Histogram-based Method Research Articles

Does Differentially Private Synthetic Data Lead to Synthetic Discoveries?

Synthetic data have been proposed as a solution for sharing anonymized versions of sensitive biomedical datasets. Ideally, synthetic data should preserve the structure and statistical properties of the original data, while protecting the privacy of the individual subjects. Differential Privacy (DP) is currently considered the gold standard approach for balancing this trade-off. The aim of this study is to investigate how trustworthy are group differences discovered by independent sample tests from DP-synthetic data. The evaluation is carried out in terms of the tests' Type I and Type II errors. With the former, we can quantify the tests' validity, i.e., whether the probability of false discoveries is indeed below the significance level, and the latter indicates the tests' power in making real discoveries. We evaluate the Mann-Whitney U test, Student's t-test, chi-squared test, and median test on DP-synthetic data. The private synthetic datasets are generated from real-world data, including a prostate cancer dataset (n = 500) and a cardiovascular dataset (n = 70,000), as well as on bivariate and multivariate simulated data. Five different DP-synthetic data generation methods are evaluated, including two basic DP histogram release methods and MWEM, Private-PGM, and DP GAN algorithms. A large portion of the evaluation results expressed dramatically inflated Type I errors, especially at levels of ϵ ≤ 1. This result calls for caution when releasing and analyzing DP-synthetic data: low p-values may be obtained in statistical tests simply as a byproduct of the noise added to protect privacy. A DP Smoothed Histogram-based synthetic data generation method was shown to produce valid Type I error for all privacy levels tested but required a large original dataset size and a modest privacy budget (ϵ ≥ 5) in order to have reasonable Type II error levels.

Simulation-based prior knowledge elicitation for parametric Bayesian models

A central characteristic of Bayesian statistics is the ability to consistently incorporate prior knowledge into various modeling processes. In this paper, we focus on translating domain expert knowledge into corresponding prior distributions over model parameters, a process known as prior elicitation. Expert knowledge can manifest itself in diverse formats, including information about raw data, summary statistics, or model parameters. A major challenge for existing elicitation methods is how to effectively utilize all of these different formats in order to formulate prior distributions that align with the expert’s expectations, regardless of the model structure. To address these challenges, we develop a simulation-based elicitation method that can learn the hyperparameters of potentially any parametric prior distribution from a wide spectrum of expert knowledge using stochastic gradient descent. We validate the effectiveness and robustness of our elicitation method in four representative simulation studies covering linear models, generalized linear models, and hierarchical models. Our results support the claim that our method is largely independent of the underlying model structure and adaptable to various elicitation techniques, including quantile-based, moment-based, and histogram-based methods.

Examining innovative unsupervised learning techniques for automated characterization of complex groundwater systems

This research proposes an innovative approach utilizing geophysical well logging data analyzed with multiple machine learning (ML) methods including, self-organizing maps (SOMs), k-means cluster analysis (CA), and most frequent value-assisted cluster analysis (MFV-CA), to automatically identify lithological variation within a complex groundwater system. The MFV method is introduced to enhance cluster center identification. In MFV, an automatedly weighted Euclidean distance is applied in which closer data points are assigned higher weights that emphasize their proximity within clusters. This method proved to be efficient, however, to ensure robustness, an innovative histogram-based selection method is employed for initial cluster center positioning to minimize the risk of choosing an inappropriate starting value. The proposed methodology is tested on the Quaternary aquifer system in the Debrecen area, Eastern Hungary which is known for its high lithological heterogeneity. The results were evaluated in both 1D and 2D to reveal the vertical and horizontal distribution of the lithofacies. Accordingly, the histogram-based MFV-CA demonstrated exceptional noise rejection capabilities and efficient recognition of lithological clusters. Moreover, the continuous estimation of hydraulic parameters including hydraulic conductivity and critical flow velocity along the hydrostratigraphical units showed a close agreement with the identified lithological units.

