Raw Radiofrequency Signals Research Articles

Radio Frequency Signal-Based Drone Classification with Frequency Domain Gramian Angular Field and Convolutional Neural Network

Over the past few years, drones have been utilized in a wide range of applications. However, the illegal operation of drones may pose a series of security risks to sensitive areas such as airports and military bases. Hence, it is vital to develop an effective method of identifying drones to address the above issues. Existing drone classification methods based on radio frequency (RF) signals have low accuracy or a high computational cost. In this paper, we propose a novel RF signal image representation scheme that incorporates a convolutional neural network (CNN), named the frequency domain Gramian Angular Field with a CNN (FDGAF-CNN), to perform drone classification. Specifically, we first compute the time–frequency spectrum of raw RF signals based on short-time Fourier transform (STFT). Then, the 1D frequency spectrum series is encoded as 2D images using a modified GAF transform. Moreover, to further improve the recognition performance, the images obtained from different channels are fused to serve as the input of a CNN classifier. Finally, numerous experiments were conducted on the two available open-source DroneRF and DroneRFa datasets. The experimental results show that the proposed FDGAF-CNN can achieve a relatively high classification accuracy of 98.72% and 98.67% on the above two datasets, respectively, confirming the effectiveness and generalization ability of the proposed method.

Skeletal Muscle Assessment Using Quantitative Ultrasound: A Narrative Review.

Ultrasound (US) is an important imaging tool for skeletal muscle analysis. The advantages of US include point-of-care access, real-time imaging, cost-effectiveness, and absence of ionizing radiation. However, US can be highly dependent on the operator and/or US system, and a portion of the potentially useful information carried by raw sonographic data is discarded in image formation for routine qualitative US. Quantitative ultrasound (QUS) methods provide analysis of the raw or post-processed data, revealing additional information about normal tissue structure and disease status. There are four QUS categories that can be used on muscle and are important to review. First, quantitative data derived from B-mode images can help determine the macrostructural anatomy and microstructural morphology of muscle tissues. Second, US elastography can provide information about muscle elasticity or stiffness through strain elastography or shear wave elastography (SWE). Strain elastography measures the induced tissue strain caused either by internal or external compression by tracking tissue displacement with detectable speckle in B-mode images of the examined tissue. SWE measures the speed of induced shear waves traveling through the tissue to estimate the tissue elasticity. These shear waves may be produced using external mechanical vibrations or internal "push pulse" ultrasound stimuli. Third, raw radiofrequency signal analyses provide estimates of fundamental tissue parameters, such as the speed of sound, attenuation coefficient, and backscatter coefficient, which correspond to information about muscle tissue microstructure and composition. Lastly, envelope statistical analyses apply various probability distributions to estimate the number density of scatterers and quantify coherent to incoherent signals, thus providing information about microstructural properties of muscle tissue. This review will examine these QUS techniques, published results on QUS evaluation of skeletal muscles, and the strengths and limitations of QUS in skeletal muscle analysis.

In Vivo Longitudinal Monitoring of Cardiac Remodeling in Murine Ischemia Models With Adaptive Bayesian Regularized Cardiac Strain Imaging: Validation Against Histology.

