Ieee transactions on antennas and propagation

Breast cancer is one of the most frequent malignancies among women worldwide. Methods for screening and diagnosis allow health care professionals to provide personalized treatments that improve the outcome and survival. Scientists and physicians are working side-by-side to develop evidence-based guidelines and equipment to detect cancer earlier. However, the lack of comprehensive interdisciplinary information and understanding between biomedical, medical, and technology professionals makes innovation of new screening and diagnosis tools difficult. This critical review gathers, for the first time, information concerning normal breast and cancer biology, established and emerging methods for screening and diagnosis, staging and grading, molecular and genetic biomarkers. Our purpose is to address key interdisciplinary information about these methods for physicians and scientists. Only the multidisciplinary interaction and communication between scientists, health care professionals, technical experts and patients will lead to the development of better detection tools and methods for an improved screening and early diagnosis.

/pdf/breast-cancer-screening-and-diagnostic-tools-all-you-need-to-3z9ztv9v3p.pdf

Breast cancer, screening and diagnostic tools: All you need to know.

Breast cancer plays a significant role in affecting female mortality. Researchers are actively seeking to develop early detection methods of breast cancer. Several technologies contributed to the reduction in mortality rate from this disease, but early detection contributes most to preventing disease spread, breast amputation and death. Thermography is a promising technology for early diagnosis where thermal cameras employed are of high resolution and sensitivity. The combination of Artificial Intelligence (AI) with thermal images is an effective tool to detect early stage breast cancer and is foreseen to provide impressive predictability levels. This paper reviews systematically the related works employing thermography with AI highlighting their contributions and drawbacks and proposing open issues for research. Several different types of Artificial Neural Networks (ANNs) and deep learning models were used in the literature to process thermographic images of breast cancer, such as Radial Basis Function Network (RBFN), K-Nearest Neighbors (KNN), Probability Neural Network (PNN), Support Vector Machine (SVM), ResNet50, SeResNet50, V Net, Bayes Net, Convolutional Neural Networks (CNN), Convolutional and DeConvolutional Neural Networks (C-DCNN), VGG-16, Hybrid (ResNet-50 and V-Net), ResNet101, DenseNet and InceptionV3. Previous studies were found limited to varying the numbers of thermal images used mostly from DMR-IR database. In addition, analysis of the literature indicate that several factors do affect the performance of the Neural Network used, such as Database, optimization method, Network model and extracted features. However, due to small sample size used, most of the studies achieved a classification accuracy of 80% to 100%.

/pdf/a-systematic-review-of-breast-cancer-detection-using-3sly01r0bw.pdf

A Systematic Review of Breast Cancer Detection Using Thermography and Neural Networks

Breast cancer is not preventable To reduce the death rate and improve the survival chances of breast cancer patients, early and accurate detection is the only panacea Delay in diagnosis of this disease causes 60% of deaths Thermal imaging is a low-risk modality for early breast cancer decision making without injecting any form of energy into the human body Thermography as a screening tool was first introduced and well accepted in 1956 However, a study in 1977 found that it lagged behind other screening tools and is subjective Soon after, its use was discontinued This review discusses various screening tools used to detect breast cancer with a focus on thermography along with their advantages and shortcomings With the maturation of thermography equipment and technological advances, this technique is emerging and has become the refocus of many biomedical researchers across the globe in the past decade This study dispenses an exhaustive review of the work done related to interpretation of breast thermal variations and confers the discipline, frameworks, and methodologies used by different authors to diagnose breast cancer Different performance metrics like accuracy, specificity, and sensitivity have also been examined This paper outlines the most pressing research gaps for future work to improvise the accuracy of results for diagnosis of breast abnormalities using image processing tools, mathematical modelling and artificial intelligence However, supplementary research is needed to affirm the potential of this technology for predicting breast cancer risk effectively Altogether, our findings inform that it is a promising research problem and a potential solution for early detection of breast cancer in younger women

Thermal Imaging - An Emerging Modality for Breast Cancer Detection: A Comprehensive Review

This article proposes gain-enhanced circular patch antenna and array with introduction of multiple shorting pins. The antenna consists of a circular patch and several shorting pins. Equivalent inductance is brought to the patch after introducing shorting pins. Thus, resonance of the patch shifts at higher frequency. Compared to a conventional circular patch without any pins, radiation area of the proposed patch is enlarged given the same resonance frequency, hence leads to gain enhancement. The number of pins introduced to a circular patch can be set freely due to its symmetrical feature. Moreover, surface current is restricted within a small area around the center of the patch after introducing multiple pins, leading to more concentrated radiation. An equivalent circuit model is built for the proposed antenna. Layout and number optimization rules for introducing shorting pins are formulated. With these rules, gain of a circular patch can be maximized for the applications under certain size restrictions. A prototype operating at 5.8 GHz is designed and fabricated. Furthermore, a 2*2 array based on the gain-enhanced circular patch elements is implemented. In the measurements, high gain, high efficiency, and narrowed half-power beamwidth of the patch antenna and the array are observed.

