Evaluation of an artificial intelligence system for the diagnosis of apical periodontitis on digital panoramic images.

Aims: The aim of the present study was to evaluate the effectiveness of an artificial intelligence (AI) system in the detection of roots with apical periodontitis (AP) on digital panoramic radiographs. Materials and Methods: Three hundred and six panoramic radiographs containing 400 roots with AP (an equal number for both jaws) were used to test the diagnostic performance of an AI system. Panoramic radiographs of the patients were selected with the terms 'apical lesion' and 'apical periodontitis' from the archive and then with the agreement of two oral and maxillofacial radiologists. The radiologists also carried out the grouping and determination of the lesion borders. A deep learning (DL) model was built and the diagnostic performance of the model was evaluated by using recall, precision, and F measure. Results: The recall, precision, and F-measure scores were 0.98, 0.56, and 0.71, respectively. While the number of roots with AP detected correctly in the mandible was 169 of 200 roots, it was only 56 of 200 roots in the maxilla. Only four roots without AP were incorrectly identified as those with AP. Conclusions: The DL method developed for the automatic detection of AP on digital panoramic radiographs showed high recall, precision, and F measure values for the mandible, but low values for the maxilla, especially for the widened periodontal ligament (PL)/uncertain AP.

Evaluation of strain values of critical anatomic regions for two different pterygomaxillary approaches in Le Fort I osteotomy: An experimental study.

BACKGROUND: The purpose of this experimental study was to measure stresses both on the pterygoid plates and the skull base following two different pterygomaxillary approaches in Le Fort I osteotomy. MATERIAL AND METHODS: The prepared skull models were randomly divided into 2 groups of 7. In the first group (A), the pterygomaxillary area was left intact. In the second group (B), pterygomaxillary separation was performed with a fine bur. The stresses were measured by using strain gauges. These strain gauges were attached to 6 different anatomical sites. The skull models were mounted on a servo-hydraulic testing unit. Each model was then subjected to a continuous linear tension until a plastic deformation was seen. RESULTS: The statistical analyses showed that there were no significant differences (p>.05) between the 2 groups regarding the strain values. Moreover, no statistical differences (p>.05) were found between the two groups in terms of maximum applied forces. CONCLUSIONS: Considering the clinical conditions, the present study shows that when Le Fort I osteotomy performed without pterygomaxillary separation, there is no significant stress on the skull base during the downfracture. Moreover, it is considered that there is no need for an excessive force applied to perform downfracture in Le Fort osteotomies without pterygomaxillary separation.

Design and implementation of a random neural network routing engine.

Random neural network (RNN) is an analytically tractable spiked neural network model that has been implemented in software for a wide range of applications for over a decade. This paper presents the hardware implementation of the RNN model. Recently, cognitive packet networks (CPN) is proposed as an alternative packet network architecture where there is no routing table, instead the RNN based reinforcement learning is used to route packets. Particularly, we describe implementation details for the RNN based routing engine of a CPN network processor chip: the smart packet processor (SPP). The SPP is a dual port device that stores, modifies, and interprets the defining characteristics of multiple RNN models. In addition to hardware design improvements over the software implementation such as the dual access memory, output calculation step, and reduced output calculation module, this paper introduces a major modification to the reinforcement learning algorithm used in the original CPN specification such that the number of weight terms are reduced from 2n/sup 2/ to 2n. This not only yields significant memory savings, but it also simplifies the calculations for the steady state probabilities (neuron outputs in RNN). Simulations have been conducted to confirm the proper functionality for the isolated SPP design as well as for the multiple SPP's in a networked environment.

Assessment of whole saliva flow rate in denture wearing patients.

It has been suggested that salivary flow rate decreases with age. As is known, the presence of a thin salivary film layer is essential for the comfort of the mucosa beneath a denture base and for denture retention. The purpose of this study was to determine the flow rates, viscosity and the pH of resting and stimulated whole saliva before and after prosthetic treatment in complete denture wearing patients. Saliva was collected under clinical conditions between 08.00 and 10.00 hours. The flow rates of whole saliva were measured at three stages: (i) resting and stimulated saliva before prosthetic treatment; (ii) immediately after the first wearing of the complete denture; and (iii) resting and stimulated saliva after 2 or 3 months of wearing the complete denture. Saliva production was stimulated by chewing paraffin wax. Flow rate was calculated as collected volume/collection time. It was found that there was a significant difference between resting and stimulated whole salivary flow rates before and after complete denture wearing.

Bond strength and failure analysis of lining materials to denture resin.

OBJECTIVES: This study was conducted to investigate the bonding properties of five lining materials to a denture base resin. Two hard (chemical-cured resin: Kooliner "Coe Labs, USA" and light-cured VLC resin: Triad "Dentsply, USA") and three soft (chemical-cured resin: Express "Alcos,-USA", heat-temperature vulcanized 'HTV' silicone material: Molloplast-B "Regneri GmbH, Germany" and room-temperature vulcanized 'RTV' silicone material:Ufi Gel-P "Voco, Germany") liners were used. METHODS: Paladent 20 "Heraeus Kulzer GmbH, Germany", a conventional heat-cured polymethylmethacrylate (PMMA), was used as the denture base resin and as the control material. Bonding strength and adhesion properties of the liners to PMMA were compared by tensile test and scanning electron microscope (SEM) analysis. After curing, an aging process was applied and the samples were immersed and stored in distilled water at 37 +/- 1 degrees C and taken out at certain aging intervals (at 0, 15, 30 and 90 days) for examination. Specimens (168) were processed for tensile tests and other specimens (24) for fracture tests. The mean and standard deviation values were calculated. Changes in the mechanical properties and the SEM findings of the adhered surfaces were evaluated. RESULTS: Triad (a hard liner) has the closest tensile strength to the control, indicating the strongest bonding between the base and the liner. Also, during the aging process, formation of better adhesion was observed in SEM micrographs. From the SEM analysis it was found that, Molloplast-B (a soft liner) also has a very good filling capacity. SIGNIFICANCE: Among the hard lining materials, VLC resin to chemical-cured resin; and among the soft lining materials, HTV resin to RTV and chemical-cured ones should be preferred for relining procedures. Molloplast-B and Express as resilient liners were found to have adequate adhesive values for clinical use.

Wetting properties of saliva substitutes on acrylic resin.

The good wetting of the acrylic resin by saliva substitutes is of clinical importance in xerostomic patients. This study evaluated the wetting properties of different artificial saliva formulations that were mucin-based, carboxymethylcellulose-based, and concentrated ion-based on poly(methyl methacrylate) denture base resin, and compared these properties with natural saliva. The wetting properties of the test materials were examined by contact angle measurements. Ninety-six samples that measured 30 x 30 x 3 mm were examined. The wetting properties of mucin-containing and carboxymethylcellulose-containing substitutes on poly(methyl methacrylate) were significantly better than those of human saliva. Mucin-containing artificial salivas had the best wetting properties on the acrylic resin for the materials tested.