Search

This study employs data from a mail survey (n=1,114) conducted among public school teachers and educational support professionals in New York State to examine the factors that contribute to individuals' attribution and information seeking about breast cancer risk. The results indicate that mass media use, as well as beliefs about existing information regarding breast cancer risk, influence individuals' causal attributions and seeking of information about breast cancer risk. Concerns about the local environment also positively relate to individuals' association of breast cancer risk with environmental factors. The conclusions argue for bottom-up dialectical health communication strategies that take into account individuals' understandings and perceptions of breast cancer risk and their local environment. ..PAT.-Unpublished Manuscript [ABSTRACT FROM AUTHOR]

Now-a-days, Breast Cancer is a serious cause in world and it raises a death ratio in drastic manner. Most of the women are suffered due to this kind of breast cancer disease, in which several literatures are available regarding this breast cancer identification, but all are strucked over certain level. Lots of researchers in industry providing different digital image processing schemes to identify the Breast Cancer in clear manner to save lives of women but all are strucked with real world prediction scenarios. For Breast Cancer identification mammography is a well-known technique, in which it screens the breast cancer cells in clear manner. However, based on the workload and manual expertise failures, a numerous failures and wrong classification procedures reported as well. So, that a novel computer assisted digital image processing technique and smart tool is required to provide intelligent prediction logics to identify the breast cancer on earlier conditions instead of detecting that in complex stages. In this paper, a novel Deep Learning enabled Image Processing tool is designed, called as Digital Image Processing Scheme enabled SmartKit (DIPSK) to identify the breast cancer disease effectively on earlier stages without any human intervention. The prop osed DIPSB enables the system to acquire the input scanning image and process that with DIP techniques with respect to pre-processing feature extraction and classification. The detailed features are cross-validated with the trained samples, in which the Deep Learning procedure called Improved Convolutional Neural Network (iCNN) is utilized by the SmartKitto provide classification process in accurate manner. The final resulting of this SmartKitis more efficient as compare to the traditional image processing schemes and provides accurate prediction on earlier stages. The resulting section provides the proper proof for the classification accuracy and prediction logics. [ABSTRACT FROM AUTHOR]

Breast cancer is by far the most common tumor. In terms of all malignant diseases, breast cancer is considered as one of the major contributors to death for postmenopausal women, taking up for 23%. There is still a lack of effective treatment. Survival rate of patients who suffer from advanced breast cancer is correlated with the amount of lymphatic metastasis, tumor size, age group and hormone receptor state, as well as the staging of the cancer itself. It also has correlation with the existence of lymph node and internal organ metastases. From the perspectives of age, immunohistochemical type, metastasis, and local treatment of terminal cancer patients, this paper summarizes from the aspect of race to explore the effect of survival prognosis of those who are diagnosed with advanced breast cancer, aimed at better guiding the clinical treatment and prolonging the survival duration. [ABSTRACT FROM AUTHOR]

Breast Cancer is one of the normal and causing passing among ladies and least essential in men; Micro calcification, an abnormality that leads to breast cancer and is detected by various imaging such as X-ray, Computerized tomography (C.T.), etc. Detection of breast carcinoma is a challenging task since the micro calcifications are buried under the background of mammography. Numbers of studies have shown the early diagnosis is a more effective method to cure breast carcinoma. In this paper, Micro calcification was distinguished by the techniques for profound learning and by numerical figuring. The capabilities of deep learning futures and mathematically calculated features are combined on the characteristic of a deep learning filter. The filtered deep learning feature provides better experimental results compare with the mathematically calculated feature. We obtained 86.6% of overall precision level and sensitivity level by applying the deep learning features filtered and providing better performance with all the features. [ABSTRACT FROM AUTHOR]

The paper surveys thermal breast images utilized for malignant growth location--an altogether harmless and non-contact imaging strategy. The technique can build the early analysis pace of breast cancer. The profound learning-based technique distinguishes breast malignant growth with a 93.95% exactness rate. In the course of recent years, a few procedures have been proposed for this reason, for example, mammography, which is often utilized for breast cancer growth determination. Be that as it may, bogus up-sides of mammography can happen when the patient is analyzed decidedly by another method. Also, the expected results of utilizing mammography might urge patients and doctors to search for other analytic strategies. Our survey investigated infrared advanced imaging, which accepts that a fundamental thermal correlation between a healthy breast and a breast with malignant growth generally shows an expansion in thermal movement in the precancerous tissues and the regions encompassing creating cancer disease. In this paper, we utilized SVM and KNN Model. [ABSTRACT FROM AUTHOR]

Breast cancer is the most common cancer in the world, according to figures provided by the International Agency for Research on Cancer (IARC) in December 2020. In 2020, approx.2.3 million women detected with breast cancer, out of which 685000 resulted in death globally. Recently; WHO Global Breast Cancer Initiative (GBCI) is aiming to lessen its death rate by 2.5% per year that will result in saving 2.5 million living upcoming 20 years. In achieving this purpose, it is required to detect the disease as early as possible with good accuracy, so that further treatment can be perform accordingly. In contribution to this goal, our paper focuses on the timely recognition of breast cancer disease using multiple logistic regression. [ABSTRACT FROM AUTHOR]