Adaptive Bayesian regularized cardiac strain imaging (ABR-CSI) uses raw radiofrequency signals to estimate myocardial wall contractility as a surrogate measure of relative tissue elasticity incorporating regularization in the Bayesian sense. We determined the feasibility of using ABR-CSI -derived strain for in vivo longitudinal monitoring of cardiac remodeling in a murine ischemic injury model (myocardial infarction [MI] and ischemia-reperfusion [IR]) and validated the findings against ground truth histology. We randomly stratified 30 BALB/CJ mice (17 females, 13 males, median age=10 wk) into three surgical groups (MI=10, IR=12, sham=8) and imaged pre-surgery (baseline) and 1, 2, 7 and 14 d post-surgery using a pre-clinical high-frequency ultrasound system (VisualSonics Vevo 2100). We then used ABR-CSI to estimate end-systolic and peak radial (er) and longitudinal (el) strain estimates. ABR-CSI was found to have the ability to serially monitor non-uniform cardiac remodeling associated with murine MI and IR non-invasively through temporal variation of strain estimates post-surgery. Furthermore, radial end-systole (ES) strain images and segmental strain curves exhibited improved discrimination among infarct, border and remote regions around the myocardium compared with longitudinal strain results. For example, the MI group had significantly lower (Friedman's with Bonferroni-Dunn test, p=0.002) ES er values in the anterior middle (infarcted) region at day 14 (n=9, 9.23 ± 7.39%) compared with the BL group (n=9, 44.32 ± 5.49). In contrast, anterior basal (remote region) mean ES er values did not differ significantly (non-significant Friedman's test, χ2=8.93, p=0.06) at day 14 (n=6, 33.05 ± 6.99%) compared with baseline (n=6, 34.02 ± 6.75%). Histology slides stained with Masson's trichrome (MT) together with a machine learning model (random forest classifier) were used to derive the ground truth cardiac fibrosis parameter termed histology percentage of myocardial fibrosis (PMF). Both radial and longitudinal strain were found to have strong statistically significant correlations with the PMF parameter. However, radial strain had a higher Spearman's correlation value (εresρ=-0.67, n=172, p < 0.001) compared with longitudinal strain (εlesρ=-0.60, n=172, p < 0.001). Overall, the results of this study indicate that ABR-CSI can reliably perform non-invasive detection of infarcted and remote myocardium in small animal studies.

Osteoporosis Diagnostic Model Using a Multichannel Convolutional Neural Network Based on Quantitative Ultrasound Radiofrequency Signal.

Quantitative ultrasound (QUS) is a promising screening method for osteoporosis. In this study, a new method to improve the diagnostic accuracy of QUS was established in which a multichannel convolutional neural network (MCNN) processes the raw radiofrequency (RF) signal of QUS. The improvement in the diagnostic accuracy of osteoporosis using this new method was evaluated by comparison with the conventional speed of sound (SOS) method. Dual-energyX-ray absorptiometry was used as the diagnostic standard. After being trained, validated and tested in a data set consisting of 274 participants, the MCNN model could significantly raise the accuracy of osteoporosis diagnosis compared with the SOS method. The adjusted MCNN model performed even better when adjusted by age, height and weight data. The sensitivity, specificity and accuracy of the adjusted MCNN method for osteoporosis diagnosis were 80.86%, 84.23% and 83.05%, respectively; the corresponding values for SOS were 50.60%, 73.68% and 66.67%. The area under the receiver operating characteristic curve of the adjusted MCNN method was also higher than that of SOS (0.846 vs. 0.679). In conclusion, our study indicates that the MCNN method may be more accurate than the conventional SOS method. The MCNN tool and ultrasound RF signal analysis are promising future developmental directions for QUS in screening for osteoporosis.

Compact automatic modulation recognition using over-the-air signals and FOS features

The recent deployment of automatic modulation recognition (AMR) for cognitive radio (CR) systems has significantly enhanced spectrum sensing capabilities. The utilization of real-time over-the-air digital radio frequency (RF) data for the development of a digital spectrum sensing model based on the automatic modulation classification (AMC) is presented in this study as a step for incorporating opportunistic spectrum sensing onto the NomadicBTS architecture. Some digital modulation techniques were studied for second-generation (2G) through fourth-generation (4G) technology. The raw RF signal dataset was digitized and curated, while non-complex first-order statistical (FOS) features were used with algorithms based on the Scaled conjugate gradient (SCG) and Levenberg-Marquardt (LM) to find the best learning algorithm for the generated AMR model. The results show that the developed AMR model has a very high likelihood of correctly classifying signals, with distinct patterns for each of the features of FOS. The results are compared to reveal a least mean square error (MSE) of 0.0131 with a maximum accuracy of 93.5 percent when the model was trained with seventy (70) neurons in the hidden layer using the LM method. The best model's accuracy will allow for the most precise identification of spectrum holes in the bands under consideration.

