The accuracy of static computer-aided implant surgery (s-CAIS) is fundamental for predictable clinical outcomes. The objective of this study was to evaluate the influence of different guide-support modalities on the linear and angular accuracy of implant placement. In this retrospective clinical investigation conducted at a single specialty hospital, a total of 180 implants were analyzed, divided into three equal groups (n = 60) based on the guide support type: tooth-supported, bone-supported, and mucosa-supported. Accuracy was assessed by superimposing preoperative virtual plans with postoperative cone-beam computed tomography (CBCT) scans, measuring linear deviations at the neck and apex of the implant, as well as angular discrepancies. The type of guide support was found to be a significant factor associated with surgical accuracy (p < 0.001). Tooth-supported guides demonstrated the highest level of accuracy, with a mean angular deviation of 1.81° ± 0.45° and linear deviations at the neck and apex of 0.59 ± 0.18 mm and 0.73 ± 0.19 mm, respectively. These were followed by bone-supported guides (2.14° ± 0.48°; 1.04 ± 0.26 mm; 1.61 ± 0.31 mm), while mucosa-supported guides exhibited the greatest deviations (2.95° ± 0.60°; 1.47 ± 0.29 mm; 1.87 ± 0.37 mm). Significant intergroup differences and large effect sizes were observed, particularly regarding angular and horizontal discrepancies. These findings demonstrate a distinct gradient of accuracy based on guide support, establishing tooth-supported guides as the most accurate, followed by bone-supported and, lastly, mucosa-supported guides. While all modalities are clinically applicable, the use of mucosa-supported guides necessitates increased safety margins to account for the increased risk of linear and angular discrepancies inherent to mucosal tissue displacement.
暂无摘要（点击查看详情）
To systematically screen and verify the active components in the Dong ethnic medicine Lengyuxiao Tang (LYXT; Semen Pharbitidis, Verbena officinalis L., and Zingiber officinale Roscoe) for treating fever and cough, this scheme established a methodology process integrating network pharmacology prediction and experimental verification. Firstly, using the traditional Chinese medicine systems pharmacology database and analysis platform (TCMSP), with an oral bioavailability (OB) ≥ 30% and drug-likeness (DL) ≥ 0.18 as criteria, the key active components of LYXT were screened, and the related targets for fever and cough were collected from multiple disease databases. Subsequently, the "component-target-disease" interaction network was constructed, and, through topological analysis and gene ontology (GO) and Kyoto encyclopedia of genes and genomes (KEGG) pathway enrichment, the core action targets (CYP3A4, POR) and key signaling pathways (MAPK pathway) were identified. Molecular docking technology was used to verify the binding ability of key components to core targets. Finally, a chronic bronchitis mouse model was established by intranasal instillation of lipopolysaccharide (LPS), and the in vivo anti-inflammatory efficacy of the predicted main active components was verified. The results showed that components such as β-carotene and saparenol, screened by network pharmacology, exhibited varying degrees of anti-inflammatory effects in animal experiments, and their mechanisms may involve inhibition of the MAPK/p38 signaling pathway. This scheme provides a repeatable example for the screening and mechanism research of active components in traditional ethnic medicines.
Accurate assessment of swallowing function is essential in the diagnosis and monitoring of dysphagia following head and neck cancer (HNC). The simultaneous analysis of video-fluoroscopy swallow studies (VFSS) and high-resolution impedance manometry (HRIM) offers a more comprehensive evaluation, reducing subjectivity in VFSS and improving anatomical context of HRIM in HNC patients. The inherently low pharyngeal pressures in post-treatment HNC patients hinder the analysis of HRIM. As such, this study proposes a deep learning method for the automatic detection of HRIM sensors in VFSS using a YOLO11-based detector, aimed at enabling the automatic delineation of manometric regions. Detection performance was evaluated on 268 frames from 8 HNC patients using a leave-one-patient-out cross-validation approach. EigenCAM-based heatmaps were produced to analyze the model's attention patterns. The model achieved 95.8% Precision, 97.4% Recall, 96.6% F1-score with minimal variation between folds. Under different noise levels and bolus-simulated obstructions, performance remained robust. Our method outperformed previous template-matching methods for manometric sensor detection in VFSS. EigenCAM visualizations confirmed consistent attention to catheter regions. The proposed YOLO11-based detector provides accurate and robust localization of manometric sensors in VFSS sequences to facilitate computer-assisted HRIM-VFSS fusion for objective swallowing assessment.
