Lung cancer is a leading cause of cancer-related mortality worldwide, with high metastatic potential and limited imaging tools for guiding targeted therapies. Poly(ADP-ribose) polymerase (PARP)-1 is overexpressed in multiple malignancies and represents a promising target for molecular imaging. Here, we evaluated the feasibility and specificity of [18F]Fluorthanatrace ([18F]FTT), a radiolabeled PARP inhibitor analogue, for noninvasive detection of lung cancer metastases in a syngeneic mouse model. Lung metastases were established by intravenous injection of LL/2 cells into C57BL/6 mice, followed by micro-CT and dynamic/static PET imaging. [18F]FTT showed high radiochemical purity (>99%) and remained stable in vitro. Dynamic PET identified 30-45 min postinjection as the optimal imaging window (tumour-to-lung ratio: 2.15 ± 0.10). Tumour uptake was significantly reduced by pre-administration of olaparib, confirming PARP-1-specific binding. Ex vivo autoradiography and immunohistochemistry demonstrated colocalization of tracer uptake with PARP-1 expression. Together, these results support the translational potential of [18F]FTT PET imaging for detecting PARP-1-expressing lung metastases in precision oncology.

Traditional wound assessment relies on subjective visual inspection, which may miss early microvascular changes. In this study, laser speckle contrast imaging (LSCI) was used to differentiate necrotic from nonnecrotic wounds using quantitative perfusion under a shortened protocol. Forty wound patients (20 acute, 15 chronic, and 5 necrotic) and 20 participants without wound lesions were included. Within-subject normalized perfusion (percent change relative to adjacent healthy skin) served as the predictor. Significant differences were observed among wound types (ε 2 = 0.23-0.40, moderate-to-large effects). ROC analysis yielded an AUC of 0.88 (95% CI: 0.66-1.00; cutoff ≤-22.6%; accuracy 0.92; sensitivity 0.80; specificity 0.94; negative predictive value (NPV) 0.97). The 10-s protocol performed comparably to the 60-s acquisition (AUC = 0.84; accuracy = 0.87; r = 0.97; intraclass correlation coefficient (ICC) = 0.97). LSCI may offer a noncontact, rapid approach for perfusion-based necrosis differentiation, although the small necrotic sample (n = 5) necessitates validation in larger cohorts.

As international standards laboratories are developing radiotherapy dose standards for megavoltage photon beams from 60Co, the National Radiation Standard Laboratory of the National Atomic Research Institute (NRSL/ NARI) in Taiwan is keeping up with the trend and has recently established the absorbed dose to water standards for 6 and 10 MV photon beams using a self-developed graphite calorimeter. The purpose of this study is to implement a regional investigation in Taiwan to evaluate the impact on reference doses when the users apply calibration coefficients from the high energy photon standards instead of the conventional 60Co standard. Eight types of commercial ionization chambers that have been used in reference dosimetry were calibrated in both standards in NRSL/NARI. And beam quality correction factors (kQ) of the ionization chambers were obtained through direct calibrations. In addition, beam quality indices of clinical LINACs were also collected to analyze the influence of beam quality differences between the calibration and clinical beams. The results show that most of the differences between the measured kQ factors and the IAEA TRS-398 values are within the combined uncertainty of 0.86%, with the largest deviation observed in the 10 MV kQ factor for Exradin A1SL. In the evaluation results of beam qualities, the photon beam qualities at NRSL/NARI may not be applicable enough to offer calibration services without beam quality corrections. Therefore, NRSL/NARI is currently establishing a third energy absorbed dose to water standard, fitting curves of calibration coefficients as a function of beam qualities are expected to be provided afterward.

