PurposeThe aim of this study was to clinically assess the impact of a prefabricated implant-retained stent clipped over healing abutments on the preservation of keratinized mucosa around implants after implant surgery, and to compare it with horizontal external mattress sutures.MethodsA total of 50 patients were enrolled in this study. In the test group, a prefabricated implant-retained stent was clipped on the healing abutment after implant surgery to replace the keratinized tissue bucco-apically. In the control group, horizontal external mattress sutures were applied instead of using a stent. After the surgical procedure, the width of the buccal keratinized mucosa was measured at the mesial, middle, and distal aspects of the healing abutment. The change in the width of the buccal keratinized mucosa was assessed at 1 and 3 months.ResultsHealing was uneventful in both groups. The difference of width between baseline and 1 month was −0.26±0.85 mm in the test group, without any statistical significance (P=0.137). Meanwhile, the corresponding difference in the control group was −0.74±0.73 mm and it showed statistical significance (P<0.001). The difference of width between baseline and 3 months was −0.57±0.97 mm in the test group and −0.86±0.71 mm in the control group. These reductions were statistically significant (P<0.05); however, there was no difference between the 2 groups.ConclusionsUsing a prefabricated implant-retained stent was shown to be effective in the preservation of the keratinized mucosa around implants and it was simple and straightforward in comparison to the horizontal external mattress suture technique.

Artificial intelligence and deep learning algorithms are infiltrating various fields of medicine and dentistry. The purpose of the current study was to review literatures applying deep learning algorithms to the dentistry and implantology. Electronic literature search through MEDLINE and IEEE Xplore library database was performed at 2019 October by combining free-text terms and entry terms associated with 'dentistry' and 'deep learning'. The searched literature was screened by title/abstract level and full text level. Following data were extracted from the included studies: information of author, publication year, the aim of the study, architecture of deep learning, input data, output data, and performance of the deep learning algorithm in the study. 340 studies were retrieved from the databases and 62 studies were included in the study. Deep learning algorithms were applied to tooth localization and numbering, detection of dental caries/periodontal disease/ periapical disease/oral cancerous lesion, localization of cephalometric landmarks, image quality enhancement, prediction and compensation of deformation error in additive manufacturing of prosthesis. Convolutional neural network was used for periapical radiograph, panoramic radiograph, or computed tomography in most of included studies. Deep learning algorithms are expected to help clinicians diagnose and make decisions by extracting dental data, detecting diseases and abnormal lesions, and improving image quality.

No abstract