Brain magnetic resonance image (MRI) segmentation using multimodal optimization

AbstractOne of the highly focused areas in the medical science community is segmenting tumors from brain magnetic resonance imaging (MRI). The diagnosis of malignant tumors at an early stage is necessary to provide treatment for patients. The patient’s prognosis will improve if it is detected early. Medical experts use a manual method of segmentation when making a diagnosis of brain tumors. This study proposes a new approach to simplify and automate this process. In recent research, multi-level segmentation has been widely used in medical image analysis, and the effectiveness and precision of the segmentation method are directly tied to the number of segments used. However, choosing the appropriate number of segments is often left up to the user and is challenging for many segmentation algorithms. The proposed method is a modified version of the 3D Histogram-based segmentation method, which can automatically determine an appropriate number of segments. The general algorithm contains three main steps: The first step is to use a Gaussian filter to smooth the 3D RGB histogram of an image. This eliminates unreliable and non-dominating histogram peaks that are too close together. Next, a multimodal particle swarm optimization method identifies the histogram’s peaks. In the end, pixels are placed in the cluster that best fits their characteristics based on the non-Euclidean distance. The proposed algorithm has been applied to a Cancer Imaging Archive (TCIA) and brain MRI Images for brain Tumor detection dataset. The results of the proposed method are compared with those of three clustering methods: FCM, FCM_FWCW, and FCM_FW. In the comparative analysis of the three algorithms across various MRI slices. Our algorithm consistently demonstrates superior performance. It achieves the top mean rank in all three metrics, indicating its robustness and effectiveness in clustering. The proposed method is effective in experiments, proving its capacity to find the proper clusters.

Estimation of complete mutual information exploiting nonlinear magnitude-phase dependence: Application to spatial FNC for complex-valued fMRI data

BackgroundReal-valued mutual information (MI) has been used in spatial functional network connectivity (FNC) to measure high-order and nonlinear dependence between spatial maps extracted from magnitude-only functional magnetic resonance imaging (fMRI). However, real-valued MI cannot fully capture the group differences in spatial FNC from complex-valued fMRI data with magnitude and phase dependence. MethodsWe propose a complete complex-valued MI method according to the chain rule of MI. We fully exploit the dependence among magnitudes and phases of two complex-valued signals using second and fourth-order joint entropies, and propose to use a Gaussian copula transformation with a lower bound property to avoid inaccurate estimation of joint probability density function when computing the joint entropies. ResultsThe proposed method achieves more accurate MI estimates than the two histogram-based (normal and symbolic approaches) and kernel density estimation methods for simulated signals, and enhances group differences in spatial functional network connectivity for experimental complex-valued fMRI data. Comparison with existing methodsCompared with the simplified complex-valued MI and real-valued MI, the proposed method yields higher MI estimation accuracy, leading to 17.4 % and 145.5 % wider MI ranges, and more significant connectivity differences between healthy controls and schizophrenia patients. A unique connection between executive control network (EC) and right frontal parietal areas, and three additional connections mainly related to EC are detected than the simplified complex-valued MI. ConclusionsWith capability in quantifying MI fully and accurately, the proposed complex-valued MI is promising in providing qualified FNC biomarkers for identifying mental disorders such as schizophrenia.

Index-based forest degradation mapping using high and medium resolution multispectral sensors

ABSTRACT Monitoring dense forest ecosystems, such as the laurel forest in Garajonay National Park, is vital for biodiversity conservation, carbon storage, and ecological balance. This study employs satellite remote sensing technologies to introduce a novel methodology, based on vegetation indices, aiming to assess and protect the health of the forest. Utilizing the Jeffries-Matusita distance and a histogram-based method, optimal indices to map forest degradation, like Wide Dynamic Range Vegetation Index (WDRVI) and Modified Simple Ratio (MSR), were identified among 19 generated indices. The study processed imagery from three satellite sensors (WorldView-2, PlanetScope and Sentinel-2), producing maps distinguishing healthy and degraded areas. The study’s practical significance lies in offering a method to assess the suitability of sensors and indices for effectively mapping forest degradation. This approach aids conservation efforts and provides valuable insights for environmental managers and policymakers, facilitating the implementation of targeted strategies to safeguard Garajonay National Park's unique laurel forest ecosystem. Emphasizing the role of remote sensing in practical vegetation protection endeavors, the study contributes to on-the-ground initiatives, ensuring the preservation and sustainability of the park's rich biodiversity.

