In-line multi-wavelength non-destructive pharma quality monitoring with ultrabroadband carbon nanotubes photo-thermoelectric imaging scanners.

While non-destructive in-line monitoring at manufacturing sites is essential for safe distribution cycles of pharmaceuticals, efforts are still insufficient to develop analytical systems for detailed dynamic visualisation of foreign substances and material composition in target pills. Although spectroscopies, expected towards pharma testing, have faced technical challenges in in-line setups for bulky equipment housing, this work demonstrates compact dynamic photo-monitoring systems by selectively extracting informative irradiation-wavelengths from comprehensive optical references of target pills. This work develops a non-destructive in-line dynamic inspection system for pharma agent pills with carbon nanotube (CNT) photo-thermoelectric imagers and the associated ultrabroadband sub-terahertz (THz)-infrared (IR) multi-wavelength monitoring.

Synthetic data generation with Worley-Perlin diffusion for robust subarachnoid hemorrhage detection in imbalanced CT Datasets.

Purpose: In this paper, we propose a novel generative model to produce high-quality SAH samples, enhancing SAH CT detection performance in imbalanced datasets. Previous methods, such as cost-sensitive learning and previous diffusion models, suffer from overfitting or noise-induced distortion, limiting their effectiveness. Accurate SAH sample generation is crucial for better detection.

IKEA effect and empathy for robots: Can assembly strengthen human-agent relationships?

Cooperative relationships between humans and agents are becoming more important for the social coexistence of anthropomorphic agents, including virtual agents and robots. One way to improve the relationship between humans and agents is for humans to empathize with agents. Empathy can increase human acceptance.

GPU-accelerated deformation mapping in hybrid organ models for real-time simulation.

Purpose: Surgical simulation is expected to be an effective way for physicians and medical students to learn surgical skills. To achieve real-time deformation of soft tissues with high visual quality, multiple resolution and adaptive mesh refinement models have been introduced. However, those models require additional processing time to map the deformation results of the deformed lattice to a polygon model.

Enhancing YOLO for laparoscopic tool detection: novel data augmentation and structural modifications addressing mis-detection of bifurcated targets.

Purpose: Laparoscopic tool detection is vital for assistance of minimally invasive surgeries, aiding tasks like tool pose estimation and surgical navigation. This study enhances YOLO models for better detection of bifurcated targets (BT) in such procedures, addressing the issue of mis-detection of bifurcated targets (MDBT) where BT tips are misidentified as separate entities or overlooked.

Methods: We proposed a data augmentation strategy, Random Target Masking, to prevent the model from identifying BT tips as separate laparoscopic tools.

Development of automatic insect-tracking robot system for measuring local activity changes in free walking.

This study aims to develop a robotic system that autonomously tracks insects during free walking to elucidate the relationship between olfactory sensory stimuli and behavioral changes in insects. The adaptability of organisms is defined by their ability to select appropriate behaviors based on sensory inputs in response to environmental changes, a capacity that insects exhibit through efficient adaptive behaviors despite their limited nervous systems. Consequently, new measurement techniques are needed to investigate the neuroethological processes in insects.

Diffusion-driven distillation and contrastive learning for class-incremental semantic segmentation of laparoscopic images.

Purpose: Understanding anatomical structures in laparoscopic images is crucial for various types of laparoscopic surgery. However, creating specialized datasets for each type is both inefficient and challenging. This highlights the clinical significance of exploring class-incremental semantic segmentation (CISS) for laparoscopic images.

Adaptive sensitivity-fisher regularization for heterogeneous transfer learning of vascular segmentation in laparoscopic videos.

Purpose: This study aims to enhance surgical safety by developing a method for vascular segmentation in laparoscopic surgery videos with limited visibility. We introduce an adaptive sensitivity-fisher regularization (ASFR) approach to adapt neural networks, initially trained on non-medical datasets, for vascular segmentation in laparoscopic videos.