Multi-core processing can decrease the cost of many Machine Learning (ML) tasks by executing them in parallel using multiple cores of a processor. Modern computers are equipped with processors that contain multiple cores that can be leveraged to decrease the execution time of many ML tasks by multiple folds. Especially ensemble of ML algorithms like Random Forest (RF) can take advantage of the multi-core processing ability for improving their performance. In this paper five models using RF algorithm using Gaussian_Quantiles (GQ), Load_Wine (LW), Load_Iris (LI), Load_Breast_Cancer (BC) and Load_Digits (LD) datasets are developed and evaluated using k-fold cross-validation respectively. In general, the execution time of RF algorithm decreases as the number of cores increases. [ABSTRACT FROM AUTHOR]

One of the most fatal diseases among women is breast cancer. It is also called the second leading cause of death due to delay in the diagnosis of cancerous tissues. The most common symptoms of breast cancer are post- menopause, obesity, family genes, hormonal imbalance, and genetically muted abnormalities. Death rates are still excessive as breast cancer detection in many developing countries is diagnosed during later stages. To reduce the death rates, we need to diagnose it at the early stages. Digital mammogram images are used as input in the proposed method. Our main focus in this paper is differentiating between normal, benign, and malignant cancer. The pre-processing is done using a median filter. The K-means Segmentation is used for the segmentation process. The feature extraction is done using GLCM (Grey Level Co-occurrence Matrix) algorithm. The last step which is object classification is done using LDA (Linear Discriminant Analysis). We have classified them into different stages of cancer using the digital image processing technique and the performance of the classifier is evaluated through a confusion matrix. [ABSTRACT FROM AUTHOR]

One of cancer that commonly causes most of the death is breast cancer. According to WHO data published in 2017, breast cancer deaths in Indonesia reached 21,287 or 1.27 % of total deaths. Delay in knowing of the condition of breast cancer in women with breast cancer, results in increased mortality, poor prognosis, and decreased survival rates, which are also associated with lower awareness of breast cancer, and also recommended non-adherence to screening. In this paper, we propose a random forest for breast cancer prediction. Random forest is one of many classification techniques, and it is an algorithm for big data classification. Random forest classification is applied to cancer microarray data to achieve a more accurate and reliable classification performance. The accuracy in this paper is 100 %. [ABSTRACT FROM AUTHOR]

In the last decade, breast cancer has become the focus of world attention as this disease is one of the primary leading cause of death for women. Therefore, it is necessary to have the correct precautions and treatment. In previous studies, Fuzzy Kennel K-Medoid algorithm has been used for multi-class data. This paper proposes an algorithm to classify the high dimensional data of breast cancer using Fuzzy Possibilistic C-means (FPCM) and a new method based on clustering analysis using Normed Kernel Function-Based Fuzzy Possibilistic C-Means (NKFPCM). The objective of this paper is to obtain the best accuracy in classification of breast cancer data. In order to improve the accuracy of the two methods, the features candidates are evaluated using feature selection, where Laplacian Score is used. The results show the comparison accuracy and running time of FPCM and NKFPCM with and without feature selection. [ABSTRACT FROM AUTHOR]

Implementing deep learning technology with FPGA as an accelerator has become a popular application due to its efficiency and performance. However, given the tremendous data generated on medical diagnosis, normal inference speed is not sufficient. Hence, the FPGA technology is implemented for fast inference. In this context, the FPGA accelerates the deep learning inference process for fast breast cancer classification with minimal latency on real-time deployment. This paper summarizes the findings of model deployment across various computing devices in deep learning technology with FPGA. The study includes model performance evaluation, throughput, and latency comparison with different batch sizes to the extent of expected delay for real-world deployment. The result concludes that FPGA is the most suitable to act as a deep learning inference accelerator with a high throughput-to-latency ratio and fast parallel inference. [ABSTRACT FROM AUTHOR]

This paper presents machine learning algorithms for predicting different stages of breast cancer tumour such as benign and malignant. Machine learning (ML) models such as Logistic regression (LR), Decision tree (DT), Naive Bayes (NB), Support vector machine (SVM), K-nearest neighbour (KNN), Random Forest (RF) and XG Boost (XGB) used for predicting different stages of breast cancer. The Breast cancer data is collected from UCI machine learning Repository, this data is used training and testing the machine algorithms. Performance and evaluation of machine learning algorithms using confusion matrix and metrics are used Accuracy, Precision, Recall and f1-score. Support vector machine (SVM) performed better result of metrics score to compared with other machine learning algorithms. [ABSTRACT FROM AUTHOR]

Breast cancer arises when cells develop uncontrollably in the breast to form tumour cells. The risk of having breast cancer rises as a woman continues to age. Thus, details about the early stages of cancer progression can help a woman make early treatment choices, preventing them from being diagnosed with these harmful cancers. It is believed that cytotoxic T lymphocytes (CTLs) act as effector cells to eradicate cancer cells. CTLs and tumor cells were discovered to be around a "predator-prey" relationship, with CTL acting as the predator along with tumor cells acting as the prey. In this paper, we examined steady-state solutions for two numerical differentiation using the Jacobian matrix. We will also examine the stability region of breast cancer cells in two different phases to describe its progress in different types of the human body at various phases. Also, compare tumour cells population development in the duration of interphase and metaphase in the presence and the absence of immune response, which is dependent on the CTL population, will be observed by applying Fourth Order Runge Kutta (RK4) method. We can see that the Runge-Kutta method is an important method for approximate solutions to ordinary systems with known initial conditions. We achieved populations value of tumour cells throughout interphase and mitosis as well as the population of the immune system using the method. Based on our observations, we draw the conclusion that persons with a higher immune system are more likely to be able to fight cancer for for a period of time than cancer sufferers with a poor immune system. We may observe that the cancer cells were reduced in a shorter period of time with a high immune response population compared to other lower CTL values. [ABSTRACT FROM AUTHOR]