Histogram-based global thresholding method for image binarization

One of the most fundamental issues in image processing is the thresholding (binarization) method. This method is generally used for segmenting regions with different homogeneity in grayscale images. In other words, it performs clustering based on the intensity levels of pixels in an image histogram. This paper presents a new and effective approach to the global thresholding method of grayscale images. In the proposed method, alpha and beta regions are determined using the mean and standard deviation values of an image histogram. The optimum threshold value is obtained by calculating the average of gray-scale values of the alpha and beta regions. The experiments were carried out on three different image sets to demonstrate the effectiveness of the thresholding method. The result of experimental studies show that the proposed method achieves promising performance compared to many traditional, state-of-the-art thresholding and document binarization methods performed in H-DIBCO'14 (Document Image Binarization Competition), Human HT29 colon-cancer cells (BBBC008) and C. elegans live/dead assay (BBBC010) datasets based on various evaluation criteria.

Intrusion Detection Model for Wireless Sensor Networks Based on FedAvg and XGBoost Algorithm

For the characteristics of channel instability in wireless sensor networks, this paper proposes an intrusion detection algorithm based on FedAvg (federated averaging) and XGBoost (extreme gradient boosting) wireless sensor networks using fog computing architecture. First, the network edge is extended by introducing fog computing nodes to reduce the communication delay. It reduces the transmission bandwidth and privacy leakage risk while improving the accuracy of jointly learned global and local models. Then, the histogram-based approximation calculation method is improved to adapt to the unbalanced data characteristics of wireless sensor networks. Finally, by introducing TOP-K gradient selection, the number of model parameter uploads is minimized, and the efficiency of model parameter interaction is improved. The experimental results show that this algorithm has superior detection performance and low energy consumption. It is also compared with other algorithms to demonstrate the high detection rate and low computational complexity of this algorithm.

An Integrated Thresholding and Morphological Process with Histogram-based Method for Brain Tumor Analysis and MRI Tumor Detection

INTRODUCTION: Over the past several years analysis of image has moved from larger system to pervasive portable devices. For example, in pervasive biomedical systems like PACS-Picture achieving and Communication system, computing is the main element. Image processing application for biomedical diagnosis needs efficient and fast algorithms and architecture for their functionality. Future pervasive systems designed for biomedical application should provide computational efficiency and portability. The discrete wavelet transform (DWT) designed in on-chip been used in several applications like data, audio signal processing and machine learning.
 OBJECTIVES: The conventional convolution based scheme is easy to implement but occupies more memory , power and delay. The conventional lifting based architecture has multiplier blocks which increase the critical delay. Designing the wavelet transform without multiplier is a effective task especially for the 2-D image analysis. Without multiplier Daubechies wavelet implementation in forward and inverse transforms may find efficient. The objective of the work is on obtaining low power and less delay architecture.
 METHODS: The proposed lifting scheme for two dimensional architecture reduces critical path through multiplier less and provides low power, area and high throughput. The proposed multiplier is delay efficient.
 RESULTS: The architecture is Multiplier less in the predict and update stage and the implementation carried out in FPGA by the use of Quartus II 9.1 and it is found that there is reduction in consumption of power at approximately 56%. There is reduction in delay due to multiplier less architecture.
 CONCLUSION: multiplier less architecture provides less delay and low power. The power observed is in milliwatts and suitable for high speed application due to low critical path delay.

