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.

Biometric Recognition: A Systematic Review on Electrocardiogram Data Acquisition Methods.

In the last decades, researchers have shown the potential of using Electrocardiogram (ECG) as a biometric trait due to its uniqueness and hidden nature. However, despite the great number of approaches found in the literature, no agreement exists on the most appropriate methodology. This paper presents a systematic review of data acquisition methods, aiming to understand the impact of some variables from the data acquisition protocol of an ECG signal in the biometric identification process. We searched for papers on the subject using Scopus, defining several keywords and restrictions, and found a total of 121 papers. Data acquisition hardware and methods vary widely throughout the literature. We reviewed the intrusiveness of acquisitions, the number of leads used, and the duration of acquisitions. Moreover, by analyzing the literature, we can conclude that the preferable solutions include: (1) the use of off-the-person acquisitions as they bring ECG biometrics closer to viable, unconstrained applications; (2) the use of a one-lead setup; and (3) short-term acquisitions as they required fewer numbers of contact points, making the data acquisition of benefit to user acceptance and allow faster acquisitions, resulting in a user-friendly biometric system. Thus, this paper reviews data acquisition methods, summarizes multiple perspectives, and highlights existing challenges and problems. In contrast, most reviews on ECG-based biometrics focus on feature extraction and classification methods.

Dielectric Characterization of Healthy Human Teeth from 0.5 to 18 GHz with an Open-Ended Coaxial Probe.

Dental caries is a major oral health issue which compromises oral health, as it is the main cause of oral pain and tooth loss. Early caries detection is essential for effective clinical intervention. However, methods commonly employed for its diagnosis often fail to detect early caries lesions, which motivates the research for more effective diagnostic solutions. In this work, the relative permittivity of healthy permanent teeth, in caries-prone areas, was studied between 0.5 and 18 GHz. The reliability of such measurements is an important first step to, ultimately, evaluate the feasibility of a microwave device for caries detection. The open-ended coaxial probe technique was employed. Its performance showed to be compromised by the poor probe-tooth contact. We proposed a method based on applying coupling media to reduce this limitation. A decrease in the measured relative permittivity variability was observed when the space between the probe tip and tooth surface was filled by coupling media instead of air. The influence of the experimental conditions in the measurement result was found to be less than 5%. Measurements conducted in ex vivo teeth showed that the relative permittivity of the dental crown and root ranges between 10.0-11.0 and 8.0-9.5, respectively.

Modelling level I Axillary Lymph Nodes depth for Microwave Imaging.

PURPOSE: Patient-specific information on the depth of Axillary Lymph Nodes (ALNs) is important for the development of new diagnostic imaging technologies, e.g. Microwave Imaging (MWI), aiming to assess the diagnosis of ALNs during breast cancer staging. Studies about ALNs depth have been presented for treatment planning, but they lack information on sample size and usability of the data to infer the depth of ALNs. The aim of this study was to create a mathematical model that can be used to predict a depth interval where level I ALNs are likely to be located. METHODS: We extracted biometric features of 98 patients who underwent breast Magnetic Resonance Imaging (MRI) to train two types of regression models. We then tested different combination of features to predict ALNs depth and found the best predictor. The final prediction models were then implemented in an algorithm used for MWI and tested with anthropomorphic phantoms of the axillary region. RESULTS: Body Mass Index (BMI) was the feature with best performance to predict ALNs depth with coefficient of determination (R2) ranging from 0.49 to 0.55 and Root Mean Squared Error (RMSE) ranging from 0.68 to 0.91 cm. The proposed model showed satisfactory results in microwave images of patients with different BMIs. CONCLUSIONS: The presented results contribute to the development of reconstruction algorithms for new imaging technologies and to the assessment of ALNs in other medical applications.

Initial Study Using Electrocardiogram for Authentication and Identification.

