Smartphone video imaging: A versatile, low-cost technology for food authentication.

This study presents a low-cost smartphone-based imaging technique called smartphone video imaging (SVI) to capture short videos of samples that are illuminated by a colour-changing screen. Assisted by artificial intelligence, the study develops new capabilities to make SVI a versatile imaging technique such as the hyperspectral imaging (HSI). SVI enables classification of samples with heterogeneous contents, spatial representation of analyte contents and reconstruction of hyperspectral images from videos. When integrated with a residual neural network, SVI outperforms traditional computer vision methods for ginseng classification. Moreover, the technique effectively maps the spatial distribution of saffron purity in powder mixtures with predictive performance that is comparable to that of HSI. In addition, SVI combined with the U-Net deep learning module can produce high-quality images that closely resemble the target images acquired by HSI. These results suggest that SVI can serve as a consumer-oriented solution for food authentication.

Modular DNA Construct Design for High-Throughput Golden Gate Assembly.

Golden Gate cloning enables the modular assembly of DNA parts into desired synthetic genetic constructs. The "one-pot" nature of Golden Gate reactions makes them particularly amenable to high-throughput automation, facilitating the generation of thousands of constructs in a massively parallel manner. One potential bottleneck in this process is the design of these constructs. There are multiple parameters that must be considered during the design of an assembly process, and the final design should also be checked and verified before implementation. Doing this by hand for large numbers of constructs is neither practical nor feasible and increases the likelihood of introducing potentially costly errors. In this chapter we describe a design workflow that utilizes bespoke computational tools to automate the key phases of the construct design process and perform sequence editing in batches.

A computer-aided, heterodimer-based "triadic" carrier-free drug delivery platform to mitigate multidrug resistance in lung cancer and enhance efficiency.

Co-delivering multiple drugs or circumventing the drug efflux mechanism can significantly decrease multidrug resistance (MDR), a major cause of cancer treatment failure. In this study, we designed and fabricated a universal "three-in-one" self-delivery system for synergistic cancer therapy using a computer-aided strategy. First, we engineered two glutathione (GSH)-responsive heterodimers, ERL-SS-CPT (erlotinib [ERL] linked with camptothecin [CPT] via a disulfide bond [SS]) and CPT-SS-ERI (CPT conjugated with erianin [ERI]), which serve as both cargo and carrier material. Next, molecular dynamics simulations indicated that multiple noncovalent molecular forces, including π-π stacking, hydrogen bonds, hydrophobic interactions, and sulfur bonds, drive the self-assembly process of these heterodimers. We then explored the universality of the heterodimers and developed a "triadic" drug delivery platform comprising 40 variants. Subsequently, we conducted case studies on docetaxel (DTX)-loaded ERL-SS-CPT nanoparticles (denoted as DTX@ERL-SS-CPT NPs) and curcumin (CUR)-loaded ERL-SS-CPT NPs (identified as CUR@CPT-SS-ERI NPs) to comprehensively investigate their self-assembly mechanism, physicochemical properties, storage stability, GSH-responsive drug release, cellular uptake, apoptosis effects, biocompatibility, and cytotoxicity. Both NPs exhibited well-defined spherical structures, high drug loading rates, and excellent storage stability. DTX@ERL-SS-CPT NPs exhibited the strongest cytotoxicity in A549 cells, following the order of DTX@ERL-SS-CPT NPs > ERL-SS-CPT NPs > CPT > DTX > ERL. Conversely, DTX@ERL-SS-CPT NPs showed negligible cytotoxicity in normal human bronchial epithelium cell line (BEAS-2B), indicating good biocompatibility and safety. Similar observations were made for CUR@CPT-SS-ERI NPs regarding biocompatibility and cytotoxicity. Upon endocytosis and encountering intracellular overexpressed GSH, the disulfide-bond linker is cleaved, resulting in the release of the versatile NPs into three parts. The spherical NPs enhance water solubility, reduce the required dosage of free drugs, and increase cellular drug accumulation while suppressing P-glycoprotein (P-gp) expression, leading to apoptosis. This work provides a computer-aided universal strategy-a heterodimer-based "triadic" drug delivery platform-to enhance anticancer efficiency while reducing multidrug resistance.

MolPredictX: A Pioneer Mobile App Version for Online Biological Activity Predictions by Machine Learning Models.

