A SVM-based approach to microwave breast cancer detection

Early breast cancer detection is of crucial importance: this form of cancer is the second most common cause of death among women due to malignant tumors, whereas early detection leads to longest survival or even full recovery. Conventional X-ray mammography possesses a range of shortcomings and new techniques must be developed. Features of microwave breast imaging make it an attractive alternative. The aim of the present work is to propose a 3-D approach based on support vector machine classifier whose output is transformed to a posteriori probability of tumor presence. Like confocal microwave imaging introduced by S.C. Hagness et al., the present approach is aimed at detecting tumor locations directly, avoiding solving computationally extensive inverse scattering problem. Microwave data have been generated using finite element method with impedance boundary conditions. Noisy environments have been considered as well. The obtained probability maps demonstrate that the region around the tumor location usually clearly stands out against the background of overall probability values.     

Enhanced waveguide bandpass filters using S‐shaped resonators

This article presents a new solution for stopband performance improvement of rectangular waveguide bandpass filters using S‐shaped resonator loaded waveguide configurations at microwave and millimeter‐wave frequencies. The proposed filter structure is compact in size when comparing with the standard E‐plane counterpart. Compactness is achieved by taking advantage of the properties of slow wave effect in half wavelength resonators. Periodicity is readily imposed upon cascading the S‐shaped resonators within the rectangular waveguide. The structure is simple and compatible with E‐plane technology. This type of bandpass filters can be easily realized with a single metallo‐dielectric insert within a standard rectangular waveguide. Simulation and experimental results are presented to validate the argument along with some design guidelines. © 2009 Wiley Periodicals, Inc. Int J RF and Microwave CAE 2009.     

Low loss and broadband transition between substrate integrated waveguide and rectangular waveguide

In this article, a novel transition between substrate integrated waveguide (SIW) and rectangular waveguide is proposed. A pair of antipodal tapered probes is developed to convert the E‐field of SIW to that of waveguide, acting as an antipodal dipole antenna to improve the performance of the SIW‐to‐waveguide transition. A back‐to‐back prototype of the proposed transition is fabricated and measured, the results show that the transition achieve a bandwidth of 51.1% from 23.7 to 40 GHz, and a size reduction of 75.3% compared to the SIW‐to‐waveguide transition using antipodal fin‐line. A tolerance analysis is performed via the simulation to verify the reliability of this transition design. For further validation, the antipodal tapered probes are employed for the design of partially filled SIW‐to‐waveguide transition. From its experimental results, it demonstrates that the loss of a single SIW‐to‐waveguide is less than 0.26 dB over the frequency range of 24.9–40 GHz. In addition, such proposed SIW‐to‐waveguide transition is suitable for hermetic packaging due to the inherent property in transition structure. These results show that the proposed transition can offer the advantages of broad bandwidth, low loss, compact size, and stable performance at millimeter‐wave frequencies. © 2015 Wiley Periodicals, Inc. Int J RF and Microwave CAE 26:54–61, 2016.     

Planar array of corrugated tapered slot antennas for ultrawideband biomedical microwave imaging system

A planar antenna array that includes 12 corrugated tapered slot elements for use in ultrawideband (UWB) biomedical microwave imaging systems is presented. The used corrugate tapered slot antenna has a compact size, low profile, moderate gain, and distortionless performance in the time domain. The array is immersed in a carefully designed matching liquid of suitable dielectric constant to improve the matching between the array and the imaged object, and thus, to increase the dynamic range of the imaging system. A suitable platform is designed and fabricated to accommodate the array, breast phantom, and a coupling liquid for the case of UWB breast imaging. The design of the whole system is optimized using trust‐region framework method in the simulation tool CST Microwave Studio. The performance of the designed array is confirmed via measurements in a realistic imaging environment. © 2012 Wiley Periodicals, Inc. Int J RF and Microwave CAE, 2013.     

一种快速微波断层成像方法的研究*

为便于微波断层成像技术的应用普及,针对乳腺肿瘤二维微波断层成像在个人计算机上的实现,提出了一种二次成像的快速方法。该方法首先采用一个粗网快速成像确定出目标图像位置,然后再使用在目标区域局部加密后的精细网,进行二次精确成像。基于仿真和实验数据的成像结果表明,与传统的采用全局精细网一次成像方法相比,这种二次成像方法可以大大降低成像计算的复杂度,节省80%左右的成像时间,同时可以获得等价的目标成像质量。     

Performance Analysis of Breast Cancer Detection Method Using ANFIS Classification Approach