暂无摘要（点击查看详情）
Ribulose-1,5-bisphosphate carboxylase/oxygenase (RuBisCo) is a prime target for enhancing the photosynthetic efficiency. Here, we employed bmDCA, a machine-learning implementation, to navigate the sequence space of Thermococcus kodakarensis RuBisCo (Tk-RuBisCo). After only two design-test cycles involving ∼30 variants, we isolated the double mutant SP9-Y168L-A361P, which exhibits a 1.5-fold increase in activity over the previous best mutant (SP9) under the same conditions. This gain far exceeds that achieved by conventional approaches. Notably, most bmDCA-designed double mutants display strictly additive effects, indicating that the incorporation of second-order coevolutionary information facilitates the identification of cooperative pairs. 1H NMR results demonstrated that the Y168L-A361P mutation enhances the carboxylation rate to a much greater extent than does the oxygenation rate. Molecular-dynamics simulations revealed that Y168L and A361P─although neither contacts the substrate directly─augment binding of the carboxylation intermediate EI II through an extended interaction network that strengthens hydrogen bonds to the substrate carboxylate.
Industrial biosynthesis of value-added glycosides in high-viscosity concentrated substrates still faces unprecedented challenges. Herein, manifold computational approaches are combined to rationally engineer the thermal tolerance of sucrose phosphorylase (SPase) for strengthening the performance in high-viscosity system. Through rational combination of ΔΔG, B-factor, and conservative amino acids, mutant V70I emerged as a superior mutant with an elevated optimal temperature, enhanced thermal tolerance, and augmented catalytic activity among 120 candidates. In a super high-viscosity system (267.8 mPa·s), mutant V70I demonstrated remarkable industrial potential as a biocatalyst, achieving 423 g/L 2-O-α-glucosyl glycerol (2-O-α-GG) production from 1.8 M sucrose and 2.16 M glycerol (a 208 g/L increase over the wild type) at 45 °C. This study highlights the industrial merits of rational integrated computational approaches, enabling efficient enzyme engineering for superior biocatalysis in high-viscosity systems.
Oral squamous cell carcinoma histopathological image classification is often challenged by staining variations and sparse local lesions, which can cause models to overfit color differences and weaken cross-domain generalization. A classification framework combining staining-bias suppression and structured multiple-instance aggregation was developed. In representation learning, stain-related features were disentangled from morphological and structural information, and a gated suppression mechanism was introduced to reduce color interference while enhancing tissue architecture and cellular morphology cues. In decision aggregation, image patches were treated as instances and spatial priors were incorporated to capture both neighborhood continuity and long-range dependencies. The proposed method achieved Acc 87.35%, F1 91.27%, and AUC 98.04% on one test set, and Acc 79.34%, F1 86.86%, and AUC 90.74% on another test set. It consistently outperformed traditional and deep learning baselines. External validation on an independent retrospective clinical cohort from a local hospital also showed stable performance. The results indicate that the proposed method can effectively alleviate the impact of staining bias and improve classification robustness. Its strong performance on external data further supports its practical value under real-world acquisition and staining variations.
