Search

The diagnostic approach toward the management of cardiac implantable electronic device–related tricuspid regurgitation is challenging and undefined. Functional cardiac computed tomography angiography provides a complementary role to echocardiography in the evaluation of lead-leaflet interaction which can help the clinical decision-making process, as presented in this case series.

While considerable progress has been made in achieving accurate lip synchronization for 3D speech-driven talking face generation, the task of incorporating expressive facial detail synthesis aligned with the speaker’s speaking status remains challenging. Existing efforts either focus on learning a dynamic talking head pose synchronized with speech rhythm or aim for stylized facial movements guided by external reference such as emotional labels or reference video clips. The former works often yield coarse alignment, neglecting the emotional nuances present in the audio content while the latter studies lead to unnatural applications, requiring manual style source selection by users. Our goal is to directly leverage the inherent style information conveyed by human speech for generating an expressive talking face that aligns with the speaking status. In this paper, we propose AVI-Talking, an Audio-Visual Instruction system for expressive Talking face generation. This system harnesses the robust contextual reasoning and hallucination capability offered by Large Language Models (LLMs) to instruct the realistic synthesis of 3D talking faces. Instead of directly learning facial movements from human speech, our two-stage strategy involves the LLMs first comprehending audio information and generating instructions implying expressive facial details seamlessly corresponding to the speech. Subsequently, a diffusion-based generative network executes these instructions. This two-stage process, coupled with the incorporation of LLMs, enhances model interpretability and provides users with flexibility to comprehend instructions and specify desired operations or modifications. Specifically, given a speech clip, we first employ a Q-Former for contrastive alignment the speech features with visual instructions, which is then projected to input text embedding of LLMs. It functions as a prompting strategy, prompting LLMs to generate plausible visual instructions that encompass diverse facial details. In order to use these predicted instructions, a language-guided talking face generation system with disentangled latent space is delicately derived, where the speech content related lip movements and emotion correlated facial expressions are separately represented in speech content space and content irrelevant space. Additionally, we introduce a contrastive instruction-style alignment and diffusion technique within the content-irrelevant space to fully exploit the talking prior network for diverse instruction-following synthesis. Extensive experiments showcase the effectiveness of our approach in producing vivid talking faces with expressive facial movements and consistent emotional status.

Robot manipulation in a physically constrained environment requires compliant manipulation. Compliant manipulation is a manipulation skill to adjust hand motion based on the force imposed by the environment. Recently, reinforcement learning (RL) has been applied to solve household operations involving compliant manipulation. However, previous RL methods have primarily focused on designing a policy for a specific operation that limits their applicability and requires separate training for every new operation. We propose a constraint-aware policy that is applicable to various unseen manipulations by grouping several manipulations together based on the type of physical constraint involved. The type of physical constraint determines the characteristic of the imposed force direction; thus, a generalized policy is trained in the environment and reward designed on the basis of this characteristic. This paper focuses on two types of physical constraints: prismatic and revolute joints. Experiments demonstrated that the same policy could successfully execute various compliant manipulation operations, both in the simulation and reality. We believe this study is the first step toward realizing a generalized household robot.

Soft robots are advantageous for human interaction owing to their adaptability and safe interactivity. However, research on soft robots is challenging because of the complex fabrication process of elastomeric materials with multiple channels. In this study, we introduce a prototyping technique for the fabrication-friendly soft robots using pneumatic artificial muscle(PAMs) and modular 3D printed reinforcement. We presented three primitive deformation structures: bending, twisting, and contraction. Moreover, we propose a novel variable stiffness technique that alters PAMs contraction and radial expansion behavior into locking, malleable, and rotational brake features. We explore both the parallel and series arrangement of the reinforcement module and propose new types of mixing configurations and scaling techniques. We quantitatively verified the force scaling technique on different types of features. We demonstrate the feasibility of this prototyping technique through six application examples and conclude with a discussion of the limitations and possible future improvements.

In the field of the acquisition of sports skills, a common way to improve sports skills, such as golf swings, is to imitate professional players’ motions. However, it is difficult for beginners to specify the keyframes on which they should focus and which part of the body they should correct because of inconsistent timing and lack of knowledge. In this study, a golf swing analysis tool using neural networks is proposed to address this gap. The proposed system compares two motion sequences and specifies keyframes in which significant differences can be observed between the two motions. In addition, the system helps users intuitively understand the differences between themselves and professional players by using interpretable clues. The main challenge of this study is to target the fine-grained differences between users and professionals that can be used for self-training. Moreover, the significance of the proposed approach is the use of an unsupervised learning method without prior knowledge and labeled data, which will benefit future applications and research in other sports and skill training processes. In our approach, neural networks are first used to create a motion synchronizer to align motions with different phases and timing. Next, a motion discrepancy detector is implemented to find fine-grained differences between motions in latent spaces that are learned by the networks. Furthermore, we consider that learning intermediate motions may be feasible for beginners because, in this way, they can gradually change their pose to match the ideal form. Therefore, based on the synchronization and discrepancy detection results, we utilize a decoder to restore the intermediate human poses between two motions from the latent space. Finally, we suggest possible applications for analyzing and visualizing the discrepancy between the two input motions and interacting with the users. With the proposed application, users can easily understand the differences between their motions and those of various experts during self-training and learn how to improve their motions.

