Deep learning-based automated detection of the dental crown finish line: An accuracy study.

STATEMENT OF PROBLEM: The marginal fit of dental prostheses is a clinically significant issue, and dental computer-aided design software programs use automated methods to expedite the extraction of finish lines. The accuracy of these automated methods should be evaluated. PURPOSE: The purpose of this study was to compare the accuracy of a new hybrid method with existing software programs that extract finish lines using fully automated and semiautomated methods. MATERIAL AND METHODS: A total of 182 jaw scans containing at least 1 natural tooth abutment were collected and divided into 2 groups depending on how the digital data were created. Group DS used desktop scanners to scan casts trimmed for improved finish line visibility, while Group IS used intraoral scans. The method from Dentbird was compared using 3 software packages from 3Shape, exocad, and MEDIT. The Hausdorff and Chamfer distances were used in this study. Three dental laboratory technicians experienced in the digital workflow evaluated clinical finish line acceptance and its Hausdorff and Chamfer distances. For statistical analysis, t tests were performed after the outliers had been removed using the Tukey interquartile range method (α=.05). RESULTS: Outliers identified by using the Tukey interquartile range method were more numerous in the semiautomatic methods than in the automatic methods. When considering data without outliers, the software performance was found to be similar for desktop scans of the trimmed casts. However, the method from Dentbird demonstrated statistically better results (P<.05) for the posterior tooth with finish lines in concave regions than the 3Shape, exocad, and MEDIT software programs. Furthermore, thresholds coherent with clinical acceptance were determined for the Hausdorff and Chamfer distances. The Hausdorff distance threshold was 0.366 mm for desktop scans and 0.566 mm for intraoral scans. For the Chamfer distance, the threshold was 0.026 for desktop scans and 0.100 for intraoral scans. CONCLUSIONS: The method from Dentbird demonstrated a comparable or better performance than the other software solutions, particularly excelling in finish line extraction for intraoral scans. Using a hybrid method combining deep learning and computer-aided design approaches enables the robust and accurate extraction of finish lines.

Time efficiency, occlusal morphology, and internal fit of anatomic contour crowns designed by dental software powered by generative adversarial network: A comparative study.

OBJECTIVES: To evaluate the time efficiency, occlusal morphology, and internal fit of dental crowns designed using generative adversarial network (GAN)-based dental software compared to conventional dental software. METHODS: Thirty datasets of partial arch scans for prepared posterior teeth were analyzed. Each crown was designed on each abutment using GAN-based software (AI) and conventional dental software (non-AI). The AI and non-AI groups were compared in terms of time efficiency by measuring the elapsed work time. The difference in the occlusal morphology of the crowns before and after design optimization and the internal fit of the crown to the prepared abutment were also evaluated by superimposition for each software. Data were analyzed using independent t tests or Mann-Whitney test with statistical significance (α=.05). RESULTS: The working time was significantly less for the AI group than the non-AI group at T1, T5, and T6 (P≤.043). The working time with AI was significantly shorter at T1, T3, T5, and T6 for the intraoral scan (P≤.036). Only at T2 (P≤.001) did the cast scan show a significant difference between the two groups. The crowns in the AI group showed less deviation in occlusal morphology and significantly better internal fit to the abutment than those in the non-AI group (both P<.001). CONCLUSIONS: Crowns designed by AI software showed improved outcomes than that designed by non-AI software, in terms of time efficiency, difference in occlusal morphology, and internal fit. CLINICAL SIGNIFICANCE: The GAN-based software showed better time efficiency and less deviation in occlusal morphology during the design process than the conventional software, suggesting a higher probability of optimized outcomes of crown design.

Functional Asymmetry-Enabled Self-Adhesive Film via Phase Separation of Binary Polymer Mixtures for Soft Bio-Integrated Electronics.

