Quasi-multistatic MIST beamforming for the early detection of breast cancer

Synthetic Microwave Focusing Techniques for Medical Imaging: Fundamentals, Limitations, and Challenges

Synthetic microwave focusing methods have been widely adopted in qualitative medical imaging to detect and localize anomalies based on their electromagnetic scattering signatures. This paper discusses the principles, challenges, and limitations of synthetic microwave-focusing techniques in medical applications. It is shown that the various focusing techniques, including time reversal, confocal imaging, and delay-and-sum, are all based on the scalar solution of the electromagnetic scattering problem, assuming the imaged object, i.e., the tissue or object, is linear, reciprocal, and time-invariant. They all aim to generate a qualitative image, revealing any strong scatterer within the imaged domain. The differences among these techniques lie only in the assumptions made to derive the solution and create an image of the relevant tissue or object. To get a fast solution using limited computational resources, those methods assume the tissue is homogeneous and non-dispersive, and thus, a simplified far-field Green's function is used. Some focusing methods compensate for dispersive effects and attenuation in lossy tissues. Other approaches replace the simplified Green's function with more representative functions. While these focusing techniques offer benefits like speed and low computational requirements, they face significant ongoing challenges in real-life applications due to their oversimplified linear solutions to the complex problem of non-linear medical microwave imaging. This paper discusses these challenges and potential solutions.

Applying dual models on optimized LSTM with U-net segmentation for breast cancer diagnosis using mammogram images

BACKGROUND OF THE STUDY

Breast cancer is the most fatal disease that widely affects women. When the cancerous lumps grow from the cells of the breast, it causes breast cancer. Self-analysis and regular medical check-ups help for detecting the disease earlier and enhance the survival rate. Hence, an automated breast cancer detection system in mammograms can assist clinicians in the patient's treatment. In medical techniques, the categorization of breast cancer becomes challenging for investigators and researchers. The advancement in deep learning approaches has established more attention to their advantages to medical imaging issues, especially for breast cancer detection.

AIM

The research work plans to develop a novel hybrid model for breast cancer diagnosis with the support of optimized deep-learning architecture.

METHODS

The required images are gathered from the benchmark datasets. These collected datasets are used in three pre-processing approaches like "Median Filtering, Histogram Equalization, and morphological operation", which helps to remove unwanted regions from the images. Then, the pre-processed images are applied to the Optimized U-net-based tumor segmentation phase for obtaining accurate segmented results along with the optimization of certain parameters in U-Net by employing "Adapted-Black Widow Optimization (A-BWO)". Further, the detection is performed in two different ways that is given as model 1 and model 2. In model 1, the segmented tumors are used to extract the significant patterns with the help of the "Gray-Level Co-occurrence Matrix (GLCM) and Local Gradient pattern (LGP)". Further, these extracted patterns are utilized in the "Dual Model accessed Optimized Long Short-Term Memory (DM-OLSTM)" for performing breast cancer detection and the detected score 1 is obtained. In model 2, the same segmented tumors are given into the different variants of CNN, such as "VGG19, Resnet150, and Inception". The extracted deep features from three CNN-based approaches are fused to form a single set of deep features. These fused deep features are inserted into the developed DM-OLSTM for getting the detected score 2 for breast cancer diagnosis. In the final phase of the hybrid model, the score 1 and score 2 obtained from model 1 and model 2 are averaged to get the final detection output.

RESULTS

The accuracy and F1-score of the offered DM-OLSTM model are achieved at 96 % and 95 %.

CONCLUSION

Experimental analysis proves that the recommended methodology achieves better performance by analyzing with the benchmark dataset. Hence, the designed model is helpful for detecting breast cancer in real-time applications.