Machine learning (ML), a core component of artificial intelligence (AI), is increasingly being used to assess children’s emotions and attention, with potential applications in developmental monitoring and early identification of neurodevelopmental conditions such as autism spectrum disorder (ASD) and attention deficit hyperactivity disorder (ADHD). This narrative review synthesizes studies published between 2012 and 2025 from PubMed, IEEE Xplore, and Web of Science. We examine multimodal data sources (including facial, speech, physiological, eye movement, and behavioral features) and computational approaches such as convolutional neural networks (CNNs), support vector machines (SVMs), and long short-term memory (LSTM) networks. These methods can capture behavioral and physiological signals and provide complementary information for assessing children’s emotional and attentional states, particularly in controlled settings. However, the current evidence remains heterogeneous, with many studies relying on limited or laboratory-based datasets, which may constrain real-world applicability. Key challenges include data bias, cross-cultural variability, ethical concerns, and the need for robust privacy protection and external validation. Recent work has explored integrating AI with virtual reality (VR), augmented reality (AR), and Internet of Things (IoT) technologies to support more adaptive monitoring systems. Nevertheless, these applications remain largely exploratory. Future research should prioritize real-world validation, pediatric-specific datasets, and interdisciplinary collaboration to better define the role of AI in children’s mental health and education.

To address the lack of standardized benchmarking in spectral micro-CT, this study establishes a comprehensive system-level performance reference for a photon-counting detector (PCD) platform. We jointly evaluated detector spectral characteristics, including X-ray fluorescence-based energy calibration and count-rate behavior, alongside core imaging metrics using standardized phantoms. Notably, the PCD-CT system demonstrated superior spatial resolution and quantitative accuracy compared to conventional energy-integrating detector (EID) systems. The system achieved a 10% MTF of 28.99 lp/mm, attributable to its direct-conversion architecture. Furthermore, NPS analysis confirmed consistent noise texture, while bone mineral density measurements indicated significantly improved accuracy over EID-CT, highlighting its reliability for precision densitometry. Spectral quantification was validated through a projection-based material decomposition pipeline; using an independent hold-out set, the system achieved sub-millimeter thickness estimation (e.g., 0.084 mm RMSE for Al). This framework enabled virtual monochromatic imaging to effectively suppress metal artifacts while preserving structural fidelity. Importantly, these comparisons were conducted without proprietary ring-artifact reduction to isolate the intrinsic algorithmic performance. This work provides a rigorous measurement-centric benchmark essential for the design, optimization, and cross-platform evaluation of next-generation spectral micro-CT systems.

The effectiveness of heavy ion therapy has attracted global attention. Taiwan's first heavy ion therapy center, which has started clinical treatments in May 2023, is the 14th operational heavy ion therapy center in the world. This study used a tissue-equivalent proportional counter (TEPC) to assess the microdosimetric parameters of three different energy beams at the heavy ion facility, in order to evaluate representative beam quality indicators such as the relative RBE (Radiation Biological Effectiveness) of the heavy ion radiation field. The maximum absorbed dose for the three energy beams were found to occur at the dmax (Bragg peak) position. After the dmax, secondary particles continue to deposit energy at deeper depths, but clinical treatment planning systems may overlook the dose contribution from these secondary particles. The effective RBE values of all three energy beams at their respective dmax positions were found to be not necessarily the highest. The effective RBE values for the evaluated heavy ion therapy facility ranged from approximately 3.1 to 3.4. The evaluation methods and related results of this study can serve as a reference for dose assessment in clinical heavy ion therapy centers.

Prolonged exposure to high-stress environments can lead to mental illnesses such as anxiety disorders, depression, and posttraumatic stress disorder. Here, a wearable device utilizing photoplethysmography (PPG) technology is developed to noninvasively measure physiological signals and analyze heart rate variability (HRV) parameters. Traditional normative HRV databases typically do not account for responses induced by specific stressors such as cognitive tasks. Therefore, machine learning is used to build a more dynamic stress assessment model. Machine learning can capture complex nonlinear relationships among HRV parameters during stress-inducing tasks, adapts to individual stress response variations, and provides real-time stress level predictions. Furthermore, machine learning models can integrate temporal patterns in HRV data to achieve nuanced stress level assessment. This study examines the feasibility of PPG signals and validates the developed stress model. The RR intervals derived from PPG signals were highly positively correlated with those from electrocardiography signals (correlation coefficient = 0.9920, R-squared = 0.9837); this confirms the usability of PPG signals for HRV analysis. The stress model is constructed via the open-source Swell dataset. In the experiments, participants complete the Depression Anxiety Stress Scales-21-Chinese (DASS-21-C) questionnaire to quantify levels of depression, anxiety, and stress over a week. Baseline and stress-state PPG data are collected, converted into HRV values, and input into the model for stress quantification. The Stroop test is used to elicit stress responses. After the experiment, the DASS-21-C stress scores were compared with the model's baseline, stress state, and combined scores. The highest correlation was observed between the model's baseline score and the DASS-21-C stress score (correlation coefficient = 0.92, R-squared = 0.8457), supporting the model's psychological significance in quantifying everyday stress. HRV parameter changes across experimental phases are discussed as well as sex differences in stress responses. In the future, this device may be applied in clinical scenarios for further validation and could be integrated with additional physiological indicators for broader application in daily health management and stress warning systems.