Recently, several studies have demonstrated the potential of electrocardiogram (ECG) to be used as a physiological signature for biometric systems (BS). We investigated the potential of ECG as a biometric trait for the identification and authentication of individuals. We used data from a public database, CYBHi, containing two off-the-person records from 63 subjects, separated by 3 months. For the BS, two templates were generated: (1) cardiac cycles (CC) and (2) scalograms. The identification with CC was performed with LDA, kNN, DT, and SVM, whereas a convolutional neural network (CNN) and a distance-based algorithm were used for scalograms. The authentication was performed with a distance-based algorithm, with a leave-one-out cross validation, for impostors evaluation. The identification system yielded accuracies of 79.37% and 69.84% for CC with LDA and scalograms with CNN, respectively. The authentication yielded an accuracy of 90.48% and an impostor score of 13.06% for CC, and it had an accuracy of 98.42% and an impostor score of 14.34% for scalograms. The obtained results support the claim that ECG can be successfully used for personal recognition. To the best of our knowledge, our study is the first to thoroughly compare templates and methodologies to optimize the performance of an ECG-based biometric system.

Development of 3D MRI-Based Anatomically Realistic Models of Breast Tissues and Tumours for Microwave Imaging Diagnosis.

Breast cancer diagnosis using radar-based medical MicroWave Imaging (MWI) has been studied in recent years. Realistic numerical and physical models of the breast are needed for simulation and experimental testing of MWI prototypes. We aim to provide the scientific community with an online repository of multiple accurate realistic breast tissue models derived from Magnetic Resonance Imaging (MRI), including benign and malignant tumours. Such models are suitable for 3D printing, leveraging experimental MWI testing. We propose a pre-processing pipeline, which includes image registration, bias field correction, data normalisation, background subtraction, and median filtering. We segmented the fat tissue with the region growing algorithm in fat-weighted Dixon images. Skin, fibroglandular tissue, and the chest wall boundary were segmented from water-weighted Dixon images. Then, we applied a 3D region growing and Hoshen-Kopelman algorithms for tumour segmentation. The developed semi-automatic segmentation procedure is suitable to segment tissues with a varying level of heterogeneity regarding voxel intensity. Two accurate breast models with benign and malignant tumours, with dielectric properties at 3, 6, and 9 GHz frequencies have been made available to the research community. These are suitable for microwave diagnosis, i.e., imaging and classification, and can be easily adapted to other imaging modalities.

Application of Machine Learning to Predict Dielectric Properties of In Vivo Biological Tissue.

In this paper we revisited a database with measurements of the dielectric properties of rat muscles. Measurements were performed both in vivo and ex vivo; the latter were performed in tissues with varying levels of hydration. Dielectric property measurements were performed with an open-ended coaxial probe between the frequencies of 500 MHz and 50 GHz at a room temperature of 25 °C. In vivo dielectric properties are more valuable for creating realistic electromagnetic models of biological tissue, but these are more difficult to measure and scarcer in the literature. In this paper, we used machine learning models to predict the in vivo dielectric properties of rat muscle from ex vivo dielectric property measurements for varying levels of hydration. We observed promising results that suggest that our model can make a fair estimation of in vivo properties from ex vivo properties.

Development of MRI-based axillary numerical models and estimation of axillary lymph node dielectric properties for microwave imaging.

PURPOSE: Microwave imaging (MWI) has been studied as a complementary imaging modality to improve sensitivity and specificity of diagnosis of axillary lymph nodes (ALNs), which can be metastasized by breast cancer. The feasibility of such a system is based on the dielectric contrast between healthy and metastasized ALNs. However, reliable information such as anatomically realistic numerical models and matching dielectric properties of the axillary region and ALNs, which are crucial to develop MWI systems, are still limited in the literature. The purpose of this work is to develop a methodology to infer dielectric properties of structures from magnetic resonance imaging (MRI), in particular, ALNs. We further use this methodology, which is tailored for structures farther away from MR coils, to create MRI-based numerical models of the axillary region and share them with the scientific community, through an open-access repository. METHODS: We use a dataset of breast MRI scans of 40 patients, 15 of them with metastasized ALNs. We apply image processing techniques to minimize the artifacts in MR images and segment the tissues of interest. The background, lung cavity, and skin are segmented using thresholding techniques and the remaining tissues are segmented using a K-means clustering algorithm. The ALNs are segmented combining the clustering results of two MRI sequences. The performance of this methodology was evaluated using qualitative criteria. We then apply a piecewise linear interpolation between voxel signal intensities and known dielectric properties, which allow us to create dielectric property maps within an MRI and consequently infer ALN properties. Finally, we compare healthy and metastasized ALN dielectric properties within and between patients, and we create an open-access repository of numerical axillary region numerical models which can be used for electromagnetic simulations. RESULTS: The proposed methodology allowed creating anatomically realistic models of the axillary region, segmenting 80 ALNs and analyzing the corresponding dielectric properties. The estimated relative permittivity of those ALNs ranged from 16.6 to 49.3 at 5 GHz. We observe there is a high variability of dielectric properties of ALNs, which can be mainly related to the ALN size and, consequently, its composition. We verified an average dielectric contrast of 29% between healthy and metastasized ALNs. Our repository comprises 10 numerical models of the axillary region, from five patients, with variable number of metastasized ALNs and body mass index. CONCLUSIONS: The observed contrast between healthy and metastasized ALNs is a good indicator for the feasibility of a MWI system aiming to diagnose ALNs. This paper presents new contributions regarding anatomical modeling and dielectric properties' characterization, in particular for axillary region applications.