Evaluating the Performance of Algorithms in Axillary Microwave Imaging towards Improved Breast Cancer Staging

Breast cancer is the most common and the fifth deadliest cancer worldwide. In more advanced stages of cancer, cancer cells metastasize through lymphatic and blood vessels. Currently there is no satisfactory neoadjuvant (i.e., preoperative) diagnosis to assess whether cancer has spread to neighboring Axillary Lymph Nodes (ALN). This paper addresses the use of radar Microwave Imaging (MWI) to detect and determine whether ALNs have been metastasized, presenting an analysis of the performance of different artifact removal and beamformer algorithms in distinct anatomical scenarios. We assess distinct axillary region models and the effect of varying the shape of the skin, muscle and subcutaneous adipose tissue layers on single ALN detection. We also study multiple ALN detection and contrast between healthy and metastasized ALNs. We propose a new beamformer algorithm denominated Channel-Ranked Delay-Multiply-And-Sum (CR-DMAS), which allows the successful detection of ALNs in order to achieve better Signal-to-Clutter Ratio, e.g., with the muscle layer up to 3.07 dB, a Signal-to-Mean Ratio of up to 20.78 dB and a Location Error of 1.58 mm. In multiple target detection, CR-DMAS outperformed other well established beamformers used in the context of breast MWI. Overall, this work provides new insights into the performance of algorithms in axillary MWI.

Microwave Imaging for Early Breast Cancer Detection: Current State, Challenges, and Future Directions

Breast cancer is the most commonly diagnosed cancer type and is the leading cause of cancer-related death among females worldwide. Breast screening and early detection are currently the most successful approaches for the management and treatment of this disease. Several imaging modalities are currently utilized for detecting breast cancer, of which microwave imaging (MWI) is gaining quite a lot of attention as a promising diagnostic tool for early breast cancer detection. MWI is a noninvasive, relatively inexpensive, fast, convenient, and safe screening tool. The purpose of this paper is to provide an up-to-date survey of the principles, developments, and current research status of MWI for breast cancer detection. This paper is structured into two sections; the first is an overview of current MWI techniques used for detecting breast cancer, followed by an explanation of the working principle behind MWI and its various types, namely, microwave tomography and radar-based imaging. In the second section, a review of the initial experiments along with more recent studies on the use of MWI for breast cancer detection is presented. Furthermore, the paper summarizes the challenges facing MWI as a breast cancer detection tool and provides future research directions. On the whole, MWI has proven its potential as a screening tool for breast cancer detection, both as a standalone or complementary technique. However, there are a few challenges that need to be addressed to unlock the full potential of this imaging modality and translate it to clinical settings.

Wearable Dual Polarized Electromagnetic Knee Imaging System

With the increasing uptake of sport activities, onsite detection of associated knee injuries at early stages is in high demand to avoid severe ligament tear and long treatment period. Portable electromagnetic imaging (EMI) systems have the potential to meet that demand, but there are challenges. For example, EMI is based on the contrast in the dielectric properties due to the accumulated fluid after knee injury. However, that fluid can be in any shape and orientation. Therefore, to capture enough data for processing, EMI should operate as a dual-polarized wearable system with compact antennas. Thus, the proposed system is a textile brace worn on the knee and consists of an 8-element dual-polarized aperture antenna array, which is matched with the knee. Each of the utilized antennas is fed by two orthogonal coaxial feed, occupies a small size of 36 ×36 ×3.1 mm³, and is backed by a full ground plane for unidirectional radiation. The antenna covers the band 0.7-3.3 GHz (130%), with front to back ratio of more than 10 dB. The textile wool-felt is used as the substrate to enable building flexible brace system. The system's capability to reconstruct knee images with different injuries is verified on realistic knee models and phantoms. The double stage delay, multiply and sum algorithm (DS-DMAS) is used to reconstruct those images, which demonstrate the efficiency of the dual-polarized system and its superiority over single-polarized systems.

Feasibility of Electromagnetic Knee Imaging Verified on ex-vivo Pig Knees

OBJECTIVE

The potential of electromagnetic (EM) knee imaging system verified on ex-vivo pig knee joint as an essential step before clinical trials is demonstrated. The system, which includes an antenna array of eight printed biconical elements operating at the band 0.7-2.2 GHz, is portable and cost-effective. Importantly, it can provide daily monitoring and onsite real-time examinations imaging tool for knee injuries.