Personalized digital humans for rehabilitation and assistive devices

Introduction: Ultrasound is routinely used by rehabilitation specialists to establish differential diagnosis of the residuum’s neuromusculoskeletal issues experienced by former and active Service Members suffering from limb loss1. Ultrasound offers real-time, non-ionizing, unspecialised facility assessment. Conventional imaging modalities record a qualitative static image. More fundamental signal/data display modalities such as the raw radio-frequency signal and A-mode are rarely utilised, although offer specialised opportunities, particularly for quantitative tissue characterisation, when the subject is mobile, and when several anatomical locations need to be synchronously assessed. Our aim is to develop a wearable ultrasound biosensor system that provides real-time assessment of various anatomical compartment dimensions within a post-amputation residual lower limb of former and active Service Members, termed Dynamic Anatomical Ultrasonography (DAU). Methods and results: The Olympus Omniscan MX is a highly-portable and rugged ultrasound instrument aimed primarily at the industrial sector. It incorporates the facility to connect up to eight individual single-element ultrasound transducers. A custom pseudo prosthetic socket was created for an asymptomatic subject, to which were attached two 1 MHz, 19 mm diameter ultrasound transducers, as shown in Fig. 1A. Ultrasound signal data was recorded for a defined measurement period of 10 seconds as the subject repeatedly lifted and lowered their thigh. Utilising the semi-automated time-gate signal detection facility, the depth of the femur bone surface was recorded, shown in Fig. 1B. Discussion/future directions: We have demonstrated the ability to monitor motions of the femur; of particular note is that measurements were obtained through the socket and silicone liner in addition to the overlying soft tissues. It is hypothesised that knowledge of the dynamic behaviour of the various tissue compartments will improve our understanding of the biomechanics associated with the residual limb of individuals suffering from limb loss and, furthermore, facilitate the fitting and development of bionics prostheses for former and active Service Members2. Our long-term aim is to investigate whether a combination of ultrasound and mechanical load biomarker data, fed into a ‘Digital Twin’ computational simulation will improve socket design, restore mobility, facilitate return to active duty, and, ultimately, enhance users’ quality of life. Acknowledgements: This work was supported by the FY19 Defense Medical Research and Development Program through the Joint Program Committee 8 / Clinical and Rehabilitative Medicine Research Program Restoring Warfighters with Neuromusculoskeletal Injuries Research Award (RESTORE) under Award No. W81XWH2110215-DM190659. Opinions, interpretations, conclusions and recommendations are those of the author and are not necessarily endorsed by the FY19 Defense Medical Research and Development Program. References 1Frossard LA, Powrie R, Langton CM. In-vivo kinestic system to sustain residuum health of service members with lower limb loss: from proof-of-concept to digital twin. Military Health System Research Symposium. Abstract #MHSRS-19-00882. Kissimmee, FL, US 2019:111 2Frossard LA, Lloyd DG. The future of bionic limbs. Res Feat 2021; 134:74-77. https://doi.org/10.26904/RF-134-7477

Spectral analysis of ultrasound radiofrequency backscatter for the identification of epicardial adipose tissue.

Purpose: The coronary arteries are embedded in a layer of fat known as epicardial adipose tissue (EAT). The EAT influences the development of coronary artery disease (CAD), and increased EAT volume can be indicative of the presence and type of CAD. Identification of EAT using echocardiography is challenging and only sometimes feasible on the free wall of the right ventricle. We investigated the use of spectral analysis of the ultrasound radiofrequency (RF) backscatter for its potential to provide a more complete characterization of the EAT. Approach: Autoregressive (AR) models facilitated analysis of the short-time signals and allowed tuning of the optimal order of the spectral estimation process. The spectra were normalized using a reference phantom and spectral features were computed from both normalized and non-normalized data. The features were used to train random forests for classification of EAT, myocardium, and blood. Results: Using an AR order of 15 with the normalized data, a Monte Carlo cross validation yielded accuracies of 87.9% for EAT, 84.8% for myocardium, and 93.3% for blood in a database of 805 regions-of-interest. Youden's index, the sum of sensitivity, and specificity minus 1 were 0.799, 0.755, and 0.933, respectively. Conclusions: We demonstrated that spectral analysis of the raw RF signals may facilitate identification of the EAT when it may not otherwise be visible in traditional B-mode images.