MolPredictX is a free-access web tool in which it is possible to analyze the prediction of biological activity of chemical molecules. MolPredictX has been available online to the general public for just over a year and has now gone through its first update. We also developed its version for android, being the first free app capable of predicting biological activities. MolPredictX is available for free at https://www.molpredictX.ufpb.br/ , and its mobile application version can be obtained from Google Play.

Competencias digitales en los ingresantes a la carrera de Licenciatura en Enfermería

Objetivo: Determinar las habilidades y conocimientos sobre las tecnologías de la información y la comunicación (TIC) de los ingresantes a la carrera de Licenciatura en Enfermería de una institución superior pública de Bahía Blanca, Provincia de Buenos Aires, Argentina. Metodología: Estudio observacional, descriptivo, transversal y cuantitativo. Se implementó un instrumento conformado por 59 preguntas con opciones de respuesta cerrada orientado a valorar las competencias digitales en los ingresantes a la carrera. Resultados: Participaron 386 ingresantes, mayormente de género femenino (85.49 %), del primer ciclo (74.35 %) y con 20 años o menos de edad (47.15 %). El 98.19 % tenía acceso a internet, el 79.27 % tiene computadora y más del 80 % tiene un amplio uso de redes sociales (WhatsApp, Instagram) y correo electrónico. Los ingresantes se autoevaluaron competentes en el programa MS Word, mientras que en MS Excel se declararon menos competentes. Hay desconocimiento y bajo desarrollo de habilidades para generar contenido, y un amplio despliegue de habilidades para buscar y descargar información de la web. La edad, el género, el tiempo diario de uso de internet y el ciclo de ingreso mostraron relación con el dominio de las herramientas digitales aplicadas a la educación. Conclusiones: Se identificó un desarrollo intermedio de competencias digitales aplicadas a la educación, lo que podría ameritar el diseño de programas que nivelen estas habilidades durante el proceso de ingreso o durante la formación.

Objetivo: determinar habilidades e conhecimentos sobre as tecnologias da informação e comunicação (TIC) dos calouros no curso de bacharelado em enfermagem em uma instituição pública de ensino superior na cidade de Bahía Blanca, província de Buenos Aires, Argentina. Metodologia: estudo observacional, descritivo, transversal e quantitativo. Foi utilizado um instrumento composto por 59 perguntas com opções de resposta fechada para avaliar as competências digitais dos calouros do curso. Resultados: Participaram 386 estudantes, em sua maioria do gênero feminino (85,49 %), do primeiro ciclo estudantil (74,35 %) e com idade igual ou inferior a 20 anos (47,15 %). 98,19 % tinham acesso à internet, 79,27 % tinham computador e mais de 80 % usavam amplamente as redes sociais (WhatsApp, Instagram) e o e-mail. Os calouros se auto-avaliaram competentes no programa MS Word, enquanto no MS Excel se declararam menos competentes. Há desconhecimento e baixo desenvolvimento de habilidades para gerar conteúdo e uma ampla demonstração de habilidades para pesquisar e baixar informações da web. A idade, o gênero, o tempo diário de uso da Internet e o ciclo de ingresso estudantil mostraram relação com o domínio das ferramentas digitais aplicadas à educação. Conclusões: Foi identificado um desenvolvimento intermediário de competências digitais aplicadas à educação, o que poderia demandar a concepção de programas que nivelem essas competências durante o processo de admissão ou durante a formação.

Objective: To determine the skills and knowledge about information and communication technologies (ICT) of entrants to the Bachelor's Degree in Nursing at a public higher institution in Bahía Blanca, Province of Buenos Aires, Argentina. Methodology: Observational, descriptive, transversal and quantitative study. An instrument was implemented consisting of 59 questions with closed response options aimed at assessing digital competencies in those entering the career. Results: 386 entrants participated, mostly female (85.49 %), from the first cycle (74.35 %) and 20 years old or younger (47.15%). 98.19 % had access to the internet, 79.27 % have a computer and more than 80 % have extensive use of social networks (WhatsApp, Instagram) and email. The entrants evaluated themselves as competent in the MS Word program, while in MS Excel they declared themselves less competent. There is a lack of knowledge and low development of skills to generate content and a wide range of skills to search and download information from the web. Age, gender, daily time of Internet use and entry cycle showed a relationship with the mastery of digital tools applied to education. Conclusions: An intermediate development of digital competencies applied to education was identified, and a high one for the use of social networks. The variables age, gender, daily time of Internet use and entry cycle were related to the knowledge and skills for using ICT applied to education.