Breast cancer is an aggressive form of cancer that kills many women. Although breast cancer has a high incidence, it death rate is not as high as incidence. This is thanks to the staging approach to breast cancer. Early detection of breast cancer can help doctors and patients better treat the disease. In the last century, the classification of breast cancer was left to the discretion of experienced pathologists. With the progress of technology, machine classification is replacing manual classification. The classifier will save society the time and cost of training pathologists. In the future, it may be possible for a highly accurate classifier algorithm to achieve even higher accuracy than manual classification. This paper summarizes the research direction and progress of breast cancer classifiers up to now and provides the latest research results for medical practitioners and researchers in the discussion section. [ABSTRACT FROM AUTHOR]

It is crucial that Breast Cancer should be detected early. Breast cancer time series forecasting is a novel data - driven approach to breast cancer diagnosis. Instead of looking at static images of the medical records, it analyses the dynamics in the tumour's growth rate, especially in its early stages. It uses machine learning models to find patterns that are not readily observable in static images, but are predictive of later outcomes. During COVID-19 it is necessary to monitor patient from home and IOT devices can be used that give moment forecast to the client and doctor during their typical day by day routine. Various Machine learning models are reviewed for classification of Breast Cancer symptoms. It is observed that data visualization and feature engineering play a crucial role in the classification before applying any model on data set. For human protection during COVID-19 it is better to depend on IoT enabled wearable device for automatic detection and appointment. The IoT enabled devices can use power of cloud computing and machine learning models to complete the framework of getting treated at home. Security of the data is another aspect to be taken into consideration. Solutions are available for the whole process and their aggregation will result in generating the desired model. In this paper, model is proposed to diagnose breast cancer at home using IoT, Blockchain, Machine learning and Cloud Computing. [ABSTRACT FROM AUTHOR]

The most common disease is breast cancer among all women in the world. The death rate of breast cancer is higher due to unawareness of cancer's initial symptoms. There are methods already existed to classify the disease using various real-time tools and algorithms. Machine learning has emerged as a fast boom in all fields of training and classification. The traditional computer programming techniques for the classification of breast cancer disease utilize the Deep Learning (DL) technique for training the model using Convolutional Neural Network (CNN) for dominant feature extraction to identify the given breast cancer test image samples. The datasets of the test samples are fed to the automated detection model for classifying the mammography images into 'Malignant' and 'Benign' breast tumors using Kernel SVM classification. In this paper, the breast cancer recognition accuracy results are compared for different kernels like linear, poly, Radial Basis Function, and sigmoid function. The linear Kernel gives better accuracy of "95.78%". The training set is varied, and their recognition performance is observed until the recognition accuracy is better. [ABSTRACT FROM AUTHOR]

In the paper we are showing a comparative study of some of the classification and the clustering algorithms so that we can find the alternatives for the datasets depending upon the requirement. These prediction systems can be used for the medical diagnosis as various algorithms in this paper have been categorized and simulation results shown. Prevalence informs the total case load at a given time. Incidence yields a pointer to extent of attention required and choice of measures. Different classification algorithms are trained on the result set to build the final classifier model based on K-fold cross validation method. The best accuracy for the given dataset is achieved in rotation forest algorithm compared to other classifiers. The proposed approach will help sort out the. This methodology is evaluated using 286 raw breast cancer data obtained from a city hospital. The best accuracy for the given dataset is achieved in bagging algorithm compared to other classifiers. The proposed approach helps doctors in their diagnosis decisions and also in their treatment planning procedures for different categories. [ABSTRACT FROM PUBLISHER]

Cancer analysis and prediction is the utmost important research field for well-being of humankind. The Cancer data are analyzed and predicted using machine learning algorithms. Most of the researcher claims the accuracy of the predicted results within 99%. However, we show that machine learning algorithms can easily predict with an accuracy of 100% on Wisconsin Diagnostic Breast Cancer dataset. We show that the method of gaining accuracy is an unethical approach that we can easily mislead the algorithms. In this paper, we exploit the weakness of Machine Learning algorithms. We perform extensive experiments for the correctness of our results to exploit the weakness of machine learning algorithms. The methods are rigorously evaluated to validate our claim. In addition, this paper focuses on correctness of accuracy. This paper report three key outcomes of the experiments, namely, correctness of accuracies, significance of minimum accuracy, and correctness of machine learning algorithms. [ABSTRACT FROM AUTHOR]