Introduction.

Diagnostic ultrasound imaging has gained wide acceptance for a broad range of clinical uses. In many cases, ultrasonography is the first-line imaging modality selected for its ease of access and absence of ionizing radiation. Over the last decades, ultrasonography has considerably evolved and is currently contributing to important improvements in patient diagnosis and treatment. Modern ultrasound imaging can provide soft tissue anatomical (shape, size…) and functional information (tissue movements, blood flow) in 3D and 4D, characterization and distinction among tissues (echostructure) and quantification of tissue properties (microstructure, tissue stiffness). Soft tissue quantitative ultrasound (QUS) refers to methods specifically developed to assess quantitative variables reflecting tissue physical properties, usually by analyzing the raw radiofrequency signals and/or its spectral characteristics.

Doppler twinkling artifact observations: an open-access database of raw ultrasonic signals

BACKGROUND: Doppler twinkling artifact is a rapid change of colors seen in CFI-mode in the presence of kidney stones and calculi. Therefore, numerous researchers use the twinkling artifact as a diagnostic sign. However, this phenomenon is under-researched, because most assumptions concerning its causes are made based on pure visual observations of the scanners screen leaving the important steps of signal transformation hidden behind the black box curtains of ultrasound machines.&#x0D; MATERIALS AND METHODS: Raw radiofrequency ultrasound signals were recorded in the phantom studies. The recorded echoes were received from objects that create the Doppler twinkling artifact and artificial blood vessels and soft tissues imitators. The data were collected between June 2016 and March 2021. Sonomed-500 with the 7.5 L38 and 3.4 C60 probes served as the research machine for the signal capture.&#x0D; Data records: We present the database containing raw radiofrequency ultrasound signals from the beam former output of the research ultrasound machine. The dataset consists of CFI and B-mode echoes recorded from twinkling objects. Therefore, this database can be useful for those who test, develop and study ultrasound signal processing algorithms. Furthermore, the database is freely available online. The 10.5 GB database consists of echoes received from five phantoms. Raw radiofrequency signals were stored in the binary files; scanning parameters were stored in text files. The database is available at: https://mosmed.ai/datasets/ultrasound_doppler_twinkling_artifact.&#x0D; Code availability: The public can visualize the database content with the specially written program TwinklingDatasetDisplay available at: https://github.com/Center-of-Diagnostics-and-Telemedicine/TwinklingDatasetDisplay.git.&#x0D; Usage notes: The database can be used to test and develop signal-processing algorithms, such as wall filtration, velocity estimation, feature extraction, speckle reduction, etc. Furthermore, the public is free to share (copy, distribute, and transmit) and remix (adapt and do derivative works) the dataset considering appropriate credit is given.

Main Uncertainties in the RF Ultrasound Scanning Simulation of the Standard Ultrasound Phantoms.

Ultrasound echoscopy technologies are continuously evolving towards new modalities including quantitative parameter imaging, elastography, 3D scanning, and others. The development and analysis of new methods and algorithms require an adequate digital simulation of radiofrequency (RF) signal transformations. The purpose of this paper is the quantitative evaluation of RF signal simulation uncertainties in resolution and contrast reproduction with the model of a phased array transducer. The method is based on three types of standard physical phantoms. Digital 3D models of those phantoms are composed of point scatterers representing the weak backscattering of the background material and stronger backscattering from inclusions. The simulation results of echoscopy with sector scanning transducer by Field II software are compared with the RF output of the Ultrasonix scanner after scanning standard phantoms with 2.5 MHz phased array. The quantitative comparison of axial, lateral, and elevation resolutions have shown uncertainties from 9 to 22% correspondingly. The echoscopy simulation with two densities of scatterers is compared with contrast phantom imaging on the backscattered RF signals and B-scan reconstructed image, showing that the main sources of uncertainties limiting the echoscopy RF signal simulation adequacy are an insufficient knowledge of the scanner and phantom’s parameters. The attempt made for the quantitative evaluation of simulation uncertainties shows both problems and the potential of echoscopy simulation in imaging technology developments. The analysis presented could be interesting for researchers developing quantitative ultrasound imaging and elastography technologies looking for simulated raw RF signals comparable to those obtained from real ultrasonic scanning.