A dental intraoral image dataset of gingivitis for image captioning.

One of the most striking topics in Artificial Intelligence (AI) is Image captioning that aims to integrate computer vision and natural language processing to create descriptions for each image. In this paper, we propose a new dataset designed specifically for image captioning in gingivitis diagnosis using deep learning. It includes 1,096 high-resolution intraoral images of 12 anterior teeth and surrounding gingival tissue that were collected under controlled conditions with professional-grade photography equipment. Each image features detailed labels and descriptive captions. The labeling process involved three periodontists with over ten years of experience who assigned Modified Gingival Index (MGI) scores to each tooth in the images, achieving high inter-rater reliability through a rigorous calibration process. Captions were then created by the same periodontists, offering diverse descriptions of gingivitis severity and locations. The dataset is systematically organized into training, validation, and testing subsets for systematic accessibility. This dataset supports the development of advanced image captioning algorithms and is a valuable educational resource for integrating real-world data into dental research and curriculum.

Deep neural networks for automated damage classification in image-based visual data of reinforced concrete structures.

Significant strides in deep learning for image recognition have expanded the potential of visual data in assessing damage to reinforced concrete (RC) structures. Our study proposes an automated technique, merging convolutional neural networks (CNNs) and fully convolutional networks (FCNs), to detect, classify, and segment building damage. These deep networks extract RC damage-related features from high-resolution smartphone images (3264 × 2448 pixels), categorized into two groups: damage (exposed reinforcement and spalled concrete) and undamaged area. With a labeled dataset of 2000 images, fine-tuning of network architecture and hyperparameters ensures effective training and testing. Remarkably, we achieve 98.75 % accuracy in damage classification and 95.98 % in segmentation, without overfitting. Both CNNs and FCNs play crucial roles in extracting features, showcasing the adaptability of deep learning. Our promising results validate the potential of these techniques for inspectors, providing an effective means to assess the severity of identified damage in image-based evaluations.

CAE-ResVGG FusionNet: A Feature Extraction Framework Integrating Convolutional Autoencoders and Transfer Learning for Immature White Blood Cells in Acute Myeloid Leukemia.

Acute myeloid leukemia (AML) is a highly aggressive cancer form that affects myeloid cells, leading to the excessive growth of immature white blood cells (WBCs) in both bone marrow and peripheral blood. Timely AML detection is crucial for effective treatment and patient well-being. Currently, AML diagnosis relies on the manual recognition of immature WBCs through peripheral blood smear analysis, which is time-consuming, prone to errors, and subject to inter-observers' variation. This study aimed to develop a computer-aided diagnostic framework for AML, called "CAE-ResVGG FusionNet", that precisely identifies and classifies immature WBCs into their respective subtypes. The proposed framework leverages an integrated approach, by combining a convolutional autoencoder (CAE) with finely tuned adaptations of the VGG19 and ResNet50 architectures to extract features from CAE-derived embeddings. The process begins with a binary classification model distinguishing between mature and immature WBCs followed by a multiclassifier further classifying immature cells into four subtypes: myeloblasts, monoblasts, erythroblasts, and promyelocytes. The CAE-ResVGG FusionNet workflow comprises four primary stages, including data preprocessing, feature extraction, classification, and validation. The preprocessing phase involves applying data augmentation methods using geometric transformations and synthetic image generation using the CAE to address imbalance in the WBC distribution. Feature extraction involves image embedding and transfer learning, where CAE-derived image representations are used by a custom integrated model of VGG19 and ResNet50 pretrained models. The classification phase employs a weighted ensemble approach that leverages VGG19 and ResNet50, where the optimal weighting parameters are selected using a grid search. The model performance was assessed during the validation phase using the overall accuracy, precision, and sensitivity, while the area under the receiver characteristic curve (AUC) was used to evaluate the model's discriminatory capability. The proposed framework exhibited notable results, achieving an average accuracy of 99.9%, sensitivity of 91.7%, and precision of 98.8%. The model demonstrated exceptional discriminatory ability, as evidenced by an AUC of 99.6%. Significantly, the proposed system outperformed previous methods, indicating its superior diagnostic ability.

Personalized subperiosteal implant­supported obturator for the rehabilitation of rhino­orbit­cerebral mucormycosis sequela: A case report.