Major challenge in the analysis of clinical data is to propose an integrated and modern access to the progressively increasing amounts of data in multiple formats, and efficient approaches for their management and processing. An approach to management of large amount of heterogeneous data sets from various data sources for a breast cancer diagnostic system is presented in this paper. Big genomic data architecture consists of data sources, storage, integration and preprocessing, real data stream, stream processing, analytical data store, analysis and reporting. Activities at data management for breast cancer diagnostic system are explained. Conceptual database architecture for storing data sets of several types in order to support breast cancer prediction is designed. The breast cancer database comprises of information related to breast cancer genes and functions - id, name, type, organism, function, and proteins coded, description, link for retrieving sequence. The patient’s database consists of individual patient data - genetic data, clinical history, individual life style parameters, clinical tests results, environmental factors. The data sets in the suggested big data management system are retrieved from the biomedical research databases. The data management system is platform independent, easy to use and provides access to other databases such PubMed, NCBI. The purpose is to be used for data storage in a system for big data analytics and knowledge discovery, especially for the case study of breast cancer diagnostic. The advantages in data management, analysis, and knowledge discovery empower the scientists to achieve new scientific breakthroughs. As a result the research work is directed towards rapid management and processing of clinical data for solving problems in the field of precision medicine. [ABSTRACT FROM AUTHOR]

Cancer is one of the most famous diseases in recent years. Cancer has various classifications, which are difficult to detect in patients. Most patients are diagnosed with cancer after being at an advanced stage. To analyze the disease and diagnose cancer in patient, we need gene expression data. Gene expression data contain so many genes, even thousands of genes, but not all of those genes contain information necessary to detect cancer for its classification. Machine learning can choose the important genes for the classification to reduce running time, cost, and increase classification accuracy. In this paper we use Stochastic SVM and Fuzzy Kernel Robust C-Means (FRKCM). Then we will compare the accuracy of the methods in breast cancer classification. Stochastic SVM achieves a high prediction accuracy by learning the optimal hyperplane from the training set, which greatly simplifies the classification and regression problems. Fuzzy Kernel Robust C-Means (FKRCM) will define the membership function, set specific data called prototype and use the learning rate on each iteration. Based on the experiment, we get 90.43 % accuracy for the Stochastic SVM and 95.65 % accuracy for Fuzzy Kernel Robust C-Means. [ABSTRACT FROM AUTHOR]

Breast cancer is the second most dominant disease diagnosed in women and the second major cause of cancer deaths globally. Digital Mammography can offer low-cost early diagnosis and reduce the breast cancer fatality rate among victims. This research aims to build a model that automatically assists in classifying malignant and benign lesions depicted on digital mammograms without any human interventions. For this purpose, the mini-MIAS dataset, which has 322 mammograms, is used. This paper focus on the Contrast enhancement technique based on Background Preserved and Feature-Oriented Contrast Improvement (BPFO-CI) using the Weighted Cumulative Distribution Function. The enhanced mammograms are then segmented using the principle of Thresholding Segmentation techniques, to extract the Region of Interest (RoI). The extracted RoIs are then passed as input to optimized Convolutional Neural Networks (CNN) for classification. The pre-processed dataset is subjected to data augmentation. The performance analysis of the proposed pre-processed CNN model is compared with other classification techniques in terms of accuracy and confusion matrix. The simulation outcomes confirm on the importance and impact of the proposed model against the other well-known existing methods. Thus, this classification mechanism is expected to serve as an assistant for breast cancer detection. [ABSTRACT FROM AUTHOR]

In this paper, breast cancer detection using Ultra Wide Band (UWB) Confocal Imaging Techniques are considered with conventional averaging technique. A new averaging technique is proposed and applied on UWB-confocal imaging techniques. From simulation results and based on observation of images, the proposed averaging technique has produced a stable power images compared to the conventional averaging technique which produced an unstable power images. The problem of tumor detection in fibroglandular/fibroconnection tissues region for UWB-confocal imaging techniques is still existed but improvement in the detection has been achieved. [ABSTRACT FROM PUBLISHER]

Cancer is one of the main death causes among health issues worldwide. There are approximately reported around 8.2 million victims in 2012. Early treatment and prevention should be conducted to reduce the high mortality. Cancer detection is necessary as an early warning system to properly treat detected cancers. Cancer imaging as one of various cancer detection techniques has become more reliable for cancer detection. This technique has been developed by using a wide spectrum of electromagnetic from microwave into optics. Terahertz (THz) imaging systems have also been developed to provide cancer imaging systems. The use of this spectrum, which is also known as a gap region between electronics and optics domain, has specific advantages for cancer detection systems, such as low radiation power and cancer transmission or reflection fingerprints located in this spectrum region. Among various cancers, breast cancer is the most common cancer suffered by women. In this paper, simulation of THz imaging is conducted by using microstrip linear array antennas for breast cancer detection. The antennas as transmitter and receiver of the THz waves are separated for a distance of 4.5 mm. An object, including the breast cancer, is modelled by considering three layers of tissue with different values of permittivity, i.e. fat (ɛr = 2.41), fibrous (ɛr = 2.8), and tumor (ɛr = 3.15). The THz imaging is simulated at frequencies of 0.302 THz, 0.312 THz, and 0.322 THz. Simulation is conducted by using CST Microwave Studio. The simulation results show that the cancer tissue can be detected by considering and analyzing the transmitted waves detected by the receiver antenna. THz imaging at a frequency of 0.312 THz gives the clearest imaging, which could affected by the antenna resonance. These results indicate that the THz imaging technique has potentials to be applied for cancer early detection. [ABSTRACT FROM AUTHOR]