Research on Pattern Recognition Technology for Music Teaching and Optimization of Its Teaching Framework

Abstract This paper proposes music rhythm perception technology and music automatic classification technology, respectively, which are pattern recognition technologies for music teaching. The short-time Fourier transform is used to analyze the audio information, transform the acoustic spectrogram into a Mel spectrogram, build the convolutional neural network architecture, and process the spectrogram sequentially to realize the automatic classification of music. The music signal is preprocessed to remove noise using normalization, and a new histogram-based method is proposed to detect music rhythms by analyzing and modeling the music beat sequence. This paper uses S High School in Qujing City, Yunnan Province, China, as the research site to implement pattern recognition technology in teaching practice. The experimental class’s music scores increased from 50.18 before the experiment to 64.52, which was higher than the control class’s, with a 28.58% increase. The experimental class’s mean values in the sentence and paragraph dimensions of music rhythmic sense, the mean values of the experimental class were 0.73 and 0.65 higher than those of the control class, showing significant differences (P<0.05). All dimensions of music core literacy, except opera knowledge and general knowledge of musical instruments, also showed significant differences (P<0.05).

Count-Free Single-Photon 3D Imaging with Race Logic.

Single-photon cameras (SPCs) have emerged as a promising new technology for high-resolution 3D imaging. A single-photon 3D camera determines the round-trip time of a laser pulse by precisely capturing the arrival of individual photons at each camera pixel. Constructing photon-timestamp histograms is a fundamental operation for a single-photon 3D camera. However, in-pixel histogram processing is computationally expensive and requires large amount of memory per pixel. Digitizing and transferring photon timestamps to an off-sensor histogramming module is bandwidth and power hungry. Can we estimate distances without explicitly storing photon counts? Yes-here we present an online approach for distance estimation suitable for resource-constrained settings with limited bandwidth, memory and compute. The two key ingredients of our approach are (a) processing photon streams using race logic, which maintains photon data in the time-delay domain, and (b) constructing count-free equi-depth histograms as opposed to conventional equi-width histograms. Equi-depth histograms are a more succinct representation for "peaky" distributions, such as those obtained by an SPC pixel from a laser pulse reflected by a surface. Our approach uses a binner element that converges on the median (or, more generally, to another k-quantile) of a distribution. We cascade multiple binners to form an equi-depth histogrammer that produces multi-bin histograms. Our evaluation shows that this method can provide at least an order of magnitude reduction in bandwidth and power consumption while maintaining similar distance reconstruction accuracy as conventional histogram-based processing methods.

PREVENTION OF RODENT ATTACK ON TERTIARY PACKAGE AT STORAGE LEVEL

This proposes to use some image processing methods as a data normalization method for machine learning. Conventionally, z-score normalization is widely used for pre-processing of data. In the proposed approach, in addition to z-score normalization, a number of histogram-based image processing methods such as histogram equalization are applied to training data and test data as a pre-processing method for machine learning. We evaluate the effectiveness of the proposed approach by using a support vector machine algorithm and a random forest one. In experiments, the proposed scheme is applied to a face-based authentication algorithm with SVM/random forest classifiers to confirm the effectiveness. For SVM classifiers, both z- score normalization and image enhancement work well as a pre-processing method for improving the accuracy. In contrast, for random forest classifiers, a number of image enhancement methods work well, although z- score normalization is unusual for improving the accuracy. The proposed pre-processing method focuses on leveraging histogram analysis to address challenges related to contrast variations, colour distributions, and noise levels in diverse image datasets. The key objectives include the development of an adaptive contrast enhancement algorithm, colour normalization techniques, and strategies for noise reduction.