Severe atrophy of the maxilla occasionally renders it impossible to place standard endosseous implants to replace absent teeth. For such cases, personalized subperiosteal implants (PSI) are presented as a treatment alternative. Due to novel design and manufacturing technologies, PSIs are fitted closely to the bone structure of the patient, after defining the anchorage areas where the bone is of higher quality and allowing a passive dental prosthesis to be attached to restore function and aesthetics to the patient. The present case report documents a patient with severe bone defects as a sequela of rhino-orbit-cerebral mucormycosis. After a failed microvascular fibula flap reconstruction, the patient was treated with a removable implant-supported prosthesis attached to a PSI, which provided occlusion with the mandible of the patient and closed the oronasal-antral communication defect. At 18 months after treatment, the patient felt well, with no biological complications and the prosthesis was well adjusted and with good function. Consequently, we consider that in some cases such as this, a customized solution of this type can avoid complex reconstruction treatments.

Large scale investigation of the effect of gender on mu rhythm suppression in motor imagery brain-computer interfaces.

The utmost issue in Motor Imagery Brain-Computer Interfaces (MI-BCI) is the BCI poor performance known as 'BCI inefficiency'. Although past research has attempted to find a solution by investigating factors influencing users' MI-BCI performance, the issue persists. One of the factors that has been studied in relation to MI-BCI performance is gender. Research regarding the influence of gender on a user's ability to control MI-BCIs remains inconclusive, mainly due to the small sample size and unbalanced gender distribution in past studies. To address these issues and obtain reliable results, this study combined four MI-BCI datasets into one large dataset with 248 subjects and equal gender distribution. The datasets included EEG signals from healthy subjects from both gender groups who had executed a right- vs. left-hand motor imagery task following the Graz protocol. The analysis consisted of extracting the Mu Suppression Index from C3 and C4 electrodes and comparing the values between female and male participants. Unlike some of the previous findings which reported an advantage for female BCI users in modulating mu rhythm activity, our results did not show any significant difference between the Mu Suppression Index of both groups, indicating that gender may not be a predictive factor for BCI performance.

Protocol for UAV fault diagnosis using signal processing and machine learning.

Unmanned aerial vehicles (UAVs) require fault diagnosis for safe operation. Here, we present a protocol for UAV fault diagnosis using signal processing and artificial intelligence. We describe steps for collecting vibration-based signal data, preprocessing, and feature extraction using a 3-axis accelerometer or similar sensors. We then detail the application of machine learning techniques, including deep neural networks, support vector machine, k-nearest neighbor, and other algorithms, for classifying faults. This protocol is applicable to various UAV models for accurate fault detection. For complete details on the use and execution of this protocol, please refer to Al-Haddad et al.,1,2,3,4 Shandookh et al.5.

Protocol to process follow-up electronic medical records of peritoneal dialysis patients to train AI models.

The absence of standardized protocols for integrating end-stage renal disease patient data into AI models has constrained the potential of AI in enhancing patient care. Here, we present a protocol for processing electronic medical records from 1,336 peritoneal dialysis patients with more than 10,000 follow-up records. We describe steps for environment setup and transforming records into analyzable formats. We then detail procedures for developing a directly usable dataset for training AI models to predict one-year all-cause mortality risk. For complete details on the use and execution of this protocol, please refer to Ma et al.1.

Prognosis of major bleeding based on residual variables and machine learning for critical patients with upper gastrointestinal bleeding: A multicenter study.

BACKGROUND: Upper gastrointestinal bleeding (UGIB) is a significant cause of morbidity and mortality worldwide. This study investigates the use of residual variables and machine learning (ML) models for predicting major bleeding in patients with severe UGIB after their first intensive care unit (ICU) admission. METHODS: The Medical Information Mart for Intensive Care IV and eICU databases were used. Conventional ML and long short-term memory models were constructed using pre-ICU and ICU admission day data to predict the recurrence of major gastrointestinal bleeding. In the models, residual data were utilized by subtracting the normal range from the test result. The models included eight algorithms. Shapley additive explanations and saliency maps were used for feature interpretability. RESULTS: Twenty-five ML models were developed using data from 2604 patients. The light gradient-boosting machine algorithm model using pre-ICU admission residual data outperformed other models that used test results directly, with an AUC of 0.96. The key factors included aspartate aminotransferase, blood urea nitrogen, albumin, length of ICU admission, and respiratory rate. CONCLUSIONS: ML models using residuals improved the accuracy and interpretability in predicting major bleeding during ICU admission in patients with UGIB. These interpretable features may facilitate the early identification and management of high-risk patients, thereby improving hemodynamic stability and outcomes.