Breast cancer patients are more likely to have serious health problems and have a higher mortality rate. The primary reason could be radiologists misinterpreting dangerous lesions as a result of technological challenges with imaging quality and varying breast densities. Breast cancer early identification may increase survival rates. Mammography is a reliable method for spotting breast cancer in its early stages. A few of the image processing techniques required for the detection of breast cancer include preprocessing, segmentation, feature extraction, and classification. Segmentation is crucial in the tumor's identification process, meanwhile. This review focuses in particular on several problems with traditional and typical methodologies that make use of machine learning and deep learning techniques. Using conventional machine learning methods for manual breast cancer screening misunderstood the erratic feature-extraction process, requiring patients to return for biopsies to rule out any concerns. Although a number of deep learning-based methods for precise breast cancer categorization and prognosis have been established, few have offered a thorough analysis of lesions segmentation. We have proposed a domain specific Deep Learning based Modified U-net model at the end of this paper. In order to offer a thorough analysis of current diagnostic approaches, this study also looks into a variety of well-known databases using the phrase "Breast Cancer." [ABSTRACT FROM AUTHOR]

Breast cancer is the second most common cancer in the world. Currently, there are no effective methods to prevent this disease. However, early diagnosis increases chances of remission. Breast thermography is an option to be considered in screening strategies. This paper proposes a new dynamic breast thermography analysis technique in order to identify patients at risk for breast cancer. Thermal signals from patients of the Antonio Pedro University Hospital (HUAP), available at the Mastology Database for Research with Infrared Image - DMR-IR were used to validate the study. First, each patient's images are registered. Then, the breast region is divided into subregions of 3x3 pixels and the average temperature from each of these regions is observed in all images of the same patient. Features of the thermal signals of such subregions are calculated. Then, the k-means algorithm is applied over feature vectors building two clusters. Silhouette index, Davies-Bouldin index and Calinski-Harabasz index are applied to evaluate the clustering. The test results showed that the methodology presented in this paper is able to identify patients with breast cancer. Classification techniques have been applied on the index values and 90.90% hit rate has been achieved. [ABSTRACT FROM AUTHOR]

Cancer is the leading cause of non-accidental deaths worldwide. Specifically, nearly 10 million people died globally from cancer in the year 2020. Breast Cancer (BC) is a common and fatal disease among women worldwide, and ranks fourth among the fatal diseases among various cancers, such as cervical, colorectal, and cervical tumors and brain tumors. In addition, the number of new breast cancer patients is expected to increase by 70% in the next 20 years. Therefore, early and accurate diagnosis plays a pivotal role in improving prognosis and increasing the survival rate of cancer patients from 30 to 50%. With technical advances in healthcare, machine learning and deep learning play an important role in processing and analyzing a large number of medical images. The aim of this study is to identify studies that have been done on the application of classification techniques in diagnosing BC and analyze them from four perspectives: classification techniques used, Dataset used, Programming language used and best accuracy. We conducted a systematic literature review of 32 selected studies published between 2002 and 2020. The results showed that among the classification techniques examined, artificial neural networks, support vector machines and k-nearest neighbor were the most widely used. Moreover, artificial neural networks, support vector machines, and group classifiers have been implemented better than other techniques, with average accuracy values between 83.45% and 99.30%. Most of the selected studies used Wisconsin CSV dataset and a few of the studies used different types of images such as mammography, ultrasound, and micro images. [ABSTRACT FROM AUTHOR]

Terahertz (THz) imaging means an imaging technique by utilizing the THz wave spectrum. The spectrum can provide a unique fingerprint for biological materials. Therefore, it has offered a solution to diagnose cancer. This paper reports a THz imaging simulation of microstrip linear array antennas as a probe in distance variations for breast cancer detections using a CST Microwave Studio software. The object is a breast tissue model in the form of a block, which consists of three types of tissue: fat (εr = 2.41), fibrous (εr = 0.80), and tumor (εr = 3.18). This research considers two microstrip antennas as a transmitter and a receiver to conduct two dimensions of translation scanning. The receiver antenna detects the irradiated power represented by the scattering parameter of S21. There are two conditions of the translation method in this study, i.e., distances in the near-field and far-field regions. In the near-field THz imaging scenario, the separation between the antenna and phantom is between 1.25 mm and 2.25 mm. While in the far-field area, the separation between the antenna and phantom is between 3.00 mm and 4.00 mm. The simulation results show that images at distances of 2.25 mm and 3.50 mm have the highest quality among the considered ranges, which have the smallest standard deviation of S21 compared to the other condition. The results show that a lower standard deviation of S21 provides a higher image quality. [ABSTRACT FROM AUTHOR]

In almost all parts of the world, breast cancer is one of the major causes of death among women. But at the same time, it is one of the most curable cancers if it is diagnosed at early stage. This paper tries to find a model that diagnoses and classifies breast cancer with high accuracy and that will help to both patients and doctors in the future. Here we present several different decision tree methods in order to classify breast cancer with high accuracy. The results achieved in this research are very promising (accuracy is 96.49 %). It is very promising result compared to previous researches where decision tree techniques were used. As benchmark test, Breast Cancer Wisconsin (Original) was used. [ABSTRACT FROM AUTHOR]