Abstract Background The safety and efficacy of an oral anticoagulant (OAC) treatment and the difference between direct OACs (DOACs) and warfarin in nonsevere frail elderly patients with AF are unclear. Methods This was a retrospective and observational study of 354 patients over 80 years of age with nonsevere frailty who were diagnosed with AF and treated with OACs. Nonsevere frailty was defined as a clinical frailty scale score of

Abstract Background and objectives Using a lung sound analysis, the prognosis of asthma was investigated in infants with risk factors for asthma development by a long‐term observation. Methods A total of 268 infants were included (median age: 8 months old). The lung sound parameters (the ratio of the third and fourth area to the total area under the curve [A3/AT and B4/AT], and the ratio of power and frequency at 50% and 75% of the highest frequency [RPF50 and RPF75]) were evaluated at the first visit. At 3 years old, using a questionnaire, we examined the relationship between the lung sound parameters and risk factors of asthma development. Results Among the 268 infants, 175 infants were in good health and 93 had a history of acute respiratory infection (ARI) within 7 days at the first visit. Among the 3‐ to 12‐month‐old infants with an ARI, the A3/AT, B4/AT values in those with a history of asthma/asthmatic bronchitis, atopic dermatitis, and atopy were smaller than in the infants without such histories. Among the 13‐ to 24‐month‐old infants with an ARI, the A3/AT and B4/AT values in those with a wheezing history were larger than in the infants without such a history. Conclusions The characteristics of the lung sounds in infants with risk factors for asthma development were demonstrated over long‐term follow‐up. Lung sound analyses may be useful for assessing the airway condition of infants.

Background: The extracellular volume (ECV) calculated by T1 mapping, and tissue-tracking strain using cardiac magnetic resonance (CMR) are useful for assessing the left ventricular (LV) function. However, those parameters are controversial for assessing left atrial (LA) function. This study aimed to investigate the usefulness of CMR to evaluate the LA function using those parameters. Furthermore, those LA function parameters were compared in each LV function. Methods: A total of 65 consecutive patients who underwent contrast CMR were prospectively enrolled (age 55.7 ± 14. 6 years, males 67.7%). Among the 65 patients, there were 15 without hypertension, diabetes, or atrial fibrillation (Healthy group). The remaining 50 patients were divided into two groups according to a left ventricular ejection fraction (LVEF) of 50%. We assessed the correlations between the LV- and LA-CMR parameters among the three groups (LVEF

MonoMR is a system that synthesizes pseudo-2.5D content from monocular videos for mixed reality (MR) head-mounted displays (HMDs). Unlike conventional systems that require multiple cameras, the MonoMR system can be used by casual end-users to generate MR content from a single camera only. In order to synthesize the content, the system detects people in the video sequence via a deep neural network, and then the detected person’s pseudo-3D position is estimated by our proposed novel algorithm through a homography matrix. Finally, the person’s texture is extracted using a background subtraction algorithm and is placed on an estimated 3D position. The synthesized content can be played in MR HMD, and users can freely change their viewpoint and the content’s position. In order to evaluate the efficiency and interactive potential of MonoMR, we conducted performance evaluations and a user study with 12 participants. Moreover, we demonstrated the feasibility and usability of the MonoMR system to generate pseudo-2.5D content using three example application scenarios.

Background: Pilsicainide, a pure Na+ channel blocker, is a popular antiarrhythmic drug for the management of atrial tachyarrhythmias (AT), in Japan. However, serious drug-induced proarrhythmias (DIPs) may unexpectedly occur. We assessed the clinical background of AT patients presenting with DIPs caused by pilsicainide. Methods: This study retrospectively enrolled 874 consecutive patients (543 men, 63.6±15.3 years old, and 57.9±16.5 kg of body weight), who were orally administered pilsicainide for AT management. We evaluated the relationship between DIPs and serum pilsicainide concentration, renal dysfunction (estimate glomerular filtration rate, eGFR), and electrocardiogram (ECG) parameters. Results: Among the patients, 154 (17.6%) had renal dysfunction (eGFR