Automatic histogram-based defect detection in glass fibre reinforced polymer composites using terahertz time-domain spectroscopy reflection imaging

We developed a method for automatic detection of defects in glass fibre reinforced polymer (GFRP) based on a terahertz time-domain spectroscopy (TDS) system. Two GFRP specimens with round defects of different sizes (inclusions and delaminations) were measured by means of a high-speed TDS reflective scanner with an electronically controlled optical sampling scheme. The algorithm provided a series of C-scans, which were then pre-selected to identify only those with features potentially associated with defects. A thresholding method based on Gaussian fitting of the histogram was developed. The results showed that 87 % of defects were detected for the specimen with inclusions and 100 % for the specimen with delaminations. The algorithm also provided information about the depth of defects, as each C-scan was assigned to a time slice. The results demonstrate that the TDS-based system, along with the proposed histogram-based method, can automatically detect defects in GFRP. © 2017 Elsevier Inc. All rights reserved.

Convolutional Neural Network for Segmenting Micro-X-ray Computed Tomography Images of Wood Cellular Structures

To further enhance the performance of wood products, improved tools are needed to study in situ cellular scale phenomena like mechanical deformations and moisture swelling. Micro-X-ray computed tomography (μXCT) using brilliant synchrotron light sources now has the spatial and temporal resolution for real-time visualization of phenomena in three-dimensional cellular structures. However, the tradeoff for speed includes the loss of intensity contrast between different types of materials within the imaged structure, such as cell wall and air in wood. This loss of contrast prevents traditional histogram-based segmentation methods from being used effectively. A new convolutional neural network (CNN) approach was therefore developed to segment fast μXCT images of wood into cell wall and air volumes. The fast μXCT and segmentation were demonstrated in the study of moisture swelling in loblolly pine (Pinus taeda) earlywood and latewood cellular structures conditioned at 0%, 33%, 75%, and 95% relative humidity (RH). The CNN segmentation results had a mean intersection over union (IoU) metric accuracy of 96%. Initial analysis of the swelling in the latewood revealed cell walls swelled about 25% when conditioned from 0% to 95% RH. Additionally, the widths of ray cell lumina in the transverse plane of latewood could be observed to increase at higher RH. The segmentation method presented here will facilitate future quantitative analyses in in situ μXCT studies of wood and other similar cellular materials.

Multi-step histogram based outlier scores for unsupervised anomaly detection: ArcelorMittal engineering dataset case of study

Anomaly detection is the task of detecting samples that behave differently from the rest of the data or that include abnormal values. Unsupervised anomaly detection is the most common scenario, which implies that the algorithms cannot train with a labeled input and do not know the anomaly behavior beforehand. Histogram-based methods are one of the most approaches in unsupervised anomaly detection, remarking a good performance and a low runtime. Despite the good performance, histogram-based anomaly detectors are not capable of processing data flows while updating their knowledge and cannot deal with a high amount of samples.In this paper, we propose a new histogram-based approach for addressing the aforementioned problems by introducing the ability to update the information inside a histogram. We have applied these strategies to design a new algorithm called Multi-step Histogram Based Outlier Scores (MHBOS), including five new histogram update mechanisms. The results have shown the performance and validity of MHBOS as well as the proposed strategies in terms of performance and computing times.

Robust reservoir identification by multi-well cluster analysis of wireline logging data

A novel clustering method is applied to well logs for improved rock type identification in hydrocarbon formations. For grouping the objects in the multi-dimensional data space, we propose a Most Frequent Value (MFV) based clustering technique applied to natural gamma ray, bulk density, sonic, photoelectric index, and resistivity logs. The MFV method is a robust estimator, which assists in finding the cluster centers more reliably than a more noise sensitive K-means clustering approach. The result of K-means cluster analysis highly depends on the choose of the initial centroids. To reduce the risk of inappropriately chosen starting values, we apply a histogram-based selection method to give the best position of the initial cluster centers. We assure the robustness of the solution by calculating the centroid as the MFV of the cluster elements and defining the overall deviation of cluster elements from the center by a weighted Euclidean (Steiner-) distance. The proposed workflow relies on a fully automated weighting of the cluster elements, which does not require a constraint on the statistical distribution of the observed variables. The processing of synthetic data shows high noise rejection capability and efficient cluster recognition even beside considerable amount of outlying and missing data; the accuracy is measured by the difference between the estimated and the exactly known distribution of cluster numbers. The clustering tool is first applied to single borehole data, then the procedure is extended to multi-well logging datasets to reconstruct the multi-dimensional spatial distributions of clusters revealing the lithological and petrophysical characteristics of the studied formations. A large in situ dataset acquired from several boreholes traversing Hungarian gas-bearing clastic reservoirs of Miocene age is analyzed. The accuracy of the field results is confirmed by core permeability measurements, independent well log analysis and a gradient metrics characterizing the noise rejection capability of the clustering method.