METHODS

Six healthy hind legs from three dead adult pigs were removed at the hip and suspended in the developed system. For each pig, the right- and left-knee were scanning sequentially. Then ligament tear was emulated by injecting distilled water into the left knee joint of each pig for early (5 mL water) and mid-stage (10 mL water) injuries. The injured left knees were re-scanned. A modified multi-static fast delay, multiply and sum algorithm (MS-FDMAS) is used to reconstruct imaging of the knee. All knees connective tissues, such as anterior and posterior cruciate ligaments (ACL, PCL), lateral and medial collateral ligaments (LCL, MCL), tendons, and meniscus, are extracted from a healthy hind leg along with collected synovial fluid. The extracted tissues and fluid were characterized and modelled as their data are not available in the literature, then imported to build an equivalent model for pig knee of 1 mm3 resolution in a realistic simulation environment.

RESULTS

The obtained results proved potential of the proposed system to detect ligament/tendon tears.

CONCLUSION

The proposed system has the potential to detect early knee injuries in a realistic environment.

SIGNIFICANCE

Contactless EM knee imaging system verified on ex-vivo pig joints confirms its potential to reconstruct knee images. This work lays the groundwork for clinical EM system for detecting and monitoring knee injuries.

Microwave breast tumor localization using wavelet feature extraction and genetic algorithm-neural network

PURPOSE

Ultra-Wide Band (UWB) microwave breast cancer detection is a promising new technology for routine physical examination and home monitoring. The existing microwave imaging algorithms for breast tumor detection are complex and the effect is still not ideal, due to the heterogeneity of breast tissue, skin reflection, and fibroglandular tissue reflection in backscatter signals. This study aims to develop a machine learning method to accurately locate breast tumor.

METHODS

A microwave-based breast tumor localization method is proposed by time-frequency feature extraction and neural network technology. First, the received microwave array signals are converted into representative and compact features by 4-level Discrete Wavelet Transform (DWT) and Principal Component Analysis (PCA). Then, the Genetic Algorithm-Neural Network (GA-NN) is developed to tune hyper-parameters of the neural network adaptively. The neural network embedded in the GA-NN algorithm is a four-layer architecture and 10-fold cross-validation is performed. Through the trained neural network, the tumor localization performance is evaluated on four datasets that are created by FDTD simulation method from 2-D MRI-derived breast models with varying tissue density, shape, and size. Each dataset consists of 1000 backscatter signals with different tumor positions, in which the ratio of training set to test set is 9:1. In order to verify the generalizability and scalability of the proposed method, the tumor localization performance is also tested on a 3-D breast model.

RESULTS

For these 2-D breast models with unknown tumor locations, the evaluation results show that the proposed method has small location errors, which are 0.6076 mm, 3.0813 mm, 2.0798 mm, and 3.2988 mm, respectively, and high accuracy, which is 99%, 80%, 94%, and 85%, respectively. Furthermore, the location error and the prediction accuracy of the 3-D breast model are 3.3896 mm and 81%.

CONCLUSIONS

These evaluation results demonstrate that the proposed machine learning method is effective and accurate for microwave breast tumor localization. The traditional microwave-based breast cancer detection method is to reconstruct the entire breast image to highlight the tumor. Compared with the traditional method, our proposed method can directly get the breast tumor location by applying neural network to the received microwave array signals, and circumvent any complicated image reconstruction processing.

3D printed PLA/copper bowtie antenna for biomedical imaging applications

This study aims to increase the performance of the microwave antenna by using 3D printed conductive substrates, which is mainly used in biomedical imaging applications. Conventional antennas such as Horn and Vivaldi have coarse dimensions to integrate into the microwave imaging systems. Therefore, 3D printed Bowtie antenna structures were developed, which yield low cost and smaller sizes. PLA, PLA/copper, and PLA/carbon substrates were produced with a 3D printer. These materials were tested in terms of their dielectric constants between 1 and 10 GHz. The conductive part of the antenna was copper, with a thickness of 0.8 mm, which was embedded in the substrate parts. The reflection coefficients of the antennas were tested within 0-3 GHz frequency range via miniVNA network analyzer. The results show that the 3D printed PLA/copper and PLA/carbon antenna are highly suitable for the usage in biomedical imaging systems.

