary Pattern are among the elements retrieved from this improved multi-resolution CI (LBP). The retrieved appearance is trained and tested using a feed-forward propagation neural network, and the ANFIS classifier is utilized to classify them. The purpose of this classifier is to distinguish between normal and pathological cervical pictures. Sensitivity is 97.52 percent, specificity is 99.46 percent, accuracy is 98.39 percent, precision is 97.48 percent, PPV is 97.38 percent, NPV is 92.27 percent, LRP is 141.81 percent, 0.0946 percent LRN, FPR is 96.82 percent, and NPR is 91.46 percent for the CC detection categorization. The proposed methodology outperforms standard CC identification and classification methodologies.

Machine Learning Models That Integrate Tumor Texture and Perfusion Characteristics Using Low-Dose Breast Computed Tomography Are Promising for Predicting Histological Biomarkers and Treatment Failure in Breast Cancer Patients.

Simple SummaryTumor angiogenesis and heterogeneity are associated with poor prognosis for breast cancer. Advances in computer technology have made it possible to noninvasively quantify tumor angiogenesis and heterogeneity appearing in imaging data. We investigated whether low-dose CT could be used as a method for functional oncology imaging to assess tumor heterogeneity and angiogenesis in breast cancer and to predict noninvasively histological biomarkers and molecular subtypes of breast cancer. Low-dose breast CT has advantages in terms of radiation safety and patient convenience. Our study produced promising results for the use of machine learning with low-dose breast CT to identify histological prognostic factors including hormone receptor and human epidermal growth factor receptor 2 status, grade, and molecular subtype in patients with invasive breast cancer. Machine learning that integrates texture and perfusion features of breast cancer with low-dose CT can provide valuable information for the realization of precision medicine.This prospective study enrolled 147 women with invasive breast cancer who underwent low-dose breast CT (80 kVp, 25 mAs, 1.01–1.38 mSv) before treatment. From each tumor, we extracted eight perfusion parameters using the maximum slope algorithm and 36 texture parameters using the filtered histogram technique. Relationships between CT parameters and histological factors were analyzed using five machine learning algorithms. Performance was compared using the area under the receiver-operating characteristic curve (AUC) with the DeLong test. The AUCs of the machine learning models increased when using both features instead of the perfusion or texture features alone. The random forest model that integrated texture and perfusion features was the best model for prediction (AUC = 0.76). In the integrated random forest model, the AUCs for predicting human epidermal growth factor receptor 2 positivity, estrogen receptor positivity, progesterone receptor positivity, ki67 positivity, high tumor grade, and molecular subtype were 0.86, 0.76, 0.69, 0.65, 0.75, and 0.79, respectively. Entropy of pre- and postcontrast images and perfusion, time to peak, and peak enhancement intensity of hot spots are the five most important CT parameters for prediction. In conclusion, machine learning using texture and perfusion characteristics of breast cancer with low-dose CT has potential value for predicting prognostic factors and risk stratification in breast cancer patients.

Do coherent structures organize scalar mixing in a turbulent boundary layer?

A scalar emanating from a point source in a turbulent boundary layer does not mix homogeneously, but is organized in large regions with little variation of the concentration: uniform concentration zones. We measure scalar concentration using laser-induced fluorescence and, simultaneously, the three-dimensional velocity field using tomographic particle image velocimetry in a water tunnel boundary layer. We identify uniform concentration zones using both a simple histogram technique, and more advanced cluster analysis. From the complete information on the turbulent velocity field, we compute two candidate velocity structures that may form the boundaries between two uniform concentration zones. One of these structures is related to the rate of point separation along Lagrangian trajectories and the other one involves the magnitude of strong shear in snapshots of the velocity field. Therefore, the first method allows for the history of the flow field to be monitored, while the second method only looks at a snapshot. The separation of fluid parcels in time was measured in two ways: the exponential growth of the separation as time progresses (related to finite-time Lyapunov exponents and unstable manifolds in the theory of dynamical systems), and the exponential growth as time moves backward (stable manifolds). Of these two, a correlation with the edges of uniform concentration zones was found for the past Lyapunov field but not with the time-forward future field. The magnitude of the correlation is comparable to that of the regions of strong shear in the instantaneous velocity field.