Methods: Our approach utilizes heterogeneous transfer learning by integrating fisher information and sensitivity analysis to mitigate catastrophic forgetting and overfitting caused by limited annotated data in laparoscopic videos.

Diversity and complexity of auditory representation in the hearing systems of mosquitoes.

Although low-frequency sounds have been reported to stimulate dispersal responses in male and female mosquitoes, only males show attraction to sound. Male attraction to female flight tones is important during courtship; however, groups of males show diverse responses to acoustic stimuli, suggesting that auditory processing can vary drastically between the sexes and individual males. To investigate diversity in auditory representation within and between the sexes, we used molecular and functional analyses to explore mosquito auditory processing.

New online in-air signature recognition dataset and embodied cognition inspired feature selection.

In this study, we introduce MIAS-427, one of the largest and most comprehensive inertial datasets for in-air signature recognition, comprising 4270 multivariate signals. This dataset addresses a critical gap in the field by providing a robust foundation for advancing research in cognitive computation and biometric authentication. Leveraging embodied cognition theory, we propose a novel feature selection approach using dimension-wise Shapley Value analysis, which uncovers the intrinsic relationship between human motoric preferences and device-specific sensor data.

All-Solution-Processable Hybrid Photothermoelectric Sensors with Carbon Nanotube Absorbers and Bismuth Composite Electrodes for Nondestructive Testing.

While photothermoelectric (PTE) sensor sheets are potentially suitable for testing applications, such as nondestructive material identifications in ultrabroad millimeter-wave infrared bands, their device designs have primarily employed a single-material channel. Herein, PTE sensor sheets generally combine photoinduced heating with associated thermoelectric (TE) conversion phenomena, and the employment of a single-material channel regulates device operations by missing opportunities for fully utilizing their fundamental parameters. For this situation, this work develops all-solution-processable and freely coatable (paintable) hybrid PTE sensors by an effective combination of the channel structure with bismuth composite (Bi) TE electrodes (Seebeck coefficient > 100 μV K) and efficient carbon nanotube film photothermal absorbers.

Steganography beyond space-time with chain of multimodal AI.

Steganography is the art and science of covert writing, with a broad range of applications interwoven within the realm of cybersecurity. As artificial intelligence continues to evolve, its ability to synthesise realistic content emerges as a threat in the hands of cybercriminals who seek to manipulate and misrepresent the truth. Such synthetic content introduces a non-trivial risk of overwriting the subtle changes made for the purpose of steganography.

Semantic segmentation dataset authoring with simplified labels.

Purpose: Semantic segmentation of laparoscopic images is a key problem in surgical scene understanding. Creating ground truth labels for semantic segmentation tasks is time consuming, and in the medical field a need for medical training of annotators adds further complications, leading to reliance on a small pool of experts. Previous research has focused on reducing the time to author datasets, by using spatially weak labels, pseudolabels, and synthetic data.

Bidirectional teaching between lightweight multi-view networks for intestine segmentation from CT volume.

Purpose: We present a semi-supervised method for intestine segmentation to assist clinicians in diagnosing intestinal diseases. Accurate segmentation is essential for planning treatments for conditions such as intestinal obstruction. Although fully supervised learning performs well with abundant labeled data, the complexity of the intestine's spatial structure makes labeling time-intensive, resulting in limited labeled data.

Enhanced self-supervised monocular depth estimation with self-attention and joint depth-pose loss for laparoscopic images.

Purpose: Depth estimation is a powerful tool for navigation in laparoscopic surgery. Previous methods utilize predicted depth maps and the relative poses of the camera to accomplish self-supervised depth estimation. However, the smooth surfaces of organs with textureless regions and the laparoscope's complex rotations make depth and pose estimation difficult in laparoscopic scenes.

Cognitive Radio Networks: Technologies, Challenges and Applications.

In recent years, Cognitive Radio Networks (CRNs) have emerged as a transformative solution to address the growing demand for wireless spectrum resources and the inefficiencies of traditional static spectrum allocation policies [...