Digital workflows have revolutionized restorative dentistry, computer-aided design and computer-aided manufacturing (CAD/CAM) milling, and three-dimensional (3D) printing provide alternatives to conventional methods of fabrication of inlays, onlays, and veneers. However, comparative evidence of their clinical performance remains scattered. This scoping review aimed to map and synthesize current evidence on the clinical outcomes of CAD/CAM- and 3D-printed inlays, onlays, and veneers, focusing on adaptation, strength, esthetics, and workflow efficiency. This scoping review followed the methodological framework proposed by Arksey and O'Malley, with refinements suggested by Levac et al., and was reported in accordance with the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews). A comprehensive search was performed in PubMed, Scopus, Web of Science, Cochrane Library, and Google Scholar for studies published from January 2000 to June 2025. Eligible studies included in vitro, clinical, and case-based reports that evaluated CAD/CAM or 3D-printed inlays, onlays, or veneers. Data were charted and analyzed thematically according to restoration type, fabrication method, material, and reported outcomes. Thirty studies were included, mainly in vitro. Inlays showed clinically acceptable adaptation, with 3D printing achieving accuracy comparable to milling, while ceramics offered superior hardness. Onlays yielded mixed outcomes: pressable ceramics had higher strength, but 3D-printed onlays often showed better adaptation. Veneers demonstrated the greatest potential for 3D printing, with printed zirconia and lithium disilicate performing well. CAD/CAM was faster and well established, whereas 3D printing provided greater customization but longer fabrication times. In conclusion, both CAD/CAM and 3D printing are capable of producing inlays, onlays, and veneers with clinically acceptable accuracy and strength. CAD/CAM remains the most established and reliable technique, particularly for ceramics, whereas 3D printing shows potential to enhance adaptation and customizability, especially for veneers. Further clinical trials are essential to validate long-term outcomes.
Monolithic zirconia has become increasingly popular in clinical dentistry as an indirect restorative material fabricated using computer-aided design/computer-aided manufacturing (CAD/CAM) technology. It is widely used due to its favorable combination of mechanical strength, aesthetic potential, and biocompatibility. Its monolithic design reduces the risk of veneer chipping, thereby improving restoration longevity. To narratively review the mechanical and adhesive properties of monolithic zirconia and discuss their clinical implications. This narrative review was based on a comprehensive, non-systematic literature search conducted using PubMed/MEDLINE, Scopus, and Web of Science. English-language publications addressing monolithic zirconia, mechanical behavior, surface treatments, adhesive strategies, and clinical performance were considered. Additional studies were identified through manual screening of reference lists. Study selection was guided by relevance to the review topic rather than predefined inclusion or exclusion criteria. Monolithic zirconia demonstrates high flexural strength and fracture toughness, supporting its use in posterior load-bearing restorations. However, direct exposure to the oral environment may promote low-temperature degradation (LTD), potentially affecting long-term mechanical stability. Despite improvements in translucency, aesthetic performance remains a consideration. Adhesive durability depends largely on appropriate surface conditioning and the use of functional primers, particularly those containing 10-methacryloyloxydecyl dihydrogen phosphate (MDP), which enhance chemical bonding to zirconia. Monolithic zirconia offers a reliable balance between strength and clinical durability. Nevertheless, its long-term performance is influenced by environmental exposure and adhesive protocols. Further research is needed to optimize the resin-zirconia interface while maintaining both mechanical reliability and aesthetic outcomes.
The color stability and translucency of contemporary Computer-Aided Design/Computer-Aided Manufacturing (CAD/CAM) glass and hybrid ceramic materials used for minimally invasive laminate veneers remain a clinical concern, particularly after exposure to aging conditions simulating oral service. The purpose of this in vitro study was to investigate the influence of accelerated artificial aging on the color stability and translucency of ceramic laminate veneers fabricated from different glass and hybrid ceramic materials. A total of 40 composite resin discs (A2 dentin shade, 8.0 mm diameter × 4.0 mm thickness) were fabricated to simulate the normal dentin substrate. They were randomly assigned to four groups (n = 10) according to the ceramic veneering material: (EC) IPS e.max CAD, (CT) Cerec Tessera, (VE) Vita Enamic, and (CS) Cerasmart. Then, 40 disc-shaped ceramic veneers (0.5 mm thickness) were fabricated and adhesively cemented to the substrates. Baseline color and translucency parameters were measured using a digital spectrophotometer. After artificial thermomechanical aging, color differences (ΔE00), using the CIEDE2000 formula and translucency parameter (TP) were calculated. The resulting data were statistically analysed using repeated-measures two-way analysis of variance (ANOVA) test (material × aging), followed by Post hoc Tukey test for multiple-group comparisons and Paired t-test for within-group comparisons, at p-value ≤ 0.05. Artificial aging significantly affected color stability and translucency for all tested materials (p < 0.001). Glass ceramics (EC and CT) demonstrated lower ΔE₀₀ values within clinically acceptable limits, whereas hybrid ceramics (VE and CS), particularly CS, exhibited significantly higher color changes exceeding acceptability threshold. Translucency significantly decreased after aging for all materials (p < 0.001). Artificial thermomechanical aging adversely affected the optical properties of all tested ceramic laminate veneers. The hybrid ceramic materials, particularly CS, were the most affected by aging in terms of color stability, whereas the glass ceramic materials (EC and CT) exhibited superior color stability. A reduction in translucency was observed for all materials after aging.