Breast cancer is one of the deadly diseases prevailing in women. Earlier detection and diagnosis might prevent the death rate. Effective diagnosis of breast cancer remains a significant challenge, and early diagnosis is essential to avoid the most severe manifestations of the disease. The existing systems have computational complexity and classification accuracy problems over various breast cancer databases. In order to overcome the above-mentioned issues, this work introduces an efficient classification and segmentation process. Hence, there is a requirement for developing a fully automatic methodology for screening the cancer regions. This paper develops a fully automated method for breast cancer detection and segmentation utilizing Adaptive Neuro Fuzzy Inference System (ANFIS) classification technique. This proposed technique comprises preprocessing, feature extraction, classifications, and segmentation stages. Here, the wavelet-based enhancement method has been employed as the preprocessing method. The texture and statistical features have been extracted from the enhanced image. Then, the ANFIS classification algorithm is used to classify the mammogram image into normal, benign, and malignant cases. Then, morphological processing is performed on malignant mammogram images to segment cancer regions. Performance analysis and comparisons are made with conventional methods. The experimental result proves that the proposed ANFIS algorithm provides better classification performance in terms of higher accuracy than the existing algorithms.     

Electronically controlled beam steering leaky wave antenna in nematic liquid crystal technology

A novel nematic liquid crystal (LC) technology‐based electronically controlled leaky wave antenna (LWA) with microstrip‐waveguide conversion working mechanism and wide beam steering range is presented in this article. The LWA is a combination of an inverted microstrip structure and rectangular waveguide. According to the characteristics of LC materials in microwave band, a broadband microstrip‐waveguide conversion device is proposed. The gradient slot leaky wave structure is combined with the microstrip‐waveguide conversion device to form an electronically controlled LWA with continuous tunable beam. Simulation and experiment results show that the LWA proposed in this article has a 32° beam scanning range at 12 GHz and good impedance matching and stable gain, suggesting the great potential of nematic LC materials for extensive applications in microwave band in the future.     

Ultrasound based application for intraglandular mapping of breast cancer

Purpose

Breast cancer is the most common malignant tumor among women worldwide. Breast cancer is one of the few cancers that can be early detected, and the survival rate of the women whose breast cancers are detected on their initial stage is virtually 100%. At the present time, ultrasound (US) is the most important imaging test together with the mammogram for the diagnostic evaluation of the breast. Recent studies have shown that ultrasound, in addition to mammography, helps doctors to spot significantly more cancers compared with mammograms alone.This work intends to standardize the process of the US breast examination, the storage and marking of the US images and their subsequent visualization and comparison.

Methods

It presents an innovative technique for the intraglandular mapping of breast cancer in a 3D scene. An anatomical based model of the breast is used for storage of the US images. Hardware equipment needed for the breast examination is described. Soft application programmed on Apple tools is fully described. The database for the storage is presented.

Results

First clinical applications of the presented tool are reported. Currently, the system is being distributed free of charge to clinical personal in order to evaluate its benefits.

Conclusions

A first version of an application to standardize the process of the US breast examination is presented. First reports show the feasibility of the system to be applied on clinics.     

超声乳腺肿瘤的全自动SVM检测与水平集分割算法

超声图像检测是当前乳腺癌诊断的主要辅助手段之一.为实现超声乳腺肿瘤的计算机自动辅助诊断,提出一种基于支持向量机(SVM)目标检测与水平集图像分割相结合的全自动肿瘤提取算法.首先提取超声图像训练集的分块特征来训练SVM分类器,对测试集图像进行检测得到可疑病灶区域;然后提取可疑区域边缘作为水平集的初始轮廓,使用加入Bhattacharyya距离项的Chan-Vese主动轮廓改进模型进行可疑病灶区域的轮廓演化,得到准确的轮廓;最后综合面积、位置、灰度、纹理等因素设计区域评价筛选准则,去除可疑病灶中的干扰区域,得到最终的肿瘤分割结果.在真实病例数据集上的测试结果表明,利用该算法在良恶性肿瘤检测分割中均有较好表现.     

Full band waveguide turnstile junction orthomode transducer with phase matched outputs

A >40% bandwidth fully scalable turnstile‐based waveguide orthomode transducer having excellent phase performance is described for the WR75 standard rectangular waveguide. Flexible bandwidth tuning is achieved through the use of an interchangeable stepped scattering element. Reduced height waveguide topology provides a simple, compact, and robust design against mechanical tolerances. The intrinsic broadband nature of half‐height E‐plane bends and single‐step power combiners assures high order mode free increased bandwidth in balanced phase operation. The designed orthomode transducer exhibits a return loss better than 23 dB at any port, an insertion loss less than 0.06 dB, and an isolation of 50 dB over the full bandwidth. Moreover, the phase difference between orthogonal polarizations is lower than 0.7° over the band, thus enabling applications where phase‐matched outputs are required. This design has been chosen for the QUIJOTE cosmic microwave background experiment due to its cost‐effective, compact design, and high‐quality performance as well as being readily scalable to the WR51 and WR28 waveguide bands. © 2010 Wiley Periodicals, Inc. Int J RF and Microwave CAE, 2010.     