Using expert judgement techniques to assess reliability for long service-life components: An application to railway wheelsets

Due to uncertainties in the deterioration process of long service-life assets, assessing reliability and planning maintenance and inspection activities are often difficult tasks. Most of the methods developed use operational or historical data from the manufacturer to predict the deterioration of the asset and estimate its reliability. However, in practice, such failure data is often scarce (e.g. very rare events) and the reliability prediction models might not be adapted to the operation of the user. In addition, available data gathered from maintenance or inspection tasks might only inform about a short period of time, and it might be difficult to obtain the corresponding reliability predictions as the associated uncertainty is still significant. Hence, this paper introduces a reliability assessment method that quantifies uncertainties regarding the failure of long service-life components. It combines Cooke’s classical method (also known as Structured Expert Judgement) with a histogram technique, creating a performance-based method to assess uncertainty in components lifetime distributions. A case study on railway wheelsets is analysed to illustrate the effectiveness of such approach. The results show that the presented method is able to assess failure rates, which can support decisions in reliability-based maintenance of engineering systems.

A novel approach to unsupervised pattern discovery in speech using Convolutional Neural Network

In this paper, a novel approach to unsupervised pattern discovery for speech signals is proposed. Recently, we introduced an image processing method (IPM) that extracts the desired keywords present in a pair of speech utterances. This method performs well in detecting true positives but, at the same time it also detects higher number of false positives. Therefore, this paper aims to reduce the detection of false positives and improve the accuracy of the pattern discovery task. In the proposed work, we use the Convolutional Neural Network (CNN) as a binary classifier to detect the true and false keyword match candidates. A new frame histogram technique is introduced to generate sufficient training samples from IPM to train the CNN. The trained CNN model classifies the matched patterns into true and false classes and identifies the pairs of speech documents that contain the same keyword. The proposed method is evaluated on the Hindi as well as Bengali speech databases. The results are compared with state-of-the-art methods. The detected matched pairs of speech utterances are grouped into broader domain clusters using Newman’s clustering algorithm. These clusters are useful for speech retrieval tasks.

WITHDRAWN: Hardware-based identification of bright lesions to diagnose diabetic retinopathy

Diabetic Retinopathy is a major problem for diabetic patients and is caused by changes in the blood vessels and abnormalities in the macular region. This disease will lead to vision loss if the diabetes is not controlled. This disease can be encountered by the primary signs of Microaneuryusm, Haemorrhages and Exudates. In this paper, a methodology is proposed for Hardware-based Detection of Exudates using RAPIDS CUDA Segmentation algorithm. The Input retinal image is pre-processed by using the Gray scale conversion method and Contrast Limited Adaptive Histogram technique. The pre-processed retinal image is further segmented by using K-mean Segmentation technique and the exudates are detected from the segmented output region. In this proposed approach RAPIDS CUDA Machine Learning algorithm runs completely on the GPU architecture which has increased the speed of the execution with less execution time.

Eye Diseases Classification Using Back Propagation Artificial Neural Network

A human eye is a vital organ responsible for a person's vision. So, the early detection of eye diseases is essential. The objective of this paper deals with diagnosing of seven different external eye diseases that can be recognized by a human eye. These diseases cause problems either in eye pupil, in sclera of eye or in both or in eyelid. Color histogram and texture features extraction techniques with classification technique are used to achieve the goal of diagnosing external eye diseases. Hue Min Max Diff (HMMD) color space is used to extract color histogram and texture features which were fed to Back Propagation Artificial Neural Network (BPANN) for classification. The comparative study states that the features extracted from HMMD color space is better than other features like Histogram of Oriented Gradient (HOG) features and give the same accuracy as features extracted directly from medical expert recorded symptoms. The proposed method is applied on external eye diseases data set consisting of 416 images with an accuracy rate of 85.26315%, which is the major result that was achieved in this study.

Dependence of the frequency distribution around a sphere on the voxel orientation

Microscopically small magnetic field inhomogeneities within an external static magnetic field cause a free induction decay in magnetic resonance imaging that generally exhibits two transverse components that are usually summarized to a complex entity. The Fourier transform of the complex-valued free induction decay is the purely real and positive-valued frequency distribution which allows an easy interpretation of the underlying dephasing mechanism. Typically, the frequency distribution inside a cubic voxel as caused by a spherical magnetic field inhomogeneity is determined by a histogram technique in terms of subdivision of the whole voxel into smaller subvoxels. A faster and more accurate computation is achieved by analytical expressions for the frequency distribution that are derived in this work. In contrast to the usually assumed simplified case of a spherical voxel, we also consider the tilt angles of the cubic voxel to the external magnetic field. The typical asymmetric form of the frequency distribution is reproduced and analyzed for the more realistic case of a cubic voxel. We observe a splitting of frequency distribution peaks for increasing tilt of the cubic voxel against the direction of the external magnetic field in analogy to the case for dephasing around cylindrical, vessel-like objects inside cubic voxels. These results are of value, e.g., for the analysis of susceptibility-weighted images or in quantitative susceptibility imaging since the reconstruction of these images is performed in cubic-shaped voxels.