A deep learning approach to case prioritisation of colorectal biopsies.

AIMS: To create and validate a weakly supervised artificial intelligence (AI) model for detection of abnormal colorectal histology, including dysplasia and cancer, and prioritise biopsies according to clinical significance (severity of diagnosis). MATERIALS AND METHODS: Triagnexia Colorectal, a weakly supervised deep learning model, was developed for the classification of colorectal samples from haematoxylin and eosin (H&E)-stained whole slide images. The model was trained on 24 983 digitised images and assessed by multiple pathologists in a simulated digital pathology environment. The AI application was implemented as part of a point and click graphical user interface to streamline decision-making. Pathologists assessed the accuracy of the AI tool, its value, ease of use and integration into the digital pathology workflow. RESULTS: Validation of the model was conducted on two cohorts: the first, on 100 single-slide cases, achieved micro-average model specificity of 0.984, micro-average model sensitivity of 0.949 and micro-average model F1 score of 0.949 across all classes. A secondary multi-institutional validation cohort, of 101 single-slide cases, achieved micro-average model specificity of 0.978, micro-average model sensitivity of 0.931 and micro-average model F1 score of 0.931 across all classes. Pathologists reflected their positive impressions on the overall accuracy of the AI in detecting colorectal pathology abnormalities. CONCLUSIONS: We have developed a high-performing colorectal biopsy AI triage model that can be integrated into a routine digital pathology workflow to assist pathologists in prioritising cases and identifying cases with dysplasia/cancer versus non-neoplastic biopsies.

Accuracy of an artificial intelligence-enabled diagnostic assistance device in recognizing normal chest radiographs: a service evaluation.

Objectives: Artificial intelligence (AI) enabled devices may be able to optimize radiologists' productivity by identifying normal and abnormal chest X-rays (CXRs) for triaging. In this service evaluation, we investigated the accuracy of one such AI device (qXR). Methods: A randomly sampled subset of general practice and outpatient-referred frontal CXRs from a National Health Service Trust was collected retrospectively from examinations conducted during November 2022 to January 2023. Ground truth was established by consensus between 2 radiologists. The main objective was to estimate negative predictive value (NPV) of AI. Results: A total of 522 CXRs (458 [87.74%] normal CXRs) from 522 patients (median age, 64 years [IQR, 49-77]; 305 [58.43%] female) were analysed. AI predicted 348 CXRs as normal, of which 346 were truly normal (NPV: 99.43% [95% CI, 97.94-99.93]). The sensitivity, specificity, positive predictive value, and area under the ROC curve of AI were found to be 96.88% (95% CI, 89.16-99.62), 75.55% (95% CI, 71.34-79.42), 35.63% (95% CI, 28.53-43.23), and 91.92% (95% CI, 89.38-94.45), respectively. A sensitivity analysis was conducted to estimate NPV by varying assumptions of the prevalence of normal CXRs. The NPV ranged from 88.96% to 99.54% as prevalence increased. Conclusions: The AI device recognized normal CXRs with high NPV and has the potential to increase radiologists' productivity. Advances in knowledge: There is a need for more evidence on the utility of AI-enabled devices in identifying normal CXRs. This work adds to such limited evidence and enables researchers to plan studies to further evaluate the impact of such devices.

Protocol for an open-source system to integrate calcium imaging, pupillometry, and locomotion-estimated tracking in head-fixed mice.

A wide selection of behavioral assays in systems neuroscience relies on head-fixation protocols to integrate in vivo multi-photon imaging approaches. For this, simultaneous pupillometry and locomotion tracking in head-fixed mice are used to measure behavioral responses and identify neural correlates. Here, we present an open-source protocol for assembling a complete head-fixation system that integrates pupillometry and locomotion-estimated tracking with multi-photon calcium imaging. We include detailed procedures for head-fixation and for data collection.

Prediction of prostate cancer recurrence after radiotherapy using a fused machine learning approach: Utilizing radiomics from pretreatment T2W MRI images with clinical and pathological information.