Accurate and efficient design technique for wideband substrate integrated waveguide directional couplers

In this article, we present an efficient technique for the accurate design of wideband substrate integrate waveguide directional couplers. By tapering the coupling section, the bandwidth of substrate integrated waveguide (SIW) directional couplers can be enlarged. Two design aspects are involved in this approach. First, the even‐mode propagation constant in the tapered coupling section is accurately extracted with the help of a numerical thru‐reflect‐line calibration technique. Then, it is fitted into the model of a uniform dielectric‐filled rectangular waveguide and thereafter extrapolated to the operation range of the odd mode. Second, equivalent circuit models of the waveguide bifurcation effects are also presented together with parametric values. Based on the results of extraction, a 90° 3‐dB directional coupler is developed to validate the proposed design approach. To achieve the reverse phasing at two output ports, the prototyped 90° 3‐dB directional coupler is subsequently integrated with a novel broadband fixed phase shifter developed with the SIW technology, of which a systematic synthesis procedure has been proposed in this article. Measured performance of both 90° and 180° 3‐dB couplers confirms the accuracy of our proposed design approach. This kind of wide‐band directional coupler can find applications in wideband power dividing/combining circuits within a single‐layer platform. © 2011 Wiley Periodicals, Inc. Int J RF and Microwave CAE, 2012.     

结合MRF能量和模糊速度的乳腺癌图像分割方法

乳腺癌灶的精确分割是乳腺癌计算机辅助诊断的重要前提. 在动态对比增强核磁共振成像(Dynamic contrast-enhanced magnetic resonance imaging, DCE-MRI)的图像中, 乳腺癌灶具有对比度低、边界模糊及亮度不均匀等特点, 传统的活动轮廓模型方法很难取得准确的分割结果. 本文提出一种结合马尔科夫随机场(Markov random field, MRF)能量和模糊速度函数的活动轮廓模型的半自动分割方法来完成乳腺癌灶的分割, 相对于专业医生的手动分割, 本文方法具有速度快、可重复性高和分割结果相对客观等优点. 首先, 计算乳腺DCE-MRI图像的MRF能量, 以增强目标区域与周围背景的差异. 其次, 在能量图中计算每个像素点的后验概率, 建立基于后验概率驱动的活动轮廓模型区域项. 最后, 结合Gabor纹理特征、DCE-MRI时域特征和灰度特征构建模糊速度函数, 将其引入到活动轮廓模型中作为边缘检测项. 在乳腺癌灶边界处, 该速度函数趋向于零, 活动轮廓曲线停止演变, 完成对乳腺癌灶的分割. 实验结果表明, 所提出的方法有助于乳腺癌灶在DCE-MRI图像中的准确分割.     

基于触诊成像的肿块识别系统研究与设计

乳腺癌的早期发现对于乳腺癌的治疗有十分重要的意义,设计了基于触诊成像的肿块识别系统。该系统由压力信号检测单元、信号控制单元和图像处理单元组成,压力信号检测单元实现压力信号的采集,信号控制单元由FPGA控制多路开关的选通来扫描压力阵列传感器的电容信号,并将数据通过EZ-USB发送给上位机,图像处理单元对压力图像进行处理来滤除噪声。其中图像处理单元是该系统的枢纽,运用最小二乘曲面拟合校正压力图像,最大类间方差法和基于滤波的图像邻域评级技术对压力图像进行分割,对压力图像进行线性插值来提高图像分辨率。实验结果表明,该系统可以在复杂噪声图像中有效地识别出肿块。     

Automatic nipple detection in breast thermograms

Breast cancer is one of the most dangerous diseases for women. Detecting breast cancer in its early stage may lead to a reduction in mortality. Although the study of mammographies is the most common method to detect breast cancer, it is outperformed by the analysis of thermographies in dense tissue (breasts of young women). In the last two decades, several computer-aided diagnosis (CAD) systems for the early detection of breast cancer have been proposed. Breast cancer CAD systems consist of many steps, such as segmentation of the region of interest, feature extraction, classification and nipple detection. Indeed, the nipple is an important anatomical landmark in thermograms. The location of the nipple is invaluable in the analysis of medical images because it can be used in several applications, such as image registration and modality fusion. This paper proposes an unsupervised, automatic, accurate, simple and fast method to detect nipples in thermograms. The main stages of the proposed method are: human body segmentation, determination of nipple candidates using adaptive thresholding and detection of the nipples using a novel selection algorithm. Experiments have been carried out on a thermograms dataset to validate the proposed method, achieving accurate nipple detection results in real-time. We also show an application of the proposed method, breast cancer classification in dynamic images, where the new nipple detection technique is used to segment the region of the two breasts from the infrared image. A dataset of dynamic thermograms has been used to validate this application, achieving good results.     