Data Integrity of Radiology Images Over an Insecure Network Using AES Technique

Background:While transmitting the medical images in radiology information systems the adversary effect can break the CIA (Confidentiality, Integrity, and Availability) triads of information security. The objective of the study was to transmit the complete set of image objects in a dataset without data integrity violation. Methods:In this paper a hybrid cryptographic technique which combines the prime details from the patient dataset (stack of axial 2D images) and the Advanced Encryption Standard (AES) method has been proposed. The steps include a) Creating an artificial X-ray image (DRR) from the 3D volume, b) dividing the DRR image in x and y directions equally into four regions, c) applying the zig-zag pattern to each quadrant, and d) encryption of each quadrant with block cipher mode using the AES algorithm. After dataset transmission the DRR image was regenerated at the receiver and compared each of the deciphered blocks (transmitted ones) using the histogram technique. Results:The technique was tested on CT and MRI scans of sixty datasets. The image injection techniques, such as adding and deleting an image from the dataset and modifying the image pixels, were tested. The results were validated statistically using mean square error and histogram matching techniques. Conclusion:The combination of the DRR and the AES technique has ensured the secured transmission of the entire dataset and not an individual image.

Uni- and multivariate probability density models for numeric subgroup discovery

Subgroup Discovery is a supervised, exploratory data mining paradigm that aims to identify subsets of a dataset that show interesting behaviour with respect to some designated target attribute. The way in which such distributional differences are quantified varies with the target attribute type. This work concerns continuous targets, which are important in many practical applications. For such targets, differences are often quantified using z-score and similar measures that compare simple statistics such as the mean and variance of the subset and the data. However, most distributions are not fully determined by their mean and variance alone. As a result, measures of distributional difference solely based on such simple statistics will miss potentially interesting subgroups. This work proposes methods to recognise distributional differences in a much broader sense. To this end, density estimation is performed using histogram and kernel density estimation techniques. In the spirit of Exceptional Model Mining, the proposed methods are extended to deal with multiple continuous target attributes, such that comparisons are not restricted to univariate distributions, but are available for joint distributions of any dimensionality. The methods can be incorporated easily into existing Subgroup Discovery frameworks, so no new frameworks are developed.

OP206 Expert Elicitation Of Probabilistic Distributions to Inform Survival Modelling of CD19 Chimeric Antigen Receptor T-Cell Therapies

IntroductionIn 2018, the National Centre for Pharmacoeconomics (NCPE) was commissioned to conduct a health technology assessment (HTA) of one of the first commercially available chimeric antigen receptor (CAR) T-cell therapies, tisagenlecleucel. CAR T-cells are a major advance in personalized cancer treatment, demonstrating promising outcomes in relapsed/refractory pediatric acute lymphoblastic leukemia (pALL). However, the results are based on short-term follow up, limiting their value in predicting long-term survival and leading to uncertainty about the most appropriate survival modeling method to employ. This study aimed to address these limitations by means of expert elicitation.MethodsAn expert elicitation method, the histogram technique, was employed. A predefined discrete numerical scale was presented in Microsoft Excel® and the expert was asked to place twenty crosses on a frequency chart. These crosses represented the expert's beliefs about the distribution of particular quantities. Each cross represented five percent of the probabilistic distribution. Individual distributions were then aggregated across experts using linear pooling.ResultsA total of seventeen experts were invited to take part; eight agreed to participate and five completed the exercise. Three experts did not consider tisagenlecleucel to be a “curative” therapy because patients had a higher risk of death, compared with the age- and sex-matched general population. The aggregated distributions indicated the five-year overall survival rate to be thirty-three percent (95% CI 8.65–56.88) in patients who do not receive a subsequent stem cell transplant and twenty percent (95% CI 2.38 -52.04) in those who do.ConclusionsThe results of this study will be used to calibrate CD19 CAR T-cell therapy survival estimates presented in HTA submissions to the NCPE to ensure more robust assessments. They will also be used to inform the construction of a de novo cost-utility model for examining the cost effectiveness of CD19 CAR T-cell therapies for relapsed/refractory pALL in the Irish healthcare setting.