Crown lengthening serves as a key procedure for addressing aesthetic concerns such as gummy smile, short clinical crowns, and uneven gingival contours. Advances in digital technology, particularly computer-aided design and computer-aided manufacturing (CAD/CAM), now allow precise translation of preoperative plans into surgical execution, enabling accurate control over gingival margin and alveolar ridge positioning. To standardize the clinical application of this technology, the Chinese Society of Digital Dental Industry (CSDDI) convened a panel of experts to develop this guideline document. It aims to define steps for digital data acquisition, integration, and design in guided crown lengthening within the aesthetic zone; standardize the digital workflow for designing surgical guides for aesthetic crown lengthening; assist clinicians in formulating appropriate digital surgical plans through thorough digital analysis and diagnosis; and offer practical guidance on performing crown lengthening surgery using digital guides in aesthetic areas. Ultimately, this guideline seeks to standardize the surgical protocol for digital guide assisted crown lengthening, thereby improving procedural accuracy and predictability of treatment outcomes. 牙冠延长术常用于改善露龈笑、临床牙冠短等口腔美学缺陷及相关功能问题，其美学效果取决于对软硬组织切除位置、形态和量的精确控制。随着数字化技术的发展，计算机辅助设计与辅助制作技术可通过导板将术前规划准确转移至手术中，从而精确引导龈缘与牙槽嵴位置。为规范该技术的临床应用，全国卫生产业企业管理协会数字化口腔产业分会（CSDDI）组织专家制订本指南，旨在建立明确的导板引导下前牙美学区牙冠延长术的数字化资料采集、整合与设计步骤，规范前牙美学区牙冠延长手术导板的数字化设计流程；指导临床医师在临床工作中通过全面的数字化分析和诊断，为前牙美学区制订适宜的牙冠延长术数字化手术方案；对临床医师应用数字化手术导板进行前牙美学区牙冠延长术操作给予指导，规范数字化手术导板的操作流程，提升治疗精准性和结果的可预期性。.
Background/Objectives: Modern dentistry focuses on the ongoing development of digital alternative technologies and the study of the properties of these innovative materials is deemed essential. Therefore, the objectives of this study were to evaluate the optical and surface characteristics of six computer-aided design/Computer-Aided Manufacturing (CAD-CAM) dental materials, both subtractive and additive, in relation to in vitro degradation. Methods: CAD-CAM dental materials, subtractively processed (Vita Enamic, Cerasmart, Brilliant and Tetric) and additively manufactured (Saremco Crowntec and Voco C&B), were prepared to standard dimensions of 14 × 10 × 1 mm, with baseline measurements taken prior to, and after, the degradation procedures, consisting of immersion in an ADA-recommended staining broth, artificial aging (thermocycling), and the combined effects of staining and in vitro aging. Additionally, two different surface treatments were investigated (polished and glazed). Results: The poorest color stability was observed for Tetric glazed specimens (mean value 25.585) subjected to staining, while the best performance was recorded for Brilliant polished Control (average value of 0.781). The staining procedure produced the most pronounced color changes. Surface treatment did not significantly affect color stability, and surface roughness was not influenced by either the degradation method or the surface treatment (p > 0.05). Atomic Force Microscopy (AFM) evaluation revealed superior performance of the glazed surfaces, characterized by lower nanoroughness values compared with polished surfaces and a smoother surface appearance. Conclusions: The staining potential of staining broth was demonstrated in this study, with the highest values recorded after the staining procedures. In addition, the influence of artificial aging alone and artificial aging combined with staining was investigated, providing relevant results for a better clinical approach. Moreover, surface treatment demonstrated reliability and therefore clinical applicability.