Study of the Refraction Effects in Microwave Breast Imaging Using a Dry Setup.

Medical Microwave Imaging (MWI) has been studied as a technique to aid breast cancer diagnosis. Several different prototypes have been proposed but most of them require the use of a coupling medium between the antennas and the breast, in order to reduce skin backscattering and avoid refraction effects. The use of dry setups has been addressed and recent publications show promising results. In this paper, we assess the importance of considering refraction effects in the image reconstruction algorithms. To this end, we consider a simplified homogeneous spherical model of the breast and analytically compute the propagating rays through the air-body interface. The comparison of results considering only direct ray propagation or refracted rays shows negligible impact on the accuracy of the images for moderately high permittivity media. Thus, we may avoid the computational burden of calculating the refracted rays in convex shapes.

Development of an Anthropomorphic Phantom of the Axillary Region for Microwave Imaging Assessment.

We produced an anatomically and dielectrically realistic phantom of the axillary region to enable the experimental assessment of Axillary Lymph Node (ALN) imaging using microwave imaging technology. We segmented a thoracic Computed Tomography (CT) scan and created a computer-aided designed file containing the anatomical configuration of the axillary region. The phantom comprises five 3D-printed parts representing the main tissues of interest of the axillary region for the purpose of microwave imaging: fat, muscle, bone, ALNs, and lung. The phantom allows the experimental assessment of multiple anatomical configurations, by including ALNs of different size, shape, and number in several locations. Except for the bone mimicking organ, which is made of solid conductive polymer, we 3D-printed cavities to represent the fat, muscle, ALN, and lung and filled them with appropriate tissue-mimicking liquids. Existing studies about complex permittivity of ALNs have reported limitations. To address these, we measured the complex permittivity of both human and animal lymph nodes using the standard open-ended coaxial-probe technique, over the 0.5 GHz-8.5 GHz frequency band, thus extending current knowledge on dielectric properties of ALNs. Lastly, we numerically evaluated the effect of the polymer which constitutes the cavities of the phantom and compared it to the realistic axillary region. The results showed a maximum difference of 7 dB at 4 GHz in the electric field magnitude coupled to the tissues and a maximum of 10 dB difference in the ALN response. Our results showed that the phantom is a good representation of the axillary region and a viable tool for pre-clinical assessment of microwave imaging technology.

Characterisation of Ex Vivo Liver Thermal Properties for Electromagnetic-Based Hyperthermic Therapies.

Electromagnetic-based hyperthermic therapies induce a controlled increase of temperature in a specific tissue target in order to increase the tissue perfusion or metabolism, or even to induce cell necrosis. These therapies require accurate knowledge of dielectric and thermal properties to optimise treatment plans. While dielectric properties have been well investigated, only a few studies have been conducted with the aim of understanding the changes of thermal properties as a function of temperature; i.e., thermal conductivity, volumetric heat capacity and thermal diffusivity. In this study, we experimentally investigate the thermal properties of ex vivo ovine liver in the hyperthermic temperature range, from 25 °C to 97 °C. A significant increase in thermal properties is observed only above 90 °C. An analytical model is developed to model the thermal properties as a function of temperature. Thermal properties are also investigated during the natural cooling of the heated tissue. A reversible phenomenon of the thermal properties is observed; during the cooling, thermal properties followed the same behaviour observed in the heating process. Additionally, tissue density and water content are evaluated at different temperatures. Density does not change with temperature; mass and volume losses change proportionally due to water vaporisation. A 30% water loss was observed above 90 °C.