Breast cancer is a steadily growing disease that provides elevated mortality than other cancer types for global women. The survival rate of this cancer type can be uplifted through appropriate screening and diagnosis where the role of early detection of breast cancer is significant. In this regard, the design of Computer-Aided Diagnosis (CAD) with improved reliability is always in demand for earlier detection. The work proposed a VGG-NiN architecture integrating the pretrained CNN of VGG-16 together with spatial pyramid pooling (SPP) layer and network-in-network (NiN). The above-said layers are stacked to classify the breast cancer severities with minimum parameters and to speed up the model convergence and training process. For this, the work utilized the INbreast dataset for digital mammogram inputs. The obtained experimental results reveal the robustness of the proposed method as compared with the state-of-the-art CAD techniques. [ABSTRACT FROM AUTHOR]

In recent days, Breast malignancy has been considered the main real for death in ladies when contrasted with any remaining diseases. Bosom malignant growth has turned into the most unsafe sort of disease among ladies on the planet. Early discovery of bosom malignant change is fundamental in diminishing life misfortunes. This paper intends to present a hybrid data mining strategy that incorporates K-Nearest Neighbour (KNN) and Support Vector Machine SVM to build up a precise arrangement model for Breast malignant growth forecast, to utilize the important data in clinical information, particularly which is typically overlooked by a large portion of the current techniques when they focus on high expectation exactness's We have done trials on WBC information. Examination results show that the proposed hybrid information mining strategy has higher expectation exactness than those techniques. Various strategies for bosom disease location are investigated, and their exactness is thought about. We induce that the SVM-based hybrid methods are more appropriate in addressing bosom disease expectations with these outcomes. We suggest utilizing these methodologies with incomparable arrangement issues. [ABSTRACT FROM AUTHOR]

Mass detection in mammogram is one of effective technology for breast cancer diagnosis. A novel method of mass segmentation in mammogram is proposed in this paper. First, a mathematical model (MM) of the mass is presented to detect the location of mass. Second, based on the time series features generated by Pulse Coupled Neural Network (PCNN), the pixels are classified by Fuzzy C-Means clustering (FCM) algorithm. Last, combining the location and the cluster results, segmentation of masses can be achieved effectively. The experimental results show that mass detected by this method is accurate and the false positive (FP) rate is very low. The detection rate of masses reached 98.82%. [ABSTRACT FROM PUBLISHER]

The traditional BP neural network is improved and developed in this paper. When the iteration of Levenberg-Marquardt takes the place of Gradient descent algorithm, the network convergence rate is improved greatly. After the analysis of breast tumors offered by Dr. William H. Wolberg from University of Wisconsin Hospitals, 9 parameters reflecting the characteristics of breast tumors are concluded. Based on the improved BP neural network, the simulation model of breast tumors is founded. Within the 83 groups of testing data, benign diagnosis rate is 100%, while malign diagnosis rate is 96.6%. [ABSTRACT FROM PUBLISHER]

Breast cancer is the second most common cancer in females, after lung cancer in the world. In Taiwan, there are about 7500 female suffering from breast cancer every year. The incidence of breast cancer has exceeded cervical cancer and has become the most common female cancer. Immunohisto chemistry (IHC) image is widely applied to the diagnosis of breast cancer, but it requires a great deal of manpower and time. Therefore, in this paper, we proposed a method to assess the grade of breast cancer in IHC images. The proposed method consists of four steps, including ROI extraction, feature extraction, feature selection, and a SVM classifier. According to the experimental results, the proposed method can automatically and effectively asses the score of IHC images. [ABSTRACT FROM PUBLISHER]

Mammography is the primary method for screening and detecting breast cancers. However, it frequently fails to detect small tumors and is not quite specific in terms of tumor benignity and malignancy. The objective of this paper is to develop a new imaging modality called elasto-mammography that generates the modulus elastograms based on conventional mammographs. A new elastic reconstruction method is described based on elastography and mammography for breast tissues. Elastic distribution can be reconstructed through the measurement of displacement provided by mammographic projection. It is shown that the proposed elasto-mammography provides higher sensitivity and specificity than the conventional mammography on its own for breast cancer diagnosis. [ABSTRACT FROM AUTHOR]

Breast cancer is the second leading cause of cancer deaths amongst women in the United States. In the past two decades, the potential of non-ionizing high power RF waves to destroy cancerous biological tissues is actively investigated for cancer therapy. This paper presents the computational feasibility study of an alternative mode of electromagnetic radiation therapy that employs dual source and deformable mirror. The adaptive focusing capability of the deformable mirror is exploited for preferential energy deposition at the tumor site in the breast irradiated by electromagnetic radiation. The outcome of the computational study for the proposed deformable mirror-based thermal therapy for breast cancer is presented in this paper. © 2007 American Institute of Physics [ABSTRACT FROM AUTHOR]

This paper explores the contestation between the mainstream breast cancer movement (MBCM) and the environmental breast cancer movement (EBCM) over the pink ribbon awareness campaign. In particular, it examines the framing employed by the mainstream breast cancer organizations for the pink ribbon campaign and the counterframes utilized by the environmental breast cancer organization, Breast Cancer Action, in their Think Before you Pink campaign. Based on evidence from the organizations' websites, it appears that the MBCM and the EBCM consist of members with different views on corporate involvement in breast cancer research, the gendered nature of breast cancer activism, and the relationship between breast cancer activists/advocates, medical science, and corporate funding. The paper concludes with a discussion of the significance of accounting for ideology in the study of social movements, as evidenced by this case, in which the movements share the goal of eradicating breast cancer, but due to sharp ideological differences, pursue the goal in different and ultimately contradictory manners. ..PAT.-Unpublished Manuscript [ABSTRACT FROM AUTHOR]