Thyroid nodule recognition using a joint convolutional neural network with information fusion of ultrasound images and radiofrequency data.

To develop a deep learning-based method with information fusion of US images and RF signals for better classification of thyroid nodules (TNs). One hundred sixty-three pairs of US images and RF signals of TNs from a cohort of adult patients were used for analysis. We developed an information fusion-based joint convolutional neural network (IF-JCNN) for the differential diagnosis of malignant and benign TNs. The IF-JCNN contains two branched CNNs for deep feature extraction: one for US images and the other one for RF signals. The extracted features are fused at the backend of IF-JCNN for TN classification. Across 5-fold cross-validation, the accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUROC) obtained by using the IF-JCNN with both US images and RF signals as inputs for TN classification were respectively 0.896 (95% CI 0.838-0.938), 0.885 (95% CI 0.804-0.941), 0.910 (95% CI 0.815-0.966), and 0.956 (95% CI 0.926-0.987), which were better than those obtained by using only US images: 0.822 (0.755-0.878; p = 0.0044), 0.792 (0.679-0.868, p = 0.0091), 0.866 (0.760-0.937, p = 0.197), and 0.901 (0.855-0.948, p = .0398), or RF signals: 0.767 (0.694-0.829, p < 0.001), 0.781 (0.685-0.859, p = 0.0037), 0.746 (0.625-0.845, p < 0.001), 0.845 (0.786-0.903, p < 0.001). The proposed IF-JCNN model filled the gap of just using US images in CNNs to characterize TNs, and it may serve as a promising tool for assisting the diagnosis of thyroid cancer. • Raw radiofrequency signals before ultrasound imaging of thyroid nodules provide useful information that is not carried by ultrasound images. • The information carried by raw radiofrequency signals and ultrasound images for thyroid nodules is complementary. • The performance of deep convolutional neural network for diagnosing thyroid nodules can be significantly improved by fusing US images and RF signals in the model as compared with just using US images.

Deep Learning and Blockchain with Edge Computing for 5G-Enabled Drone Identification and Flight Mode Detection

Nowadays, drones are not just deployed for defense and military establishments, but they are widely used in many applications such as natural disaster monitoring, soil and crop analysis, road and traffic surveillance, and consumer product delivery. Some information, such as drone identification and flight modes, can be transmitted to other drones. This information can be shared between drones by using radio frequency (RF) signals and through 5G networks. Recently, few studies have been proposed to use deep neural networks (DNNs) on RF signals for identifying drones and detecting their flight modes, such as off, on and connected, flying, hovering, and video recording. However, transmitting RF signals between drones and 5G nodes needs to be secure and decentralized; in addition, the performance of identification and detection needs to be more accurate. In this article, we introduce a framework that combines a blockchain with a deep recurrent neural network (DRNN) and edge computing for 5G-enabled drone identification and flight mode detection. In the proposed framework, raw RF signals of different drones under several flight modes are remotely sensed and collected on a cloud server to train a DRNN model and then distribute the trained model on edge devices for detecting drones and their flight modes. Blockchain is used in the proposed framework for data integrity and securing data transmission. The DRNN model is evaluated on a public dataset, called DroneRF. Experimental evaluation results show that the DRNN model of the proposed framework can detect drones and their flight modes from real RF signals with high accuracy as compared to recent related work.

Ultrasound measurement of fetal arterial pulse pressure using phased-tracking methods: A phantom study and clinical experience with antenatal corticosteroid therapy.