Development of a 3D Anthropomorphic Phantom Generator for Microwave Imaging Applications of the Head and Neck Region.

The development of 3D anthropomorphic head and neck phantoms is of crucial and timely importance to explore novel imaging techniques, such as radar-based MicroWave Imaging (MWI), which have the potential to accurately diagnose Cervical Lymph Nodes (CLNs) in a neoadjuvant and non-invasive manner. We are motivated by a significant diagnostic blind-spot regarding mass screening of LNs in the case of head and neck cancer. The timely detection and selective removal of metastatic CLNs will prevent tumor cells from entering the lymphatic and blood systems and metastasizing to other body regions. The present paper describes the developed phantom generator which allows the anthropomorphic modelling of the main biological tissues of the cervical region, including CLNs, as well as their dielectric properties, for a frequency range from 1 to 10 GHz, based on Magnetic Resonance images. The resulting phantoms of varying complexity are well-suited to contribute to all stages of the development of a radar-based MWI device capable of detecting CLNs. Simpler models are essential since complexity could hinder the initial development stages of MWI devices. Besides, the diversity of anthropomorphic phantoms resulting from the developed phantom generator can be explored in other scientific contexts and may be useful to other medical imaging modalities.

Classification of breast tumor models with a prototype microwave imaging system.

PURPOSE: The assessment of the size and shape of breast tumors is of utter importance to the correct diagnosis and staging of breast cancer. In this paper, we classify breast tumor models of varying sizes and shapes using signals collected with a monostatic ultra-wideband radar microwave imaging prototype system with machine learning algorithms specifically tailored to the collected data. METHODS: A database comprising 13 benign and 13 malignant tumor models with sizes between 13 and 40 mm was created using dielectrically representative tissue mimicking materials. These tumor models were placed inside two breast phantoms: a homogeneous breast phantom and a breast phantom with clusters of fibroglandular mimicking tissue, accounting for breast heterogeneity. The breast phantoms with tumors were imaged with a monostatic microwave imaging prototype system, over a 1-6 GHz frequency range. The classification of benign and malignant tumors embedded in the two breast phantoms was completed, and tumor classification was evaluated with Principal Component Analysis as a feature extraction method, and tuned Naïve Bayes (NB), decision trees (DT), and k-nearest neighbours (kNN) as classifiers. We further study which antenna positions are better placed to classify tumors, discuss the feature extraction method and optimize classification algorithms, by tuning their hyperparameters, to improve sensitivity, specificity and the receiver operating characteristic curve, while ensuring maximum generalization and avoiding overfitting and data contamination. We also added a realistic synthetic skin response to the collected signals and examined its global effect on classification of benign vs malignant tumors. RESULTS: In terms of global classification performance, kNN outperformed DT and NB machine learning classifiers, achieving a classification accuracy of 96.2% when classifying between benign and malignant tumor phantoms in a homogeneous breast phantom (both when the skin artifact is and is not considered). CONCLUSIONS: We experimentally classified tumor models as benign or malignant with a microwave imaging system, and we showed a methodology that can potentially assess the shape of breast tumors, which will give further insight into the correct diagnosis and staging of breast cancer.

Optimal b-values for diffusion kurtosis imaging in invasive ductal carcinoma versus ductal carcinoma in situ breast lesions.

Diffusion kurtosis imaging (DKI) is a diffusion-weighted MRI technique that probes the non-Gaussian diffusion of water molecules within biological tissues. The purpose of this study was to investigate the DKI model optimal b-values combinations in invasive ductal carcinoma (IDC) versus ductal carcinoma in situ (DCIS) breast lesions. The study included 114 malignant breast lesions (64 IDC and 50 DCIS). Patients underwent a breast MRI examination which included a diffusion-weighted sequence (b = 0-3000 s/mm2). For each lesion, the b-values were combined among each other (109 combinations) and each mean kurtosis (MK) parameter was obtained. Differences between the lesion groups and b-values combinations were assessed. Also, the diagnostic performance of the combinations was determined through receiver operating characteristic (ROC) curve analysis, and compared. Root mean square error (RMSE) was also obtained. All the b-values combinations showed significant differences between the lesion groups (p < 0.05). The combination 0, 50, 200, 750, 1000, 2000 s/mm2 showed the best performance (AUC = 0.930, sensitivity = 95.3%, specificity = 82.0%, accuracy = 89.5%), with a RMSE of 17.65. The b-values combinations with the worst performance were composed of only high or ultra-high b-values, or with b = 1000 s/mm2 as the maximum b-value. Better results were obtained when zero b-value was included in the DKI model fitting with at least one b-value below 1000 s/mm2 and one b-value above 1000 s/mm2 (conserving b = 1000 s/mm2). Six was the optimal number of b-values, nonetheless other combinations with less b-values may be considered, but with a consequent diagnostic performance loss.