This review explores the relationships between physiological parameters and emotions, as well as the potential value and applications of the use of machine learning to facilitate emotion recognition. First, the relationships between physiological parameters (such as heart rate, respiration, blood pressure, galvanic skin response, electroencephalography, and heart rate variability [HRV]) and emotions are discussed. The impacts of emotional states on these physiological parameters represent a crucial aspect of emotion research. For example, the increased heart rates and faster breathing resulting from excitement or anxiety are physiological changes that cannot be ignored. Subsequently, models used for emotion recognition are introduced. These models employ techniques such as machine learning or deep learning and are trained to detect emotional states on the basis of changes in physiological parameters. These techniques have important applications in clinical psychology, including by helping doctors assess patients' status, diagnose emotional disorders, and guide treatment. In the context of managing emotional disorders such as depression, anxiety, bipolar disorder, and borderline personality disorder, emotion recognition technologies can facilitate accurate emotional monitoring and early intervention, thereby reducing the risk of disease recurrence. These models can be used in the contexts of emotion management and health monitoring, thus helping individuals understand and cope with emotional changes more effectively and improving their quality of life. This paper identifies HRV, which reflects an individual's ability to adapt to stress, emotions, and physical conditions, as a key indicator that can be used in the contexts of emotion recognition and physiological parameter analysis. By incorporating HRV parameters into relevant models, emotional changes can be analyzed more precisely, thereby providing more effective emotion management and health monitoring tools, which can enhance individuals' quality of life. However, the use of these physiological parameters entails many challenges, including those pertaining to the collection of physiological data, privacy and security concerns, and the need for personalized adjustments as a result of the variability observed among individuals in this context. These challenges require continuous efforts on the part of technical experts and researchers to advance the development and application of emotion recognition technologies. Finally, this paper presents an in-depth investigation of the associations between physiological parameters and emotions, and it explores the potential value and challenges associated with the use of machine learning to facilitate emotion recognition. The results of these studies suggest that emotion recognition technology can be used more widely in the contexts of mental health, emotional management, and health monitoring to provide individuals with better emotional support and care.

The skin perfusion pressure (SPP) is traditionally measured with laser Doppler flowmetry (LDF), but this technique is limited by its single-point fiber optic probe, the need to contact the skin, and susceptibility to various factors, resulting in poor data consistency. Therefore, we developed a noncontact system for measuring the SPP over a large area based on laser speckle contrast imaging (LSCI). When it was paired with a pressure cuff device, the system accurately recorded blood flow changes during various pressure interventions, and the reperfusion pressure point could be calibrated to overcome traditional measurement limitations. Cross-comparison experiments revealed that the measurements obtained with the LSCI and LDF systems were highly correlated (r > 0.7), confirming the reliability of LSCI in assessing microcirculatory function. Since supine measurements are not always suitable in clinical environments, such as in space-constrained clinics or when the patient cannot lie flat, we compared SPP measurements obtained from individuals in sitting versus supine positions, revealing minimal differences (Cohen's d = 0.1, p > 0.05), which demonstrates the system's stability over different patient postures. Under cold water stimulation, which induces microvascular contraction, simulating poor circulation, the measured SPP was significantly lower than that measured under normal conditions (Cohen's d = 2.6, p < 0.05), verifying the system's potential applicability under different pathological conditions. According to our results, the LSCI system not only obtains SPP measurements that are correlated with the LDF-measured SPP but also overcomes the limitations of the latter system, providing noncontact, instant, and large-scale microcirculation monitoring. This study offers a reliable microcirculatory assessment tool based on LSCI technology, and the results support the future application of this tool in the early diagnosis and monitoring of diabetic foot neuropathy and peripheral arterial disease.