RF breast cancer detection employing a noncharacterized vivaldi antenna and a MUSIC‐inspired algorithm

A novel microwave breast cancer detection system consisting of an Evolutionary Global Optimized Vivaldi antenna and an algorithm inspired by MUltiple SIgnal Classification (MUSIC) is presented. Its performance is assessed by using a simplified numerical breast phantom for a number of critical conditions including the presence of fibroglandular tissues. © 2012 Wiley Periodicals, Inc. Int J RF and Microwave CAE, 2013.     

Breast cancer image assessment using an adaptative network-based fuzzy inference system

In Brazil breast cancer is the foremost cause of fatality by cancer for women. Given that the causes are unidentified, it cannot be prevented. Mammography is one of the most reliable exams for breast cancer detection and it is based on image analysis by radiologists. Early detection is the key issue for breast cancer control and computer-aided diagnosis system can help ra diologists in detection and diagnosing breast abnormalities. Hybrid neuro-fuzzy systems are suitable for pattern recognition tasks and therefore useful for medical diagnosis support through pattern identification in mammographic images. This study presents an Adaptative Network-based Fuzzy Inference System (ANFIS) that classifies the mammographic images calcification region of interest as benign or malign and provides an important tool for breast cancer image assessment. The ANFIS model, utilized in the mammogram region of interest’s classification phase, reached a maximum accuracy rate of 99.75%.     

Sidelobe reduction based on spectrum reshaping in microwave imaging

Sidelobe artifacts are a common problem in image reconstruction from finite-extent Fourier data obtained by microwave imaging system.In order to enhance the image quality,sidelobe reduction must be implemented.Taking the sidelobe reduction in microwave imaging as the research subject,this paper presents Fourier imaging technique firstly.Then the point spread function is obtained through Fourier inversion of rectangular spectral support data and the changing effect of sidelobe direction due to reshaping spec...     

RETRACTED ARTICLE: An improved data mining technique for classification and detection of breast cancer from mammograms

The high incidence of breast cancer in women has increased significantly in the recent years. Mammogram breast X-ray imaging is considered the most effective, low-cost, and reliable method in early detection of breast cancer. Although general rules for the differentiation between benign and malignant breast lesion exist, only 15–30% of masses referred for surgical biopsy are actually malignant. Physician experience of detecting breast cancer can be assisted by using some computerized feature extraction and classification algorithms. Computer-aided classification system was used to help in diagnosing abnormalities faster than traditional screening program without the drawback attribute to human factors. In this work, an approach is proposed to develop a computer-aided classification system for cancer detection from digital mammograms. The proposed system consists of three major steps. The first step is region of interest (ROI) extraction of 256 × 256 pixels size. The second step is the feature extraction; we used a set of 26 features, and we found that these features are capable of differentiating between normal and cancerous breast tissues in order to minimize the classification error. The third step is the classification process; we used the technique of the association rule mining to classify between normal and cancerous tissues. The proposed system was shown to have the large potential for cancer detection from digital mammograms.

     

A microfluidic sensor based on ferromagnetic resonance induced in magnetic bead labels

This report details preliminary studies towards the development of a microfluidic sensor that exploits ferromagnetic resonance, excited in magnetic bead labels, for signal transduction. The device consists of a microwave circuit in which a slotline and a coplanar waveguide are integrated with a biochemically activated sensor area. The magnetic beads are immobilized in the sensor area by bio-specific reactions. A microwave signal applied to the slotline is coupled to the coplanar waveguide only in the presence of magnetic beads at the functionalized sensor area. Ferromagnetic resonance in the beads further enhances the coupling. This inductive detection technique lends itself to miniaturization, is inexpensive to fabricate and can be adapted for the detection of a wide range of molecules for which bio-specific ligands are available.Experimentally, the variation of the output signal as a function of the location of magnetic beads was studied for the proposed technique. Subsequently, a prototype device was constructed by biotinylation of the sensor area and integration with a microfluidic chip fabricated in polydimethyl siloxane (PDMS). Preliminary experiments were conducted on this prototype using streptavidin-functionalized magnetic beads as labels. It was shown that the magnetic beads, immobilized at the sensor area by streptavidin-biotin linkage, produced a distinct ferromagnetic resonance response easily discernable from the background signal.