Diagnosing Breast Cancer with Microwave Technology: remaining challenges and potential solutions with machine learning.

Currently, breast cancer often requires invasive biopsies for diagnosis, motivating researchers to design and develop non-invasive and automated diagnosis systems. Recent microwave breast imaging studies have shown how backscattered signals carry relevant information about the shape of a tumour, and tumour shape is often used with current imaging modalities to assess malignancy. This paper presents a comprehensive analysis of microwave breast diagnosis systems which use machine learning to learn characteristics of benign and malignant tumours. The state-of-the-art, the main challenges still to overcome and potential solutions are outlined. Specifically, this work investigates the benefit of signal pre-processing on diagnostic performance, and proposes a new set of extracted features that capture the tumour shape information embedded in a signal. This work also investigates if a relationship exists between the antenna topology in a microwave system and diagnostic performance. Finally, a careful machine learning validation methodology is implemented to guarantee the robustness of the results and the accuracy of performance evaluation.

Compressive sampling for time critical microwave imaging applications.

Across all biomedical imaging applications, there is a growing emphasis placed on reducing data acquisition and imaging times. This research explores the use of a technique, known as compressive sampling or compressed sensing (CS), as an efficient technique to minimise the data acquisition time for time critical microwave imaging (MWI) applications. Where a signal exhibits sparsity in the time domain, the proposed CS implementation allows for sub-sampling acquisition in the frequency domain and consequently shorter imaging times, albeit at the expense of a slight degradation in reconstruction quality of the signals as the compression increases. This Letter focuses on ultra wideband (UWB) radar MWI applications where reducing acquisition is of critical importance therefore a slight degradation in reconstruction quality may be acceptable. The analysis demonstrates the effectiveness and suitability of CS with UWB applications.

Optimization of convergent collimators for pixelated SPECT systems.

PURPOSE: The optimization of the collimator design is essential to obtain the best possible sensitivity in single photon emission computed tomography imaging. The aim of this work is to present a methodology for maximizing the sensitivity of convergent collimators, specifically designed to match the pitch of pixelated detectors, for a fixed spatial resolution value and to present some initial results using this approach. METHODS: Given the matched constraint, the optimal collimator design cannot be simply found by allowing the highest level of septal penetration and spatial resolution consistent with the imposed restrictions, as it is done for the optimization of conventional collimators. Therefore, an algorithm that interactively calculates the collimator dimensions, with the maximum sensitivity, which respect the imposed restrictions was developed and used to optimize cone and fan beam collimators with tapered square-shaped holes for low (60-300 keV) and high energy radiation (300-511 keV). The optimal collimator dimensions were locally calculated based on the premise that each hole and septa of the convergent collimator should locally resemble an appropriate optimal matched parallel collimator. RESULTS: The optimal collimator dimensions, calculated for subcentimeter resolutions (3 and 7.5 mm), common pixel sizes (1.6, 2.1, and 2.5 mm), and acceptable septal penetration at 140 keV, were approximately constant throughout the collimator, despite their different hole incidence angles. By using these input parameters and a less strict septal penetration value of 5%, the optimal collimator dimensions and the corresponding mass per detector area were calculated for 511 keV. It is shown that a low value of focal distance leads to improvements in the average sensitivity at a fixed source-collimator distance and resolution. The optimal cone beam performance outperformed that of other optimal collimation geometries (fan and parallel beam) in imaging objects close to the collimator surface. CONCLUSIONS: These results demonstrate the potential of this kind of optimal convergent collimators for the use in small field of view imaging applications.