A dilated inception CNN-LSTM network for fetal heart rate estimation.

Objective. Fetal heart rate (HR) monitoring is routinely used during pregnancy and labor to assess fetal well-being. The noninvasive fetal electrocardiogram (ECG), obtained by electrodes on the maternal abdomen, is a promising alternative to standard fetal monitoring. Subtraction of the maternal ECG from the abdominal measurements results in fetal ECG signals, in which the fetal HR can be determined typically through R-peak detection. However, the low signal-to-noise ratio and the nonstationary nature of the fetal ECG make R-peak detection a challenging task.Approach. We propose an alternative approach that instead of performing R-peak detection employs deep learning to directly determine the fetal HR from the extracted fetal ECG signals. We introduce a combination of dilated inception convolutional neural networks (CNN) with long short-term memory networks to capture both short-term and long-term temporal dynamics of the fetal HR. The robustness of the method is reinforced by a separate CNN-based classifier that estimates the reliability of the outcome.Main results. Our method achieved a positive percent agreement (within 10% of the actual fetal HR value) of 97.3% on a dataset recorded during labor and 99.6% on set-A of the 2013 Physionet/Computing in Cardiology Challenge exceeding top-performing state-of-the-art algorithms from the literature.Significance. The proposed method can potentially improve the accuracy and robustness of fetal HR extraction in clinical practice.

Deep Convolutional Long Short-Term Memory Network for Fetal Heart Rate Extraction.

Fetal electrocardiography is a valuable alternative to standard fetal monitoring. Suppression of the maternal electrocardiogram (ECG) in the abdominal measurements, results in fetal ECG signals, from which the fetal heart rate (HR) can be determined. This HR detection typically requires fetal R-peak detection, which is challenging, especially during low signal-to-noise ratio periods, caused for example by uterine activity. In this paper, we propose the combination of a convolutional neural network and a long short-term memory network that directly predicts the fetal HR from multichannel fetal ECG. The network is trained on a dataset, recorded during labor, while the performance of the method is evaluated both on a test dataset and on set-A of the 2013 Physionet /Computing in Cardiology Challenge. The algorithm achieved a positive percent agreement of 92.1% and 98.1% for the two datasets respectively, outperforming a top-performing state-of-the-art signal processing algorithm.

Synthetic Elastography Using B-Mode Ultrasound Through a Deep Fully Convolutional Neural Network.

Shear-wave elastography (SWE) permits local estimation of tissue elasticity, an important imaging marker in biomedicine. This recently developed, advanced technique assesses the speed of a laterally traveling shear wave after an acoustic radiation force "push" to estimate local Young's moduli in an operator-independent fashion. In this work, we show how synthetic SWE (sSWE) images can be generated based on conventional B-mode imaging through deep learning. Using side-by-side-view B-mode/SWE images collected in 50 patients with prostate cancer, we show that sSWE images with a pixel-wise mean absolute error of 4.5 ± 0.96 kPa with regard to the original SWE can be generated. Visualization of high-level feature levels through t -distributed stochastic neighbor embedding reveals substantial overlap between data from two different scanners. Qualitatively, we examined the use of the sSWE methodology for B-mode images obtained with a scanner without SWE functionality. We also examined the use of this type of network in elasticity imaging in the thyroid. Limitations of the technique reside in the fact that networks have to be retrained for different organs, and that the method requires standardization of the imaging settings and procedure. Future research will be aimed at the development of sSWE as an elasticity-related tissue typing strategy that is solely based on B-mode ultrasound acquisition, and the examination of its clinical utility.

Blind Source Separation for Clutter and Noise Suppression in Ultrasound Imaging: Review for Different Applications.

