Search Results (20)

In the dentistry field, dental caries is a common issue affecting all age groups. The presence of dental braces and dental restoration makes the detection of caries more challenging. Traditionally, dentists rely on visual examinations to diagnose caries under restoration and dental braces, which can be prone to errors and are time-consuming. This study proposes an innovative deep learning and image processing-based approach for automated caries detection under restoration and dental braces, aiming to reduce the clinical burden on dental practitioners. The contributions of this research are summarized as follows: (1) YOLOv8 was employed to detect individual teeth in bitewing radiographs, and a rotation-aware segmentation method was introduced to handle angular variations in BW. The method achieved a sensitivity of 99.40% and a recall of 98.5%. (2) Using the original unprocessed images, AlexNet achieved an accuracy of 95.83% for detecting caries under restoration and dental braces. By incorporating the image processing techniques developed in this study, the accuracy of Inception-v3 improved to a maximum of 99.17%, representing a 3.34% increase over the baseline. (3) In clinical evaluation scenarios, the proposed AlexNet-based model achieved a specificity of 99.94% for non-caries cases and a precision of 99.99% for detecting caries under restoration and dental braces. All datasets used in this study were obtained with IRB approval (certificate number: 02002030B0). A total of 505 bitewing radiographs were collected from Chang Gung Memorial Hospital in Taoyuan, Taiwan. Patients with a history of the human immunodeficiency virus (HIV) were excluded from the dataset. The proposed system effectively identifies caries under restoration and dental braces, strengthens the dentist–patient relationship, and reduces dentist time during clinical consultations. Full article

Background and Objectives: Implant brand identification is critical in modern dental clinical diagnostics. With the increasing variety of implant brands and the difficulty of accurate identification in periapical radiographs, there is a growing demand for automated solutions. This study aims to leverage deep learning techniques to assist in dental implant classification, providing dentists with an efficient and reliable tool for implant brand detection. Methods: We proposed an innovative implant brand feature extraction method with multiple image enhancement techniques to improve implant visibility and classification accuracy. Additionally, we introduced a PA resolution enhancement technique that utilizes Dark Channel Prior and Lanczos interpolation for image resolution upscaling. Results: We evaluated the performance differences among various YOLO models for implant brand detection. Additionally, we analyzed the impact of implant brand feature extraction and PA resolution enhancement techniques on YOLO’s detection accuracy. Our results show that IB-YOLOv10 achieves a 17.8% accuracy improvement when incorporating these enhancement techniques compared to IB-YOLOv10 without enhancements. In real-world clinical applications, IB-YOLOv10 can classify implant brands in just 6.47 ms per PA, significantly reducing diagnostic time. Compared to existing studies, our model improves implant detection accuracy by 2.3%, achieving an overall classification accuracy of 94.5%. Conclusions: The findings of this study demonstrate that IB-YOLOv10 effectively reduces the diagnostic burden on dentists while providing a fast and reliable implant brand detection solution, improves clinical efficiency, and establishes a robust deep learning approach for automated implant detection in PA. Full article

An apical lesion is caused by bacteria invading the tooth apex through caries. Periodontal disease is caused by plaque accumulation. Peri-endo combined lesions include both diseases and significantly affect dental prognosis. The lack of clear symptoms in the early stages of onset makes diagnosis challenging, and delayed treatment can lead to the spread of symptoms. Early infection detection is crucial for preventing complications. PAs used as the database were provided by Chang Gung Memorial Medical Center, Taoyuan, Taiwan, with permission from the Institutional Review Board (IRB): 02002030B0. The tooth apex image enhancement method is a new technology in PA detection. This image enhancement method is used with convolutional neural networks (CNN) to classify apical lesions, peri-endo combined lesions, and asymptomatic cases, and to compare with You Only Look Once-v8-Oriented Bounding Box (YOLOv8-OBB) disease detection results. The contributions lie in the utilization of database augmentation and adaptive histogram equalization on individual tooth images, achieving the highest comprehensive validation accuracy of 95.23% with the ConvNextv2 model. Furthermore, the CNN outperformed YOLOv8 in identifying apical lesions, achieving an F1-Score of 92.45%. For the classification of peri-endo combined lesions, CNN attained the highest F1-Score of 96.49%, whereas YOLOv8 scored 88.49%. Full article