Proper organ functioning relies on adequate blood circulation; thus, monitoring blood flow is crucial for early disease diagnosis. Laser speckle contrast imaging (LSCI) is a noninvasive technique that is widely used for measuring superficial blood flow. In this study, we developed a portable LSCI system using an 805-nm near-infrared laser and a monochrome CMOS camera with a 10 × macro zoom lens. The system achieved a high-resolution imaging (1280 × 1024 pixels) with a working distance of 10 to 35 cm. The relative flow velocities were visualized via a spatial speckle contrast analysis algorithm with a 5 × 5 sliding window. In vitro experiments demonstrated the system’s ability to image flow velocities in a fluid model, and a linear relationship was observed between the actual flow rate and the relative flow rate obtained by the system. The correlation coefficient (R2) exceeded 0.83 for volumetric flow rates of 0 to 0.2 ml/min when channel widths were greater than 1.2 mm, and R2 > 0.94 was obtained for channel widths exceeding 1.6 mm. Comparisons with laser Doppler flowmetry (LDF) revealed a strong positive correlation between the LSCI and LDF results. In vivo experiments captured postocclusive reactive hyperemic responses in rat hind limbs and human palms and feet. The main research contribution is the development of this compact and portable LSCI device, as well as the validation of its reliability and convenience in various scenarios and environments. Future applications of this technology include evaluating blood flow changes during skin injuries, such as abrasions, burns, and diabetic foot ulcers, to aid medical institutions in treatment optimization and to reduce treatment duration.

Zebrafish are ideal model organisms for various fields of biological research, including genetics, neural transmission patterns, disease and drug testing, and heart disease studies, because of their unique ability to regenerate cardiac muscle. Tracking zebrafish trajectories is essential for understanding their behavior, physiological states, and disease associations. While 2D tracking methods are limited, 3D tracking provides more accurate descriptions of their movements, leading to a comprehensive understanding of their behavior. In this study, we used deep learning models to track the 3D movements of zebrafish. Videos were captured by two custom-made cameras, and 21,360 images were labeled for the dataset. The YOLOv7 model was trained using hyperparameter tuning, with the top- and side-view camera models trained using the v7x.pt and v7.pt weights, respectively, over 300 iterations with 10,680 data points each. The models achieved impressive results, with an accuracy of 98.7% and a recall of 98.1% based on the test set. The collected data were also used to generate dynamic 3D trajectories. Based on a test set with 3,632 3D coordinates, the final model detected 173.11% more coordinates than the initial model. Compared to the ground truth, the maximum and minimum errors decreased by 97.39% and 86.36%, respectively, and the average error decreased by 90.5%.This study presents a feasible 3D tracking method for zebrafish trajectories. The results can be used for further analysis of movement-related behavioral data, contributing to experimental research utilizing zebrafish.

Researchers in animal behavior and neuroscience devote considerable time to observing rodents behavior and physiological responses, with AI monitoring systems reducing personnel workload. This study presents the RodentWatch (RW) system, which leverages deep learning to automatically identify experimental animal behaviors in home cage environments. A single multifunctional camera and edge device are installed inside the animal’s home cage, allowing continuous real-time monitoring of the animal’s behavior, position, and body temperature for extended periods. We investigated identifying the drinking and resting behaviors of rats, with recognition accuracy enhanced through contextual object labeling and modified non-maximum suppression (NMS) schemes. Two tests—a light cycle change test and a sucrose preference test—were conducted to evaluate the usability of this system in rat behavioral experiments. This system enables notable advancements in image-based behavior recognition for living rodents.

