Citations

Abstract Objective . Penile vibro-elastography (PVE) is complicated by reverberant shear wavefields from the cylindrical geometry of the corpus cavernosum (CC), which bias shear wave speed (SWS) estimates. This study evaluated local phase velocity imaging with wavefield-based filtering (LPVI-WBF) for CC stiffness assessment in post-prostatectomy erectile dysfunction (ED), compared against phase gradient (PG) and time-of-flight (TOF) methods. Approach . Six patients with post-prostatectomy ED underwent PVE at four longitudinal visits (902 acquisitions). SWS was estimated in flaccid and erect states at 100, 150, and 200 Hz using LPVI-WBF, PG, and TOF. Wavefield composition was quantified via the standing wave index. Simulations evaluated accuracy and frequency stability under clean and reverberant conditions. Main results . Reverberant components dominated penile acquisitions, with traveling wave energy absent in 59% of acquisitions and mean standing wave fraction of 57 ± 17%. LPVI-WBF was the only method producing physiologically consistent estimates, with erect SWS exceeding flaccid (3.59 ± 0.48 vs 3.25 ± 0.58 m s −1 , p < 0.0001). PG and TOF yielded reversed results ( E < F, p < 0.0001). The dispersion exponent was near-zero for LPVI-WBF ( α = 0.048, p = 0.21), consistent with weakly viscoelastic tissue, while PG ( α = 0.184) and TOF ( α = 0.321) showed significant frequency dependence from reverberant contamination. Simulations confirm PG accuracy in clean wavefields but collapse under reverberant ones. Significance . LPVI-WBF produced SWS estimates consistent with expected CC biomechanics across all patients and frequencies, a criterion PG and TOF failed to satisfy. Phantom validation and multi-directional wavefield simulation are needed to establish accuracy.

Background: Timely intervention and effective control of Alzheimer’s disease (AD) have been shown to limit memory loss and preserve cognitive function and the ability to perform simple activities in older adults. In addition, magnetic resonance imaging (MRI) scans are one of the most common and effective methods for early detection of AD. With the rapid development of deep learning (DL) algorithms, AD detection based on deep learning has wide applications. Methods: In this research, we have developed an AD detection method based on three-dimensional (3D) convolutional neural networks (CNNs) for 3D MRI images, which can achieve strong accuracy when compared with traditional 3D CNN models. The proposed model has four main blocks, and the multi-layer fusion functionality of each block was used to improve the efficiency of the proposed model. The performance of the proposed model was compared with three different pre-trained 3D CNN architectures (i.e., 3D ResNet-18, 3D InceptionResNet-v2, and 3D Efficientnet-b2) in both tasks of multi-/binary-class classification of AD. Results: Our model achieved impressive classification results of 91.4% for binary-class as well as 80.6% for multi-class classification on the Open Access Series of Imaging Studies (OASIS) database. Conclusions: Such results serve to demonstrate that multi-stage feature fusion of 3D CNN is an effective solution to improve the accuracy of diagnosis of AD with 3D MRI, thus enabling earlier and more accurate diagnosis.

This paper presents a novel approach for classifying electrocardiogram (ECG) signals in healthcare applications using federated learning and stacked convolutional neural networks (CNNs). Our innovative technique leverages the distributed nature of federated learning to collaboratively train a highperformance model while preserving data privacy on local devices. We propose a stacked CNN architecture tailored for ECG data, effectively extracting discriminative features across different temporal scales. The evaluation confirms the strength of our approach, culminating in a final model accuracy of 98.6% after 100 communication rounds, significantly exceeding baseline performance. This promising result paves the way for accurate and privacy-preserving ECG classification in diverse healthcare settings, potentially leading to improved diagnosis and patient monitoring.

Excess extravascular lung water (EVLW) is a common consequence for patients with congestive heart failure, inflammatory conditions, or acute respiratory distress syndrome. Computed tomography (CT) is widely used to assess EVLW, but with a higher radiation dose and logistical complexity. Lung ultrasound (LUS) using B-line artifacts demonstrates a reasonable correlation with EVLW, but user experience with the acquisition technique, equipment-dependent factors and the subjective analysis of the B-line artifacts results in significant inter-observer variability. We propose a technique to automatically detect lung ultrasound B-lines over heart cycles. The method first extracts B-mode image features from videos in a region of interest (ROI). A ResNet50-UNet network is then applied to segment regions of B-lines. This technique was performed on 8 videos (i.e., 4 patients versus 4 controls with the duration of each video 2–3 s, resolution 1024 × 758 pixels, and frame rate 28 fps). The training accuracy and lossvalue of proposed models were 96.5% and 0.05, respectively. The paired t-test statical analysis shows that there is significant difference (p-value = 0.0035) of total number of B-line between normal and lungs with edema. The proposed method improves the accuracy for counting the B-lines and reduces the labor work and intra-observer variability from different users.