Blind source separation (BSS) refers to a number of signal processing techniques that decompose a signal into several "source" signals. In recent years, BSS is increasingly employed for the suppression of clutter and noise in ultrasonic imaging. In particular, its ability to separate sources based on measures of independence rather than their temporal or spatial frequency content makes BSS a powerful filtering tool for data in which the desired and undesired signals overlap in the spectral domain. The purpose of this work was to review the existing BSS methods and their potential in ultrasound imaging. Furthermore, we tested and compared the effectiveness of these techniques in the field of contrast-ultrasound super-resolution, contrast quantification, and speckle tracking. For all applications, this was done in silico, in vitro, and in vivo. We found that the critical step in BSS filtering is the identification of components containing the desired signal and highlighted the value of a priori domain knowledge to define effective criteria for signal component selection.

Convective-Dispersion Modeling in 3D Contrast-Ultrasound Imaging for the Localization of Prostate Cancer.

Despite being the solid tumor with the highest incidence in western men, prostate cancer (PCa) still lacks reliable imaging solutions that can overcome the need for systematic biopsies. Dynamic contrast-enhanced ultrasound imaging (DCE-US) allows us to quantitatively characterize the vascular bed in the prostate, due to its ability to visualize an intravenously administered bolus of contrast agents. Previous research has demonstrated that DCE-US parameters related to the vascular architecture are useful markers for the localization of PCa lesions. In this paper, we propose a novel method to assess the convective dispersion (D) and velocity (v) of the contrast bolus spreading through the prostate from three-dimensional (3D) DCE-US recordings. By assuming that D and v are locally constant, we solve the convective-dispersion equation by minimizing the corresponding regularized least-squares problem. 3D multiparametric maps of D and v were compared with 3D histopathology retrieved from the radical prostatectomy specimens of six patients. With a pixel-wise area under the receiver operating characteristic curve of 0.72 and 0.80, respectively, the method shows diagnostic value for the localization of PCa.

The prostate cancer detection rates of CEUS-targeted versus MRI-targeted versus systematic TRUS-guided biopsies in biopsy-naïve men: a prospective, comparative clinical trial using the same patients.

BACKGROUND: The current standard for Prostate Cancer (PCa) detection in biopsy-naïve men consists of 10-12 systematic biopsies under ultrasound guidance. This approach leads to underdiagnosis and undergrading of significant PCa while insignificant PCa may be overdiagnosed. The recent developments in MRI and Contrast Enhanced Ultrasound (CEUS) imaging have sparked an increasing interest in PCa imaging with the ultimate goal of replacing these "blind" systematic biopsies with reliable imaging-based targeted biopsies. METHODS/DESIGN: In this trial, we evaluate and compare the PCa detection rates of multiparametric (mp)MRI-targeted biopsies, CEUS-targeted biopsies and systematic biopsies under ultrasound guidance in the same patients. After informed consent, 299 biopsy-naïve men will undergo mpMRI scanning and CEUS imaging 1 week prior to the prostate biopsy procedure. During the biopsy procedure, a systematic transrectal 12-core biopsy will be performed by one operator blinded for the imaging results and targeted biopsy procedure. Subsequently a maximum of 4 CEUS-targeted biopsies and/or 4 mpMRI-targeted biopsies of predefined locations determined by an expert CEUS reader using quantification techniques and an expert radiologist, respectively, will be taken by a second operator using an MRI-US fusion device. The primary outcome is the detection rate of PCa (all grades) and clinically significant PCa (defined as Gleason score ≥7) compared between the three biopsy protocols. DISCUSSION: This trial compares the detection rate of (clinically significant) PCa, between both traditional systematic biopsies and targeted biopsies based on predefined regions of interest identified by two promising imaging technologies. It follows published recommendations on study design for the evaluation of imaging guided prostate biopsy techniques, minimizing bias and allowing data pooling. It is the first trial to combine mpMRI imaging and advanced CEUS imaging with quantification. TRIAL REGISTRATION: The Dutch Central Committee on Research Involving Human Subjects registration number NL52851.018.15, registered on 3 Nov 2015. Clinicaltrials.gov database registration number NCT02831920 , retrospectively registered on 5 July 2016.