Using Sentinel-1 and Google Earth Engine cloud computing for detecting historical flood hazards in tropical urban regions: a case of Dar es Salaam

This study investigates the potential of freely available Sentinel-1 imagery coupled with Google Earth Engine (GEE) for mapping and monitoring flooding in Dar es Salaam. Sentinel-1 images (n = 55) available during the rainy season (March–May) since 2016 were used and processed in GEE. For separating water and land surfaces, we used a histogram-based automatic thresholding method. The binarization accuracy was assessed using confusion matrix based on 1064 randomly generated points in GEE. Overall accuracy of 95% (Kappa = 0.90) were achieved. Dar es Salaam has experienced flood inundation per flood event on average over an area of 50 km2 in March 2019 and 2021. Territories located along the Ocean and inland water shores, built and bare ground were subject to flooding compared to other land cover types. Flooding inundations have been difficult to detect in the city center. With the current temporal and spatial resolution of Sentinel-1, flood detection in city centers remains a challenge yet. However, Sentinel-1 images, coupled with GEE cloud computing simplified flood mapping and monitoring in a large urban region and this approach can be applied in other large cities and their surroundings for countries where data gap and lack of processing tools are critical challenges.

Evaluation of thresholding methods for the quantification of [68Ga]Ga-PSMA-11 PET molecular tumor volume and their effect on survival prediction in patients with advanced prostate cancer undergoing [177Lu]Lu-PSMA-617 radioligand therapy

PurposeThe aim of this study was to systematically evaluate the effect of thresholding algorithms used in computer vision for the quantification of prostate-specific membrane antigen positron emission tomography (PET) derived tumor volume (PSMA-TV) in patients with advanced prostate cancer. The results were validated with respect to the prognostication of overall survival in patients with advanced-stage prostate cancer.Materials and methodsA total of 78 patients who underwent [177Lu]Lu-PSMA-617 radionuclide therapy from January 2018 to December 2020 were retrospectively included in this study. [68Ga]Ga-PSMA-11 PET images, acquired prior to radionuclide therapy, were used for the analysis of thresholding algorithms. All PET images were first analyzed semi-automatically using a pre-evaluated, proprietary software solution as the baseline method. Subsequently, five histogram-based thresholding methods and two local adaptive thresholding methods that are well established in computer vision were applied to quantify molecular tumor volume. The resulting whole-body molecular tumor volumes were validated with respect to the prognostication of overall patient survival as well as their statistical correlation to the baseline methods and their performance on standardized phantom scans.ResultsThe whole-body PSMA-TVs, quantified using different thresholding methods, demonstrate a high positive correlation with the baseline methods. We observed the highest correlation with generalized histogram thresholding (GHT) (Pearson r (r), p value (p): r = 0.977, p < 0.001) and Sauvola thresholding (r = 0.974, p < 0.001) and the lowest correlation with Multiotsu (r = 0.877, p < 0.001) and Yen thresholding methods (r = 0.878, p < 0.001). The median survival time of all patients was 9.87 months (95% CI [9.3 to 10.13]). Stratification by median whole-body PSMA-TV resulted in a median survival time from 11.8 to 13.5 months for the patient group with lower tumor burden and 6.5 to 6.6 months for the patient group with higher tumor burden. The patient group with lower tumor burden had significantly higher probability of survival (p < 0.00625) in eight out of nine thresholding methods (Fig. 2); those methods were SUVmax50 (p = 0.0038), SUV ≥3 (p = 0.0034), Multiotsu (p = 0.0015), Yen (p = 0.0015), Niblack (p = 0.001), Sauvola (p = 0.0001), Otsu (p = 0.0053), and Li thresholding (p = 0.0053).ConclusionThresholding methods commonly used in computer vision are promising tools for the semiautomatic quantification of whole-body PSMA-TV in [68Ga]Ga-PSMA-11-PET. The proposed algorithm-driven thresholding strategy is less arbitrary and less prone to biases than thresholding with predefined values, potentially improving the application of whole-body PSMA-TV as an imaging biomarker.