Taiwan’s provincial highways span approximately 5000 km and are crucial for connecting cities and towns. As pavement deteriorates over time and maintenance funds are limited, efficient pavement inspection and maintenance decision-making are challenging. Traditional inspections rely on manual visual assessments, consuming significant human resources and time without providing quantitative results. This study addresses current maintenance practices by introducing automated pavement damage detection technology to replace manual surveys. This technology significantly improves inspection efficiency and reduces costs. For example, traditional methods inspect 1 km per day, while automated survey vehicles cover 4 km per day, increasing efficiency fourfold. Additionally, automated surveys reduce inspection costs per kilometer by about 1.7 times, lowering long-term operational costs. Inspection results include the crack rate, rut depth, and roughness (IRI). Using K-means clustering analysis, maintenance thresholds for these indicators are established for decision-making. This method is applied to real cases and validated against actual maintenance decisions, showing that the introduced detection technology efficiently and objectively guides maintenance decisions and meets the needs of maintenance units. Finally, the inspection results are integrated into a pavement management platform, allowing direct maintenance decision-making and significantly enhancing management efficiency. Full article

The traffic volume and maintenance demand on Taiwan’s provincial highways have been steadily increasing. One of the most challenging issues in maintenance is determining the optimal timing and allocation of funds to avoid duplicative investments and maximize resource utilization. Currently, provincial highway maintenance units rely heavily on manual processes and paper-based records, using experiential methods to formulate maintenance strategies and conduct maintenance operations. This indicates a lack of objective maintenance strategies and pavement management systems in these units. This study aims to address this gap by integrating domestic and international literature on pavement maintenance decision-making. Existing approaches typically fall into two categories: “Pavement Indicator Rating” and “Pavement Maintenance Prioritization”. However, there has not been research integrating these methods for decision-making. Therefore, this research integrates these two approaches to establish a comprehensive maintenance strategy for Taiwan’s provincial highways. The Analytic Hierarchy Process (AHP) is employed as the decision-making theory, involving expert interviews to calculate maintenance weights for different pavement maintenance indicators. The results show that the pothole count, International Roughness Index (IRI), and Pavement Condition Index (PCI) are the three most critical maintenance indicators. The first phase of the maintenance strategy uses the “Pavement Indicator Rating“ to directly assess the pothole count, IRI, and PCI to categorize pavement sections as “maintenance sections” or “observation sections”. The second phase employs “Pavement Maintenance Prioritization”, integrating maintenance weights for each indicator to calculate maintenance scores. This phase prioritizes maintenance activities based on the results of the first phase’s rating for “maintenance sections”. Additionally, a provincial highway pavement management system is proposed to implement these strategies, enhancing maintenance management efficiency and ensuring the overall quality and longevity of provincial highway maintenance efforts. Full article

It is crucial to regulate N-methyl-D-aspartate (NMDA) function bivalently depending on the central nervous system (CNS) conditions. CNS disorders with NMDA hyperfunction are involved in the pathogenesis of neurotoxic and/or neurodegenerative disorders with elevated D-serine, one of the NMDA receptor co-agonists. On the contrary, NMDA-enhancing agents have been demonstrated to improve psychotic symptoms and cognition in CNS disorders with NMDA hypofunction. Serine racemase (SR), the enzyme regulating both D- and L-serine levels through both racemization (catalysis from L-serine to D-serine) and β-elimination (degradation of both D- and L-serine), emerges as a promising target for bidirectional regulation of NMDA function. In this study, we explored using dimethyl malonate (DMM), a pro-drug of the SR inhibitor malonate, to modulate NMDA activity in C57BL/6J male mice via intravenous administration. Unexpectedly, 400 mg/kg DMM significantly elevated, rather than decreased (as a racemization inhibitor), D-serine levels in the cerebral cortex and plasma. This outcome prompted us to investigate the regulatory effects of dodecagalloyl-α-D-xylose (α12G), a synthesized tannic acid analog, on SR activity. Our findings showed that α12G enhanced the racemization activity of human SR by about 8-fold. The simulated and fluorescent assay of binding affinity suggested a noncooperative binding close to the catalytic residues, Lys56 and Ser84. Moreover, α12G treatment can improve behaviors associated with major CNS disorders with NMDA hypofunction including hyperactivity, prepulse inhibition deficit, and memory impairment in animal models of positive symptoms and cognitive impairment of psychosis. In sum, our findings suggested α12G is a potential therapeutic for treating CNS disorders with NMDA hypofunction. Full article