Review of Microwaves Techniques for Breast Cancer Detection

Conventional breast cancer detection techniques including X-ray mammography, magnetic resonance imaging, and ultrasound scanning suffer from shortcomings such as excessive cost, harmful radiation, and inconveniences to the patients. These challenges motivated researchers to investigate alternative methods including the use of microwaves. This article focuses on reviewing the background of microwave techniques for breast tumour detection. In particular, this study reviews the recent advancements in active microwave imaging, namely microwave tomography and radar-based techniques. The main objective of this paper is to provide researchers and physicians with an overview of the principles, techniques, and fundamental challenges associated with microwave imaging for breast cancer detection. Furthermore, this study aims to shed light on the fact that until today, there are very few commercially available and cost-effective microwave-based systems for breast cancer imaging or detection. This conclusion is not intended to imply the inefficacy of microwaves for breast cancer detection, but rather to encourage a healthy debate on why a commercially available system has yet to be made available despite almost 30 years of intensive research.

Parameter Search Algorithms for Microwave Radar-Based Breast Imaging: Focal Quality Metrics as Fitness Functions

Inaccurate estimation of average dielectric properties can have a tangible impact on microwave radar-based breast images. Despite this, recent patient imaging studies have used a fixed estimate although this is known to vary from patient to patient. Parameter search algorithms are a promising technique for estimating the average dielectric properties from the reconstructed microwave images themselves without additional hardware. In this work, qualities of accurately reconstructed images are identified from point spread functions. As the qualities of accurately reconstructed microwave images are similar to the qualities of focused microscopic and photographic images, this work proposes the use of focal quality metrics for average dielectric property estimation. The robustness of the parameter search is evaluated using experimental dielectrically heterogeneous phantoms on the three-dimensional volumetric image. Based on a very broad initial estimate of the average dielectric properties, this paper shows how these metrics can be used as suitable fitness functions in parameter search algorithms to reconstruct clear and focused microwave radar images.

Microwave breast cancer detection using time-frequency representations

Microwave-based breast cancer detection has been proposed as a complementary approach to compensate for some drawbacks of existing breast cancer detection techniques. Among the existing microwave breast cancer detection methods, machine learning-type algorithms have recently become more popular. These focus on detecting the existence of breast tumours rather than performing imaging to identify the exact tumour position. A key component of the machine learning approaches is feature extraction. One of the most widely used feature extraction method is principle component analysis (PCA). However, it can be sensitive to signal misalignment. This paper proposes feature extraction methods based on time-frequency representations of microwave data, including the wavelet transform and the empirical mode decomposition. Time-invariant statistics can be generated to provide features more robust to data misalignment. We validate results using clinical data sets combined with numerically simulated tumour responses. Experimental results show that features extracted from decomposition results of the wavelet transform and EMD improve the detection performance when combined with an ensemble selection-based classifier.

Performance of leading artifact removal algorithms assessed across microwave breast imaging prototype scan configurations

Microwave imaging is a promising imaging modality for the detection of early-stage breast cancer. One of the most important signal processing components of microwave radar-based breast imaging is early-stage artifact removal. Several artifact removal algorithms have been reported in the literature. However, the neighbourhood-based skin subtraction and hybrid artifact removal algorithms have shown particularly promising results in different realistic 3D breast phantoms. For the first time in this paper, both algorithms have been evaluated and compared using the scan approaches of the most common microwave breast imaging prototype systems. The tests include 3D numerical as well as experimental breast phantoms scanned with hemispherical, cylindrical and adaptive scanning patterns. The efficacy of both algorithms has been evaluated across a range of appropriate performance metrics.

Recent Advances in Microwave Imaging for Breast Cancer Detection

Breast cancer is a disease that occurs most often in female cancer patients. Early detection can significantly reduce the mortality rate. Microwave breast imaging, which is noninvasive and harmless to human, offers a promising alternative method to mammography. This paper presents a review of recent advances in microwave imaging for breast cancer detection. We conclude by introducing new research on a microwave imaging system with time-domain measurement that achieves short measurement time and low system cost. In the time-domain measurement system, scan time would take less than 1 sec, and it does not require very expensive equipment such as VNA.