With the rapid advancement of digital technologies, dentistry has witnessed significant innovations, particularly in the fabrication of removable complete dentures. The objective of this narrative review is to examine the evolution, current state, and future directions of digital removable complete dentures, with a focus on comparing computer-aided design and computer-aided manufacturing (CAD/CAM) approaches to conventional techniques in terms of clinical efficiency and patient satisfaction. A narrative review was conducted by searching PubMed, Scopus, Embase, and Web of Science for articles published between January 2010 and April 2025. Relevant keywords related to digital dentures, CAD/CAM, 3D printing, and patient outcomes were used. Studies focusing on digital complete denture fabrication and comparisons with conventional methods were included. Evidence indicates that digitally fabricated complete dentures demonstrate comparable or superior outcomes in retention, adaptation, and patient satisfaction. They also reduce the number of clinical visits and post-insertion adjustments. However, concerns remain regarding material properties, cost-effectiveness, and long-term performance. Digital denture fabrication presents a promising alternative to conventional methods, although further advancements in materials and long-term clinical validation are needed. Tailored implementation of digital workflows can enhance treatment efficiency and patient experience in removable prosthodontics.
Introduction Endodontically treated posterior teeth are weakened by the loss of coronal structure and require durable restoration to prevent fracture. Conventional post-core-crown systems often involve additional dentin removal, which increases the risk of root fracture. Endocrowns may offer a conservative alternative that uses the pulp chamber for retention. This in vitro study aimed to compare the fracture resistance and failure modes of endodontically treated mandibular first molars restored with lithium disilicate endocrowns versus fiber post-core and lithium disilicate full crowns. Materials and methods Sixty extracted mandibular first molars were root canal treated, randomly divided into two groups (n = 30 each), and restored: Group 1 with computer-aided design and computer-aided manufacturing lithium disilicate endocrowns and Group 2 with fiber posts, composite cores, and lithium disilicate crowns. All specimens were cemented with dual-cure resin cement, stored in water for 24 hours, embedded in acrylic, and tested under compressive load (1 mm/min) using a universal testing machine. The fracture load (N) and failure mode (favorable versus unfavorable) were recorded. Data were analyzed using the Shapiro-Wilk test, independent samples t-test, and descriptive statistics (α = 0.05). Results The mean fracture resistance of teeth restored with lithium disilicate endocrowns was 1250.45 ± 152.30 N, whereas the post-core-crown group demonstrated a mean value of 1180.20 ± 178.60 N. Although the endocrown group exhibited slightly higher fracture resistance, the difference between the groups was not statistically significant (p = 0.106). Failure mode analysis revealed a marked difference in the pattern of fractures between the groups. Endocrowns showed a significantly higher proportion of favorable (restorable) failures, primarily involving debonding or fractures above the cemento-enamel junction. In contrast, the post-core-crown group exhibited a higher incidence of unfavorable (non-restorable) fractures, including vertical root fractures and post-related failures. Conclusions Within the limitations of this in vitro study, lithium disilicate endocrowns demonstrated fracture resistance comparable to conventional fiber post-core restorations followed by full crowns. Importantly, endocrowns were associated with a significantly higher proportion of favorable, restorable failure patterns, suggesting a biomechanical advantage. The absence of intraradicular post placement likely contributes to improved stress distribution and reduced risk of catastrophic root fractures. Clinically, these findings support the use of endocrowns as a conservative and reliable restorative option for endodontically treated posterior teeth with adequate coronal structure. Their use may enhance long-term prognosis while preserving tooth structure and simplifying the restorative procedure.