This paper discusses the role of 'artworks' produced by women with breast cancer in the context of breast cancer activism. We argue that such works play a key role in making visible and collective the ideological issues surrounding this disease. They do this through their potential for anchoring social practices relating to its treatment and what might be done about it (Klawiter 2004, Swidler 2001). The paper focuses upon the work of two women artists diagnosed with breast cancer - the British photographer Jo Spence, and Martha Hall, an American who made artist's books. We examine specific works from these collections, and the context of their production. In this way we show how and why artworks are important in establishing visual and discursive space related to social practices associated with disease regimes, and how they provide emancipatory potential for women living with breast cancer. This analysis enables criticism of both the functionalist position that sees artworks as outside the social context of illness (rather than constitutive of it), and the constructivist position that regards artworks as needing interpretation in order to bring them into being. Instead, we argue that artworks are already ideological, working through and on bodies to enable a redemptive and emancipatory potential. As mediators of representations of illness, they deserve attention from sociologists researching social movements, the sharing of illness experience and strategies for survival. ..PAT.-Unpublished Manuscript [ABSTRACT FROM AUTHOR]

Background: Only 11% of breast cancer survivors currently meet the exercise oncology guidelines, and the restrictions to gyms and time outside of home related to the COVID-19 pandemic may have aggravated this situation. To address this, we are testing the efficacy of a twice-weekly, 8-week, supervised, synchronous exercise program delivered virtually for participants diagnosed with breast cancer, called the BE-FIT program. Objective: The aim of this paper is to examine the preliminary participant's satisfaction in participating in the BE-FIT program. Methods: Participants are asked to complete a "Participant Satisfaction Questionnaire" using a range of 1-5 for each question (1 represents "very difficult," 2 "difficult," 3 "neutral," 4 "easy," and 5 "very easy"). The questions were related to the following: level of difficulty to access classes; level of clarity of information received during classes; level of capacity to continue practicing exercises independently after finishing the exercise program; and level of how likely one would recommend the program to a friend. Results: For the ongoing efficacy trial, we collected responses from 40 participants. The participants reported that it was "very easy" and "easy" to access and participate in the virtual exercise session (63% and 37%, respectively). When asked if the information received from the exercise training was clear and easy to understand during virtual exercise sessions, 93% reported "very easy," and the remainder reported "easy." Regarding continuing the exercise independently with the content learned in the program, 87% of the participants reported "very easy" or "easy" (31% and 56%, respectively), and 13% reported "neutral." Lastly, 80% of participants reported "very easy" to recommend the BE-FIT program to a friend, 18% reported "easy," and 2% reported "neutral." Conclusions: A virtually delivered supervised program seems to be an excellent alternative to in-person supervised exercise programs to provide easy access and clear information during the classes with potential influence on the future practice of exercises. [ABSTRACT FROM AUTHOR]

Patient-reported outcome measures (PROMs) have been increasingly integrated into patient-facing technologies to engage and empower patients in cancer self-management at home. However, researchers and developers face several challenges in selecting the best-suited PROMs for patient-facing technologies, due to the complex nature of the disease, the multitude of PROMs with high psychometric quality, and the lack of clear standards for PROM utilization. In this paper, we have discussed these challenges, illustrated by breast cancer instruments. [ABSTRACT FROM AUTHOR]

In breast cancer, most of the patients who died, have developed bone metastasis as disease progression. Bone metastases in case of breast cancer are mainly bone destructive (osteolytic). To understand pathogenesis and to analyse response to different treatments, animal models, in our case rats, are examined. For assessment of treatment response to bone remodelling therapies exact segmentations of osteolytic lesions are needed. Manual segmentations are not only time-consuming but lack in reproducibility. Computerized segmentation tools are essential. In this paper we present an approach for the computerized quantification of osteolytic lesion volumes using a comparison to a healthy reference model. The presented qualitative and quantitative evaluation of the reconstructed bone volumes show, that the automatically segmented lesion volumes complete missing bone in a reasonable way. [ABSTRACT FROM AUTHOR]

Early detection of breast cancer is carried out by using mammographic images. Due to low contrast nature of these images, it is difficult to detect signs such as microcalcifications and masses. This paper describes novel algorithms for early detection of breast cancer using image enhancement techniques to identify masses and microcalcifications. We implemented algorithm for 1) Image enhancement using wavelets and adaptive histogram equalization technique 2) Segmentation of masses is done using region growing technique 3) Extraction of border of the mass using canny edge detection and morphological operations. Bilateral asymmetry was detected using fluctuating asymmetry [9]. The paper presents case studies of four patients, though fourteen patient breast images are processed having different mammographic features. [ABSTRACT FROM PUBLISHER]

Breast cancer is the leading cause of deaths among women. To reduce the number of deaths, early diagnosis and treatment have been pointed at as the most reliable approach. This paper introduces the application of cluster-knearest neighbor for breast cancer diagnosis. First, we apply wavelet transform to extract features. Feature selection is applied to select the most relevant features out of the huge number of coefficients that are extracted. After that, we apply the cluster-k-nearest neighbor classifier for classification. [ABSTRACT FROM AUTHOR]