Wound monitoring is crucial for effective healing, as nonhealing wounds can lead to tissue ulceration and necrosis. Evaluating wound recovery involves observing changes in angiogenesis. Laser speckle contrast imaging (LSCI) is vital for wound assessment due to its rapid imaging, high resolution, wide coverage, and noncontact properties. When using LSCI equipment, regions of interest (ROIs) must be delineated in lesion areas in images for quantitative analysis. However, patients with serious wounds cannot maintain constant postures because the affected areas are often associated with discomfort and pain. This leads to deviations between the drawn ROI and actual wound position when using LSCI for wound assessment, affecting the reliability of relevant assessments. To address these issues, we used the channel and spatial reliability tracker object tracking algorithm to develop an automatic ROI tracking function for LSCI systems. This algorithm is used to track and correct artificial movements in blood flow images, address the ROI position offset caused by the movement of the affected body part, increase the blood flow analysis accuracy, and improve the clinical applicability of LSCI systems. ROI tracking experiments were performed by simulating wounds, and the results showed that the intraclass correlation coefficient (ICC) ranged from 0.134 to 0.976. Furthermore, the object within the ROI affected tracking performance. Clinical assessments across wound types showed ICCs ranging from 0.798 to 0.917 for acute wounds and 0.628–0.849 for chronic wounds. We also discuss factors affecting tracking performance and propose strategies to enhance implementation effectiveness.

For pregnant workers in nuclear medicine, radiation doses can pose a risk to their foetus. However, foetal radiation doses cannot be measured directly. In this study, a method of estimating foetal radiation doses was developed through simulations and measurements of phantoms of pregnant women in the three trimesters. The uterus and abdominal surface doses for monoenergetic photons (137Cs) and medical diagnostic X-rays were measured, and uterine dose conversion coefficients (UDCCs) were calculated. The accuracy of the UDCC estimates were validated for measurements from thermoluminescent dosemeter (TLD) chips and TLD badges on the abdomen or chest. The foetal effective dose could be estimated using TLD chips and TLD badges on the abdomen or chest, or through literature estimation method. The proposed method can be used to easily and accurately estimate foetal effective doses from chest-worn TLD badges, ensuring accurate estimation in the early stage of pregnancy when a worker may not yet be wearing an abdominal badge. A flowchart for applying the UDCC method to approximate a foetal dose is also provided to ensure that total doses remain below the maximum of 1 mSv recommended in the International Commission on Radiological Protection 103 guidelines.

Digital therapy has gained popularity in the mental health field because of its convenience and accessibility. One major benefit of digital therapy is its ability to address therapist shortages. Posttraumatic stress disorder (PTSD) is a debilitating mental health condition that can develop after an individual experiences or witnesses a traumatic event. Digital therapy is an important resource for individuals with PTSD who may not have access to traditional in-person therapy. Cognitive behavioral therapy (CBT) and eye movement desensitization and reprocessing (EMDR) are two evidence-based psychotherapies that have shown efficacy in treating PTSD. This paper examines the mechanisms and clinical symptoms of PTSD as well as the principles and applications of CBT and EMDR. Additionally, the potential of digital therapy, including internet-based CBT, video conferencing-based therapy, and exposure therapy using augmented and virtual reality, is explored. This paper also discusses the engineering techniques employed in digital psychotherapy, such as emotion detection models and text analysis, for assessing patients' emotional states. Furthermore, it addresses the challenges faced in digital therapy, including regulatory issues, hardware limitations, privacy and security concerns, and effectiveness considerations. Overall, this paper provides a comprehensive overview of the current state of digital psychotherapy for PTSD treatment and highlights the opportunities and challenges in this rapidly evolving field.

This study presents a novel hierarchical nested honeycomb drawing inspiration from the hierarchical structures found in energy-absorbing citrus peels. Our investigation reveals that integrating secondary hierarchical units into primary honeycomb cells results in energy absorption profiles featuring two distinct plateaus. Notably, we found that these profiles can be finely tuned by adjusting the thickness of primary and secondary cell walls. Additionally, our study demonstrates a strategic removal of cell walls at key positions, reducing material consumption without compromising specific energy absorption. By establishing comprehensive structure-property relationships, we offer valuable insights into the design and optimization of hierarchical cellular materials. Compared with traditional honeycomb structures, the nested honeycomb structure shows a twofold increase in compressive strength and a fivefold increase in specific energy absorption, positioning them as promising candidates for applications requiring two-step impact protection and tunable performance, ranging from packaging to high-speed automobiles.