This in vitro study evaluated the vertical marginal gap and fracture strength of four CAD/CAM (computer-aided design/computer-aided manufacturing) ceramic materials: a hybrid ceramic (Vita Enamic, Vita Zahnfabrik; VE), zirconia-reinforced lithium silicate (Vita Suprinity, Vita Zahnfabrik; VS), Virgilite-containing lithium disilicate (Cerec Tessera, Dentsply Sirona; CT), and using lithium disilicate (IPS e.max CAD, Ivoclar; Emax) as a control. A standardized all-ceramic crown preparation was conducted on a first maxillary premolar tooth. The prepared tooth was duplicated into 40 epoxy resin dies, allocated into four groups (n = 10) according to the four ceramic materials tested. The crowns' marginal gaps were measured using a metallurgical microscope. Cementation of the crowns was done using a self-adhesive resin cement, then tested to failure under a single load using a universal testing machine. The results were statistically analyzed with one-way ANOVA (analysis of variance) and post-hoc Tukey's honest significant difference tests. VS crowns demonstrated significantly higher (p < 0.001) marginal gap (80.14 ± 7.64 µm) than the other materials, VE (55.56 ± 7.20 µm), CT (58.20 ± 5.22 µm), and Emax (60.13 ± 3.63 µm), whereas VE (1,002.8 ± 78.9 N) showed significantly lower (p < 0.001) fracture strength value than CT (1,850 ± 90 N), Emax (1761.6 ± 101 N), and VS (1633.5 ± 149.5 N). All tested materials exhibited clinically acceptable marginal gaps and fracture strength values that exceeded the maximum reported masticatory forces. CT exhibited the highest fracture strength, while VE showed the lowest marginal gap. CT's superior fracture strength and excellent marginal fit highlight its suitability for mechanically challenging posterior restorations while maintaining marginal integrity.
This study evaluates and compares the flexural properties of computer-aided design-computer-aided manufacturing (CAD-CAM) resin composite and polyetheretherketone (PEEK) blocks used for molar crowns under three storage conditions. Furthermore, the relationship between the inorganic filler content (>70 wt. %) and the flexural properties of the resin composite blocks was clarified. Five commercially available resin composite blocks and one PEEK block were subjected to three storage conditions: dry storage, water immersion for 7 d at 37 °C, and 10,000 thermal cycles between 5 and 55 °C. The flexural strength and flexural modulus were analyzed using two-way ANOVA, followed by Tukey's post-hoc comparisons. The inorganic filler content and water sorption were analyzed via one-way ANOVA and the Tukey-Kramer post-hoc test, with the level of significance set at 5%. The resin composite blocks exhibited a significantly higher flexural strength and flexural modulus than the PEEK block. A positive correlation was observed between the inorganic filler content and the flexural properties of the CAD-CAM blocks, specifically for the flexural strength (r = 0.49) and flexural modulus (r = 0.63). However, the PEEK block exhibited the lowest water sorption and minimal flexural properties changes across all conditions, as compared to the resin composite blocks. Both the inorganic filler content and matrix resin composition influenced the flexural properties of the CAD-CAM crown materials. PEEK demonstrated superior durability under thermal and humid conditions, indicating its potential as a long-term restorative material for posterior crowns.