PCA-based artifact removal algorithm for stroke detection using UWB radar imaging

Stroke patients should be dispatched at the highest level of care available in the shortest time. In this context, a transportable system in specialized ambulances, able to evaluate the presence of an acute brain lesion in a short time interval (i.e., few minutes), could shorten delay of treatment. UWB radar imaging is an emerging diagnostic branch that has great potential for the implementation of a transportable and low-cost device. Transportability, low cost and short response time pose challenges to the signal processing algorithms of the backscattered signals as they should guarantee good performance with a reasonably low number of antennas and low computational complexity, tightly related to the response time of the device. The paper shows that a PCA-based preprocessing algorithm can: (1) achieve good performance already with a computationally simple beamforming algorithm; (2) outperform state-of-the-art preprocessing algorithms; (3) enable a further improvement in the performance (and/or decrease in the number of antennas) by using a multistatic approach with just a modest increase in computational complexity. This is an important result toward the implementation of such a diagnostic device that could play an important role in emergency scenario.

A multistage selective weighting method for improved microwave breast tomography

Microwave tomography has shown potential to successfully reconstruct the dielectric properties of the human breast, thereby providing an alternative to other imaging modalities used in breast imaging applications. Considering the costly forward solution and complex iterative algorithms, computational complexity becomes a major bottleneck in practical applications of microwave tomography. In addition, the natural tendency of microwave inversion algorithms to reward high contrast breast tissue boundaries, such as the skin-adipose interface, usually leads to a very slow reconstruction of the internal tissue structure of human breast. This paper presents a multistage selective weighting method to improve the reconstruction quality of breast dielectric properties and minimize the computational cost of microwave breast tomography. In the proposed two stage approach, the skin layer is approximated using scaled microwave measurements in the first pass of the inversion algorithm; a numerical skin model is then constructed based on the estimated skin layer and the assumed dielectric properties of the skin tissue. In the second stage of the algorithm, the skin model is used as a priori information to reconstruct the internal tissue structure of the breast using a set of temporal scaling functions. The proposed method is evaluated on anatomically accurate MRI-derived breast phantoms and a comparison with the standard single-stage technique is presented.

Compound Radar Approach for Breast Imaging

Multistatic radar apertures record scattering at a number of receivers when the target is illuminated by a single transmitter, providing more scattering information than its monostatic counterpart per transmission angle. This paper considers the well-known problem of detecting tumor targets within breast phantoms using multistatic radar. To accurately image potentially cancerous targets size within the breast, a significant number of multistatic channels are required in order to adequately calibrate-out unwanted skin reflections, increase the immunity to clutter, and increase the dynamic range of a breast radar imaging system. However, increasing the density of antennas within a physical array is inevitably limited by the geometry of the antenna elements designed to operate with biological tissues at microwave frequencies. A novel compound imaging approach is presented to overcome these physical constraints and improve the imaging capabilities of a multistatic radar imaging modality for breast scanning applications. The number of transmit-receive (TX-RX) paths available for imaging are increased by performing a number of breast scans with varying array positions. A skin calibration method is presented to reduce the influence of skin reflections from each channel. Calibrated signals are applied to receive a beamforming method, compounding the data from each scan to produce a microwave radar breast profile. The proposed imaging method is evaluated with experimental data obtained from constructed phantoms of varying complexity, skin contour asymmetries, and challenging tumor positions and sizes. For each imaging scenario outlined in this study, the proposed compound imaging technique improves skin calibration, clearly detects small targets, and substantially reduces the level of undesirable clutter within the profile.

Artifact removal algorithms for stroke detection using a multistatic MIST beamforming algorithm

Microwave imaging (MWI) has been recently proved as a promising imaging modality for low-complexity, low-cost and fast brain imaging tools, which could play a fundamental role to efficiently manage emergencies related to stroke and hemorrhages. This paper focuses on the UWB radar imaging approach and in particular on the processing algorithms of the backscattered signals. Assuming the use of the multistatic version of the MIST (Microwave Imaging Space-Time) beamforming algorithm, developed by Hagness et al. for the early detection of breast cancer, the paper proposes and compares two artifact removal algorithms. Artifacts removal is an essential step of any UWB radar imaging system and currently considered artifact removal algorithms have been shown not to be effective in the specific scenario of brain imaging. First of all, the paper proposes modifications of a known artifact removal algorithm. These modifications are shown to be effective to achieve good localization accuracy and lower false positives. However, the main contribution is the proposal of an artifact removal algorithm based on statistical methods, which allows to achieve even better performance but with much lower computational complexity.