WITHDRAWN: An invisible based watermarking technique for biometric image authentication

Biometric image authentication is an important and challenging area of research. It involves an analysis of the candidate’s biometrics for security purposes. Exposure to such sensitive information can be a threat to an individual’s identity and system security. In this paper, we have proposed an invisible watermarking scheme to protect biometric information from harmful attacks. Initially, the technique segments the host image into blocks using edge entropy and then selects the appropriate band coefficients using 2D-DWT transformation. The adaptive histogram technique is used to embed the watermarking image properly. Finally, to retrieve the original watermark, a reversible data hiding approach (RDH) and visual cryptography technique (VC) is used that provides safety and security to biometric images. The proposed method was tested on two datasets, namely, CASIA-v5 and UBIRIS-v1 and is evaluated on various measuring metrics such as PSNR, NC, and BER. Further, the proposed technique is analyzed and compared with different traditionally implemented watermarking techniques based on PSNR and NC values. Results show that the presented method outperforms the other methods by achieving best in class results and highest PSNR (62.52, 61.25) and NC values (0.95, 0.94).

Dynamics and thermodynamics of core/shell formation of icosahedral NimAgn bimetallic nanostructures

The molecular dynamics and multiple histogram techniques were used to understand the core/shell formation of bimetallic silver-nickel nanostructures at sizes of 55 and 147 atoms. Two core/shell structures of 55 atoms icosahedra, Ag13Ni42 and Ni13Ag42 with their isomers, Ni13(Ni29Ag13) and Ag13(Ag29Ni13) were considered. In the case of 147 atoms icosahedra, homogeneous motifs (either Ag or Ni) of the core, inner shell, and outer shell were produced along with their heterogeneous isomers. Energetically, nickel-core structures are found to be more favorable than corresponding silver-core motifs. Constant volume heat capacity was used to characterize the phase transition of each cluster. The trend in the variation of melting temperatures of 55 atoms icosahedra with the nickel composition aggreses with the observed trend in the energy variation, thus values of heat capacity reveals more solid-like characteristics of NicoreAgshell motifs and liquid-like characteristic of AgcoreNishell motifs. Thermodynamic feasibility of the nickel-core/silver-shell formation was established by comparing Helmholtz free energy changes in the transition of silver atoms from the center to the shell and nickel penetration from shell to the center. The free energy changes in surface mixing and segregation of silver atoms revealed that the mixing of silver atoms with nickel atoms on the surface is more favorable than segregation. In a low nickel environment, the formation of homogeneous core/shell structures occurs, while in moderate nickel composition, mixing of silver atoms is favorable than being in the homogeneous core/shell configurations.

Measuring scour level based on spatial and temporal image analyses

Scour monitoring is an important measurement process to determine the soil erosion level at the pillar of bridge. Image-based approach is attractive because it allows monitoring process to be conducted continuously without halting the flow of the water during experiment. Scour images provide abundance of information from a single source of camera sensor. However, this information may appear in different features, orientation, size and brightness. Therefore, it is important to detect and recognise features that are related to scour monitoring and filtered out irrelevant features like image noises and artefacts. This paper presents implementation of image processing techniques to extract various information from scour images. Image inpainting technique is used to separate information of scour level and scale markers into two different images. A proposed gradient of marginal histogram technique is used to detect the horizontal scale line markers and scour level. Backpropagation neural network is used to recognise scale text markers and convert the measurement of the scour level from a pixel unit into a centimetre unit. Interpolation techniques are used to connect scour points and delineate the boundary indicating the level of the scour. Time series acquisition of scour images allows observation of the temporal variation of the scour levels. Results show that the proposed approach achieved higher accuracy than existence method. This approach allows the detection of the scour level for even and uneven sediments, contributing to the high accurate results at the spatial and temporal measurements, thus potentially offering continuous scour monitoring solution.

The qualitative and quantitative assessment of the renal cortex of the clinically healthy rabbits

Qualitative ultrasonographic images in diagnosing renal parenchymal diseases can be inadequate. The relationship between renal cortical echogenicity and parenchymal disease has been demonstrated in people. However, it is difficult to determine diffuse fat vacuoles and the parenchymal diseases at qualitative renal assessment. Disorders of the renal cortex are frequently seen in rabbits. The aim of this study was to qualitatively and quantitatively evaluate the echogenicity of the renal cortex in clinically healthy rabbits. Fourty-two clinically normal and with no history of renal disease rabbits were used. The each rabbit was investigated by complete blood count, urinalysis and renal biopsy. Renal ultrasonography was performed with a 6.5 MHz probe. For each image, three equally sized regions of interest was detected within the renal cortex. The mean pixel intensity was determined using an 8-bit grayscale, with 256 colour of grey colours. Qualitative echogenicity was evaluated by two observers. Observer 1 evaluated as an isoechoic (36/42) and hyperechoic (6/42). Observer 2 evaluated as an isoechoic (35/42) and hyperechoic (7/42). Quantitatively, the mean pixel intensities analysed for the renal cortex was 59.2±2.23 (range: 28-91). The result of this study indicates that analysis of digitized renal cortical ultrasonographic images from rabbits using the histogram technique can be used to quantitatively determine echogenicity.