Intelligent Bladder Volume Monitoring for Wearable Ultrasound Devices: Enhancing Accuracy Through Deep Learning-Based Coarse-to-Fine Shape Estimation.

Accurate and continuous bladder volume monitoring is crucial for managing urinary dysfunctions. Wearable ultrasound (US) devices offer a solution by enabling noninvasive and real-time monitoring. Previous studies have limitations in power consumption and computation cost or quantitative volume estimation capability. To alleviate this, we present a novel pipeline that effectively integrates conventional feature extraction and deep learning (DL) to achieve continuous quantitative bladder volume monitoring efficiently. Particularly, in the proposed pipeline, bladder shape is coarsely estimated by a simple bladder wall detection algorithm in wearable devices, and the bladder wall coordinates are wirelessly transferred to an external server. Subsequently, a roughly estimated bladder shape from the wall coordinates is refined in an external server with a diffusion-based model. With this approach, power consumption and computation costs on wearable devices remained low, while fully harnessing the potential of DL for accurate shape estimation. To evaluate the proposed pipeline, we collected a dataset of bladder US images and RF signals from 250 patients. By simulating data acquisition from wearable devices using the dataset, we replicated real-world scenarios and validated the proposed method within these scenarios. Experimental results exhibit superior improvements, including +9.32% of IoU value in 2-D segmentation and -22.06 of RMSE in bladder volume regression compared to state-of-the-art (SOTA) performance from alternative methods, emphasizing the potential of this approach in continuous bladder volume monitoring in clinical settings. Therefore, this study effectively bridges the gap between accurate bladder volume estimation and the practical deployment of wearable US devices, promising improved patient care and quality of life.

Deep Learning-Based Framework for Fast and Accurate Acoustic Hologram Generation.

Acoustic holography has been gaining attention for various applications, such as noncontact particle manipulation, noninvasive neuromodulation, and medical imaging. However, only a few studies on how to generate acoustic holograms have been conducted, and even conventional acoustic hologram algorithms show limited performance in the fast and accurate generation of acoustic holograms, thus hindering the development of novel applications. We here propose a deep learning-based framework to achieve fast and accurate acoustic hologram generation. The framework has an autoencoder-like architecture; thus, the unsupervised training is realized without any ground truth. For the framework, we demonstrate a newly developed hologram generator network, the holographic ultrasound generation network (HU-Net), which is suitable for unsupervised learning of hologram generation, and a novel loss function that is devised for energy-efficient holograms. Furthermore, for considering various hologram devices (i.e., ultrasound transducers), we propose a physical constraint (PC) layer. Simulation and experimental studies were carried out for two different hologram devices, such as a 3-D printed lens, attached to a single element transducer, and a 2-D ultrasound array. The proposed framework was compared with the iterative angular spectrum approach (IASA) and the state-of-the-art (SOTA) iterative optimization method, Diff-PAT. In the simulation study, our framework showed a few hundred times faster generation speed, along with comparable or even better reconstruction quality, than those of IASA and Diff-PAT. In the experimental study, the framework was validated with 3-D printed lenses fabricated based on different methods, and the physical effect of the lenses on the reconstruction quality was discussed. The outcomes of the proposed framework in various cases (i.e., hologram generator networks, loss functions, and hologram devices) suggest that our framework may become a very useful alternative tool for other existing acoustic hologram applications, and it can expand novel medical applications.

Speckle Reduction via Deep Content-Aware Image Prior for Precise Breast Tumor Segmentation in an Ultrasound Image.

The performance of computer-aided diagnosis (CAD) systems that are based on ultrasound imaging has been enhanced owing to the advancement in deep learning. However, because of the inherent speckle noise in ultrasound images, the ambiguous boundaries of lesions deteriorate and are difficult to distinguish, resulting in the performance degradation of CAD. Although several methods have been proposed to reduce speckle noise over decades, this task remains a challenge that must be improved to enhance the performance of CAD. In this article, we propose a deep content-aware image prior (DCAIP) with a content-aware attention module (CAAM) for superior despeckling of ultrasound images without clean images. For the image prior, we developed a CAAM to deal with the content information in an input image. In this module, super-pixel pooling (SPP) is used to give attention to salient regions in an ultrasound image. Therefore, it can provide more content information regarding the input image when compared to other attention modules. The DCAIP consists of deep learning networks based on this attention module. The DCAIP is validated by applying it as a preprocessing step for breast tumor segmentation in ultrasound images, which is one of the tasks in CAD. Our method improved the segmentation performance by 15.89% in terms of the area under the precision-recall (PR) curve (AUPRC). The results demonstrate that our method enhances the quality of ultrasound images by effectively reducing speckle noise while preserving important information in the image, promising for the design of superior CAD systems.