This study aimed to compare the accuracy of fetal pulse pressure estimated with a vascular simulator with that obtained by a manometer (reference) and evaluate the pulse pressure in normal human fetuses and fetuses whose mothers received corticosteroids. Fetal pulse pressure was estimated as the product of blood flow velocity and pulse wave velocity, based on the water hammer equation. Ultrasonic raw radiofrequency signals for blood flow velocity were captured from the fetal descending aortas at the diaphragm level, and pulse wave velocity was simultaneously measured from different directions using the phased-tracking method. First, the precision and accuracy of pulse pressure in the estimated method were verified by a circulatory phantom simulator, which reproduced fetal blood flow using a pulsating pump. Then, the pulse pressure of 98 normal human fetuses after 17 weeks of gestation and the fetal pulse pressure in 21 mothers who received antenatal corticosteroids for fetal maturation were measured. A significant correlation between the estimated pulse pressure values and the actual values was found in the phantom simulation (r = 0.99, P < 0.01). The estimated pulse pressure was significantly correlated with gestational age in normal fetuses (r = 0.74, P < 0.01). In steroid-treated pregnant women, fetal pulse pressure was observed to increase significantly on the second day of administration (P < 0.01). A noninvasive and accurate estimation model of fetal pulse pressure could be established using phased-tracking method, and this method has the potential to improve the assessment of human fetal hemodynamics.

New Reconstruction Method for Needle Contrast Optimization in B-Mode Ultrasound Image by Extracting RF Signal Parameters in Frequency Domain

Ultrasound-guided needle insertion has become standard in medical interventional procedures. Regardless of its advantages, it still has crucial problems related to needle visibility. Some technical factors affect the visibility with non-linear characteristic, i.e. frequency, insertion angle and depth. Here, backscattered signal parameters from measurement were compared to a simulation of a resonance scattering model. Raw radio frequency (RF) data were reconstructed with a new method to represent unique information on total backpropagation from the needle, which consists of non-resonance and resonance scattering components. The result suggests that reconstruction of the needle in B-mode images should be derived from the maximum power spectral density and the energy spectral density to optimize the contrast of the needle. In measurements with the center frequency at 1.87 MHz, the effect of resonance scattering on the total backpropagation around critical angles could be observed more clearly with this method than with standard reconstruction based on the signal envelope. The simulation showed that the fractional bandwidth of the spectrum of the backscattered pressure field centered at 1.87 MHz was relatively optimal at 40% to 100%. So that the simulation of the resonance scattering model can be used to predict the backscattered response from the needle, it must be able to confirm it to the real conditions of RF data with random characteristics. Therefore, extraction of the backscattered pressure field in a simulation with fractional bandwidth should be a concern.

Study of classification of breast lesions using texture GLCM features obtained from the raw ultrasound signal

Most of the methods of classification of breast lesions in ultrasound (US) images have been tested on B-mode images from the commercial equipment. The new possibility of further analysis of this problem showed up with the availability of a public database containing original raw radio frequency (RF) signals. In particular, it appeared that the original texture might contain diagnostic information which could be modified in the typical image processing and which is more difficult to perceive than the details of lesion shape/contour. In this paper a detailed analysis of the lesion texture is conducted by means of the decision trees and logistic regression. The decision trees turned out useful mainly for selecting texture features to be used in the stepwise logistic regression. The RF signals database of 200 breast lesions was used for testing the performance of the benign vs malignant lesion classifier. The Gray Level Cooccurrence Matrix (GLCM) was calculated with the vertical/horizontal offset of up to five pixels. For each of these matrices six features were calculated resulting in a total of 210 features. Using these features a sufficient number of decision trees were generated to calculate pseudo-Receiver Operating Characteristics (ROCs). The outcome of this process is a collection of generated trees for which the employed features are known. These features were then used for generating generalized linear model by means of stepwise logistic regression. The analyzed regression models included the coefficients of up-to-the second degree terms. The texture features were further completed by a single shape feature, that is tumor circularity (TC). The automatic procedure for finding the exact mask of a lesion is also provided for the conditions when the acoustic shadowing makes it impossible to obtain the entire contour reliably and a half-contour has to be used. The selected logistic regression models gave ROCs with the Area Under Curve (AUC) of up to 0.83 and the 95 \% confidence region (0.63 0.96). Analyzing classification results one comes to the conclusion that the tumor circularity, which is the most informative among shape/contour features, is not essential against the background of textural features. The reported study shows that a relatively straightforward procedure can be employed to obtain benign vs malignant classifier comparable with that originally used for the database of the raw RF signals and based on the more complicated segmentation of the parameter maps of homodyned K distribution.

