CycleGAN-Based Image to Image Translation for Realistic Surgical Training Phantoms.

Training in surgery is essential for surgeons to develop skill and dexterity. Physical training phantoms provide excellent haptic feedback and tissue properties for stitching and operating with authentic instruments and are easily available. However, they lack realistic traits and fail to reflect the complex environment of a surgical scene. Generative Adversarial Networks can be used for image-to-image translation, addressing the lack of realism in physical phantoms, by mapping patterns from the intraoperative domain onto the video stream captured during training with these surgical simulators. This work aims to achieve a successful I2I translation, from intra-operatory mitral valve surgery images onto a surgical simulator, using the CycleGAN model. Different experiments are performed - comparing the Mean Square Error Loss with the Binary Cross Entropy Loss; validating the Fréchet Inception Distance as a training and image quality metric; and studying the impact of input variability on the model performance. Differences between MSE and BCE are modest, with MSE being marginally more robust. The FID score proves to be very useful in identifying the best training epochs for the CycleGAN I2I translation architecture. Carefully selecting the input images can have a great impact in the end results. Using less style variability and input images with good feature details and clearly defined characteristics enables the network to achieve better results.Clinical Relevance- This work further contributes for the domain of realistic surgical training, successfully generating fake intra operatory images from a surgical simulator of the cardiac mitral valve.

Postoperative Sensitivity of Composite Replacement of Amalgam Restoration: A Randomized Clinical Trial.

PURPOSE: This randomized clinical trial aimed to evaluate the postoperative sensitivity of different resin composite/adhesive materials, placed either by an incremental or bulk-fill technique in posterior resin composite replacement of amalgam restorations. METHODS AND MATERIALS: A total of 47 patients with good overall health and at least four class I or class II amalgam restorations to be replaced participated in this study. The characteristics of 188 cavities were registered and randomly restored using incremental (Z350XT, 3M) or bulk-fill (Filtek Bulk Fill, 3M; Sonic Fill, Kerr; and Opus Bulk Fill, FGM) technique. The postoperative sensitivity was assessed using a Visual Analog Scale (0-100) after 24 hours, 7 days, and 30 days. Pain scores were temporally analyzed using Friedman test followed by Dunn post hoc test (α=0.05). The frequency of tests was calculated according to the frequency and percentage of the McNemar test. RESULTS: The restorative technique and the bulk-fill system used did not affect the postoperative sensitivity, except for Filtek Bulk Fill group, which presented less postoperative sensitivity after 24 hours (p=0.037). Regardless of the restorative material, the postoperative sensitivity decreased after 24 hours, and no differences were found after 7 and 30 days. CONCLUSIONS: After 1 week, the filling technique and the bulk-fill system have no influence on the postoperative sensitivity.

Biomaterial and Biofilm Interactions with the Pulp-Dentin Complex-on-a-Chip.

Calcium silicate cements (CSCs) are the choice materials for vital pulp therapy because of their bioactive properties, promotion of pulp repair, and dentin bridge formation. Despite the significant progress made in understanding CSCs' mechanisms of action, the key events that characterize the early interplay between CSC-dentin-pulp are still poorly understood. To address this gap, a microfluidic device, the "tooth-on-a-chip," which was developed to emulate the biomaterial-dentin-pulp interface, was used to test 1) the effect of CSCs (ProRoot, Biodentine, and TheraCal) on the viability and proliferation of human dental pulp stem cells, 2) variations of pH, and 3) release within the pulp chamber of transforming growth factor-ß (TGFß) as a surrogate of the bioactive dentin matrix molecules. ProRoot significantly increased the extraction of TGFß (P < 0.05) within 24 to 72 h and, along with Biodentine, induced higher cell proliferation (P > 0.05), while TheraCal decreased cell viability and provoked atypical changes in cell morphology. No correlation between TGFß levels and pH was observed. Further, we established a biofilm of Streptococcus mutans on-chip to model the biomaterial-biofilm-dentin interface and conducted a live and dead assay to test the antimicrobial capability of ProRoot in real time. In conclusion, the device allows for direct characterization of the interaction of bioactive dental materials with the dentin-pulp complex on a model of restored tooth while enabling assessment of antibiofilm properties at the interface in real time that was previously unattainable.