Effects of transcranial ultrasound stimulation pulsed at 40 Hz on Aß plaques and brain rhythms in 5×FAD mice.

BACKGROUND: Alzheimer's disease (AD) is the most common cause of dementia, and is characterized by amyloid-ß (Aß) plaques and tauopathy. Reducing Aß has been considered a major AD treatment strategy in pharmacological and non-pharmacological approaches. Impairment of gamma oscillations, which play an important role in perception and cognitive function, has been shown in mouse AD models and human patients. Recently, the therapeutic effect of gamma entrainment in AD mouse models has been reported. Given that ultrasound is an emerging neuromodulation modality, we investigated the effect of ultrasound stimulation pulsed at gamma frequency (40 Hz) in an AD mouse model. METHODS: We implanted electroencephalogram (EEG) electrodes and a piezo-ceramic disc ultrasound transducer on the skull surface of 6-month-old 5×FAD and wild-type control mice (n = 12 and 6, respectively). Six 5×FAD mice were treated with two-hour ultrasound stimulation at 40 Hz daily for two weeks, and the other six mice received sham treatment. Soluble and insoluble Aß levels in the brain were measured by enzyme-linked immunosorbent assay. Spontaneous EEG gamma power was computed by wavelet analysis, and the brain connectivity was examined with phase-locking value and cross-frequency phase-amplitude coupling. RESULTS: We found that the total Aß42 levels, especially insoluble Aß42, in the treatment group decreased in pre- and infra-limbic cortex (PIL) compared to that of the sham treatment group. A reduction in the number of Aß plaques was also observed in the hippocampus. There was no increase in microbleeding in the transcranial ultrasound stimulation (tUS) group. In addition, the length and number of microglial processes decreased in PIL and hippocampus. Encelphalographic spontaneous gamma power was increased, and cross-frequency coupling was normalized, implying functional improvement after tUS stimulation. CONCLUSION: These results suggest that the transcranial ultrasound-based gamma-band entrainment technique can be an effective therapy for AD by reducing the Aß load and improving brain connectivity.

Ultrasonic blood flowmeter with a novel Xero algorithm for a mechanical circulatory support system.

Mechanical circulatory support systems (MCSSs) are crucial devices for transplants in patients with heart failure. The blood flowing through the MCSS can be recirculated or even stagnated in the event of critical blood flow issues. To avoid emergencies due to abnormal changes in the flow, continuous changes of the flowrate should be measured with high accuracy and robustness. For better flowrate measurements, a more advanced ultrasonic blood flowmeter (UFM), which is a noninvasive measurement tool, is needed. In this paper, we propose a novel UFM sensor module using a novel algorithm (Xero) that can exploit the advantages of both conventional cross-correlation (Xcorr) and zero-crossing (Zero) algorithms, using only the zero-crossing-based algorithm. To ensure the capability of our own developed and optimized ultrasonic sensor module for MCSSs, the accuracy, robustness, and continuous monitoring performance of the proposed algorithm were compared to those of conventional algorithms after application to the developed sensor module. The results show that Xero is superior to other algorithms for flowrate measurements under different environments and offers an error rate of at least 0.92%, higher robustness for changing fluid temperatures than conventional algorithms, and sensitive responses to sudden changes in flowrates. Thus, the proposed UFM system with Xero has a great potential for flowrate measurements in MCSSs.

Imbalanced Loss-Integrated Deep-Learning-Based Ultrasound Image Analysis for Diagnosis of Rotator-Cuff Tear.