Breast lesion classification based on ultrasonic radio-frequency signals using convolutional neural networks

We propose a novel approach to breast mass classification based on deep learning models that utilize raw radio-frequency (RF) ultrasound (US) signals. US images, typically displayed by US scanners and used to develop computer-aided diagnosis systems, are reconstructed using raw RF data. However, information related to physical properties of tissues present in RF signals is partially lost due to the irreversible compression necessary to make raw data readable to the human eye. To utilize the information present in raw US data, we develop deep learning models that can automatically process small 2D patches of RF signals and their amplitude samples. We compare our approach with classification method based on the Nakagami parameter, a widely used quantitative US technique utilizing RF data amplitude samples. Our better performing deep learning model, trained using RF signals and their envelope samples, achieved good classification performance, with the area under the receiver attaining operating characteristic curve (AUC) and balanced accuracy of 0.772 and 0.710, respectively. The proposed method significantly outperformed the Nakagami parameter-based classifier, which achieved AUC and accuracy of 0.64 and 0.611, respectively. The developed deep learning models were used to generate parametric maps illustrating the level of mass malignancy. Our study presents the feasibility of using RF data for the development of deep learning breast mass classification models.

RF-based drone detection and identification using deep learning approaches: An initiative towards a large open source drone database

Abstract The omnipresence of unmanned aerial vehicles, or drones, among civilians can lead to technical, security, and public safety issues that need to be addressed, regulated and prevented. Security agencies are in continuous search for technologies and intelligent systems that are capable of detecting drones. Unfortunately, breakthroughs in relevant technologies are hindered by the lack of open source databases for drone’s Radio Frequency (RF) signals, which are remotely sensed and stored to enable developing the most effective way for detecting and identifying these drones. This paper presents a stepping stone initiative towards the goal of building a database for the RF signals of various drones under different flight modes. We systematically collect, analyze, and record raw RF signals of different drones under different flight modes such as: off, on and connected, hovering, flying, and video recording. In addition, we design intelligent algorithms to detect and identify intruding drones using the developed RF database. Three deep neural networks (DNN) are used to detect the presence of a drone, the presence of a drone and its type, and lastly, the presence of a drone, its type, and flight mode. Performance of each DNN is validated through a 10-fold cross-validation process and evaluated using various metrics. Classification results show a general decline in performance when increasing the number of classes. Averaged accuracy has decreased from 99.7% for the first DNN (2-classes), to 84.5% for the second DNN (4-classes), and lastly, to 46.8% for the third DNN (10-classes). Nevertheless, results of the designed methods confirm the feasibility of the developed drone RF database to be used for detection and identification. The developed drone RF database along with our implementations are made publicly available for students and researchers alike.

Radiofrequency spectral analysis of EBUS for peripheral pulmonary lesions.

We previously reported that histogram-based quantitative evaluation for endobronchial ultrasonography (EBUS) B-mode images could differentiate between benign and malignant lesions. However, these images were generated from reconstructed raw radiofrequency (RF) signals and had some limitations. Currently, there are no reports on raw RF signal data to quantitatively differentiate ultrasound information for peripheral pulmonary lesions. We prospectively hypothesized that RF spectral analysis from EBUS images could reveal sonographic features of peripheral pulmonary diseases. RF data were imported into a frequency spectral analysis software programme, comparing four parameters: mean frequency (MHz); slope; mid-band fit (dB); and y-intercept (dB), to differentiate between benign and malignant lesions. Furthermore, we compared subgroup analysis within benign and malignant lesions. RF data from EBUS images were obtained in 146 cases, of which, 106 lung cancers and 40 inflammatory diseases were present. Significant differences were observed for three parameters in benign and malignant lesions (mean frequency: P < 0.05, slope: P < 0.05, y-intercept: P < 0.01) with diagnostic accuracy of 61%, 57.5%, 63%, respectively. In subgroup analysis, the acute pneumonia group showed higher mean frequency, higher slope and lower y-intercept patterns compared to mycobacterial and fibrotic diseases (P < 0.05). In malignant lesions, small cell carcinoma showed higher mean frequency, higher slope and lower y-intercept pattern compared to other histopathological lung cancers (P < 0.01). RF analysis might be capable of demonstrating aspects of the lesion's pathological heterogeneity rather than precisely differentiating between benign and malignant lesions.