Breast cancer detection using interferometric MUSIC: experimental and numerical assessment

PURPOSE

In microwave breast cancer detection, it is often beneficial to arrange sensors in close proximity to the breast. The resultant coupling generally changes the antenna response. As an a priori characterization of the radio frequency system becomes difficult, this can lead to severe degradation of the detection efficacy. The purpose of this paper is to demonstrate the advantages of adopting an interferometric multiple signal classification (I-MUSIC) approach due to its limited dependence from a priori information on the antenna. The performance of I-MUSIC detection was measured in terms of signal-to-clutter ratio (SCR), signal-to-mean ratio (SMR), and spatial displacement (SD) and compared to other common linear noncoherent imaging methods, such as migration and the standard wideband MUSIC (WB-MUSIC) which also works when the antenna is not accounted for.

METHODS

The data were acquired by scanning a synthetic oil-in-gelatin phantom that mimics the dielectric properties of breast tissues across the spectrum 1-3 GHz using a proprietary breast microwave multi-monostatic radar system. The phantom is a multilayer structure that includes skin, adipose, fibroconnective, fibroglandular, and tumor tissue with an adipose component accounting for 60% of the whole structure. The detected tumor has a diameter of 5 mm and is inserted inside a fibroglandular region with a permittivity contrast εr-tumor/εr-fibroglandular < 1.5 over the operating band. Three datasets were recorded corresponding to three antennas with different coupling mechanisms. This was done to assess the independence of the I-MUSIC method from antenna characterizations. The datasets were processed by using I-MUSIC, noncoherent migration, and wideband MUSIC under equivalent conditions (i.e., operative bandwidth, frequency samples, and scanning positions). SCR, SMR, and SD figures were measured from all reconstructed images. In order to benchmark experimental results, numerical simulations of equivalent scenarios were carried out by using CST Microwave Studio. The three numerical datasets were then processed following the same procedure that was designed for the experimental case.

RESULTS

Detection results are presented for both experimental and numerical phantoms, and higher performance of the I-MUSIC method in comparison with the WB-MUSIC and noncoherent migration is achieved. This finding is confirmed for the three different antennas in this study. Although a delocalization effect occurs, experimental datasets show that the signal-to-clutter ratio and the signal-to-mean performance with the I-MUSIC are at least 5 and 2.3 times better than the other methods, respectively. The numerical datasets calculated on an equivalent phantom for cross-testing confirm the improved performance of the I-MUSIC in terms of SCR and SMR. In numerical simulations, the delocalization effect is dramatically reduced up to an SD value of 1.61 achieved with the I-MUSIC in combination with the antipodal Vivaldi antenna. This shows that mechanical uncertainties are the main reason for the delocalization effect in the measurements.

CONCLUSIONS

Experimental results show that the I-MUSIC generates images with signal-to-clutter levels higher than 5.46 dB across all working conditions and it reaches 7.84 dB in combination with the antipodal Vivaldi antenna. Numerical simulations confirm this trend and due to ideal mechanical conditions return a signal-to-clutter level higher than 7.61 dB. The I-MUSIC largely outperforms the methods under comparison and is able to detect a 5-mm tumor with a permittivity contrast of 1.5.

A comparison of data-independent microwave beamforming algorithms for the early detection of breast cancer

Ultrawideband (UWB) radar is one of the most promising alternatives to X-ray mammography as an imaging modality for the early detection of breast cancer. Several beamforming algorithms have been developed which exploit the dielectric contrast between normal and cancerous tissue at microwave frequencies in order to detect tumors. Dielectric heterogeneity within the breast greatly effects the ability of a beamformer to detect very small tumors, therefore the design of an effective beamformer for this application represents a significant challenge. This paper analyzes and compares 3 data-independent beamforming algorithms, testing each system on an anatomically correct, MRI derived breast model which incorporates recently-published data on dielectric properties.