BACKGROUND: The risk of biochemical recurrence (BCR) after radiotherapy for localized prostate cancer (PCa) varies widely within standard risk groups. There is a need for low-cost tools to more robustly predict recurrence and personalize therapy. Radiomic features from pretreatment MRI show potential as noninvasive biomarkers for BCR prediction. However, previous research has not fully combined radiomics with clinical and pathological data to predict BCR in PCa patients following radiotherapy. Purpose: This study aims to predict 5-year BCR using radiomics from pretreatment T2W MRI and clinical-pathological data in PCa patients treated with radiation therapy, and to develop a unified model compatible with both 1.5T and 3T MRI scanners. Methods: A total of 150 T2W scans and clinical parameters were preprocessed. Of these, 120 cases were used for training and validation, and 30 for testing. Four distinct machine learning models were developed: Model 1 used radiomics, Model 2 used clinical and pathological data, and Model 3 combined these using late fusion. Model 4 integrated radiomic and clinical-pathological data using early fusion. Results: Model 1 achieved an AUC of 0.73, while Model 2 had an AUC of 0.64 for predicting outcomes in 30 new test cases. Model 3, using late fusion, had an AUC of 0.69. Early fusion models showed strong potential, with Model 4 reaching an AUC of 0.84, highlighting the effectiveness of the early fusion model. Conclusions: This study is the first to use a fusion technique for predicting BCR in PCa patients following radiotherapy, utilizing pre-treatment T2W MRI images and clinical-pathological data. The methodology improves predictive accuracy by fusing radiomics with clinical-pathological information, even with a relatively small dataset, and introduces the first unified model for both 1.5T and 3T MRI images.

Clinical and in vitro application of robotic computer-assisted implant surgery: a scoping review.

In recent years, the emergence and application of robotic computer-assisted implant surgery (r-CAIS) has resulted in a revolutionary shift in conventional implant diagnosis and treatment. This scoping review was performed to verify the null hypothesis that r-CAIS has a relatively high accuracy of within 1 mm, with relatively few complications and a short operative time. This review was conducted in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews (PRISMA-ScR). From the 3355 publications identified in the PubMed, Scopus, Web of Science, and Google Scholar databases, 28 were finally included after a comprehensive review and analysis. The null hypothesis is partly accepted, as r-CAIS has a relatively high accuracy (coronal and apical deviation within 1 mm), and no significant adverse events or complications have been reported to date, although additional confirmatory studies are needed. However, there is insufficient evidence for a shorter surgical time, and further clinical research on this topic is required.

IG-Net: An Instrument-guided real-time semantic segmentation framework for prostate dissection during surgery for low rectal cancer.

BACKGROUND AND OBJECTIVE: Accurate prostate dissection is crucial in transanal surgery for patients with low rectal cancer. Improper dissection can lead to adverse events such as urethral injury, severely affecting the patient's postoperative recovery. However, unclear boundaries, irregular shape of the prostate, and obstructive factors such as smoke present significant challenges for surgeons. METHODS: Our innovative contribution lies in the introduction of a novel video semantic segmentation framework, IG-Net, which incorporates prior surgical instrument features for real-time and precise prostate segmentation. Specifically, we designed an instrument-guided module that calculates the surgeon's region of attention based on instrument features, performs local segmentation, and integrates it with global segmentation to enhance performance. Additionally, we proposed a keyframe selection module that calculates the temporal correlations between consecutive frames based on instrument features. This module adaptively selects non-keyframe for feature fusion segmentation, reducing noise and optimizing speed. RESULTS: To evaluate the performance of IG-Net, we constructed the most extensive dataset known to date, comprising 106 video clips and 6153 images. The experimental results reveal that this method achieves favorable performance, with 72.70% IoU, 82.02% Dice, and 35 FPS. CONCLUSIONS: For the task of prostate segmentation based on surgical videos, our proposed IG-Net surpasses all previous methods across multiple metrics. IG-Net balances segmentation accuracy and speed, demonstrating strong robustness against adverse factors.

Novel use of dynamic navigation for guiding a piezoelectric device during window osteotomy for maxillary sinus floor elevation in complex clinical scenarios.

In patients with severe atrophy of the posterior maxilla requiring lateral maxillary sinus floor elevation (MSFE), the window location and size are commonly designed according to the future implants and anatomical conditions. A window osteotomy becomes challenging when there is an extended edentulous space in the maxilla with no reference from the natural dentition, or when the surgical site involves anatomical variations, for example in the course of a large vessel or a sinus septum. Through preoperative planning and real-time visualization, the application of dynamic navigation allows an accurate location, optimal dimension, and customized shape during lateral window osteotomy. This article introduces a digital protocol for ensuring an accurate and safe window osteotomy for MSFE in complex clinical scenarios, by integrating dynamic navigation and a piezoelectric device.