A Nonlinear Beamformer Based on p-th Root Compression—Application to Plane Wave Ultrasound Imaging

Ultrafast medical ultrasound imaging is necessary for 3D and 4D ultrasound imaging, and it can also achieve high temporal resolution (thousands of frames per second) for monitoring of transient biological phenomena. However, reaching such frame rates involves reduction of image quality compared with that obtained with conventional ultrasound imaging, since the latter requires each image line to be reconstructed separately with a thin ultrasonic focused beam. There are many techniques to simultaneously acquire several image lines, although at the expense of resolution and contrast, due to interference from echoes from the whole medium. In this paper, a nonlinear beamformer is applied to plane wave imaging to improve resolution and contrast of ultrasound images. The method consists of the introduction of nonlinear operations in the conventional delay-and-sum (DAS) beamforming algorithm. To recover the value of each pixel, the raw radiofrequency signals are first dynamically focused and summed on the plane wave dimension. Then, their amplitudes are compressed using the signed p t h root. After summing on the element dimension, the signed p-power is applied to restore the original dimensionality in volts. Finally, a band-pass filter is used to remove artificial harmonics introduced by these nonlinear operations. The proposed method is referred to as p-DAS, and it has been tested here on numerical and experimental data from the open access platform of the Plane wave Imaging Challenge in Medical UltraSound (PICMUS). This study demonstrates that p-DAS achieves better resolution and artifact rejection than the conventional DAS (for p = 2 with eleven plane wave imaging on experimental phantoms, the lateral resolution is improved by 21 % , and contrast ratio (CR) by 59 % ). However, like many coherence-based beamformers, it tends to distort the conventional speckle structure (contrast-to-noise-ratio (CNR) decreased by 45 % ). It is demonstrated that p-DAS, for p = 2 , is very similar to the nonlinear filtered-delay-multiply-and-sum (FDMAS) beamforming, but also that its impact on image quality can be tuned changing the value of p.

High-Frequency Ultrasound Imaging of Tidemark In Vitro in Advanced Knee Osteoarthritis

High-frequency ultrasound imaging has been widely adopted for assessment of the degenerative changes of articular cartilage in osteoarthritis (OA). Yet, there are few reports on investigating its capability to evaluate subchondral bone. Here, we employed high-frequency ultrasound imaging (25 MHz) to examine in vitro the tidemark in cylindrical osteochondral disks (n = 33) harvested from advanced OA knees of humans. We found good correspondence in morphology observed by ultrasound imaging and micro-computed tomography. Ultrasound roughness index (URI) of tidemark was derived from the raw radiofrequency signals to compare with bone quality factors, including bone volume fraction (BV/TV) and bone mineral density (BMD) measured by micro-computed tomography, using the Spearman correlation (ρ). URI of the tidemark was negatively associated with the subchondral plate BV/TV (ρ = −0.73, p < 0.001), BMD (ρ = −0.40, p = 0.020), as well as the underneath trabecular bone BV/TV (ρ = −0.39, p = 0.025) and BMD (ρ = −0.43, p = 0.012). In conclusion, this preliminary study demonstrated that morphology measured by high-frequency ultrasound imaging could reflect the quality of the subchondral bone. High-frequency ultrasound is a promising imaging tool to evaluate the changes of the subchondral bone in addition to those of the overlying cartilage in OA.