Breast cancer is one of the most common fatal diseases in women. Early detection of malignant breast cancer could be a great help in treating this cancer. Many studies have been performed in order to detect the malignant of cancer tumor till now. It has been tried to contribute more in accurate diagnosis of breast cancer by Support Vector Machine, in this paper. LS and SMO methods have been utilized instead of conventional learning method of QP in SVM in this probe. The feasibility of 100 percent in sensitivity for LS-SVM, and 100 percent in specificity for SMO-SVM has been achieved in this assay by the proposed method, which this percentage has not been achieved so far in the previous studies. The highest value among the previous studies has been presented by the obtained accuracy in LS-SVM method. [ABSTRACT FROM PUBLISHER]

Breast cancer remains one of the deadliest diseases among women. Microcalcifications can be an early indicator of a breast cancer. Thus when they are present their detection during a screening test is very crucial. But due to their small size and low contrast in mammographies their detection is difficult. Therefore many computer aided diagnosis mathods have been developped to help and assist rediologist during their screening tests. This paper presents a novel approach to detect microcalcifications on digitized mammaographies using fuzzy logic and support vector machines. Our method was tested on 16 mammograms from Mias database including both positive and negative cases. We have obtained very satisfactory results with a sensitivity of 99,60% and a specificity of 99,11% during the learning phase. [ABSTRACT FROM PUBLISHER]

In the paper, we proposed a mass detection method based on texture analysis and neural classifier. The proposed mass detection method is composed of two parts: ROI selection, feature extraction, and neural classifier. ROI selection is used to reduce the computational complexity of the proposed scheme. In the texture analysis, the intensity and texture information extracted from spatial and wavelet domains are utilized to find the candidates of mass regions. These texture features are extracted and combined with a supervised neural network to be classifier. The experimental result shows that the average recall rate of our proposed scheme is more than 93%. The result demonstrates that our proposed method can achieve mass detection. [ABSTRACT FROM PUBLISHER]

Tomlins et al. (2005) found that the differential expressed genes might only exist in a subset of the cancer group, rather than in all samples of the group. From then on, lots of methods have been proposed by considering this point. In this paper, we first surveyed the recent research progress of detection methods for differential gene expression (DGE) in micro array data of cancer subgroup, and then applied six commonly used methods to simulated data and database provided by West. Through analyzing experimental results, we compared the performance of the six detection methods. This paper performs a comprehensive comparison study of currently popular detection methods of differential gene expression for micro array data analysis with regard to over-expressed cancer subgroup. The obtained results are helpful for dealing with micro array data using detection methods. [ABSTRACT FROM PUBLISHER]

Survival analysis is an important part of medical statistics or for the study of failures in mechanical systems. The latter is called reliability analysis in engineering. This paper addresses the survival analysis in medical research. In this context of medical research, the survival analysis is frequently used to define prognostic indices for survival or recurrence of a disease, and to study outcome of treatment. Within the broader domain of medical survival analysis or more specifically for the study of patients with cancer disease, there are a number of clinical/prognostic techniques developed over the last half of century in many research groups, universities and hospitals around the globe. Despite numerous publications on each of these techniques, there is still a need of evaluating the numerical outputs of the different prognostic algorithms on identical medical datasets. Hence the need to benchmark the mathematical algorithms against the available medical and other cancer datasets held by various research groups from universities or hospitals. The main scope of a benchmark process is to specifically inform and to provide prognostic advice and choice of post-operative adjuvant therapy. It is also essential to define data acquisition protocols, to create the necessary databases on which the benchmarked methodologies can be tested. In case there are several research groups which are taking part in a benchmark study, then they form a multicentre study. This paper presents the steps to be followed in order to realize such a multicentre study. [ABSTRACT FROM PUBLISHER]

This paper proposes a novel background subtraction method to detect microcalcifications. The proposed method is a Laplacian pyramid scheme with the low pass filter replaced by the squeeze box filter (SBF). The SBF was originally developed to remove speckle noise from medical B mode ultrasound images. The SBF is adapted to identify the background of mammographic images. Thus microcalcifications can be isolated in regions of interest to enhance visual examination or automatic detection methods. [ABSTRACT FROM PUBLISHER]

Computer Aided Diagnosis (CAD) was approved to automate breast cancer detection with mammograms in 1998. But due to the great variability in tumor sizes and shapes, and underlying breast tissue structures, pattern recognition algorithms have a difficult time adapting to different situations. In this paper, a marker-controlled watershed segmentation algorithm was developed to locate breast mass tumor candidates. The approach first selected foreground and background markers, and then applied watershed segmentation algorithm to isolate a tumor region from its surrounding tissue. Since watershed segmentation is based on pixel density variation that is present in all mass tumors, the proposed approach was fairly successful in locating tumors under all conditions. Experiment results with Mammographic Image Analysis Society (MIAS) data set showed the overall detection rate for mass tumors is 90%. [ABSTRACT FROM PUBLISHER]

Breast cancer is one of the main causes of death among American women. The use of screening mammography is widely recommended for early diagnosis of breast cancer. In this paper, we propose a highly efficient algorithm for medical mammogram image classification, based on the generalized Beta mixture model. The proposed method, first extracts texture information from mammographic images then model it using the generalized Beta mixture models. For classification, we use the Earth Mover Distance (EMD) metric. Our work is motivated by the fact that mammographic images contain non-Gaussian texture characteristics, impossible to model using rigid distributions like the Gaussian. Experimental results are provided to show the merits of the proposed approach. [ABSTRACT FROM PUBLISHER]