Biocompatible adhesive films are important for many applications (e.g., wearable devices, implantable devices, and attachable sensors). In particular, achieving self-adhesion on one side of a film with biocompatible materials is a compelling goal in adhesion science. Herein, we report a simple and easy manufacturing process using water-soluble hyaluronic acid (HA) that allows adhesiveness on only one side using binary polymer mixtures based on a phase-separation strategy with an elastomer. HA influx allows for the entangled polymer chains of the elastomer to spontaneously deform, permitting tunable mechanical elasticity, conformability, and adhesion. The proposed adhesive film enables the transfer of nanopatterning and the attachment of various surfaces without the use of additional chemicals. In addition, the film can be used for measuring epidermal biopotential and for skin fixation of drug devices. Therefore, the developed facile asymmetric adhesion can block the interferences of other materials on the unnecessary adhesion side, providing considerable potential for the development of functional, multifunctional, and smart bioadhesives.

Biocompatible All-in-One Adhesive Needle-Free Cup Patch for Enhancing Transdermal Drug Delivery.

Patch-type drug delivery has garnered increased attention as an attractive alternative to the existing drug delivery techniques. Thus far, needle phobia and efficient drug delivery remain huge challenges. To address the issue of needle phobia and enhance drug delivery, we developed a needle-free and self-adhesive microcup patch that can be loaded with an ultrathin salmon DNA (SDNA) drug carrier film. This physically integrated system can facilitate efficient skin penetration of drugs loaded into the microcup patch. The system consists of three main components, namely, a cup that acts as a drug reservoir, an adhesive system that attaches the patch to the skin, and physical stimulants that can be used to increase the efficiency of drug delivery. In addition, an ultrathin SDNA/drug film allows the retention of the drug in the cup and its efficient release by dissolution in the presence of moisture. This latter feature has been validated using gelatin as a skin mimic. The cup design itself has been validated by comparing its deformation and displacement with those of a cylindrical structure. Integration of the self-adhesive microcup patch with both ultrasonic waves and an electric current allows the model drug to penetrate the stratum corneum of the skin barrier and the whole epidermis, thereby enhancing transdermal drug delivery and reducing skin irritation. This system can be used as a wearable biomedical device for efficient transdermal and needle-free drug delivery.

Biocompatible Nanotransfer Printing Based on Water Bridge Formation in Hyaluronic Acid and Its Application to Smart Contact Lenses.

Many conventional micropatterning and nanopatterning techniques employ toxic chemicals, rendering them nonbiocompatible and unsuited for biodevice production. Herein the formation of water bridges on the surface of hyaluronic acid (HA) films is exploited to develop a transfer-based nanopatterning method applicable to diverse structures and materials. The HA film surface, made deformable via water bridge generation, is brought into contact with a functional material and subjected to thermal treatment, which results in film shrinkage, allowing a robust pattern transfer. The proposed biocompatible method, which avoids the use of extra chemicals, enables the transfer of nanoscale, microscale, and thin-film structures as well as functional materials such as metals and metal oxides. A nanopatterned HA film is transferred onto a moisture-containing contact lens to fabricate smart contact lenses with unique optical characteristics of rationally designed optical nanopatterns. These lenses demonstrated binocular parallax-induced stereoscopy via nanoline array polarization and acted as cutoff filters, with nanodot arrays, capable of treating Irlen syndrome.

Synergetic Effect of Porous Elastomer and Percolation of Carbon Nanotube Filler toward High Performance Capacitive Pressure Sensors.

Wearable pressure sensors have been attracting great attention for a variety of practical applications, including electronic skin, smart textiles, and healthcare devices. However, it is still challenging to realize wearable pressure sensors with sufficient sensitivity and low hysteresis under small mechanical stimuli. Herein, we introduce simple, cost-effective, and sensitive capacitive pressure sensor based on porous Ecoflex-multiwalled carbon nanotube composite (PEMC) structures, which leads to enhancing the sensitivity (6.42 and 1.72 kPa-1 in a range of 0-2 and 2-10 kPa, respectively) due to a synergetic effect of the porous elastomer and percolation of carbon nanotube fillers. The PEMC structure shows excellent mechanical deformability and compliance for an effective integration with practical wearable devices. Also, the PEMC-based pressure sensor shows not only the long-term stability, low-hysteresis, and fast response under dynamic loading but also the high robustness against temperature and humidity changes. Finally, we demonstrate a prosthetic robot finger integrated with a PEMC-based pressure sensor and an actuator as well as a healthcare wristband capable of continuously monitoring blood pressure and heart rate.