The aim of this study was to compare the radiological and functional outcomes of the extended lateral and sinus tarsi approaches for managing displaced intraarticular calcaneal fractures. This retrospective study involved 44 patients with displaced intra-articular calcaneal fractures. The patients were treated with either the extended lateral or sinus tarsi approach and followed up for at least a year. The radiological and clinical outcomes were compared between the approaches. The waiting time for surgery was shorter and the complication rate was lower in the sinus tarsi approach group than in the other group. There were no significant differences in the American Orthopedic Foot and Ankle Society ankle–hindfoot score, Foot Function Index, or visual analog scale score between the groups. In both groups, the radiological outcomes (Böhler angle, calcaneal width, and calcaneal height) were better postoperatively than preoperatively. The sinus tarsi approach is a safe and effective alternative to the extended lateral approach for managing displaced intraarticular calcaneal fractures. It is associated with a lower complication rate and a shorter waiting time for surgery than the extended lateral approach, with similar functional and radiological outcomes. Full article

In this paper, we report an all-dielectric metamaterial terahertz biosensor, which exhibits a high Q factor of 35 at an 0.82 resonance peak. A structure with an electromagnetically induced transparency effect was designed and fabricated to perform a Mie resonance for the terahertz response. The biosensor exhibits a limit of detection of 100 pg/mL for cytokine interleukin 2 (IL-2) and a linear response for the logarithm of the concentration of IL-2 in the range of 100 pg/mL to 1 μg/mL. This study implicates an important potential for the detection of cytokines in serum and has potential application in the clinical detection of cytokine release syndrome. Full article

Furcation defects pose a significant challenge in the diagnosis and treatment planning of periodontal diseases. The accurate detection of furcation involvements (FI) on periapical radiographs (PAs) is crucial for the success of periodontal therapy. This research proposes a deep learning-based approach to furcation defect detection using convolutional neural networks (CNN) with an accuracy rate of 95%. This research has undergone a rigorous review by the Institutional Review Board (IRB) and has received accreditation under number 202002030B0C505. A dataset of 300 periapical radiographs of teeth with and without FI were collected and preprocessed to enhance the quality of the images. The efficient and innovative image masking technique used in this research better enhances the contrast between FI symptoms and other areas. Moreover, this technology highlights the region of interest (ROI) for the subsequent CNN models training with a combination of transfer learning and fine-tuning techniques. The proposed segmentation algorithm demonstrates exceptional performance with an overall accuracy up to 94.97%, surpassing other conventional methods. Moreover, in comparison with existing CNN technology for identifying dental problems, this research proposes an improved adaptive threshold preprocessing technique that produces clearer distinctions between teeth and interdental molars. The proposed model achieves impressive results in detecting FI with identification rates ranging from 92.96% to a remarkable 94.97%. These findings suggest that our deep learning approach holds significant potential for improving the accuracy and efficiency of dental diagnosis. Such AI-assisted dental diagnosis has the potential to improve periodontal diagnosis, treatment planning, and patient outcomes. This research demonstrates the feasibility and effectiveness of using deep learning algorithms for furcation defect detection on periapical radiographs and highlights the potential for AI-assisted dental diagnosis. With the improvement of dental abnormality detection, earlier intervention could be enabled and could ultimately lead to improved patient outcomes. Full article

Heart failure (HF) is a global pandemic public health burden affecting one in five of the general population in their lifetime. For high-risk individuals, early detection and prediction of HF progression reduces hospitalizations, reduces mortality, improves the individual’s quality of life, and reduces associated medical costs. In using an artificial intelligence (AI)-assisted genome-wide association study of a single nucleotide polymorphism (SNP) database from 117 asymptomatic high-risk individuals, we identified a SNP signature composed of 13 SNPs. These were annotated and mapped into six protein-coding genes (GAD2, APP, RASGEF1C, MACROD2, DMD, and DOCK1), a pseudogene (PGAM1P5), and various non-coding RNA genes (LINC01968, LINC00687, LOC105372209, LOC101928047, LOC105372208, and LOC105371356). The SNP signature was found to have a good performance when predicting HF progression, namely with an accuracy rate of 0.857 and an area under the curve of 0.912. Intriguingly, analysis of the protein connectivity map revealed that DMD, RASGEF1C, MACROD2, DOCK1, and PGAM1P5 appear to form a protein interaction network in the heart. This suggests that, together, they may contribute to the pathogenesis of HF. Our findings demonstrate that a combination of AI-assisted identifications of SNP signatures and clinical parameters are able to effectively identify asymptomatic high-risk subjects that are predisposed to HF. Full article