High-Gain Circular Patch Antenna and Array With Introduction of Multiple Shorting Pins

Prolonging network lifetime by salvaging the energy of low battery capacity nodes is a prime concern in Wireless Sensor Networks. Energy efficient routing protocols try to improve the node lifetime by restricting their participation in the routing process. This leads to selfish node behavior causing disruption of inherent network cooperation. This paper proposes an elegant routing mechanism based on direct reciprocity principle, named energy efficient cooperative ad hoc on-demand distance vector (EECoAODV). Proposed protocol correctly differentiates between inherently selfish nodes that use the energy of other nodes to relay their packets, but refuse to reciprocate; and the energy critical nodes that have turned non-cooperative for their own survival. Selfish nodes are punished and eliminated from the routing process thus prolonging the battery capacity of energy critical nodes to improve the overall network performance. EECoAODV is implemented in Qualnet simulator and its performance is compared with conventional AODV and reinforcement based stateaction-reward-action (SARSA) routing mechanism. Results show that EECoAODV improves the lifetime of energy critical nodes and thus delivers improved packet delivery ratio than SARSA-AODV and conventional AODV.

/pdf/reciprocity-based-energy-efficient-cooperative-routing-41z7va1b72.pdf

Reciprocity based Energy Efficient Cooperative Routing Protocol for WSNs

Image registration, a technique of alignment of two different images sharing familiar information, is a crucial step in most of image processing applications that needs visual information from numerous images for evaluation or analysis. Four image processing techniques viz. geometric transformation, discrete cosine transform, phase correlation & log polar transform (LPT) for image registration are implemented. However, limitations in terms of implementation of all these operations simultaneously still exist in image registration applications. This paper provides in depth analysis of LPT, its advantages like relevant information to medical practitioner. Log-polar techniques are proposed to address above limitation so that all these operations can be carried out in sink.

Image registration on biomedical images with composite algorithm

Objectives: To propose a better image fusion approach for detecting different stages of cancer and suggesting suitable technique for treating cancer to medical practitioners. Methods: Diagnosis of cancerous region is carried out by wavelet based fusion technique on PET/CT images and the thermal effect on cancer tissue growth is analysed using RF module of COMSOL-Multi-physics software. Findings: Multimodal image fusion technique helps to identify the growth of object which is carried out by wavelet technique. The Computed Tomography (CT) scan helps to determine extent of the cancer, while Positron Emisson Tomography (PET) scan finds areas of cancer spread. There after the results acquired will enhance visual effect and help the medical practitioners to examine the development of tumour. In case of tumour, cell spreads beyond the infected portion of the organ, treatment using chemotheraphy is harmful while, surgery can be fatal, and hence Radio Frequency (RF) heating technique may be a better solution. The important issue in cancer treatment is to bind the area of human body under the RF energy influence, to avoid unwanted radiation or heating effects on healthy human tissue. Applications: The results acquired will enhance visual effect and help the medical practitioners to examine development of tumour. Further in this paper, the various graphs of temperature variation, electric field distribution, degree of tissue injured, at various times instant versus cancer region are plotted, also expression for the space Eletromagnetic (EM) wave propagation and its mathematical analysis is carried out.

Diagnosis of Abdominal Cancer Tumour by Fusion Technique and Treatment using Radio Frequency Heat

One of the applications of machine learning is analysis of a multi-parameter patient monitoring system. A python 3.7 or higher-based system is developed which can be used in paramedicine to execute different ML algorithms with available datasets such as ECG, heartbeat signal, Blood oxygen saturation (SPO2), temperature, and generates different signals from the data set. This Machine learning-based Multi-Parameter Monitoring (MPM) system is designed in which parameters are monitored by utilizing corresponding sensors and analyzing the parameters using different ML algorithms. In the proposed system sensors and hardware parts are omitted and outputs of sensors are directly taken from the available sources for implementation. The project focuses on improving the performance of a multi-parameter patient monitoring system using machine learning classifier algorithms such as Support Vector Machine (SVM), Random Forest, and Naive Bayes classifiers. Although, other ML classifier algorithm are also available, but from practical implementation point of view these three algorithms provide good results. For data analysis, these three-machine learning-based classifier algorithms are used, and datasets are collected online and arranged in a particular sequence. These datasets are trained, tested, and analyzed using machine learning. At last, the results of all classifiers are compared with each other. Based on this comparison, the one with good result is used to decide patient's health condition. 

Analysis of IoT based multi-parameter patient monitoring system using machine learning

Cancer is the leading risk factor for death. It is critical to develop effective methods for identifying cancer types and detecting them early. Because of the TCGA (The Cancer genome atlas), genomic data is now more widely available and used extensively. This study applies machine learning techniques to an RNA-Seq gene expression dataset to classify the many types and subtypes of cancer. These datasets typically have multiple dimensions and hundreds of columns with no labels. Because of this, creating high-performing production models requires a certain machine learning implementation. The development and application of machine learning models for the study of genomic datasets is continued in this research work. Machine learning methods are employed to examine and compare cancer categorization in our study. Decision Tree, Naive Bayes, Support Vector Machine (SVM), K-Nearest Neighbour (KNN) and Random Forest are the algorithms used. The dataset is high throughput sequencing RNA seq data which includes 22 types of cancer along with their subtypes as well as normal types of samples. To improve model accuracy, the data is preprocessed, oversampling technique SMOTE and feature selection approaches are applied. As a result, we have compared the comparative parameters like accuracy, area under the ROC Curve (AUC) score, precision, recall, F1 score and receiver operating characteristic curve (ROC) curve. The results show that SVM shows the best accuracy when feature selection and oversampling technique is applied.

R. N. Awale

Papers

Reciprocity based Energy Efficient Cooperative Routing Protocol for WSNs

Image registration on biomedical images with composite algorithm

Diagnosis of Abdominal Cancer Tumour by Fusion Technique and Treatment using Radio Frequency Heat

Analysis of IoT based multi-parameter patient monitoring system using machine learning

Performance Analysis of Various Cancers Using Genetic Data with Variance Threshold