Introduction The COVID-19 pandemic has created an urgent demand for research, which has spurred the development of enhanced biosafety protocols in biosafety level (BSL)-3 laboratories to safeguard against the risks associated with handling highly contagious pathogens. Laboratory management failures can pose significant hazards. Methods An external system captured images of personnel entering a laboratory, which were then analyzed by an AI-based system to verify their compliance with personal protective equipment (PPE) regulations, thereby introducing an additional layer of protection. A deep learning model was trained to detect the presence of essential PPE items, such as clothing, masks, hoods, double-layer gloves, shoe covers, and respirators, ensuring adherence to World Health Organization (WHO) standards. The internal laboratory management system used a deep learning model to delineate alert zones and monitor compliance with the imposed safety protocols. Results The external detection system was trained on a dataset consisting of 4,112 images divided into 15 PPE compliance classes. The model achieved an accuracy of 97.52% and a recall of 97.03%. The identification results were presented in real time via a visual interface and simultaneously stored on the administrator’s dashboard for future reference. We trained the internal management system on 3347 images, achieving 90% accuracy and 85% recall. The results were transmitted in JSON format to the internal monitoring system, which triggered alerts in response to violations of safe practices or alert zones. Real-time notifications were sent to the administrators when the safety thresholds were met. Conclusion The BSL-3 laboratory monitoring system significantly reduces the risk of exposure to pathogens for personnel during laboratory operations. By ensuring the correct use of PPE and enhancing adherence to the imposed safety protocols, this system contributes to maintaining the integrity of BSL-3 facilities and mitigates the risk of personnel becoming infection vectors.

Cell segmentation’s low precision due to the intensity differences hinders widespread use of whole brain microscopy imaging. Previous studies used ResNet or CNN to account for this problem, but are unapplicable to immunolabeled signals across samples. Here we present a semiauto ground truth generation and weakly-supervised U-Net-based Deep-learning precise segmentation pipeline for whole brain immunopositive c-FOS signals, which reveals the distinct neural activity maps with different social motivations.

Metal artifacts present a major challenge to computed tomography (CT) because they reduce the image quality in medical diagnosis and treatment. Several metal artifact reduction (MAR) methods have been proposed to address this issue in previous studies. This study aimed to synthesize a virtual monochromatic image for MAR in CT images using projection-based material decomposition (MD) algorithms. We developed a spectral micro-CT prototype system equipped with a photon-counting detector (PCD) and PCD-CT imaging simulator to assess the performances of different MAR methods. Two projection-based MD algorithms were implemented and evaluated for their MAR performances in CT images and compared with conventional sinogram inpainting MAR methods. Different parts of digital 4D-extended cardiac torso (XCAT) phantoms with metal implants were designed to simulate various real scenarios. A homemade metal artifact evaluation (MAE) phantom was used to evaluate the MAR performance in experiments. The simulated results of the XCAT phantom indicated that the projection-based virtual monochromatic CT (VMCT) images provided better image quality than the conventional MAR images without blurring the normal tissues at the position of the metal artifacts. Various quantitative indicators support this conclusion. Additionally, the experimental results of the MAE phantom reveal that projection-based VMCT images can avoid image distortion caused by metal artifacts, unlike conventional MAR methods. In regards to the projection-based VMCT images, the simulated and experimental results demonstrated that using the linear maximum likelihood estimators with an error correction look-up table algorithm yielded better MAR performance compared to that obtained using a polynomial algorithm. Furthermore, projection-based VMCT images can not only reduce metal artifacts effectively but also simultaneously prevents object blurring at the metal artifact position and image distortion of the metal implants. Hence, the CT image quality can be further improved to increase the abilities for both preoperative and postoperative assessment of metal implants.

The Oak Ridge National Laboratory (ORNL) phantoms based on data of Caucasians have been widely used for fetal dosimetry. However, there are differences in body size during pregnancy among Taiwanese and Caucasians. In this study, the uterine dose conversion coefficients (DCCs) of Taiwanese pregnant women were evaluated to facilitate the use of it to estimate the possible uterine dose (usually regarded as fetal dose) of pregnant Taiwanese women during radiation practice or medical exposures. The uterine DCCs in this study were calculated based on the established Taiwanese pregnancy voxel phantoms, and were compared with the uterine DCCs of the International Commission on Radiological Protection. The applicability of evaluating uterine DCCs with different phantoms was also discussed. Results showed that if the ORNL phantoms are used to evaluate the uterine dose of Taiwanese pregnant women, the uterine dose may be underestimated. This study provides the uterine DCCs assessed with the Taiwanese pregnancy phantoms for future dose assessment of Taiwanese.