Patients bitten by Naja atra who are treated with bivalent freeze-dried neurotoxic antivenom in Taiwan have an improved survival rate but develop necrotic wound changes. The World Health Organization (WHO) has suggested using the minimum necrotizing dose (MND) of venom as a method of evaluating the neutralization effect of antivenom. The aim of this study was to evaluate the effectiveness of antivenom for the prevention of necrosis based on the MND and clarify which component of the venom of N. atra induces necrosis. The neurotoxins (NTXs) were removed from the crude venom (deNTXs), and different concentrations of deNTXs were injected intradermally into the dorsal skin of mice. After three days, the necrotic lesion diameter was found to be approximately 5 mm, and the MND was calculated. A reduction in the necrotic diameter of 50% was used to identify the MND₅₀. Furthermore, both phospholipase A₂ (PLA₂) and cytotoxins (CTXs) were separately removed from the deNTXs to identify the major necrosis-inducing factor, and the necrotic lesions were scored. All mice injected with deNTXs survived for three days and developed necrotic wounds. The MND of the deNTXs for mice was 0.494 ± 0.029 µg/g, that of the deNTXs-dePLA₂ (major component retained: CTXs) was 0.294 ± 0.05 µg/g, and that of the deNTX-deCTX (major component retained: PLA₂) venom was greater than 1.25 µg/g. These values show that CTX is the major factor inducing necrosis. These results suggest that the use of the deNTXs is necessary to enable the mice to survive long enough to develop venom-induced cytolytic effects. CTXs play a major role in N. atra-related necrosis. However, the MND₅₀ could not be identified in this study, which meant that the antivenom did not neutralize venom-induced necrosis. Full article

In this paper, an inorganic polymer composite film is proposed as an effective radiative cooling device. The inherent absorption is enhanced by choosing an appropriately sized SiO₂ microsphere with a diameter of 6 μm. The overall absorption at the transparent window of the atmosphere is higher than 90%, as the concentration of SiO₂–PMMA composite is 35 wt%. As a result, an effective radiative device is made by a spin coating process. Moreover, the device is stacked on the cold side of a thermoelectric generator chip. It is found that the temperature gradient can be increased via the effective radiative cooling process. An enhanced Seebeck effect is observed, and the corresponding output current can be enhanced 1.67-fold via the photonic-assisted radiative cooling. Full article

Naja atra bites cause severe soft tissue injury and are prone to wound infections. The pathogens of Naja atra bite-wound infections are highly variable in different geographical regions. Here, we report the first coinfection with Shewanella algae and Morganella morganii from a Naja atra bite wound with resistome analysis using whole genome sequencing. Full article

Background and Objectives: To investigate the health literacy (HL) among older adults in Taiwan, we referenced an existing integrated model of HL to confirm the influencing factors of HL in older adults. We propose this study to examine the personal, situational, and socioenvironmental factors influencing HL among older adults. Materials and Methods: A cross-sectional survey was conducted at a district hospital and affiliated community center in northern Taiwan from August 2016 to May 2017. This study used the Mandarin Chinese version of the European Health Literacy Survey Questionnaire (EU-Q47). We designed three models based on the three domains of HL. Model 1 assesses personal factors. Model 2 incorporates situational factors. Model 3 adds the socioenvironmental factor. Results: We recruited 161 participants aged over 65 years. Most adults in this study had limited overall HL. The final regression model revealed that age >85 years, unknown insurance status, and dominant spoken dialect of Hakka or Taiwanese were significantly associated with higher scores of HL. Conclusions: Our study results may help clinicians with early identification of older adults at high risk for poor HL and help health administrators establish geriatric policies and health education plans. Full article

In the production process from green beans to coffee bean packages, the defective bean removal (or in short, defect removal) is one of most labor-consuming stages, and many companies investigate the automation of this stage for minimizing human efforts. In this paper, we propose a deep-learning-based defective bean inspection scheme (DL-DBIS), together with a GAN (generative-adversarial network)-structured automated labeled data augmentation method (GALDAM) for enhancing the proposed scheme, so that the automation degree of bean removal with robotic arms can be further improved for coffee industries. The proposed scheme is aimed at providing an effective model to a deep-learning-based object detection module for accurately identifying defects among dense beans. The proposed GALDAM can be used to greatly reduce labor costs, since the data labeling is the most labor-intensive work in this sort of solutions. Our proposed scheme brings two main impacts to intelligent agriculture. First, our proposed scheme is can be easily adopted by industries as human effort in labeling coffee beans are minimized. The users can easily customize their own defective bean model without spending a great amount of time on labeling small and dense objects. Second, our scheme can inspect all classes of defective beans categorized by the SCAA (Specialty Coffee Association of America) at the same time and can be easily extended if more classes of defective beans are added. These two advantages increase the degree of automation in the coffee industry. The prototype of the proposed scheme was developed for studying integrated tests. Testing results of a case study reveal that the proposed scheme can efficiently and effectively generate models for identifying defective beans with accuracy and precision values up to $80\%$ . Full article