The use of computer-aided design/computer-aided manufacturing (CAD/CAM) enables a faster and more flexible workflow, reducing costs and work time. This study aimed to determine factors associated with the level of knowledge about CAD/CAM use among Peruvian dental students. This analytical, cross-sectional, observational study assessed 301 Peruvian dental students between March and April 2025 using a CAD/CAM knowledge questionnaire. A multivariable Poisson regression model with robust variance was fitted to estimate adjusted prevalence ratios (APR) for the association between knowledge level and sex, age, year of study, marital status, place of origin, occupation, and prior CAD/CAM training. Statistical significance was set at p < 0.05. When summarized using prespecified descriptive score groupings, 14.0% (95% CI: 10.0-17.9%) of students fell into the poor range, 66.4% (95% CI 61.1-71.8%) into the fair range, and 19.6% (95% CI 15.1-24.1%) into the good range regarding CAD/CAM use. Item-level findings were examined for descriptive and exploratory purposes and suggested frequent misconceptions, particularly concerning the complete elimination of physical impressions and the materials compatible with the system. In the adjusted analysis, third-year students showed a higher prevalence of belonging to the poor score grouping for CAD/CAM knowledge than fifth-year students (APR = 2.54; 95% CI 1.27-5.12). No significant associations were observed for age group, sex, marital status, place of origin, occupation, or prior CAD/CAM training. Dental students showed relevant knowledge gaps regarding CAD/CAM, with frequent misconceptions and a predominance of scores in the fair descriptive range. Third-year students showed a higher prevalence of belonging to the poor score grouping for CAD/CAM knowledge than fifth-year students, whereas demographic variables and prior training were not significantly associated; however, these findings should be interpreted cautiously given the preliminary measurement evidence and because the score groupings were used solely as operational, descriptive categories within this study rather than as validated or competency-based thresholds.
Accurate segmentation of dermoscopic images is essential for early melanoma diagnosis, yet current methods remain limited. CNN-based models capture local details but lack global context, whereas Transformer-based approaches model long-range dependencies but often lose fine structures; both struggle with blurred boundaries and scale variations. To address these challenges, we propose IFGNet, a hybrid segmentation framework that integrates CNN-Transformer synergy, multi-scale convolution, and boundary-aware decoding. Specifically, our design combines local-global feature fusion, large-kernel parallel convolutions without dilation, and a boundary refinement strategy to enhance lesion consistency. Extensive experiments on the ISIC 2016, ISIC 2017, and ISIC 2018 benchmarks demonstrate that IFGNet consistently surpasses state-of-the-art methods in Dice and IoU. These results highlight the effectiveness of IFGNet for accurate high-resolution skin lesion segmentation, and suggest its potential for clinical computer-aided melanoma diagnosis.
Monkeypox virus (MPXV) is emerging as a global public health concern due to its nature of spread. There are limited treatment options, as the sole drug for treatment is lacking, highlighting the need for new therapeutic options. The use of computer-aided drugs discovery such as molecular docking, molecular dynamic (MD) simulations and post-simulation analysis are important tools in identifying potential compounds that can target specific proteins of the virus, such as DNA polymerase to stop virus replication. This study employed molecular docking and molecular simulation with the aim to identify potential inhibitors for MPXV treatment from the ZINC Database. Molecular docking was performed using PyRx 0.8 version after virtual screening of the ZINC database using the Tranches tool; then, toxicity prediction of the selected compounds was performed using the ProTox-3.0 web server. Molecular dynamics simulation was conducted using GROMACS version 4.5 to evaluate the structural stability and dynamic behavior of the protein-ligand complex for the best interacting compound. Furthermore, post-simulation analysis was conducted using standard GROMACS utilities for visualizing time-dependent properties from MD simulations. A total of 16 compounds were shortlisted based on their molecular docking scores and interaction profiles with the monkeypox virus DNA polymerase (PDB ID: 8HG1). The leading compound, ZINC000019418450, demonstrated strong binding affinity (-7.4 kcal/mol). According to post-simulation analysis, all top compounds formed between one and five hydrogen bonds and up to eleven hydrophobic contacts with residues within the active site, thus providing strong geometric and energetic evidence for binding stability. Notably, our identification of ZINC000104288636 as a Class 6 compound with an LD50 of 23,000 mg/kg adds translational value by highlighting candidates with low predicted acute toxicity. Overall, this study lays a solid foundation for the rational design of next-generation monkeypox antiviral therapeutics. Future work is needed for experimental validation of prioritized compounds to assess their biochemical efficacy and pharmacological potential.