A rotator cuff tear (RCT) is an injury in adults that causes difficulty in moving, weakness, and pain. Only limited diagnostic tools such as magnetic resonance imaging (MRI) and ultrasound Imaging (UI) systems can be utilized for an RCT diagnosis. Although UI offers comparable performance at a lower cost to other diagnostic instruments such as MRI, speckle noise can occur the degradation of the image resolution. Conventional vision-based algorithms exhibit inferior performance for the segmentation of diseased regions in UI. In order to achieve a better segmentation for diseased regions in UI, deep-learning-based diagnostic algorithms have been developed. However, it has not yet reached an acceptable level of performance for application in orthopedic surgeries. In this study, we developed a novel end-to-end fully convolutional neural network, denoted as Segmentation Model Adopting a pRe-trained Classification Architecture (SMART-CA), with a novel integrated on positive loss function (IPLF) to accurately diagnose the locations of RCT during an orthopedic examination using UI. Using the pre-trained network, SMART-CA can extract remarkably distinct features that cannot be extracted with a normal encoder. Therefore, it can improve the accuracy of segmentation. In addition, unlike other conventional loss functions, which are not suited for the optimization of deep learning models with an imbalanced dataset such as the RCT dataset, IPLF can efficiently optimize the SMART-CA. Experimental results have shown that SMART-CA offers an improved precision, recall, and dice coefficient of 0.604% (+38.4%), 0.942% (+14.0%) and 0.736% (+38.6%) respectively. The RCT segmentation from a normal ultrasound image offers the improved precision, recall, and dice coefficient of 0.337% (+22.5%), 0.860% (+15.8%) and 0.484% (+28.5%), respectively, in the RCT segmentation from an ultrasound image with severe speckle noise. The experimental results demonstrated the IPLF outperforms other conventional loss functions, and the proposed SMART-CA optimized with the IPLF showed better performance than other state-of-the-art networks for the RCT segmentation with high robustness to speckle noise.

Involvement of TRPA1 in the cinnamaldehyde-induced pulpal blood flow change in the feline dental pulp.

OBJECTIVES: The purpose of this study was to investigate the involvement of TRPA1 in the cinnamaldehyde-induced pulpal blood flow (PBF) change in the feline dental pulp. MATERIALS AND METHODS: Mandibles of eight cats were immobilized and PBF was monitored with a laser Doppler flowmetry at the mandibular canine tooth. To evaluate the effect of cinnamaldehyde on PBF, cinnamaldehyde was injected into the pulp through the lingual artery at a constant rate for 60 seconds. As a control, a mixture of 70% ethanol and 30% dimethyl sulfoxide (DMSO, vehicle) was used. To evaluate the involvement of transient receptor potential ankyrin 1 (TRPA1) in PBF change, AP18, a specific TRPA1 antagonist, was applied into the pulp through the Class V dentinal cavity followed by cinnamaldehyde-administration 3 minutes later. The paired variables of experimental data were statistically analyzed using paired t-test. A p value of less than 0.05 was considered as statistically significant. RESULTS: Administration of cinnamaldehyde (0.5 mg/kg, intra-arterial [i.a.]) induced significant increases in PBF (p < 0.05). While administration of a TRPA1 antagonist, AP18 (2.5 - 3.0 mM, into the dentinal cavity [i.c.]) caused insignificant change of PBF (p > 0.05), administration of cinnamaldehyde (0.5 mg/kg, i.a.) following the application of AP18 (2.5 - 3.0 mM, i.c.) resulted in an attenuation of PBF increase from the control level (p < 0.05). As a result, a TRPA1 antagonist, AP18 effectively inhibited the vasodilative effect of cinnamaldehyde (p < 0.05). CONCLUSIONS: The result of the present study provided a functional evidence that TRPA1 is involved in the mechanism of cinnamaldehyde-induced vasodilation in the feline dental pulp.

Endodontic treatment of maxillary lateral incisors with anatomical variations.

Maxillary lateral incisors usually exhibit a single root with a single canal. However, maxillary lateral incisor teeth with unusual morphology of root canal system are frequently reported. These cases of variable root canal anatomy can be treated well by nonsurgical endodontic methods. A detailed description of root canal morphology is fundamental for successful endodontic treatment. Treatment using an operating microscope, radiographs from different angles, and cone-beam computerized tomography (CBCT) can produce more predictable endodontic outcomes.