Multi-dimensional consistency learning between 2D Swin U-Net and 3D U-Net for intestine segmentation from CT volume.

Purpose: The paper introduces a novel two-step network based on semi-supervised learning for intestine segmentation from CT volumes. The intestine folds in the abdomen with complex spatial structures and contact with neighboring organs that bring difficulty for accurate segmentation and labeling at the pixel level. We propose a multi-dimensional consistency learning method to reduce the insufficient intestine segmentation results caused by complex structures and the limited labeled dataset.

Classification of fundus autofluorescence images based on macular function in retinitis pigmentosa using convolutional neural networks.

Purpose: To determine whether convolutional neural networks (CNN) can classify the severity of central vision loss using fundus autofluorescence (FAF) images and color fundus images of retinitis pigmentosa (RP), and to evaluate the utility of those images for severity classification.

Study Design: Retrospective observational study.

Methods: Medical charts of patients with RP who visited Nagoya University Hospital were reviewed.

Double-mix pseudo-label framework: enhancing semi-supervised segmentation on category-imbalanced CT volumes.

Purpose: Deep-learning-based supervised CT segmentation relies on fully and densely labeled data, the labeling process of which is time-consuming. In this study, our proposed method aims to improve segmentation performance on CT volumes with limited annotated data by considering category-wise difficulties and distribution.

Methods: We propose a novel confidence-difficulty weight (CDifW) allocation method that considers confidence levels, balancing the training across different categories, influencing the loss function and volume-mixing process for pseudo-label generation.

Response of to Flooding with Physical Flow.

Flooding causes severe yield losses worldwide, making it urgent to enhance crop tolerance to this stress. Since natural flooding often involves physical flow, we hypothesized that the effects of submergence on plants could change when combined with physical flow. In this study, we analyzed the growth and transcriptome of exposed to submergence or flooding with physical flow.

In toto biological framework: Modeling interconnectedness during human development.

Recent advancements in pluripotent stem cell and synthetic tissue technology have brought significant breakthroughs in studying early embryonic development, particularly within the first trimester of development in humans. However, during fetal stage development, investigating further biological events represents a major challenge, partly due to the evolving complexity and continued interaction across multiple organ systems. To bridge this gap, we propose an "in toto" biological framework that leverages a triad of technologies: synthetic tissues, intravital microscopy, and computer vision to capture in vivo cellular morphodynamics, conceptualized as single-cell choreography.

A proficient approach for the classification of Alzheimer's disease using a hybridization of machine learning and deep learning.

Alzheimer's disease (AD) is a neurodegenerative disorder. It causes progressive degeneration of the nervous system, affecting the cognitive ability of the human brain. Over the past two decades, neuroimaging data from Magnetic Resonance Imaging (MRI) scans has been increasingly used in the study of brain pathology related to the birth and growth of AD.

The role of sonic hedgehog signaling in the oropharyngeal epithelium during jaw development.

Sonic hedgehog (Shh) is expressed in the oropharyngeal epithelium, including the frontonasal ectodermal zone (FEZ), which is defined as the boundary between Shh and Fgf8 expression domains in the frontonasal epithelium. To investigate the role of SHH signaling from the oropharyngeal epithelium, we generated mice in which Shh expression is specifically deleted in the oropharyngeal epithelium (Isl1-Cre; Shh). In the mutant mouse, Shh expression was excised in the oropharyngeal epithelium as well as FEZ and ventral forebrain, consistent with the expression pattern of Isl1.

Comparison of the Quality of Lymphatic Vessel Images Obtained Using Two Photoacoustic Imaging Systems.

Photoacoustic imaging (PAI) can evaluate lymphatic vessels with a high resolution (0.2 mm) compared with other methods. LUB0, a new PAI device that is smaller than the PAI-05 used since 2020 (both from Luxonus, Inc.