Stress changes during exhumation of a high-pressure nappe (Phyllite-Quartzite unit, Greece): Insights from quartz microstructures and recrystallized grain size statistics

In this study, we carried out microstructural and grain size analysis of recrystallized quartz in quartz-rich samples collected from different structural levels of a 1.5–2.0 km thick high-pressure nappe (Phyllite-Quartzite unit, Greece). Exhumation-related deformation led to recrystallization of quartz by subgrain rotation (SGR) and the formation of different generations of recrystallized quartz with different grain sizes. Applying a new, fully automated histogram-based method, we reconstructed the “hidden” empirical probability density functions included in the histograms of the initial grain size distributions. Statistical analysis showed that most grain-size histograms display bimodal distributions with mean grain sizes in cluster A ranging from 46 to 48 μm, and a cluster B with mean grain sizes between 81 and 93 μm. Few grain size histograms display trimodal distributions and show an additional cluster C with mean grain sizes ranging from 100 to 115 μm. Microstructural observations indicate that the grains of cluster C are the oldest whereas those of cluster A are the youngest. Bimodal and trimodal distributions may reflect an episodic increase in the differential stress from 17 to 19 MPa and then to 31 MPa during exhumation, accompanied by a strain rate increase of at least one order of magnitude (from 10−13 s−1 to 10−12 s−1). This stress increase likely occurred at the early stages of the exhumation and may have lasted less than 0.5 Myr. Stress increase was followed by a stress drop expressed by partial foam structures of quartz in a few samples.

Enhancement of Mammographic Images Using Histogram-Based Techniques for Their Classification Using CNN

In the world, one in eight women will develop breast cancer. Men can also develop it, but less frequently. This condition starts with uncontrolled cell division brought on by a change in the genes that regulate cell division and growth, which leads to the development of a nodule or tumour. These tumours can be either benign, which poses no health risk, or malignant, also known as cancerous, which puts patients' lives in jeopardy and has the potential to spread. The most common way to diagnose this problem is via mammograms. This kind of examination enables the detection of abnormalities in breast tissue, such as masses and microcalcifications, which are thought to be indicators of the presence of disease. This study aims to determine how histogram-based image enhancement methods affect the classification of mammograms into five groups: benign calcifications, benign masses, malignant calcifications, malignant masses, and healthy tissue, as determined by a CAD system of automatic mammography classification using convolutional neural networks. Both Contrast-limited Adaptive Histogram Equalization (CAHE) and Histogram Intensity Windowing (HIW) will be used (CLAHE). By improving the contrast between the image's background, fibrous tissue, dense tissue, and sick tissue, which includes microcalcifications and masses, the mammography histogram is modified using these procedures. In order to help neural networks, learn, the contrast has been increased to make it easier to distinguish between various types of tissue. The proportion of correctly classified images could rise with this technique. Using Deep Convolutional Neural Networks, a model was developed that allows classifying different types of lesions. The model achieved an accuracy of 62%, based on mini-MIAS data. The final goal of the project is the creation of an update algorithm that will be incorporated into the CAD system and will enhance the automatic identification and categorization of microcalcifications and masses. As a result, it would be possible to increase the possibility of early disease identification, which is important because early discovery increases the likelihood of a cure to almost 100%.